maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/lib/Analysis/DependenceAnalysis.cpp

3947 lines
144 KiB
C++
Raw Normal View History

dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
//===-- DependenceAnalysis.cpp - DA Implementation --------------*- C++ -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// DependenceAnalysis is an LLVM pass that analyses dependences between memory
// accesses. Currently, it is an (incomplete) implementation of the approach
// described in
//
// Practical Dependence Testing
// Goff, Kennedy, Tseng
// PLDI 1991
//
// There's a single entry point that analyzes the dependence between a pair
// of memory references in a function, returning either NULL, for no dependence,
// or a more-or-less detailed description of the dependence between them.
//
// Currently, the implementation cannot propagate constraints between
// coupled RDIV subscripts and lacks a multi-subscript MIV test.
// Both of these are conservative weaknesses;
// that is, not a source of correctness problems.
//
add more comments around the delinearization of arrays llvm-svn: 194612
2013-11-14 06:37:58 +08:00
// The implementation depends on the GEP instruction to differentiate
// subscripts. Since Clang linearizes some array subscripts, the dependence
// analysis is using SCEV->delinearize to recover the representation of multiple
// subscripts, and thus avoid the more expensive and less precise MIV tests. The
// delinearization is controlled by the flag -da-delinearize.
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
//
// We should pay some careful attention to the possibility of integer overflow
// in the implementation of the various tests. This could happen with Add,
// Subtract, or Multiply, with both APInt's and SCEV's.
//
// Some non-linear subscript pairs can be handled by the GCD test
// (and perhaps other tests).
// Should explore how often these things occur.
//
// Finally, it seems like certain test cases expose weaknesses in the SCEV
// simplification, especially in the handling of sign and zero extensions.
// It could be useful to spend time exploring these.
//
// Please note that this is work in progress and the interface is subject to
// change.
//
//===----------------------------------------------------------------------===//
// //
// In memory of Ken Kennedy, 1945 - 2007 //
// //
//===----------------------------------------------------------------------===//
#include "llvm/Analysis/DependenceAnalysis.h"
Add missing includes. make_unique proliferated everywhere. llvm-svn: 230909
2015-03-02 05:28:53 +08:00
#include "llvm/ADT/STLExtras.h"
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
#include "llvm/ADT/Statistic.h"
DependenceAnalysis: Push #includes down into the implementation. llvm-svn: 166688
2012-10-26 00:15:22 +08:00
#include "llvm/Analysis/AliasAnalysis.h"
#include "llvm/Analysis/LoopInfo.h"
#include "llvm/Analysis/ScalarEvolution.h"
#include "llvm/Analysis/ScalarEvolutionExpressions.h"
Use the new script to sort the includes of every file under lib. Sooooo many of these had incorrect or strange main module includes. I have manually inspected all of these, and fixed the main module include to be the nearest plausible thing I could find. If you own or care about any of these source files, I encourage you to take some time and check that these edits were sensible. I can't have broken anything (I strictly added headers, and reordered them, never removed), but they may not be the headers you'd really like to identify as containing the API being implemented. Many forward declarations and missing includes were added to a header files to allow them to parse cleanly when included first. The main module rule does in fact have its merits. =] llvm-svn: 169131
2012-12-04 00:50:05 +08:00
#include "llvm/Analysis/ValueTracking.h"
[Modules] Move InstIterator out of the Support library, where it had no business. This header includes Function and BasicBlock and directly uses the interfaces of both classes. It has to do with the IR, it even has that in the name. =] Put it in the library it belongs to. This is one step toward making LLVM's Support library survive a C++ modules bootstrap. llvm-svn: 202814
2014-03-04 18:30:26 +08:00
#include "llvm/IR/InstIterator.h"
DataLayout is mandatory, update the API to reflect it with references. Summary: Now that the DataLayout is a mandatory part of the module, let's start cleaning the codebase. This patch is a first attempt at doing that. This patch is not exactly NFC as for instance some places were passing a nullptr instead of the DataLayout, possibly just because there was a default value on the DataLayout argument to many functions in the API. Even though it is not purely NFC, there is no change in the validation. I turned as many pointer to DataLayout to references, this helped figuring out all the places where a nullptr could come up. I had initially a local version of this patch broken into over 30 independant, commits but some later commit were cleaning the API and touching part of the code modified in the previous commits, so it seemed cleaner without the intermediate state. Test Plan: Reviewers: echristo Subscribers: llvm-commits From: Mehdi Amini <mehdi.amini@apple.com> llvm-svn: 231740
2015-03-10 10:37:25 +08:00
#include "llvm/IR/Module.h"
Move all of the header files which are involved in modelling the LLVM IR into their new header subdirectory: include/llvm/IR. This matches the directory structure of lib, and begins to correct a long standing point of file layout clutter in LLVM. There are still more header files to move here, but I wanted to handle them in separate commits to make tracking what files make sense at each layer easier. The only really questionable files here are the target intrinsic tablegen files. But that's a battle I'd rather not fight today. I've updated both CMake and Makefile build systems (I think, and my tests think, but I may have missed something). I've also re-sorted the includes throughout the project. I'll be committing updates to Clang, DragonEgg, and Polly momentarily. llvm-svn: 171366
2013-01-02 19:36:10 +08:00
#include "llvm/IR/Operator.h"
delinearization of arrays llvm-svn: 194527
2013-11-13 06:47:20 +08:00
#include "llvm/Support/CommandLine.h"
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
#include "llvm/Support/Debug.h"
#include "llvm/Support/ErrorHandling.h"
DependenceAnalysis: Push #includes down into the implementation. llvm-svn: 166688
2012-10-26 00:15:22 +08:00
#include "llvm/Support/raw_ostream.h"
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
using namespace llvm;
[Modules] Fix potential ODR violations by sinking the DEBUG_TYPE definition below all the header #include lines, lib/Analysis/... edition. This one has a bit extra as there were *other* #define's before #include lines in addition to DEBUG_TYPE. I've sunk all of them as a block. llvm-svn: 206843
2014-04-22 10:48:03 +08:00
#define DEBUG_TYPE "da"
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
//===----------------------------------------------------------------------===//
// statistics
STATISTIC(TotalArrayPairs, "Array pairs tested");
STATISTIC(SeparableSubscriptPairs, "Separable subscript pairs");
STATISTIC(CoupledSubscriptPairs, "Coupled subscript pairs");
STATISTIC(NonlinearSubscriptPairs, "Nonlinear subscript pairs");
STATISTIC(ZIVapplications, "ZIV applications");
STATISTIC(ZIVindependence, "ZIV independence");
STATISTIC(StrongSIVapplications, "Strong SIV applications");
STATISTIC(StrongSIVsuccesses, "Strong SIV successes");
STATISTIC(StrongSIVindependence, "Strong SIV independence");
STATISTIC(WeakCrossingSIVapplications, "Weak-Crossing SIV applications");
STATISTIC(WeakCrossingSIVsuccesses, "Weak-Crossing SIV successes");
STATISTIC(WeakCrossingSIVindependence, "Weak-Crossing SIV independence");
STATISTIC(ExactSIVapplications, "Exact SIV applications");
STATISTIC(ExactSIVsuccesses, "Exact SIV successes");
STATISTIC(ExactSIVindependence, "Exact SIV independence");
STATISTIC(WeakZeroSIVapplications, "Weak-Zero SIV applications");
STATISTIC(WeakZeroSIVsuccesses, "Weak-Zero SIV successes");
STATISTIC(WeakZeroSIVindependence, "Weak-Zero SIV independence");
STATISTIC(ExactRDIVapplications, "Exact RDIV applications");
STATISTIC(ExactRDIVindependence, "Exact RDIV independence");
STATISTIC(SymbolicRDIVapplications, "Symbolic RDIV applications");
STATISTIC(SymbolicRDIVindependence, "Symbolic RDIV independence");
STATISTIC(DeltaApplications, "Delta applications");
STATISTIC(DeltaSuccesses, "Delta successes");
STATISTIC(DeltaIndependence, "Delta independence");
STATISTIC(DeltaPropagations, "Delta propagations");
STATISTIC(GCDapplications, "GCD applications");
STATISTIC(GCDsuccesses, "GCD successes");
STATISTIC(GCDindependence, "GCD independence");
STATISTIC(BanerjeeApplications, "Banerjee applications");
STATISTIC(BanerjeeIndependence, "Banerjee independence");
STATISTIC(BanerjeeSuccesses, "Banerjee successes");
delinearization of arrays llvm-svn: 194527
2013-11-13 06:47:20 +08:00
static cl::opt<bool>
Delinearize("da-delinearize", cl::init(false), cl::Hidden, cl::ZeroOrMore,
cl::desc("Try to delinearize array references."));
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
//===----------------------------------------------------------------------===//
// basics
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
DependenceAnalysis::Result
DependenceAnalysis::run(Function &F, FunctionAnalysisManager &FAM) {
auto &AA = FAM.getResult<AAManager>(F);
auto &SE = FAM.getResult<ScalarEvolutionAnalysis>(F);
auto &LI = FAM.getResult<LoopAnalysis>(F);
return DependenceInfo(&F, &AA, &SE, &LI);
}
[PM] Change the static object whose address is used to uniquely identify analyses to have a common type which is enforced rather than using a char object and a `void *` type when used as an identifier. This has a number of advantages. First, it at least helps some of the confusion raised in Justin Lebar's code review of why `void *` was being used everywhere by having a stronger type that connects to documentation about this. However, perhaps more importantly, it addresses a serious issue where the alignment of these pointer-like identifiers was unknown. This made it hard to use them in pointer-like data structures. We were already dodging this in dangerous ways to create the "all analyses" entry. In a subsequent patch I attempted to use these with TinyPtrVector and things fell apart in a very bad way. And it isn't just a compile time or type system issue. Worse than that, the actual alignment of these pointer-like opaque identifiers wasn't guaranteed to be a useful alignment as they were just characters. This change introduces a type to use as the "key" object whose address forms the opaque identifier. This both forces the objects to have proper alignment, and provides type checking that we get it right everywhere. It also makes the types somewhat less mysterious than `void *`. We could go one step further and introduce a truly opaque pointer-like type to return from the `ID()` static function rather than returning `AnalysisKey *`, but that didn't seem to be a clear win so this is just the initial change to get to a reliably typed and aligned object serving is a key for all the analyses. Thanks to Richard Smith and Justin Lebar for helping pick plausible names and avoid making this refactoring many times. =] And thanks to Sean for the super fast review! While here, I've tried to move away from the "PassID" nomenclature entirely as it wasn't really helping and is overloaded with old pass manager constructs. Now we have IDs for analyses, and key objects whose address can be used as IDs. Where possible and clear I've shortened this to just "ID". In a few places I kept "AnalysisID" to make it clear what was being identified. Differential Revision: https://reviews.llvm.org/D27031 llvm-svn: 287783
2016-11-24 01:53:26 +08:00
AnalysisKey DependenceAnalysis::Key;
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
INITIALIZE_PASS_BEGIN(DependenceAnalysisWrapperPass, "da",
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
"Dependence Analysis", true, true)
[PM] Split the LoopInfo object apart from the legacy pass, creating a LoopInfoWrapperPass to wire the object up to the legacy pass manager. This switches all the clients of LoopInfo over and paves the way to port LoopInfo to the new pass manager. No functionality change is intended with this iteration. llvm-svn: 226373
2015-01-17 22:16:18 +08:00
INITIALIZE_PASS_DEPENDENCY(LoopInfoWrapperPass)
[PM] Port ScalarEvolution to the new pass manager. This change makes ScalarEvolution a stand-alone object and just produces one from a pass as needed. Making this work well requires making the object movable, using references instead of overwritten pointers in a number of places, and other refactorings. I've also wired it up to the new pass manager and added a RUN line to a test to exercise it under the new pass manager. This includes basic printing support much like with other analyses. But there is a big and somewhat scary change here. Prior to this patch ScalarEvolution was never *actually* invalidated!!! Re-running the pass just re-wired up the various other analyses and didn't remove any of the existing entries in the SCEV caches or clear out anything at all. This might seem OK as everything in SCEV that can uses ValueHandles to track updates to the values that serve as SCEV keys. However, this still means that as we ran SCEV over each function in the module, we kept accumulating more and more SCEVs into the cache. At the end, we would have a SCEV cache with every value that we ever needed a SCEV for in the entire module!!! Yowzers. The releaseMemory routine would dump all of this, but that isn't realy called during normal runs of the pipeline as far as I can see. To make matters worse, there *is* actually a key that we don't update with value handles -- there is a map keyed off of Loop*s. Because LoopInfo *does* release its memory from run to run, it is entirely possible to run SCEV over one function, then over another function, and then lookup a Loop* from the second function but find an entry inserted for the first function! Ouch. To make matters still worse, there are plenty of updates that *don't* trip a value handle. It seems incredibly unlikely that today GVN or another pass that invalidates SCEV can update values in *just* such a way that a subsequent run of SCEV will incorrectly find lookups in a cache, but it is theoretically possible and would be a nightmare to debug. With this refactoring, I've fixed all this by actually destroying and recreating the ScalarEvolution object from run to run. Technically, this could increase the amount of malloc traffic we see, but then again it is also technically correct. ;] I don't actually think we're suffering from tons of malloc traffic from SCEV because if we were, the fact that we never clear the memory would seem more likely to have come up as an actual problem before now. So, I've made the simple fix here. If in fact there are serious issues with too much allocation and deallocation, I can work on a clever fix that preserves the allocations (while clearing the data) between each run, but I'd prefer to do that kind of optimization with a test case / benchmark that shows why we need such cleverness (and that can test that we actually make it faster). It's possible that this will make some things faster by making the SCEV caches have higher locality (due to being significantly smaller) so until there is a clear benchmark, I think the simple change is best. Differential Revision: http://reviews.llvm.org/D12063 llvm-svn: 245193
2015-08-17 10:08:17 +08:00
INITIALIZE_PASS_DEPENDENCY(ScalarEvolutionWrapperPass)
[PM/AA] Rebuild LLVM's alias analysis infrastructure in a way compatible with the new pass manager, and no longer relying on analysis groups. This builds essentially a ground-up new AA infrastructure stack for LLVM. The core ideas are the same that are used throughout the new pass manager: type erased polymorphism and direct composition. The design is as follows: - FunctionAAResults is a type-erasing alias analysis results aggregation interface to walk a single query across a range of results from different alias analyses. Currently this is function-specific as we always assume that aliasing queries are *within* a function. - AAResultBase is a CRTP utility providing stub implementations of various parts of the alias analysis result concept, notably in several cases in terms of other more general parts of the interface. This can be used to implement only a narrow part of the interface rather than the entire interface. This isn't really ideal, this logic should be hoisted into FunctionAAResults as currently it will cause a significant amount of redundant work, but it faithfully models the behavior of the prior infrastructure. - All the alias analysis passes are ported to be wrapper passes for the legacy PM and new-style analysis passes for the new PM with a shared result object. In some cases (most notably CFL), this is an extremely naive approach that we should revisit when we can specialize for the new pass manager. - BasicAA has been restructured to reflect that it is much more fundamentally a function analysis because it uses dominator trees and loop info that need to be constructed for each function. All of the references to getting alias analysis results have been updated to use the new aggregation interface. All the preservation and other pass management code has been updated accordingly. The way the FunctionAAResultsWrapperPass works is to detect the available alias analyses when run, and add them to the results object. This means that we should be able to continue to respect when various passes are added to the pipeline, for example adding CFL or adding TBAA passes should just cause their results to be available and to get folded into this. The exception to this rule is BasicAA which really needs to be a function pass due to using dominator trees and loop info. As a consequence, the FunctionAAResultsWrapperPass directly depends on BasicAA and always includes it in the aggregation. This has significant implications for preserving analyses. Generally, most passes shouldn't bother preserving FunctionAAResultsWrapperPass because rebuilding the results just updates the set of known AA passes. The exception to this rule are LoopPass instances which need to preserve all the function analyses that the loop pass manager will end up needing. This means preserving both BasicAAWrapperPass and the aggregating FunctionAAResultsWrapperPass. Now, when preserving an alias analysis, you do so by directly preserving that analysis. This is only necessary for non-immutable-pass-provided alias analyses though, and there are only three of interest: BasicAA, GlobalsAA (formerly GlobalsModRef), and SCEVAA. Usually BasicAA is preserved when needed because it (like DominatorTree and LoopInfo) is marked as a CFG-only pass. I've expanded GlobalsAA into the preserved set everywhere we previously were preserving all of AliasAnalysis, and I've added SCEVAA in the intersection of that with where we preserve SCEV itself. One significant challenge to all of this is that the CGSCC passes were actually using the alias analysis implementations by taking advantage of a pretty amazing set of loop holes in the old pass manager's analysis management code which allowed analysis groups to slide through in many cases. Moving away from analysis groups makes this problem much more obvious. To fix it, I've leveraged the flexibility the design of the new PM components provides to just directly construct the relevant alias analyses for the relevant functions in the IPO passes that need them. This is a bit hacky, but should go away with the new pass manager, and is already in many ways cleaner than the prior state. Another significant challenge is that various facilities of the old alias analysis infrastructure just don't fit any more. The most significant of these is the alias analysis 'counter' pass. That pass relied on the ability to snoop on AA queries at different points in the analysis group chain. Instead, I'm planning to build printing functionality directly into the aggregation layer. I've not included that in this patch merely to keep it smaller. Note that all of this needs a nearly complete rewrite of the AA documentation. I'm planning to do that, but I'd like to make sure the new design settles, and to flesh out a bit more of what it looks like in the new pass manager first. Differential Revision: http://reviews.llvm.org/D12080 llvm-svn: 247167
2015-09-10 01:55:00 +08:00
INITIALIZE_PASS_DEPENDENCY(AAResultsWrapperPass)
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
INITIALIZE_PASS_END(DependenceAnalysisWrapperPass, "da", "Dependence Analysis",
true, true)
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
char DependenceAnalysisWrapperPass::ID = 0;
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
FunctionPass *llvm::createDependenceAnalysisWrapperPass() {
return new DependenceAnalysisWrapperPass();
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
}
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
bool DependenceAnalysisWrapperPass::runOnFunction(Function &F) {
auto &AA = getAnalysis<AAResultsWrapperPass>().getAAResults();
auto &SE = getAnalysis<ScalarEvolutionWrapperPass>().getSE();
auto &LI = getAnalysis<LoopInfoWrapperPass>().getLoopInfo();
info.reset(new DependenceInfo(&F, &AA, &SE, &LI));
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
return false;
}
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
DependenceInfo &DependenceAnalysisWrapperPass::getDI() const { return *info; }
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
void DependenceAnalysisWrapperPass::releaseMemory() { info.reset(); }
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
void DependenceAnalysisWrapperPass::getAnalysisUsage(AnalysisUsage &AU) const {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
AU.setPreservesAll();
[PM/AA] Rebuild LLVM's alias analysis infrastructure in a way compatible with the new pass manager, and no longer relying on analysis groups. This builds essentially a ground-up new AA infrastructure stack for LLVM. The core ideas are the same that are used throughout the new pass manager: type erased polymorphism and direct composition. The design is as follows: - FunctionAAResults is a type-erasing alias analysis results aggregation interface to walk a single query across a range of results from different alias analyses. Currently this is function-specific as we always assume that aliasing queries are *within* a function. - AAResultBase is a CRTP utility providing stub implementations of various parts of the alias analysis result concept, notably in several cases in terms of other more general parts of the interface. This can be used to implement only a narrow part of the interface rather than the entire interface. This isn't really ideal, this logic should be hoisted into FunctionAAResults as currently it will cause a significant amount of redundant work, but it faithfully models the behavior of the prior infrastructure. - All the alias analysis passes are ported to be wrapper passes for the legacy PM and new-style analysis passes for the new PM with a shared result object. In some cases (most notably CFL), this is an extremely naive approach that we should revisit when we can specialize for the new pass manager. - BasicAA has been restructured to reflect that it is much more fundamentally a function analysis because it uses dominator trees and loop info that need to be constructed for each function. All of the references to getting alias analysis results have been updated to use the new aggregation interface. All the preservation and other pass management code has been updated accordingly. The way the FunctionAAResultsWrapperPass works is to detect the available alias analyses when run, and add them to the results object. This means that we should be able to continue to respect when various passes are added to the pipeline, for example adding CFL or adding TBAA passes should just cause their results to be available and to get folded into this. The exception to this rule is BasicAA which really needs to be a function pass due to using dominator trees and loop info. As a consequence, the FunctionAAResultsWrapperPass directly depends on BasicAA and always includes it in the aggregation. This has significant implications for preserving analyses. Generally, most passes shouldn't bother preserving FunctionAAResultsWrapperPass because rebuilding the results just updates the set of known AA passes. The exception to this rule are LoopPass instances which need to preserve all the function analyses that the loop pass manager will end up needing. This means preserving both BasicAAWrapperPass and the aggregating FunctionAAResultsWrapperPass. Now, when preserving an alias analysis, you do so by directly preserving that analysis. This is only necessary for non-immutable-pass-provided alias analyses though, and there are only three of interest: BasicAA, GlobalsAA (formerly GlobalsModRef), and SCEVAA. Usually BasicAA is preserved when needed because it (like DominatorTree and LoopInfo) is marked as a CFG-only pass. I've expanded GlobalsAA into the preserved set everywhere we previously were preserving all of AliasAnalysis, and I've added SCEVAA in the intersection of that with where we preserve SCEV itself. One significant challenge to all of this is that the CGSCC passes were actually using the alias analysis implementations by taking advantage of a pretty amazing set of loop holes in the old pass manager's analysis management code which allowed analysis groups to slide through in many cases. Moving away from analysis groups makes this problem much more obvious. To fix it, I've leveraged the flexibility the design of the new PM components provides to just directly construct the relevant alias analyses for the relevant functions in the IPO passes that need them. This is a bit hacky, but should go away with the new pass manager, and is already in many ways cleaner than the prior state. Another significant challenge is that various facilities of the old alias analysis infrastructure just don't fit any more. The most significant of these is the alias analysis 'counter' pass. That pass relied on the ability to snoop on AA queries at different points in the analysis group chain. Instead, I'm planning to build printing functionality directly into the aggregation layer. I've not included that in this patch merely to keep it smaller. Note that all of this needs a nearly complete rewrite of the AA documentation. I'm planning to do that, but I'd like to make sure the new design settles, and to flesh out a bit more of what it looks like in the new pass manager first. Differential Revision: http://reviews.llvm.org/D12080 llvm-svn: 247167
2015-09-10 01:55:00 +08:00
AU.addRequiredTransitive<AAResultsWrapperPass>();
[PM] Port ScalarEvolution to the new pass manager. This change makes ScalarEvolution a stand-alone object and just produces one from a pass as needed. Making this work well requires making the object movable, using references instead of overwritten pointers in a number of places, and other refactorings. I've also wired it up to the new pass manager and added a RUN line to a test to exercise it under the new pass manager. This includes basic printing support much like with other analyses. But there is a big and somewhat scary change here. Prior to this patch ScalarEvolution was never *actually* invalidated!!! Re-running the pass just re-wired up the various other analyses and didn't remove any of the existing entries in the SCEV caches or clear out anything at all. This might seem OK as everything in SCEV that can uses ValueHandles to track updates to the values that serve as SCEV keys. However, this still means that as we ran SCEV over each function in the module, we kept accumulating more and more SCEVs into the cache. At the end, we would have a SCEV cache with every value that we ever needed a SCEV for in the entire module!!! Yowzers. The releaseMemory routine would dump all of this, but that isn't realy called during normal runs of the pipeline as far as I can see. To make matters worse, there *is* actually a key that we don't update with value handles -- there is a map keyed off of Loop*s. Because LoopInfo *does* release its memory from run to run, it is entirely possible to run SCEV over one function, then over another function, and then lookup a Loop* from the second function but find an entry inserted for the first function! Ouch. To make matters still worse, there are plenty of updates that *don't* trip a value handle. It seems incredibly unlikely that today GVN or another pass that invalidates SCEV can update values in *just* such a way that a subsequent run of SCEV will incorrectly find lookups in a cache, but it is theoretically possible and would be a nightmare to debug. With this refactoring, I've fixed all this by actually destroying and recreating the ScalarEvolution object from run to run. Technically, this could increase the amount of malloc traffic we see, but then again it is also technically correct. ;] I don't actually think we're suffering from tons of malloc traffic from SCEV because if we were, the fact that we never clear the memory would seem more likely to have come up as an actual problem before now. So, I've made the simple fix here. If in fact there are serious issues with too much allocation and deallocation, I can work on a clever fix that preserves the allocations (while clearing the data) between each run, but I'd prefer to do that kind of optimization with a test case / benchmark that shows why we need such cleverness (and that can test that we actually make it faster). It's possible that this will make some things faster by making the SCEV caches have higher locality (due to being significantly smaller) so until there is a clear benchmark, I think the simple change is best. Differential Revision: http://reviews.llvm.org/D12063 llvm-svn: 245193
2015-08-17 10:08:17 +08:00
AU.addRequiredTransitive<ScalarEvolutionWrapperPass>();
[PM] Split the LoopInfo object apart from the legacy pass, creating a LoopInfoWrapperPass to wire the object up to the legacy pass manager. This switches all the clients of LoopInfo over and paves the way to port LoopInfo to the new pass manager. No functionality change is intended with this iteration. llvm-svn: 226373
2015-01-17 22:16:18 +08:00
AU.addRequiredTransitive<LoopInfoWrapperPass>();
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
}
// Used to test the dependence analyzer.
DependenceAnalysis: Print all dependency pairs when dumping. Update all testcases. Part of a patch by Preston Briggs. llvm-svn: 167827
2012-11-13 20:12:02 +08:00
// Looks through the function, noting loads and stores.
// Calls depends() on every possible pair and prints out the result.
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
// Ignores all other instructions.
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
static void dumpExampleDependence(raw_ostream &OS, DependenceInfo *DA) {
auto *F = DA->getFunction();
for (inst_iterator SrcI = inst_begin(F), SrcE = inst_end(F); SrcI != SrcE;
++SrcI) {
DependenceAnalysis: Print all dependency pairs when dumping. Update all testcases. Part of a patch by Preston Briggs. llvm-svn: 167827
2012-11-13 20:12:02 +08:00
if (isa<StoreInst>(*SrcI) || isa<LoadInst>(*SrcI)) {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
for (inst_iterator DstI = SrcI, DstE = inst_end(F);
DstI != DstE; ++DstI) {
DependenceAnalysis: Print all dependency pairs when dumping. Update all testcases. Part of a patch by Preston Briggs. llvm-svn: 167827
2012-11-13 20:12:02 +08:00
if (isa<StoreInst>(*DstI) || isa<LoadInst>(*DstI)) {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
OS << "da analyze - ";
Analysis: unique_ptr-ify DependenceAnalysis::depends llvm-svn: 216357
2014-08-25 08:28:39 +08:00
if (auto D = DA->depends(&*SrcI, &*DstI, true)) {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
D->dump(OS);
for (unsigned Level = 1; Level <= D->getLevels(); Level++) {
if (D->isSplitable(Level)) {
OS << "da analyze - split level = " << Level;
Analysis: take a reference instead of pointer This parameter is never null. llvm-svn: 216356
2014-08-25 08:28:35 +08:00
OS << ", iteration = " << *DA->getSplitIteration(*D, Level);
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
OS << "!\n";
}
}
}
else
OS << "none!\n";
}
}
}
}
}
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
void DependenceAnalysisWrapperPass::print(raw_ostream &OS,
const Module *) const {
dumpExampleDependence(OS, info.get());
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
}
//===----------------------------------------------------------------------===//
// Dependence methods
// Returns true if this is an input dependence.
bool Dependence::isInput() const {
return Src->mayReadFromMemory() && Dst->mayReadFromMemory();
}
// Returns true if this is an output dependence.
bool Dependence::isOutput() const {
return Src->mayWriteToMemory() && Dst->mayWriteToMemory();
}
// Returns true if this is an flow (aka true) dependence.
bool Dependence::isFlow() const {
return Src->mayWriteToMemory() && Dst->mayReadFromMemory();
}
// Returns true if this is an anti dependence.
bool Dependence::isAnti() const {
return Src->mayReadFromMemory() && Dst->mayWriteToMemory();
}
// Returns true if a particular level is scalar; that is,
// if no subscript in the source or destination mention the induction
// variable associated with the loop at this level.
// Leave this out of line, so it will serve as a virtual method anchor
bool Dependence::isScalar(unsigned level) const {
return false;
}
//===----------------------------------------------------------------------===//
// FullDependence methods
Reformat. llvm-svn: 231336
2015-03-05 09:25:19 +08:00
FullDependence::FullDependence(Instruction *Source, Instruction *Destination,
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
bool PossiblyLoopIndependent,
Reformat. llvm-svn: 231336
2015-03-05 09:25:19 +08:00
unsigned CommonLevels)
: Dependence(Source, Destination), Levels(CommonLevels),
LoopIndependent(PossiblyLoopIndependent) {
Revert r231104, "unique_ptrify FullDependenceAnalysis::DV", to appease msc18 C2280. llvm-svn: 231334
2015-03-05 09:25:06 +08:00
Consistent = true;
-Wdeprecated-clean: Fix cases of violating the rule of 5 in ways that are deprecated in C++11 llvm-svn: 243788
2015-08-01 05:37:09 +08:00
if (CommonLevels)
DV = make_unique<DVEntry[]>(CommonLevels);
Revert r231104, "unique_ptrify FullDependenceAnalysis::DV", to appease msc18 C2280. llvm-svn: 231334
2015-03-05 09:25:06 +08:00
}
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
// The rest are simple getters that hide the implementation.
// getDirection - Returns the direction associated with a particular level.
unsigned FullDependence::getDirection(unsigned Level) const {
assert(0 < Level && Level <= Levels && "Level out of range");
return DV[Level - 1].Direction;
}
// Returns the distance (or NULL) associated with a particular level.
const SCEV *FullDependence::getDistance(unsigned Level) const {
assert(0 < Level && Level <= Levels && "Level out of range");
return DV[Level - 1].Distance;
}
// Returns true if a particular level is scalar; that is,
// if no subscript in the source or destination mention the induction
// variable associated with the loop at this level.
bool FullDependence::isScalar(unsigned Level) const {
assert(0 < Level && Level <= Levels && "Level out of range");
return DV[Level - 1].Scalar;
}
// Returns true if peeling the first iteration from this loop
// will break this dependence.
bool FullDependence::isPeelFirst(unsigned Level) const {
assert(0 < Level && Level <= Levels && "Level out of range");
return DV[Level - 1].PeelFirst;
}
// Returns true if peeling the last iteration from this loop
// will break this dependence.
bool FullDependence::isPeelLast(unsigned Level) const {
assert(0 < Level && Level <= Levels && "Level out of range");
return DV[Level - 1].PeelLast;
}
// Returns true if splitting this loop will break the dependence.
bool FullDependence::isSplitable(unsigned Level) const {
assert(0 < Level && Level <= Levels && "Level out of range");
return DV[Level - 1].Splitable;
}
//===----------------------------------------------------------------------===//
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
// DependenceInfo::Constraint methods
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
// If constraint is a point <X, Y>, returns X.
// Otherwise assert.
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
const SCEV *DependenceInfo::Constraint::getX() const {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
assert(Kind == Point && "Kind should be Point");
return A;
}
// If constraint is a point <X, Y>, returns Y.
// Otherwise assert.
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
const SCEV *DependenceInfo::Constraint::getY() const {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
assert(Kind == Point && "Kind should be Point");
return B;
}
// If constraint is a line AX + BY = C, returns A.
// Otherwise assert.
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
const SCEV *DependenceInfo::Constraint::getA() const {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
assert((Kind == Line || Kind == Distance) &&
"Kind should be Line (or Distance)");
return A;
}
// If constraint is a line AX + BY = C, returns B.
// Otherwise assert.
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
const SCEV *DependenceInfo::Constraint::getB() const {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
assert((Kind == Line || Kind == Distance) &&
"Kind should be Line (or Distance)");
return B;
}
// If constraint is a line AX + BY = C, returns C.
// Otherwise assert.
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
const SCEV *DependenceInfo::Constraint::getC() const {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
assert((Kind == Line || Kind == Distance) &&
"Kind should be Line (or Distance)");
return C;
}
// If constraint is a distance, returns D.
// Otherwise assert.
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
const SCEV *DependenceInfo::Constraint::getD() const {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
assert(Kind == Distance && "Kind should be Distance");
return SE->getNegativeSCEV(C);
}
// Returns the loop associated with this constraint.
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
const Loop *DependenceInfo::Constraint::getAssociatedLoop() const {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
assert((Kind == Distance || Kind == Line || Kind == Point) &&
"Kind should be Distance, Line, or Point");
return AssociatedLoop;
}
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
void DependenceInfo::Constraint::setPoint(const SCEV *X, const SCEV *Y,
const Loop *CurLoop) {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
Kind = Point;
A = X;
B = Y;
AssociatedLoop = CurLoop;
}
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
void DependenceInfo::Constraint::setLine(const SCEV *AA, const SCEV *BB,
const SCEV *CC, const Loop *CurLoop) {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
Kind = Line;
A = AA;
B = BB;
C = CC;
AssociatedLoop = CurLoop;
}
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
void DependenceInfo::Constraint::setDistance(const SCEV *D,
const Loop *CurLoop) {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
Kind = Distance;
[SCEV] Introduce ScalarEvolution::getOne and getZero. Summary: It is fairly common to call SE->getConstant(Ty, 0) or SE->getConstant(Ty, 1); this change makes such uses a little bit briefer. I've refactored the call sites I could find easily to use getZero / getOne. Reviewers: hfinkel, majnemer, reames Subscribers: sanjoy, llvm-commits Differential Revision: http://reviews.llvm.org/D12947 llvm-svn: 248362
2015-09-23 09:59:04 +08:00
A = SE->getOne(D->getType());
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
B = SE->getNegativeSCEV(A);
C = SE->getNegativeSCEV(D);
AssociatedLoop = CurLoop;
}
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
void DependenceInfo::Constraint::setEmpty() { Kind = Empty; }
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
void DependenceInfo::Constraint::setAny(ScalarEvolution *NewSE) {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
SE = NewSE;
Kind = Any;
}
// For debugging purposes. Dumps the constraint out to OS.
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
void DependenceInfo::Constraint::dump(raw_ostream &OS) const {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
if (isEmpty())
OS << " Empty\n";
else if (isAny())
OS << " Any\n";
else if (isPoint())
OS << " Point is <" << *getX() << ", " << *getY() << ">\n";
else if (isDistance())
OS << " Distance is " << *getD() <<
" (" << *getA() << "*X + " << *getB() << "*Y = " << *getC() << ")\n";
else if (isLine())
OS << " Line is " << *getA() << "*X + " <<
*getB() << "*Y = " << *getC() << "\n";
else
llvm_unreachable("unknown constraint type in Constraint::dump");
}
// Updates X with the intersection
// of the Constraints X and Y. Returns true if X has changed.
// Corresponds to Figure 4 from the paper
//
// Practical Dependence Testing
// Goff, Kennedy, Tseng
// PLDI 1991
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
bool DependenceInfo::intersectConstraints(Constraint *X, const Constraint *Y) {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
++DeltaApplications;
DEBUG(dbgs() << "\tintersect constraints\n");
DEBUG(dbgs() << "\t X ="; X->dump(dbgs()));
DEBUG(dbgs() << "\t Y ="; Y->dump(dbgs()));
assert(!Y->isPoint() && "Y must not be a Point");
if (X->isAny()) {
if (Y->isAny())
return false;
*X = *Y;
return true;
}
if (X->isEmpty())
return false;
if (Y->isEmpty()) {
X->setEmpty();
return true;
}
if (X->isDistance() && Y->isDistance()) {
DEBUG(dbgs() << "\t intersect 2 distances\n");
if (isKnownPredicate(CmpInst::ICMP_EQ, X->getD(), Y->getD()))
return false;
if (isKnownPredicate(CmpInst::ICMP_NE, X->getD(), Y->getD())) {
X->setEmpty();
++DeltaSuccesses;
return true;
}
// Hmmm, interesting situation.
// I guess if either is constant, keep it and ignore the other.
if (isa<SCEVConstant>(Y->getD())) {
*X = *Y;
return true;
}
return false;
}
// At this point, the pseudo-code in Figure 4 of the paper
// checks if (X->isPoint() && Y->isPoint()).
// This case can't occur in our implementation,
// since a Point can only arise as the result of intersecting
// two Line constraints, and the right-hand value, Y, is never
// the result of an intersection.
assert(!(X->isPoint() && Y->isPoint()) &&
"We shouldn't ever see X->isPoint() && Y->isPoint()");
if (X->isLine() && Y->isLine()) {
DEBUG(dbgs() << "\t intersect 2 lines\n");
const SCEV *Prod1 = SE->getMulExpr(X->getA(), Y->getB());
const SCEV *Prod2 = SE->getMulExpr(X->getB(), Y->getA());
if (isKnownPredicate(CmpInst::ICMP_EQ, Prod1, Prod2)) {
// slopes are equal, so lines are parallel
DEBUG(dbgs() << "\t\tsame slope\n");
Prod1 = SE->getMulExpr(X->getC(), Y->getB());
Prod2 = SE->getMulExpr(X->getB(), Y->getC());
if (isKnownPredicate(CmpInst::ICMP_EQ, Prod1, Prod2))
return false;
if (isKnownPredicate(CmpInst::ICMP_NE, Prod1, Prod2)) {
X->setEmpty();
++DeltaSuccesses;
return true;
}
return false;
}
if (isKnownPredicate(CmpInst::ICMP_NE, Prod1, Prod2)) {
// slopes differ, so lines intersect
DEBUG(dbgs() << "\t\tdifferent slopes\n");
const SCEV *C1B2 = SE->getMulExpr(X->getC(), Y->getB());
const SCEV *C1A2 = SE->getMulExpr(X->getC(), Y->getA());
const SCEV *C2B1 = SE->getMulExpr(Y->getC(), X->getB());
const SCEV *C2A1 = SE->getMulExpr(Y->getC(), X->getA());
const SCEV *A1B2 = SE->getMulExpr(X->getA(), Y->getB());
const SCEV *A2B1 = SE->getMulExpr(Y->getA(), X->getB());
const SCEVConstant *C1A2_C2A1 =
dyn_cast<SCEVConstant>(SE->getMinusSCEV(C1A2, C2A1));
const SCEVConstant *C1B2_C2B1 =
dyn_cast<SCEVConstant>(SE->getMinusSCEV(C1B2, C2B1));
const SCEVConstant *A1B2_A2B1 =
dyn_cast<SCEVConstant>(SE->getMinusSCEV(A1B2, A2B1));
const SCEVConstant *A2B1_A1B2 =
dyn_cast<SCEVConstant>(SE->getMinusSCEV(A2B1, A1B2));
if (!C1B2_C2B1 || !C1A2_C2A1 ||
!A1B2_A2B1 || !A2B1_A1B2)
return false;
[SCEV] Add and use SCEVConstant::getAPInt; NFCI llvm-svn: 255921
2015-12-18 04:28:46 +08:00
APInt Xtop = C1B2_C2B1->getAPInt();
APInt Xbot = A1B2_A2B1->getAPInt();
APInt Ytop = C1A2_C2A1->getAPInt();
APInt Ybot = A2B1_A1B2->getAPInt();
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
DEBUG(dbgs() << "\t\tXtop = " << Xtop << "\n");
DEBUG(dbgs() << "\t\tXbot = " << Xbot << "\n");
DEBUG(dbgs() << "\t\tYtop = " << Ytop << "\n");
DEBUG(dbgs() << "\t\tYbot = " << Ybot << "\n");
APInt Xq = Xtop; // these need to be initialized, even
APInt Xr = Xtop; // though they're just going to be overwritten
APInt::sdivrem(Xtop, Xbot, Xq, Xr);
APInt Yq = Ytop;
Remove extraneous semicolon. llvm-svn: 187806
2013-08-07 00:40:40 +08:00
APInt Yr = Ytop;
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
APInt::sdivrem(Ytop, Ybot, Yq, Yr);
if (Xr != 0 || Yr != 0) {
X->setEmpty();
++DeltaSuccesses;
return true;
}
DEBUG(dbgs() << "\t\tX = " << Xq << ", Y = " << Yq << "\n");
if (Xq.slt(0) || Yq.slt(0)) {
X->setEmpty();
++DeltaSuccesses;
return true;
}
if (const SCEVConstant *CUB =
collectConstantUpperBound(X->getAssociatedLoop(), Prod1->getType())) {
Avoid copies of std::strings and APInt/APFloats where we only read from it As suggested by clang-tidy's performance-unnecessary-copy-initialization. This can easily hit lifetime issues, so I audited every change and ran the tests under asan, which came back clean. llvm-svn: 272126
2016-06-08 18:01:20 +08:00
const APInt &UpperBound = CUB->getAPInt();
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
DEBUG(dbgs() << "\t\tupper bound = " << UpperBound << "\n");
if (Xq.sgt(UpperBound) || Yq.sgt(UpperBound)) {
X->setEmpty();
++DeltaSuccesses;
return true;
}
}
X->setPoint(SE->getConstant(Xq),
SE->getConstant(Yq),
X->getAssociatedLoop());
++DeltaSuccesses;
return true;
}
return false;
}
// if (X->isLine() && Y->isPoint()) This case can't occur.
assert(!(X->isLine() && Y->isPoint()) && "This case should never occur");
if (X->isPoint() && Y->isLine()) {
DEBUG(dbgs() << "\t intersect Point and Line\n");
const SCEV *A1X1 = SE->getMulExpr(Y->getA(), X->getX());
const SCEV *B1Y1 = SE->getMulExpr(Y->getB(), X->getY());
const SCEV *Sum = SE->getAddExpr(A1X1, B1Y1);
if (isKnownPredicate(CmpInst::ICMP_EQ, Sum, Y->getC()))
return false;
if (isKnownPredicate(CmpInst::ICMP_NE, Sum, Y->getC())) {
X->setEmpty();
++DeltaSuccesses;
return true;
}
return false;
}
llvm_unreachable("shouldn't reach the end of Constraint intersection");
return false;
}
//===----------------------------------------------------------------------===//
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
// DependenceInfo methods
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
// For debugging purposes. Dumps a dependence to OS.
void Dependence::dump(raw_ostream &OS) const {
bool Splitable = false;
if (isConfused())
OS << "confused";
else {
if (isConsistent())
OS << "consistent ";
if (isFlow())
OS << "flow";
else if (isOutput())
OS << "output";
else if (isAnti())
OS << "anti";
else if (isInput())
OS << "input";
unsigned Levels = getLevels();
Modified dump() to provide a little more information for dependences between instructions that don't share a common loop. Updated the test results appropriately. llvm-svn: 168965
2012-11-30 08:44:47 +08:00
OS << " [";
for (unsigned II = 1; II <= Levels; ++II) {
if (isSplitable(II))
Splitable = true;
if (isPeelFirst(II))
OS << 'p';
const SCEV *Distance = getDistance(II);
if (Distance)
OS << *Distance;
else if (isScalar(II))
OS << "S";
else {
unsigned Direction = getDirection(II);
if (Direction == DVEntry::ALL)
OS << "*";
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
else {
Modified dump() to provide a little more information for dependences between instructions that don't share a common loop. Updated the test results appropriately. llvm-svn: 168965
2012-11-30 08:44:47 +08:00
if (Direction & DVEntry::LT)
OS << "<";
if (Direction & DVEntry::EQ)
OS << "=";
if (Direction & DVEntry::GT)
OS << ">";
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
}
}
Modified dump() to provide a little more information for dependences between instructions that don't share a common loop. Updated the test results appropriately. llvm-svn: 168965
2012-11-30 08:44:47 +08:00
if (isPeelLast(II))
OS << 'p';
if (II < Levels)
OS << " ";
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
}
Modified dump() to provide a little more information for dependences between instructions that don't share a common loop. Updated the test results appropriately. llvm-svn: 168965
2012-11-30 08:44:47 +08:00
if (isLoopIndependent())
OS << "|<";
OS << "]";
if (Splitable)
OS << " splitable";
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
}
OS << "!\n";
}
[PM/AA] Hoist the AliasResult enum out of the AliasAnalysis class. This will allow classes to implement the AA interface without deriving from the class or referencing an internal enum of some other class as their return types. Also, to a pretty fundamental extent, concepts such as 'NoAlias', 'MayAlias', and 'MustAlias' are first class concepts in LLVM and we aren't saving anything by scoping them heavily. My mild preference would have been to use a scoped enum, but that feature is essentially completely broken AFAICT. I'm extremely disappointed. For example, we cannot through any reasonable[1] means construct an enum class (or analog) which has scoped names but converts to a boolean in order to test for the possibility of aliasing. [1]: Richard Smith came up with a "solution", but it requires class templates, and lots of boilerplate setting up the enumeration multiple times. Something like Boost.PP could potentially bundle this up, but even that would be quite painful and it doesn't seem realistically worth it. The enum class solution would probably work without the need for a bool conversion. Differential Revision: http://reviews.llvm.org/D10495 llvm-svn: 240255
2015-06-22 10:16:51 +08:00
static AliasResult underlyingObjectsAlias(AliasAnalysis *AA,
const DataLayout &DL, const Value *A,
const Value *B) {
DataLayout is mandatory, update the API to reflect it with references. Summary: Now that the DataLayout is a mandatory part of the module, let's start cleaning the codebase. This patch is a first attempt at doing that. This patch is not exactly NFC as for instance some places were passing a nullptr instead of the DataLayout, possibly just because there was a default value on the DataLayout argument to many functions in the API. Even though it is not purely NFC, there is no change in the validation. I turned as many pointer to DataLayout to references, this helped figuring out all the places where a nullptr could come up. I had initially a local version of this patch broken into over 30 independant, commits but some later commit were cleaning the API and touching part of the code modified in the previous commits, so it seemed cleaner without the intermediate state. Test Plan: Reviewers: echristo Subscribers: llvm-commits From: Mehdi Amini <mehdi.amini@apple.com> llvm-svn: 231740
2015-03-10 10:37:25 +08:00
const Value *AObj = GetUnderlyingObject(A, DL);
const Value *BObj = GetUnderlyingObject(B, DL);
[PM/AA] Simplify the AliasAnalysis interface by removing a wrapper around a DataLayout interface in favor of directly querying DataLayout. This wrapper specifically helped handle the case where this no DataLayout, but LLVM now requires it simplifynig all of this. I've updated callers to directly query DataLayout. This in turn exposed a bunch of places where we should have DataLayout readily available but don't which I've fixed. This then in turn exposed that we were passing DataLayout around in a bunch of arguments rather than making it readily available so I've also fixed that. No functionality changed. llvm-svn: 244189
2015-08-06 10:05:46 +08:00
return AA->alias(AObj, DL.getTypeStoreSize(AObj->getType()),
BObj, DL.getTypeStoreSize(BObj->getType()));
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
}
// Returns true if the load or store can be analyzed. Atomic and volatile
// operations have properties which this analysis does not understand.
static
bool isLoadOrStore(const Instruction *I) {
if (const LoadInst *LI = dyn_cast<LoadInst>(I))
return LI->isUnordered();
else if (const StoreInst *SI = dyn_cast<StoreInst>(I))
return SI->isUnordered();
return false;
}
static
removes a few "const" qualifiers so that I can (someday) call SE->getSCEV without complaint. No semantic change intended. Patch from Preston Briggs <preston.briggs@gmail.com>. llvm-svn: 168391
2012-11-21 06:28:04 +08:00
Value *getPointerOperand(Instruction *I) {
if (LoadInst *LI = dyn_cast<LoadInst>(I))
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
return LI->getPointerOperand();
removes a few "const" qualifiers so that I can (someday) call SE->getSCEV without complaint. No semantic change intended. Patch from Preston Briggs <preston.briggs@gmail.com>. llvm-svn: 168391
2012-11-21 06:28:04 +08:00
if (StoreInst *SI = dyn_cast<StoreInst>(I))
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
return SI->getPointerOperand();
llvm_unreachable("Value is not load or store instruction");
[C++11] More 'nullptr' conversion. In some cases just using a boolean check instead of comparing to nullptr. llvm-svn: 206243
2014-04-15 12:59:12 +08:00
return nullptr;
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
}
// Examines the loop nesting of the Src and Dst
// instructions and establishes their shared loops. Sets the variables
// CommonLevels, SrcLevels, and MaxLevels.
// The source and destination instructions needn't be contained in the same
// loop. The routine establishNestingLevels finds the level of most deeply
// nested loop that contains them both, CommonLevels. An instruction that's
// not contained in a loop is at level = 0. MaxLevels is equal to the level
// of the source plus the level of the destination, minus CommonLevels.
// This lets us allocate vectors MaxLevels in length, with room for every
// distinct loop referenced in both the source and destination subscripts.
// The variable SrcLevels is the nesting depth of the source instruction.
// It's used to help calculate distinct loops referenced by the destination.
// Here's the map from loops to levels:
// 0 - unused
// 1 - outermost common loop
// ... - other common loops
// CommonLevels - innermost common loop
// ... - loops containing Src but not Dst
// SrcLevels - innermost loop containing Src but not Dst
// ... - loops containing Dst but not Src
// MaxLevels - innermost loops containing Dst but not Src
// Consider the follow code fragment:
// for (a = ...) {
// for (b = ...) {
// for (c = ...) {
// for (d = ...) {
// A[] = ...;
// }
// }
// for (e = ...) {
// for (f = ...) {
// for (g = ...) {
// ... = A[];
// }
// }
// }
// }
// }
// If we're looking at the possibility of a dependence between the store
// to A (the Src) and the load from A (the Dst), we'll note that they
// have 2 loops in common, so CommonLevels will equal 2 and the direction
// vector for Result will have 2 entries. SrcLevels = 4 and MaxLevels = 7.
// A map from loop names to loop numbers would look like
// a - 1
// b - 2 = CommonLevels
// c - 3
// d - 4 = SrcLevels
// e - 5
// f - 6
// g - 7 = MaxLevels
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
void DependenceInfo::establishNestingLevels(const Instruction *Src,
const Instruction *Dst) {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
const BasicBlock *SrcBlock = Src->getParent();
const BasicBlock *DstBlock = Dst->getParent();
unsigned SrcLevel = LI->getLoopDepth(SrcBlock);
unsigned DstLevel = LI->getLoopDepth(DstBlock);
const Loop *SrcLoop = LI->getLoopFor(SrcBlock);
const Loop *DstLoop = LI->getLoopFor(DstBlock);
SrcLevels = SrcLevel;
MaxLevels = SrcLevel + DstLevel;
while (SrcLevel > DstLevel) {
SrcLoop = SrcLoop->getParentLoop();
SrcLevel--;
}
while (DstLevel > SrcLevel) {
DstLoop = DstLoop->getParentLoop();
DstLevel--;
}
while (SrcLoop != DstLoop) {
SrcLoop = SrcLoop->getParentLoop();
DstLoop = DstLoop->getParentLoop();
SrcLevel--;
}
CommonLevels = SrcLevel;
MaxLevels -= CommonLevels;
}
// Given one of the loops containing the source, return
// its level index in our numbering scheme.
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
unsigned DependenceInfo::mapSrcLoop(const Loop *SrcLoop) const {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
return SrcLoop->getLoopDepth();
}
// Given one of the loops containing the destination,
// return its level index in our numbering scheme.
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
unsigned DependenceInfo::mapDstLoop(const Loop *DstLoop) const {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
unsigned D = DstLoop->getLoopDepth();
if (D > CommonLevels)
return D - CommonLevels + SrcLevels;
else
return D;
}
// Returns true if Expression is loop invariant in LoopNest.
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
bool DependenceInfo::isLoopInvariant(const SCEV *Expression,
const Loop *LoopNest) const {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
if (!LoopNest)
return true;
return SE->isLoopInvariant(Expression, LoopNest) &&
isLoopInvariant(Expression, LoopNest->getParentLoop());
}
// Finds the set of loops from the LoopNest that
// have a level <= CommonLevels and are referred to by the SCEV Expression.
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
void DependenceInfo::collectCommonLoops(const SCEV *Expression,
const Loop *LoopNest,
SmallBitVector &Loops) const {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
while (LoopNest) {
unsigned Level = LoopNest->getLoopDepth();
if (Level <= CommonLevels && !SE->isLoopInvariant(Expression, LoopNest))
Loops.set(Level);
LoopNest = LoopNest->getParentLoop();
}
}
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
void DependenceInfo::unifySubscriptType(ArrayRef<Subscript *> Pairs) {
[DependenceAnalysis] Extend unifySubscriptType for handling coupled subscript groups. Summary: In continuation to an earlier commit to DependenceAnalysis.cpp by jingyue (r222100), the type for all subscripts in a coupled group need to be the same since constraints from one subscript may be propagated to another during testing. During testing, new SCEVs may be created and the operands for these need to be the same. This patch extends unifySubscriptType() to work on lists of subscript pairs, ensuring a common extended type for all of them. Test Plan: Added a test case to NonCanonicalizedSubscript.ll which causes dependence analysis to crash without this fix. All regression tests pass. Reviewers: spop, sebpop, jingyue Reviewed By: jingyue Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9698 llvm-svn: 238573
2015-05-30 00:58:08 +08:00
unsigned widestWidthSeen = 0;
Type *widestType;
// Go through each pair and find the widest bit to which we need
// to extend all of them.
Apply clang-tidy's modernize-loop-convert to lib/Analysis. Only minor manual fixes. No functionality change intended. llvm-svn: 273816
2016-06-27 01:27:42 +08:00
for (Subscript *Pair : Pairs) {
const SCEV *Src = Pair->Src;
const SCEV *Dst = Pair->Dst;
[DependenceAnalysis] Extend unifySubscriptType for handling coupled subscript groups. Summary: In continuation to an earlier commit to DependenceAnalysis.cpp by jingyue (r222100), the type for all subscripts in a coupled group need to be the same since constraints from one subscript may be propagated to another during testing. During testing, new SCEVs may be created and the operands for these need to be the same. This patch extends unifySubscriptType() to work on lists of subscript pairs, ensuring a common extended type for all of them. Test Plan: Added a test case to NonCanonicalizedSubscript.ll which causes dependence analysis to crash without this fix. All regression tests pass. Reviewers: spop, sebpop, jingyue Reviewed By: jingyue Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9698 llvm-svn: 238573
2015-05-30 00:58:08 +08:00
IntegerType *SrcTy = dyn_cast<IntegerType>(Src->getType());
IntegerType *DstTy = dyn_cast<IntegerType>(Dst->getType());
if (SrcTy == nullptr || DstTy == nullptr) {
assert(SrcTy == DstTy && "This function only unify integer types and "
"expect Src and Dst share the same type "
"otherwise.");
continue;
}
if (SrcTy->getBitWidth() > widestWidthSeen) {
widestWidthSeen = SrcTy->getBitWidth();
widestType = SrcTy;
}
if (DstTy->getBitWidth() > widestWidthSeen) {
widestWidthSeen = DstTy->getBitWidth();
widestType = DstTy;
}
[DependenceAnalysis] Allow subscripts of different types Summary: Several places in DependenceAnalysis assumes both SCEVs in a subscript pair share the same integer type. For instance, isKnownPredicate calls SE->getMinusSCEV(X, Y) which asserts X and Y share the same type. However, DependenceAnalysis fails to ensure this assumption when producing a subscript pair, causing tests such as NonCanonicalizedSubscript to crash. With this patch, DependenceAnalysis runs unifySubscriptType before producing any subscript pair, ensuring the assumption. Test Plan: Added NonCanonicalizedSubscript.ll on which DependenceAnalysis before the fix crashed because subscripts have different types. Reviewers: spop, sebpop, jingyue Reviewed By: jingyue Subscribers: eliben, meheff, llvm-commits Differential Revision: http://reviews.llvm.org/D6289 llvm-svn: 222100
2014-11-17 00:52:44 +08:00
}
[DependenceAnalysis] Extend unifySubscriptType for handling coupled subscript groups. Summary: In continuation to an earlier commit to DependenceAnalysis.cpp by jingyue (r222100), the type for all subscripts in a coupled group need to be the same since constraints from one subscript may be propagated to another during testing. During testing, new SCEVs may be created and the operands for these need to be the same. This patch extends unifySubscriptType() to work on lists of subscript pairs, ensuring a common extended type for all of them. Test Plan: Added a test case to NonCanonicalizedSubscript.ll which causes dependence analysis to crash without this fix. All regression tests pass. Reviewers: spop, sebpop, jingyue Reviewed By: jingyue Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9698 llvm-svn: 238573
2015-05-30 00:58:08 +08:00
assert(widestWidthSeen > 0);
// Now extend each pair to the widest seen.
Apply clang-tidy's modernize-loop-convert to lib/Analysis. Only minor manual fixes. No functionality change intended. llvm-svn: 273816
2016-06-27 01:27:42 +08:00
for (Subscript *Pair : Pairs) {
const SCEV *Src = Pair->Src;
const SCEV *Dst = Pair->Dst;
[DependenceAnalysis] Extend unifySubscriptType for handling coupled subscript groups. Summary: In continuation to an earlier commit to DependenceAnalysis.cpp by jingyue (r222100), the type for all subscripts in a coupled group need to be the same since constraints from one subscript may be propagated to another during testing. During testing, new SCEVs may be created and the operands for these need to be the same. This patch extends unifySubscriptType() to work on lists of subscript pairs, ensuring a common extended type for all of them. Test Plan: Added a test case to NonCanonicalizedSubscript.ll which causes dependence analysis to crash without this fix. All regression tests pass. Reviewers: spop, sebpop, jingyue Reviewed By: jingyue Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9698 llvm-svn: 238573
2015-05-30 00:58:08 +08:00
IntegerType *SrcTy = dyn_cast<IntegerType>(Src->getType());
IntegerType *DstTy = dyn_cast<IntegerType>(Dst->getType());
if (SrcTy == nullptr || DstTy == nullptr) {
assert(SrcTy == DstTy && "This function only unify integer types and "
"expect Src and Dst share the same type "
"otherwise.");
continue;
}
if (SrcTy->getBitWidth() < widestWidthSeen)
// Sign-extend Src to widestType
Apply clang-tidy's modernize-loop-convert to lib/Analysis. Only minor manual fixes. No functionality change intended. llvm-svn: 273816
2016-06-27 01:27:42 +08:00
Pair->Src = SE->getSignExtendExpr(Src, widestType);
[DependenceAnalysis] Extend unifySubscriptType for handling coupled subscript groups. Summary: In continuation to an earlier commit to DependenceAnalysis.cpp by jingyue (r222100), the type for all subscripts in a coupled group need to be the same since constraints from one subscript may be propagated to another during testing. During testing, new SCEVs may be created and the operands for these need to be the same. This patch extends unifySubscriptType() to work on lists of subscript pairs, ensuring a common extended type for all of them. Test Plan: Added a test case to NonCanonicalizedSubscript.ll which causes dependence analysis to crash without this fix. All regression tests pass. Reviewers: spop, sebpop, jingyue Reviewed By: jingyue Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9698 llvm-svn: 238573
2015-05-30 00:58:08 +08:00
if (DstTy->getBitWidth() < widestWidthSeen) {
// Sign-extend Dst to widestType
Apply clang-tidy's modernize-loop-convert to lib/Analysis. Only minor manual fixes. No functionality change intended. llvm-svn: 273816
2016-06-27 01:27:42 +08:00
Pair->Dst = SE->getSignExtendExpr(Dst, widestType);
[DependenceAnalysis] Extend unifySubscriptType for handling coupled subscript groups. Summary: In continuation to an earlier commit to DependenceAnalysis.cpp by jingyue (r222100), the type for all subscripts in a coupled group need to be the same since constraints from one subscript may be propagated to another during testing. During testing, new SCEVs may be created and the operands for these need to be the same. This patch extends unifySubscriptType() to work on lists of subscript pairs, ensuring a common extended type for all of them. Test Plan: Added a test case to NonCanonicalizedSubscript.ll which causes dependence analysis to crash without this fix. All regression tests pass. Reviewers: spop, sebpop, jingyue Reviewed By: jingyue Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9698 llvm-svn: 238573
2015-05-30 00:58:08 +08:00
}
[DependenceAnalysis] Allow subscripts of different types Summary: Several places in DependenceAnalysis assumes both SCEVs in a subscript pair share the same integer type. For instance, isKnownPredicate calls SE->getMinusSCEV(X, Y) which asserts X and Y share the same type. However, DependenceAnalysis fails to ensure this assumption when producing a subscript pair, causing tests such as NonCanonicalizedSubscript to crash. With this patch, DependenceAnalysis runs unifySubscriptType before producing any subscript pair, ensuring the assumption. Test Plan: Added NonCanonicalizedSubscript.ll on which DependenceAnalysis before the fix crashed because subscripts have different types. Reviewers: spop, sebpop, jingyue Reviewed By: jingyue Subscribers: eliben, meheff, llvm-commits Differential Revision: http://reviews.llvm.org/D6289 llvm-svn: 222100
2014-11-17 00:52:44 +08:00
}
}
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
// removeMatchingExtensions - Examines a subscript pair.
// If the source and destination are identically sign (or zero)
// extended, it strips off the extension in an effect to simplify
// the actual analysis.
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
void DependenceInfo::removeMatchingExtensions(Subscript *Pair) {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
const SCEV *Src = Pair->Src;
const SCEV *Dst = Pair->Dst;
if ((isa<SCEVZeroExtendExpr>(Src) && isa<SCEVZeroExtendExpr>(Dst)) ||
(isa<SCEVSignExtendExpr>(Src) && isa<SCEVSignExtendExpr>(Dst))) {
const SCEVCastExpr *SrcCast = cast<SCEVCastExpr>(Src);
const SCEVCastExpr *DstCast = cast<SCEVCastExpr>(Dst);
[DependenceAnalysis] Allow subscripts of different types Summary: Several places in DependenceAnalysis assumes both SCEVs in a subscript pair share the same integer type. For instance, isKnownPredicate calls SE->getMinusSCEV(X, Y) which asserts X and Y share the same type. However, DependenceAnalysis fails to ensure this assumption when producing a subscript pair, causing tests such as NonCanonicalizedSubscript to crash. With this patch, DependenceAnalysis runs unifySubscriptType before producing any subscript pair, ensuring the assumption. Test Plan: Added NonCanonicalizedSubscript.ll on which DependenceAnalysis before the fix crashed because subscripts have different types. Reviewers: spop, sebpop, jingyue Reviewed By: jingyue Subscribers: eliben, meheff, llvm-commits Differential Revision: http://reviews.llvm.org/D6289 llvm-svn: 222100
2014-11-17 00:52:44 +08:00
const SCEV *SrcCastOp = SrcCast->getOperand();
const SCEV *DstCastOp = DstCast->getOperand();
if (SrcCastOp->getType() == DstCastOp->getType()) {
Pair->Src = SrcCastOp;
Pair->Dst = DstCastOp;
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
}
}
}
// Examine the scev and return true iff it's linear.
// Collect any loops mentioned in the set of "Loops".
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
bool DependenceInfo::checkSrcSubscript(const SCEV *Src, const Loop *LoopNest,
SmallBitVector &Loops) {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
const SCEVAddRecExpr *AddRec = dyn_cast<SCEVAddRecExpr>(Src);
if (!AddRec)
return isLoopInvariant(Src, LoopNest);
const SCEV *Start = AddRec->getStart();
const SCEV *Step = AddRec->getStepRecurrence(*SE);
[DependenceAnalysis] Fix for PR21585: collectUpperBound triggers asserts collectUpperBound hits an assertion when the back edge count is wider then the desired type. If that happens, truncate the backedge count. Patch by Philip Pfaffe! llvm-svn: 237439
2015-05-15 20:17:22 +08:00
const SCEV *UB = SE->getBackedgeTakenCount(AddRec->getLoop());
if (!isa<SCEVCouldNotCompute>(UB)) {
if (SE->getTypeSizeInBits(Start->getType()) <
SE->getTypeSizeInBits(UB->getType())) {
if (!AddRec->getNoWrapFlags())
return false;
}
}
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
if (!isLoopInvariant(Step, LoopNest))
return false;
Loops.set(mapSrcLoop(AddRec->getLoop()));
return checkSrcSubscript(Start, LoopNest, Loops);
}
// Examine the scev and return true iff it's linear.
// Collect any loops mentioned in the set of "Loops".
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
bool DependenceInfo::checkDstSubscript(const SCEV *Dst, const Loop *LoopNest,
SmallBitVector &Loops) {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
const SCEVAddRecExpr *AddRec = dyn_cast<SCEVAddRecExpr>(Dst);
if (!AddRec)
return isLoopInvariant(Dst, LoopNest);
const SCEV *Start = AddRec->getStart();
const SCEV *Step = AddRec->getStepRecurrence(*SE);
[DependenceAnalysis] Fix for PR21585: collectUpperBound triggers asserts collectUpperBound hits an assertion when the back edge count is wider then the desired type. If that happens, truncate the backedge count. Patch by Philip Pfaffe! llvm-svn: 237439
2015-05-15 20:17:22 +08:00
const SCEV *UB = SE->getBackedgeTakenCount(AddRec->getLoop());
if (!isa<SCEVCouldNotCompute>(UB)) {
if (SE->getTypeSizeInBits(Start->getType()) <
SE->getTypeSizeInBits(UB->getType())) {
if (!AddRec->getNoWrapFlags())
return false;
}
}
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
if (!isLoopInvariant(Step, LoopNest))
return false;
Loops.set(mapDstLoop(AddRec->getLoop()));
return checkDstSubscript(Start, LoopNest, Loops);
}
// Examines the subscript pair (the Src and Dst SCEVs)
// and classifies it as either ZIV, SIV, RDIV, MIV, or Nonlinear.
// Collects the associated loops in a set.
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
DependenceInfo::Subscript::ClassificationKind
DependenceInfo::classifyPair(const SCEV *Src, const Loop *SrcLoopNest,
const SCEV *Dst, const Loop *DstLoopNest,
SmallBitVector &Loops) {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
SmallBitVector SrcLoops(MaxLevels + 1);
SmallBitVector DstLoops(MaxLevels + 1);
if (!checkSrcSubscript(Src, SrcLoopNest, SrcLoops))
return Subscript::NonLinear;
if (!checkDstSubscript(Dst, DstLoopNest, DstLoops))
return Subscript::NonLinear;
Loops = SrcLoops;
Loops |= DstLoops;
unsigned N = Loops.count();
if (N == 0)
return Subscript::ZIV;
if (N == 1)
return Subscript::SIV;
if (N == 2 && (SrcLoops.count() == 0 ||
DstLoops.count() == 0 ||
(SrcLoops.count() == 1 && DstLoops.count() == 1)))
return Subscript::RDIV;
return Subscript::MIV;
}
// A wrapper around SCEV::isKnownPredicate.
// Looks for cases where we're interested in comparing for equality.
// If both X and Y have been identically sign or zero extended,
// it strips off the (confusing) extensions before invoking
// SCEV::isKnownPredicate. Perhaps, someday, the ScalarEvolution package
// will be similarly updated.
//
// If SCEV::isKnownPredicate can't prove the predicate,
// we try simple subtraction, which seems to help in some cases
// involving symbolics.
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
bool DependenceInfo::isKnownPredicate(ICmpInst::Predicate Pred, const SCEV *X,
const SCEV *Y) const {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
if (Pred == CmpInst::ICMP_EQ ||
Pred == CmpInst::ICMP_NE) {
if ((isa<SCEVSignExtendExpr>(X) &&
isa<SCEVSignExtendExpr>(Y)) ||
(isa<SCEVZeroExtendExpr>(X) &&
isa<SCEVZeroExtendExpr>(Y))) {
const SCEVCastExpr *CX = cast<SCEVCastExpr>(X);
const SCEVCastExpr *CY = cast<SCEVCastExpr>(Y);
const SCEV *Xop = CX->getOperand();
const SCEV *Yop = CY->getOperand();
if (Xop->getType() == Yop->getType()) {
X = Xop;
Y = Yop;
}
}
}
if (SE->isKnownPredicate(Pred, X, Y))
return true;
// If SE->isKnownPredicate can't prove the condition,
// we try the brute-force approach of subtracting
// and testing the difference.
// By testing with SE->isKnownPredicate first, we avoid
// the possibility of overflow when the arguments are constants.
const SCEV *Delta = SE->getMinusSCEV(X, Y);
switch (Pred) {
case CmpInst::ICMP_EQ:
return Delta->isZero();
case CmpInst::ICMP_NE:
return SE->isKnownNonZero(Delta);
case CmpInst::ICMP_SGE:
return SE->isKnownNonNegative(Delta);
case CmpInst::ICMP_SLE:
return SE->isKnownNonPositive(Delta);
case CmpInst::ICMP_SGT:
return SE->isKnownPositive(Delta);
case CmpInst::ICMP_SLT:
return SE->isKnownNegative(Delta);
default:
llvm_unreachable("unexpected predicate in isKnownPredicate");
}
}
// All subscripts are all the same type.
// Loop bound may be smaller (e.g., a char).
// Should zero extend loop bound, since it's always >= 0.
[DependenceAnalysis] Fix for PR21585: collectUpperBound triggers asserts collectUpperBound hits an assertion when the back edge count is wider then the desired type. If that happens, truncate the backedge count. Patch by Philip Pfaffe! llvm-svn: 237439
2015-05-15 20:17:22 +08:00
// This routine collects upper bound and extends or truncates if needed.
// Truncating is safe when subscripts are known not to wrap. Cases without
// nowrap flags should have been rejected earlier.
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
// Return null if no bound available.
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
const SCEV *DependenceInfo::collectUpperBound(const Loop *L, Type *T) const {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
if (SE->hasLoopInvariantBackedgeTakenCount(L)) {
const SCEV *UB = SE->getBackedgeTakenCount(L);
[DependenceAnalysis] Fix for PR21585: collectUpperBound triggers asserts collectUpperBound hits an assertion when the back edge count is wider then the desired type. If that happens, truncate the backedge count. Patch by Philip Pfaffe! llvm-svn: 237439
2015-05-15 20:17:22 +08:00
return SE->getTruncateOrZeroExtend(UB, T);
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
}
[C++11] More 'nullptr' conversion. In some cases just using a boolean check instead of comparing to nullptr. llvm-svn: 206243
2014-04-15 12:59:12 +08:00
return nullptr;
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
}
// Calls collectUpperBound(), then attempts to cast it to SCEVConstant.
// If the cast fails, returns NULL.
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
const SCEVConstant *DependenceInfo::collectConstantUpperBound(const Loop *L,
Type *T) const {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
if (const SCEV *UB = collectUpperBound(L, T))
return dyn_cast<SCEVConstant>(UB);
[C++11] More 'nullptr' conversion. In some cases just using a boolean check instead of comparing to nullptr. llvm-svn: 206243
2014-04-15 12:59:12 +08:00
return nullptr;
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
}
// testZIV -
// When we have a pair of subscripts of the form [c1] and [c2],
// where c1 and c2 are both loop invariant, we attack it using
// the ZIV test. Basically, we test by comparing the two values,
// but there are actually three possible results:
// 1) the values are equal, so there's a dependence
// 2) the values are different, so there's no dependence
// 3) the values might be equal, so we have to assume a dependence.
//
// Return true if dependence disproved.
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
bool DependenceInfo::testZIV(const SCEV *Src, const SCEV *Dst,
FullDependence &Result) const {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
DEBUG(dbgs() << " src = " << *Src << "\n");
DEBUG(dbgs() << " dst = " << *Dst << "\n");
++ZIVapplications;
if (isKnownPredicate(CmpInst::ICMP_EQ, Src, Dst)) {
DEBUG(dbgs() << " provably dependent\n");
return false; // provably dependent
}
if (isKnownPredicate(CmpInst::ICMP_NE, Src, Dst)) {
DEBUG(dbgs() << " provably independent\n");
++ZIVindependence;
return true; // provably independent
}
DEBUG(dbgs() << " possibly dependent\n");
Result.Consistent = false;
return false; // possibly dependent
}
// strongSIVtest -
// From the paper, Practical Dependence Testing, Section 4.2.1
//
// When we have a pair of subscripts of the form [c1 + a*i] and [c2 + a*i],
// where i is an induction variable, c1 and c2 are loop invariant,
// and a is a constant, we can solve it exactly using the Strong SIV test.
//
// Can prove independence. Failing that, can compute distance (and direction).
// In the presence of symbolic terms, we can sometimes make progress.
//
// If there's a dependence,
//
// c1 + a*i = c2 + a*i'
//
// The dependence distance is
//
// d = i' - i = (c1 - c2)/a
//
// A dependence only exists if d is an integer and abs(d) <= U, where U is the
// loop's upper bound. If a dependence exists, the dependence direction is
// defined as
//
// { < if d > 0
// direction = { = if d = 0
// { > if d < 0
//
// Return true if dependence disproved.
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
bool DependenceInfo::strongSIVtest(const SCEV *Coeff, const SCEV *SrcConst,
const SCEV *DstConst, const Loop *CurLoop,
unsigned Level, FullDependence &Result,
Constraint &NewConstraint) const {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
DEBUG(dbgs() << "\tStrong SIV test\n");
DEBUG(dbgs() << "\t Coeff = " << *Coeff);
DEBUG(dbgs() << ", " << *Coeff->getType() << "\n");
DEBUG(dbgs() << "\t SrcConst = " << *SrcConst);
DEBUG(dbgs() << ", " << *SrcConst->getType() << "\n");
DEBUG(dbgs() << "\t DstConst = " << *DstConst);
DEBUG(dbgs() << ", " << *DstConst->getType() << "\n");
++StrongSIVapplications;
assert(0 < Level && Level <= CommonLevels && "level out of range");
Level--;
const SCEV *Delta = SE->getMinusSCEV(SrcConst, DstConst);
DEBUG(dbgs() << "\t Delta = " << *Delta);
DEBUG(dbgs() << ", " << *Delta->getType() << "\n");
// check that |Delta| < iteration count
if (const SCEV *UpperBound = collectUpperBound(CurLoop, Delta->getType())) {
DEBUG(dbgs() << "\t UpperBound = " << *UpperBound);
DEBUG(dbgs() << ", " << *UpperBound->getType() << "\n");
const SCEV *AbsDelta =
SE->isKnownNonNegative(Delta) ? Delta : SE->getNegativeSCEV(Delta);
const SCEV *AbsCoeff =
SE->isKnownNonNegative(Coeff) ? Coeff : SE->getNegativeSCEV(Coeff);
const SCEV *Product = SE->getMulExpr(UpperBound, AbsCoeff);
if (isKnownPredicate(CmpInst::ICMP_SGT, AbsDelta, Product)) {
// Distance greater than trip count - no dependence
++StrongSIVindependence;
++StrongSIVsuccesses;
return true;
}
}
// Can we compute distance?
if (isa<SCEVConstant>(Delta) && isa<SCEVConstant>(Coeff)) {
[SCEV] Add and use SCEVConstant::getAPInt; NFCI llvm-svn: 255921
2015-12-18 04:28:46 +08:00
APInt ConstDelta = cast<SCEVConstant>(Delta)->getAPInt();
APInt ConstCoeff = cast<SCEVConstant>(Coeff)->getAPInt();
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
APInt Distance = ConstDelta; // these need to be initialized
APInt Remainder = ConstDelta;
APInt::sdivrem(ConstDelta, ConstCoeff, Distance, Remainder);
DEBUG(dbgs() << "\t Distance = " << Distance << "\n");
DEBUG(dbgs() << "\t Remainder = " << Remainder << "\n");
// Make sure Coeff divides Delta exactly
if (Remainder != 0) {
// Coeff doesn't divide Distance, no dependence
++StrongSIVindependence;
++StrongSIVsuccesses;
return true;
}
Result.DV[Level].Distance = SE->getConstant(Distance);
NewConstraint.setDistance(SE->getConstant(Distance), CurLoop);
if (Distance.sgt(0))
Result.DV[Level].Direction &= Dependence::DVEntry::LT;
else if (Distance.slt(0))
Result.DV[Level].Direction &= Dependence::DVEntry::GT;
else
Result.DV[Level].Direction &= Dependence::DVEntry::EQ;
++StrongSIVsuccesses;
}
else if (Delta->isZero()) {
// since 0/X == 0
Result.DV[Level].Distance = Delta;
NewConstraint.setDistance(Delta, CurLoop);
Result.DV[Level].Direction &= Dependence::DVEntry::EQ;
++StrongSIVsuccesses;
}
else {
if (Coeff->isOne()) {
DEBUG(dbgs() << "\t Distance = " << *Delta << "\n");
Result.DV[Level].Distance = Delta; // since X/1 == X
NewConstraint.setDistance(Delta, CurLoop);
}
else {
Result.Consistent = false;
NewConstraint.setLine(Coeff,
SE->getNegativeSCEV(Coeff),
SE->getNegativeSCEV(Delta), CurLoop);
}
// maybe we can get a useful direction
bool DeltaMaybeZero = !SE->isKnownNonZero(Delta);
bool DeltaMaybePositive = !SE->isKnownNonPositive(Delta);
bool DeltaMaybeNegative = !SE->isKnownNonNegative(Delta);
bool CoeffMaybePositive = !SE->isKnownNonPositive(Coeff);
bool CoeffMaybeNegative = !SE->isKnownNonNegative(Coeff);
// The double negatives above are confusing.
// It helps to read !SE->isKnownNonZero(Delta)
// as "Delta might be Zero"
unsigned NewDirection = Dependence::DVEntry::NONE;
if ((DeltaMaybePositive && CoeffMaybePositive) ||
(DeltaMaybeNegative && CoeffMaybeNegative))
NewDirection = Dependence::DVEntry::LT;
if (DeltaMaybeZero)
NewDirection |= Dependence::DVEntry::EQ;
if ((DeltaMaybeNegative && CoeffMaybePositive) ||
(DeltaMaybePositive && CoeffMaybeNegative))
NewDirection |= Dependence::DVEntry::GT;
if (NewDirection < Result.DV[Level].Direction)
++StrongSIVsuccesses;
Result.DV[Level].Direction &= NewDirection;
}
return false;
}
// weakCrossingSIVtest -
// From the paper, Practical Dependence Testing, Section 4.2.2
//
// When we have a pair of subscripts of the form [c1 + a*i] and [c2 - a*i],
// where i is an induction variable, c1 and c2 are loop invariant,
// and a is a constant, we can solve it exactly using the
// Weak-Crossing SIV test.
//
// Given c1 + a*i = c2 - a*i', we can look for the intersection of
// the two lines, where i = i', yielding
//
// c1 + a*i = c2 - a*i
// 2a*i = c2 - c1
// i = (c2 - c1)/2a
//
// If i < 0, there is no dependence.
// If i > upperbound, there is no dependence.
// If i = 0 (i.e., if c1 = c2), there's a dependence with distance = 0.
// If i = upperbound, there's a dependence with distance = 0.
// If i is integral, there's a dependence (all directions).
// If the non-integer part = 1/2, there's a dependence (<> directions).
// Otherwise, there's no dependence.
//
// Can prove independence. Failing that,
// can sometimes refine the directions.
// Can determine iteration for splitting.
//
// Return true if dependence disproved.
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
bool DependenceInfo::weakCrossingSIVtest(
const SCEV *Coeff, const SCEV *SrcConst, const SCEV *DstConst,
const Loop *CurLoop, unsigned Level, FullDependence &Result,
Constraint &NewConstraint, const SCEV *&SplitIter) const {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
DEBUG(dbgs() << "\tWeak-Crossing SIV test\n");
DEBUG(dbgs() << "\t Coeff = " << *Coeff << "\n");
DEBUG(dbgs() << "\t SrcConst = " << *SrcConst << "\n");
DEBUG(dbgs() << "\t DstConst = " << *DstConst << "\n");
++WeakCrossingSIVapplications;
assert(0 < Level && Level <= CommonLevels && "Level out of range");
Level--;
Result.Consistent = false;
const SCEV *Delta = SE->getMinusSCEV(DstConst, SrcConst);
DEBUG(dbgs() << "\t Delta = " << *Delta << "\n");
NewConstraint.setLine(Coeff, Coeff, Delta, CurLoop);
if (Delta->isZero()) {
fix warning DependenceAnalysis.cpp:1164:32: warning: implicit truncation from 'int' to bitfield changes value from -5 to 3 [-Wconstant-conversion] Result.DV[Level].Direction &= ~Dependence::DVEntry::GT; ^ ~~~~~~~~~~~~~~~~~~~~~~~~ Patch from Preston Briggs <preston.briggs@gmail.com>. llvm-svn: 165784
2012-10-12 10:04:32 +08:00
Result.DV[Level].Direction &= unsigned(~Dependence::DVEntry::LT);
Result.DV[Level].Direction &= unsigned(~Dependence::DVEntry::GT);
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
++WeakCrossingSIVsuccesses;
if (!Result.DV[Level].Direction) {
++WeakCrossingSIVindependence;
return true;
}
Result.DV[Level].Distance = Delta; // = 0
return false;
}
const SCEVConstant *ConstCoeff = dyn_cast<SCEVConstant>(Coeff);
if (!ConstCoeff)
return false;
Result.DV[Level].Splitable = true;
if (SE->isKnownNegative(ConstCoeff)) {
ConstCoeff = dyn_cast<SCEVConstant>(SE->getNegativeSCEV(ConstCoeff));
assert(ConstCoeff &&
"dynamic cast of negative of ConstCoeff should yield constant");
Delta = SE->getNegativeSCEV(Delta);
}
assert(SE->isKnownPositive(ConstCoeff) && "ConstCoeff should be positive");
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
// compute SplitIter for use by DependenceInfo::getSplitIteration()
[SCEV] Introduce ScalarEvolution::getOne and getZero. Summary: It is fairly common to call SE->getConstant(Ty, 0) or SE->getConstant(Ty, 1); this change makes such uses a little bit briefer. I've refactored the call sites I could find easily to use getZero / getOne. Reviewers: hfinkel, majnemer, reames Subscribers: sanjoy, llvm-commits Differential Revision: http://reviews.llvm.org/D12947 llvm-svn: 248362
2015-09-23 09:59:04 +08:00
SplitIter = SE->getUDivExpr(
SE->getSMaxExpr(SE->getZero(Delta->getType()), Delta),
SE->getMulExpr(SE->getConstant(Delta->getType(), 2), ConstCoeff));
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
DEBUG(dbgs() << "\t Split iter = " << *SplitIter << "\n");
const SCEVConstant *ConstDelta = dyn_cast<SCEVConstant>(Delta);
if (!ConstDelta)
return false;
// We're certain that ConstCoeff > 0; therefore,
// if Delta < 0, then no dependence.
DEBUG(dbgs() << "\t Delta = " << *Delta << "\n");
DEBUG(dbgs() << "\t ConstCoeff = " << *ConstCoeff << "\n");
if (SE->isKnownNegative(Delta)) {
// No dependence, Delta < 0
++WeakCrossingSIVindependence;
++WeakCrossingSIVsuccesses;
return true;
}
// We're certain that Delta > 0 and ConstCoeff > 0.
// Check Delta/(2*ConstCoeff) against upper loop bound
if (const SCEV *UpperBound = collectUpperBound(CurLoop, Delta->getType())) {
DEBUG(dbgs() << "\t UpperBound = " << *UpperBound << "\n");
const SCEV *ConstantTwo = SE->getConstant(UpperBound->getType(), 2);
const SCEV *ML = SE->getMulExpr(SE->getMulExpr(ConstCoeff, UpperBound),
ConstantTwo);
DEBUG(dbgs() << "\t ML = " << *ML << "\n");
if (isKnownPredicate(CmpInst::ICMP_SGT, Delta, ML)) {
// Delta too big, no dependence
++WeakCrossingSIVindependence;
++WeakCrossingSIVsuccesses;
return true;
}
if (isKnownPredicate(CmpInst::ICMP_EQ, Delta, ML)) {
// i = i' = UB
fix warning DependenceAnalysis.cpp:1164:32: warning: implicit truncation from 'int' to bitfield changes value from -5 to 3 [-Wconstant-conversion] Result.DV[Level].Direction &= ~Dependence::DVEntry::GT; ^ ~~~~~~~~~~~~~~~~~~~~~~~~ Patch from Preston Briggs <preston.briggs@gmail.com>. llvm-svn: 165784
2012-10-12 10:04:32 +08:00
Result.DV[Level].Direction &= unsigned(~Dependence::DVEntry::LT);
Result.DV[Level].Direction &= unsigned(~Dependence::DVEntry::GT);
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
++WeakCrossingSIVsuccesses;
if (!Result.DV[Level].Direction) {
++WeakCrossingSIVindependence;
return true;
}
Result.DV[Level].Splitable = false;
[SCEV] Introduce ScalarEvolution::getOne and getZero. Summary: It is fairly common to call SE->getConstant(Ty, 0) or SE->getConstant(Ty, 1); this change makes such uses a little bit briefer. I've refactored the call sites I could find easily to use getZero / getOne. Reviewers: hfinkel, majnemer, reames Subscribers: sanjoy, llvm-commits Differential Revision: http://reviews.llvm.org/D12947 llvm-svn: 248362
2015-09-23 09:59:04 +08:00
Result.DV[Level].Distance = SE->getZero(Delta->getType());
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
return false;
}
}
// check that Coeff divides Delta
[SCEV] Add and use SCEVConstant::getAPInt; NFCI llvm-svn: 255921
2015-12-18 04:28:46 +08:00
APInt APDelta = ConstDelta->getAPInt();
APInt APCoeff = ConstCoeff->getAPInt();
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
APInt Distance = APDelta; // these need to be initialzed
APInt Remainder = APDelta;
APInt::sdivrem(APDelta, APCoeff, Distance, Remainder);
DEBUG(dbgs() << "\t Remainder = " << Remainder << "\n");
if (Remainder != 0) {
// Coeff doesn't divide Delta, no dependence
++WeakCrossingSIVindependence;
++WeakCrossingSIVsuccesses;
return true;
}
DEBUG(dbgs() << "\t Distance = " << Distance << "\n");
// if 2*Coeff doesn't divide Delta, then the equal direction isn't possible
APInt Two = APInt(Distance.getBitWidth(), 2, true);
Remainder = Distance.srem(Two);
DEBUG(dbgs() << "\t Remainder = " << Remainder << "\n");
if (Remainder != 0) {
// Equal direction isn't possible
fix warning DependenceAnalysis.cpp:1164:32: warning: implicit truncation from 'int' to bitfield changes value from -5 to 3 [-Wconstant-conversion] Result.DV[Level].Direction &= ~Dependence::DVEntry::GT; ^ ~~~~~~~~~~~~~~~~~~~~~~~~ Patch from Preston Briggs <preston.briggs@gmail.com>. llvm-svn: 165784
2012-10-12 10:04:32 +08:00
Result.DV[Level].Direction &= unsigned(~Dependence::DVEntry::EQ);
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
++WeakCrossingSIVsuccesses;
}
return false;
}
// Kirch's algorithm, from
//
// Optimizing Supercompilers for Supercomputers
// Michael Wolfe
// MIT Press, 1989
//
// Program 2.1, page 29.
// Computes the GCD of AM and BM.
Fix comment of findGCD. llvm-svn: 198660
2014-01-07 09:54:16 +08:00
// Also finds a solution to the equation ax - by = gcd(a, b).
// Returns true if dependence disproved; i.e., gcd does not divide Delta.
Apply most suggestions of clang-tidy's performance-unnecessary-value-param Avoids unnecessary copies. All changes audited & pass tests with asan. No functional change intended. llvm-svn: 272190
2016-06-09 03:09:22 +08:00
static bool findGCD(unsigned Bits, const APInt &AM, const APInt &BM,
const APInt &Delta, APInt &G, APInt &X, APInt &Y) {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
APInt A0(Bits, 1, true), A1(Bits, 0, true);
APInt B0(Bits, 0, true), B1(Bits, 1, true);
APInt G0 = AM.abs();
APInt G1 = BM.abs();
APInt Q = G0; // these need to be initialized
APInt R = G0;
APInt::sdivrem(G0, G1, Q, R);
while (R != 0) {
APInt A2 = A0 - Q*A1; A0 = A1; A1 = A2;
APInt B2 = B0 - Q*B1; B0 = B1; B1 = B2;
G0 = G1; G1 = R;
APInt::sdivrem(G0, G1, Q, R);
}
G = G1;
DEBUG(dbgs() << "\t GCD = " << G << "\n");
X = AM.slt(0) ? -A1 : A1;
Y = BM.slt(0) ? B1 : -B1;
// make sure gcd divides Delta
R = Delta.srem(G);
if (R != 0)
return true; // gcd doesn't divide Delta, no dependence
Q = Delta.sdiv(G);
X *= Q;
Y *= Q;
return false;
}
Apply most suggestions of clang-tidy's performance-unnecessary-value-param Avoids unnecessary copies. All changes audited & pass tests with asan. No functional change intended. llvm-svn: 272190
2016-06-09 03:09:22 +08:00
static APInt floorOfQuotient(const APInt &A, const APInt &B) {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
APInt Q = A; // these need to be initialized
APInt R = A;
APInt::sdivrem(A, B, Q, R);
if (R == 0)
return Q;
if ((A.sgt(0) && B.sgt(0)) ||
(A.slt(0) && B.slt(0)))
return Q;
else
return Q - 1;
}
Apply most suggestions of clang-tidy's performance-unnecessary-value-param Avoids unnecessary copies. All changes audited & pass tests with asan. No functional change intended. llvm-svn: 272190
2016-06-09 03:09:22 +08:00
static APInt ceilingOfQuotient(const APInt &A, const APInt &B) {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
APInt Q = A; // these need to be initialized
APInt R = A;
APInt::sdivrem(A, B, Q, R);
if (R == 0)
return Q;
if ((A.sgt(0) && B.sgt(0)) ||
(A.slt(0) && B.slt(0)))
return Q + 1;
else
return Q;
}
static
APInt maxAPInt(APInt A, APInt B) {
return A.sgt(B) ? A : B;
}
static
APInt minAPInt(APInt A, APInt B) {
return A.slt(B) ? A : B;
}
// exactSIVtest -
// When we have a pair of subscripts of the form [c1 + a1*i] and [c2 + a2*i],
// where i is an induction variable, c1 and c2 are loop invariant, and a1
// and a2 are constant, we can solve it exactly using an algorithm developed
// by Banerjee and Wolfe. See Section 2.5.3 in
//
// Optimizing Supercompilers for Supercomputers
// Michael Wolfe
// MIT Press, 1989
//
// It's slower than the specialized tests (strong SIV, weak-zero SIV, etc),
// so use them if possible. They're also a bit better with symbolics and,
// in the case of the strong SIV test, can compute Distances.
//
// Return true if dependence disproved.
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
bool DependenceInfo::exactSIVtest(const SCEV *SrcCoeff, const SCEV *DstCoeff,
const SCEV *SrcConst, const SCEV *DstConst,
const Loop *CurLoop, unsigned Level,
FullDependence &Result,
Constraint &NewConstraint) const {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
DEBUG(dbgs() << "\tExact SIV test\n");
DEBUG(dbgs() << "\t SrcCoeff = " << *SrcCoeff << " = AM\n");
DEBUG(dbgs() << "\t DstCoeff = " << *DstCoeff << " = BM\n");
DEBUG(dbgs() << "\t SrcConst = " << *SrcConst << "\n");
DEBUG(dbgs() << "\t DstConst = " << *DstConst << "\n");
++ExactSIVapplications;
assert(0 < Level && Level <= CommonLevels && "Level out of range");
Level--;
Result.Consistent = false;
const SCEV *Delta = SE->getMinusSCEV(DstConst, SrcConst);
DEBUG(dbgs() << "\t Delta = " << *Delta << "\n");
NewConstraint.setLine(SrcCoeff, SE->getNegativeSCEV(DstCoeff),
Delta, CurLoop);
const SCEVConstant *ConstDelta = dyn_cast<SCEVConstant>(Delta);
const SCEVConstant *ConstSrcCoeff = dyn_cast<SCEVConstant>(SrcCoeff);
const SCEVConstant *ConstDstCoeff = dyn_cast<SCEVConstant>(DstCoeff);
if (!ConstDelta || !ConstSrcCoeff || !ConstDstCoeff)
return false;
// find gcd
APInt G, X, Y;
[SCEV] Add and use SCEVConstant::getAPInt; NFCI llvm-svn: 255921
2015-12-18 04:28:46 +08:00
APInt AM = ConstSrcCoeff->getAPInt();
APInt BM = ConstDstCoeff->getAPInt();
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
unsigned Bits = AM.getBitWidth();
[SCEV] Add and use SCEVConstant::getAPInt; NFCI llvm-svn: 255921
2015-12-18 04:28:46 +08:00
if (findGCD(Bits, AM, BM, ConstDelta->getAPInt(), G, X, Y)) {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
// gcd doesn't divide Delta, no dependence
++ExactSIVindependence;
++ExactSIVsuccesses;
return true;
}
DEBUG(dbgs() << "\t X = " << X << ", Y = " << Y << "\n");
// since SCEV construction normalizes, LM = 0
APInt UM(Bits, 1, true);
bool UMvalid = false;
// UM is perhaps unavailable, let's check
if (const SCEVConstant *CUB =
collectConstantUpperBound(CurLoop, Delta->getType())) {
[SCEV] Add and use SCEVConstant::getAPInt; NFCI llvm-svn: 255921
2015-12-18 04:28:46 +08:00
UM = CUB->getAPInt();
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
DEBUG(dbgs() << "\t UM = " << UM << "\n");
UMvalid = true;
}
APInt TU(APInt::getSignedMaxValue(Bits));
APInt TL(APInt::getSignedMinValue(Bits));
// test(BM/G, LM-X) and test(-BM/G, X-UM)
APInt TMUL = BM.sdiv(G);
if (TMUL.sgt(0)) {
TL = maxAPInt(TL, ceilingOfQuotient(-X, TMUL));
DEBUG(dbgs() << "\t TL = " << TL << "\n");
if (UMvalid) {
TU = minAPInt(TU, floorOfQuotient(UM - X, TMUL));
DEBUG(dbgs() << "\t TU = " << TU << "\n");
}
}
else {
TU = minAPInt(TU, floorOfQuotient(-X, TMUL));
DEBUG(dbgs() << "\t TU = " << TU << "\n");
if (UMvalid) {
TL = maxAPInt(TL, ceilingOfQuotient(UM - X, TMUL));
DEBUG(dbgs() << "\t TL = " << TL << "\n");
}
}
// test(AM/G, LM-Y) and test(-AM/G, Y-UM)
TMUL = AM.sdiv(G);
if (TMUL.sgt(0)) {
TL = maxAPInt(TL, ceilingOfQuotient(-Y, TMUL));
DEBUG(dbgs() << "\t TL = " << TL << "\n");
if (UMvalid) {
TU = minAPInt(TU, floorOfQuotient(UM - Y, TMUL));
DEBUG(dbgs() << "\t TU = " << TU << "\n");
}
}
else {
TU = minAPInt(TU, floorOfQuotient(-Y, TMUL));
DEBUG(dbgs() << "\t TU = " << TU << "\n");
if (UMvalid) {
TL = maxAPInt(TL, ceilingOfQuotient(UM - Y, TMUL));
DEBUG(dbgs() << "\t TL = " << TL << "\n");
}
}
if (TL.sgt(TU)) {
++ExactSIVindependence;
++ExactSIVsuccesses;
return true;
}
// explore directions
unsigned NewDirection = Dependence::DVEntry::NONE;
// less than
APInt SaveTU(TU); // save these
APInt SaveTL(TL);
DEBUG(dbgs() << "\t exploring LT direction\n");
TMUL = AM - BM;
if (TMUL.sgt(0)) {
TL = maxAPInt(TL, ceilingOfQuotient(X - Y + 1, TMUL));
DEBUG(dbgs() << "\t\t TL = " << TL << "\n");
}
else {
TU = minAPInt(TU, floorOfQuotient(X - Y + 1, TMUL));
DEBUG(dbgs() << "\t\t TU = " << TU << "\n");
}
if (TL.sle(TU)) {
NewDirection |= Dependence::DVEntry::LT;
++ExactSIVsuccesses;
}
// equal
TU = SaveTU; // restore
TL = SaveTL;
DEBUG(dbgs() << "\t exploring EQ direction\n");
if (TMUL.sgt(0)) {
TL = maxAPInt(TL, ceilingOfQuotient(X - Y, TMUL));
DEBUG(dbgs() << "\t\t TL = " << TL << "\n");
}
else {
TU = minAPInt(TU, floorOfQuotient(X - Y, TMUL));
DEBUG(dbgs() << "\t\t TU = " << TU << "\n");
}
TMUL = BM - AM;
if (TMUL.sgt(0)) {
TL = maxAPInt(TL, ceilingOfQuotient(Y - X, TMUL));
DEBUG(dbgs() << "\t\t TL = " << TL << "\n");
}
else {
TU = minAPInt(TU, floorOfQuotient(Y - X, TMUL));
DEBUG(dbgs() << "\t\t TU = " << TU << "\n");
}
if (TL.sle(TU)) {
NewDirection |= Dependence::DVEntry::EQ;
++ExactSIVsuccesses;
}
// greater than
TU = SaveTU; // restore
TL = SaveTL;
DEBUG(dbgs() << "\t exploring GT direction\n");
if (TMUL.sgt(0)) {
TL = maxAPInt(TL, ceilingOfQuotient(Y - X + 1, TMUL));
DEBUG(dbgs() << "\t\t TL = " << TL << "\n");
}
else {
TU = minAPInt(TU, floorOfQuotient(Y - X + 1, TMUL));
DEBUG(dbgs() << "\t\t TU = " << TU << "\n");
}
if (TL.sle(TU)) {
NewDirection |= Dependence::DVEntry::GT;
++ExactSIVsuccesses;
}
// finished
Result.DV[Level].Direction &= NewDirection;
if (Result.DV[Level].Direction == Dependence::DVEntry::NONE)
++ExactSIVindependence;
return Result.DV[Level].Direction == Dependence::DVEntry::NONE;
}
// Return true if the divisor evenly divides the dividend.
static
bool isRemainderZero(const SCEVConstant *Dividend,
const SCEVConstant *Divisor) {
Avoid copies of std::strings and APInt/APFloats where we only read from it As suggested by clang-tidy's performance-unnecessary-copy-initialization. This can easily hit lifetime issues, so I audited every change and ran the tests under asan, which came back clean. llvm-svn: 272126
2016-06-08 18:01:20 +08:00
const APInt &ConstDividend = Dividend->getAPInt();
const APInt &ConstDivisor = Divisor->getAPInt();
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
return ConstDividend.srem(ConstDivisor) == 0;
}
// weakZeroSrcSIVtest -
// From the paper, Practical Dependence Testing, Section 4.2.2
//
// When we have a pair of subscripts of the form [c1] and [c2 + a*i],
// where i is an induction variable, c1 and c2 are loop invariant,
// and a is a constant, we can solve it exactly using the
// Weak-Zero SIV test.
//
// Given
//
// c1 = c2 + a*i
//
// we get
//
// (c1 - c2)/a = i
//
// If i is not an integer, there's no dependence.
// If i < 0 or > UB, there's no dependence.
// If i = 0, the direction is <= and peeling the
// 1st iteration will break the dependence.
// If i = UB, the direction is >= and peeling the
// last iteration will break the dependence.
// Otherwise, the direction is *.
//
// Can prove independence. Failing that, we can sometimes refine
// the directions. Can sometimes show that first or last
// iteration carries all the dependences (so worth peeling).
//
// (see also weakZeroDstSIVtest)
//
// Return true if dependence disproved.
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
bool DependenceInfo::weakZeroSrcSIVtest(const SCEV *DstCoeff,
const SCEV *SrcConst,
const SCEV *DstConst,
const Loop *CurLoop, unsigned Level,
FullDependence &Result,
Constraint &NewConstraint) const {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
// For the WeakSIV test, it's possible the loop isn't common to
// the Src and Dst loops. If it isn't, then there's no need to
// record a direction.
DEBUG(dbgs() << "\tWeak-Zero (src) SIV test\n");
DEBUG(dbgs() << "\t DstCoeff = " << *DstCoeff << "\n");
DEBUG(dbgs() << "\t SrcConst = " << *SrcConst << "\n");
DEBUG(dbgs() << "\t DstConst = " << *DstConst << "\n");
++WeakZeroSIVapplications;
assert(0 < Level && Level <= MaxLevels && "Level out of range");
Level--;
Result.Consistent = false;
const SCEV *Delta = SE->getMinusSCEV(SrcConst, DstConst);
[SCEV] Introduce ScalarEvolution::getOne and getZero. Summary: It is fairly common to call SE->getConstant(Ty, 0) or SE->getConstant(Ty, 1); this change makes such uses a little bit briefer. I've refactored the call sites I could find easily to use getZero / getOne. Reviewers: hfinkel, majnemer, reames Subscribers: sanjoy, llvm-commits Differential Revision: http://reviews.llvm.org/D12947 llvm-svn: 248362
2015-09-23 09:59:04 +08:00
NewConstraint.setLine(SE->getZero(Delta->getType()), DstCoeff, Delta,
CurLoop);
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
DEBUG(dbgs() << "\t Delta = " << *Delta << "\n");
if (isKnownPredicate(CmpInst::ICMP_EQ, SrcConst, DstConst)) {
if (Level < CommonLevels) {
Result.DV[Level].Direction &= Dependence::DVEntry::LE;
Result.DV[Level].PeelFirst = true;
++WeakZeroSIVsuccesses;
}
return false; // dependences caused by first iteration
}
const SCEVConstant *ConstCoeff = dyn_cast<SCEVConstant>(DstCoeff);
if (!ConstCoeff)
return false;
const SCEV *AbsCoeff =
SE->isKnownNegative(ConstCoeff) ?
SE->getNegativeSCEV(ConstCoeff) : ConstCoeff;
const SCEV *NewDelta =
SE->isKnownNegative(ConstCoeff) ? SE->getNegativeSCEV(Delta) : Delta;
// check that Delta/SrcCoeff < iteration count
// really check NewDelta < count*AbsCoeff
if (const SCEV *UpperBound = collectUpperBound(CurLoop, Delta->getType())) {
DEBUG(dbgs() << "\t UpperBound = " << *UpperBound << "\n");
const SCEV *Product = SE->getMulExpr(AbsCoeff, UpperBound);
if (isKnownPredicate(CmpInst::ICMP_SGT, NewDelta, Product)) {
++WeakZeroSIVindependence;
++WeakZeroSIVsuccesses;
return true;
}
if (isKnownPredicate(CmpInst::ICMP_EQ, NewDelta, Product)) {
// dependences caused by last iteration
if (Level < CommonLevels) {
Result.DV[Level].Direction &= Dependence::DVEntry::GE;
Result.DV[Level].PeelLast = true;
++WeakZeroSIVsuccesses;
}
return false;
}
}
// check that Delta/SrcCoeff >= 0
// really check that NewDelta >= 0
if (SE->isKnownNegative(NewDelta)) {
// No dependence, newDelta < 0
++WeakZeroSIVindependence;
++WeakZeroSIVsuccesses;
return true;
}
// if SrcCoeff doesn't divide Delta, then no dependence
if (isa<SCEVConstant>(Delta) &&
!isRemainderZero(cast<SCEVConstant>(Delta), ConstCoeff)) {
++WeakZeroSIVindependence;
++WeakZeroSIVsuccesses;
return true;
}
return false;
}
// weakZeroDstSIVtest -
// From the paper, Practical Dependence Testing, Section 4.2.2
//
// When we have a pair of subscripts of the form [c1 + a*i] and [c2],
// where i is an induction variable, c1 and c2 are loop invariant,
// and a is a constant, we can solve it exactly using the
// Weak-Zero SIV test.
//
// Given
//
// c1 + a*i = c2
//
// we get
//
// i = (c2 - c1)/a
//
// If i is not an integer, there's no dependence.
// If i < 0 or > UB, there's no dependence.
// If i = 0, the direction is <= and peeling the
// 1st iteration will break the dependence.
// If i = UB, the direction is >= and peeling the
// last iteration will break the dependence.
// Otherwise, the direction is *.
//
// Can prove independence. Failing that, we can sometimes refine
// the directions. Can sometimes show that first or last
// iteration carries all the dependences (so worth peeling).
//
// (see also weakZeroSrcSIVtest)
//
// Return true if dependence disproved.
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
bool DependenceInfo::weakZeroDstSIVtest(const SCEV *SrcCoeff,
const SCEV *SrcConst,
const SCEV *DstConst,
const Loop *CurLoop, unsigned Level,
FullDependence &Result,
Constraint &NewConstraint) const {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
// For the WeakSIV test, it's possible the loop isn't common to the
// Src and Dst loops. If it isn't, then there's no need to record a direction.
DEBUG(dbgs() << "\tWeak-Zero (dst) SIV test\n");
DEBUG(dbgs() << "\t SrcCoeff = " << *SrcCoeff << "\n");
DEBUG(dbgs() << "\t SrcConst = " << *SrcConst << "\n");
DEBUG(dbgs() << "\t DstConst = " << *DstConst << "\n");
++WeakZeroSIVapplications;
assert(0 < Level && Level <= SrcLevels && "Level out of range");
Level--;
Result.Consistent = false;
const SCEV *Delta = SE->getMinusSCEV(DstConst, SrcConst);
[SCEV] Introduce ScalarEvolution::getOne and getZero. Summary: It is fairly common to call SE->getConstant(Ty, 0) or SE->getConstant(Ty, 1); this change makes such uses a little bit briefer. I've refactored the call sites I could find easily to use getZero / getOne. Reviewers: hfinkel, majnemer, reames Subscribers: sanjoy, llvm-commits Differential Revision: http://reviews.llvm.org/D12947 llvm-svn: 248362
2015-09-23 09:59:04 +08:00
NewConstraint.setLine(SrcCoeff, SE->getZero(Delta->getType()), Delta,
CurLoop);
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
DEBUG(dbgs() << "\t Delta = " << *Delta << "\n");
if (isKnownPredicate(CmpInst::ICMP_EQ, DstConst, SrcConst)) {
if (Level < CommonLevels) {
Result.DV[Level].Direction &= Dependence::DVEntry::LE;
Result.DV[Level].PeelFirst = true;
++WeakZeroSIVsuccesses;
}
return false; // dependences caused by first iteration
}
const SCEVConstant *ConstCoeff = dyn_cast<SCEVConstant>(SrcCoeff);
if (!ConstCoeff)
return false;
const SCEV *AbsCoeff =
SE->isKnownNegative(ConstCoeff) ?
SE->getNegativeSCEV(ConstCoeff) : ConstCoeff;
const SCEV *NewDelta =
SE->isKnownNegative(ConstCoeff) ? SE->getNegativeSCEV(Delta) : Delta;
// check that Delta/SrcCoeff < iteration count
// really check NewDelta < count*AbsCoeff
if (const SCEV *UpperBound = collectUpperBound(CurLoop, Delta->getType())) {
DEBUG(dbgs() << "\t UpperBound = " << *UpperBound << "\n");
const SCEV *Product = SE->getMulExpr(AbsCoeff, UpperBound);
if (isKnownPredicate(CmpInst::ICMP_SGT, NewDelta, Product)) {
++WeakZeroSIVindependence;
++WeakZeroSIVsuccesses;
return true;
}
if (isKnownPredicate(CmpInst::ICMP_EQ, NewDelta, Product)) {
// dependences caused by last iteration
if (Level < CommonLevels) {
Result.DV[Level].Direction &= Dependence::DVEntry::GE;
Result.DV[Level].PeelLast = true;
++WeakZeroSIVsuccesses;
}
return false;
}
}
// check that Delta/SrcCoeff >= 0
// really check that NewDelta >= 0
if (SE->isKnownNegative(NewDelta)) {
// No dependence, newDelta < 0
++WeakZeroSIVindependence;
++WeakZeroSIVsuccesses;
return true;
}
// if SrcCoeff doesn't divide Delta, then no dependence
if (isa<SCEVConstant>(Delta) &&
!isRemainderZero(cast<SCEVConstant>(Delta), ConstCoeff)) {
++WeakZeroSIVindependence;
++WeakZeroSIVsuccesses;
return true;
}
return false;
}
// exactRDIVtest - Tests the RDIV subscript pair for dependence.
// Things of the form [c1 + a*i] and [c2 + b*j],
// where i and j are induction variable, c1 and c2 are loop invariant,
// and a and b are constants.
// Returns true if any possible dependence is disproved.
Fix a couple of comment typos. llvm-svn: 167113
2012-10-31 19:25:32 +08:00
// Marks the result as inconsistent.
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
// Works in some cases that symbolicRDIVtest doesn't, and vice versa.
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
bool DependenceInfo::exactRDIVtest(const SCEV *SrcCoeff, const SCEV *DstCoeff,
const SCEV *SrcConst, const SCEV *DstConst,
const Loop *SrcLoop, const Loop *DstLoop,
FullDependence &Result) const {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
DEBUG(dbgs() << "\tExact RDIV test\n");
DEBUG(dbgs() << "\t SrcCoeff = " << *SrcCoeff << " = AM\n");
DEBUG(dbgs() << "\t DstCoeff = " << *DstCoeff << " = BM\n");
DEBUG(dbgs() << "\t SrcConst = " << *SrcConst << "\n");
DEBUG(dbgs() << "\t DstConst = " << *DstConst << "\n");
++ExactRDIVapplications;
Result.Consistent = false;
const SCEV *Delta = SE->getMinusSCEV(DstConst, SrcConst);
DEBUG(dbgs() << "\t Delta = " << *Delta << "\n");
const SCEVConstant *ConstDelta = dyn_cast<SCEVConstant>(Delta);
const SCEVConstant *ConstSrcCoeff = dyn_cast<SCEVConstant>(SrcCoeff);
const SCEVConstant *ConstDstCoeff = dyn_cast<SCEVConstant>(DstCoeff);
if (!ConstDelta || !ConstSrcCoeff || !ConstDstCoeff)
return false;
// find gcd
APInt G, X, Y;
[SCEV] Add and use SCEVConstant::getAPInt; NFCI llvm-svn: 255921
2015-12-18 04:28:46 +08:00
APInt AM = ConstSrcCoeff->getAPInt();
APInt BM = ConstDstCoeff->getAPInt();
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
unsigned Bits = AM.getBitWidth();
[SCEV] Add and use SCEVConstant::getAPInt; NFCI llvm-svn: 255921
2015-12-18 04:28:46 +08:00
if (findGCD(Bits, AM, BM, ConstDelta->getAPInt(), G, X, Y)) {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
// gcd doesn't divide Delta, no dependence
++ExactRDIVindependence;
return true;
}
DEBUG(dbgs() << "\t X = " << X << ", Y = " << Y << "\n");
// since SCEV construction seems to normalize, LM = 0
APInt SrcUM(Bits, 1, true);
bool SrcUMvalid = false;
// SrcUM is perhaps unavailable, let's check
if (const SCEVConstant *UpperBound =
collectConstantUpperBound(SrcLoop, Delta->getType())) {
[SCEV] Add and use SCEVConstant::getAPInt; NFCI llvm-svn: 255921
2015-12-18 04:28:46 +08:00
SrcUM = UpperBound->getAPInt();
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
DEBUG(dbgs() << "\t SrcUM = " << SrcUM << "\n");
SrcUMvalid = true;
}
APInt DstUM(Bits, 1, true);
bool DstUMvalid = false;
// UM is perhaps unavailable, let's check
if (const SCEVConstant *UpperBound =
collectConstantUpperBound(DstLoop, Delta->getType())) {
[SCEV] Add and use SCEVConstant::getAPInt; NFCI llvm-svn: 255921
2015-12-18 04:28:46 +08:00
DstUM = UpperBound->getAPInt();
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
DEBUG(dbgs() << "\t DstUM = " << DstUM << "\n");
DstUMvalid = true;
}
APInt TU(APInt::getSignedMaxValue(Bits));
APInt TL(APInt::getSignedMinValue(Bits));
// test(BM/G, LM-X) and test(-BM/G, X-UM)
APInt TMUL = BM.sdiv(G);
if (TMUL.sgt(0)) {
TL = maxAPInt(TL, ceilingOfQuotient(-X, TMUL));
DEBUG(dbgs() << "\t TL = " << TL << "\n");
if (SrcUMvalid) {
TU = minAPInt(TU, floorOfQuotient(SrcUM - X, TMUL));
DEBUG(dbgs() << "\t TU = " << TU << "\n");
}
}
else {
TU = minAPInt(TU, floorOfQuotient(-X, TMUL));
DEBUG(dbgs() << "\t TU = " << TU << "\n");
if (SrcUMvalid) {
TL = maxAPInt(TL, ceilingOfQuotient(SrcUM - X, TMUL));
DEBUG(dbgs() << "\t TL = " << TL << "\n");
}
}
// test(AM/G, LM-Y) and test(-AM/G, Y-UM)
TMUL = AM.sdiv(G);
if (TMUL.sgt(0)) {
TL = maxAPInt(TL, ceilingOfQuotient(-Y, TMUL));
DEBUG(dbgs() << "\t TL = " << TL << "\n");
if (DstUMvalid) {
TU = minAPInt(TU, floorOfQuotient(DstUM - Y, TMUL));
DEBUG(dbgs() << "\t TU = " << TU << "\n");
}
}
else {
TU = minAPInt(TU, floorOfQuotient(-Y, TMUL));
DEBUG(dbgs() << "\t TU = " << TU << "\n");
if (DstUMvalid) {
TL = maxAPInt(TL, ceilingOfQuotient(DstUM - Y, TMUL));
DEBUG(dbgs() << "\t TL = " << TL << "\n");
}
}
if (TL.sgt(TU))
++ExactRDIVindependence;
return TL.sgt(TU);
}
// symbolicRDIVtest -
// In Section 4.5 of the Practical Dependence Testing paper,the authors
// introduce a special case of Banerjee's Inequalities (also called the
// Extreme-Value Test) that can handle some of the SIV and RDIV cases,
// particularly cases with symbolics. Since it's only able to disprove
// dependence (not compute distances or directions), we'll use it as a
// fall back for the other tests.
//
// When we have a pair of subscripts of the form [c1 + a1*i] and [c2 + a2*j]
// where i and j are induction variables and c1 and c2 are loop invariants,
// we can use the symbolic tests to disprove some dependences, serving as a
// backup for the RDIV test. Note that i and j can be the same variable,
// letting this test serve as a backup for the various SIV tests.
//
// For a dependence to exist, c1 + a1*i must equal c2 + a2*j for some
// 0 <= i <= N1 and some 0 <= j <= N2, where N1 and N2 are the (normalized)
// loop bounds for the i and j loops, respectively. So, ...
//
// c1 + a1*i = c2 + a2*j
// a1*i - a2*j = c2 - c1
//
// To test for a dependence, we compute c2 - c1 and make sure it's in the
// range of the maximum and minimum possible values of a1*i - a2*j.
// Considering the signs of a1 and a2, we have 4 possible cases:
//
// 1) If a1 >= 0 and a2 >= 0, then
// a1*0 - a2*N2 <= c2 - c1 <= a1*N1 - a2*0
// -a2*N2 <= c2 - c1 <= a1*N1
//
// 2) If a1 >= 0 and a2 <= 0, then
// a1*0 - a2*0 <= c2 - c1 <= a1*N1 - a2*N2
// 0 <= c2 - c1 <= a1*N1 - a2*N2
//
// 3) If a1 <= 0 and a2 >= 0, then
// a1*N1 - a2*N2 <= c2 - c1 <= a1*0 - a2*0
// a1*N1 - a2*N2 <= c2 - c1 <= 0
//
// 4) If a1 <= 0 and a2 <= 0, then
// a1*N1 - a2*0 <= c2 - c1 <= a1*0 - a2*N2
// a1*N1 <= c2 - c1 <= -a2*N2
//
// return true if dependence disproved
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
bool DependenceInfo::symbolicRDIVtest(const SCEV *A1, const SCEV *A2,
const SCEV *C1, const SCEV *C2,
const Loop *Loop1,
const Loop *Loop2) const {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
++SymbolicRDIVapplications;
DEBUG(dbgs() << "\ttry symbolic RDIV test\n");
DEBUG(dbgs() << "\t A1 = " << *A1);
DEBUG(dbgs() << ", type = " << *A1->getType() << "\n");
DEBUG(dbgs() << "\t A2 = " << *A2 << "\n");
DEBUG(dbgs() << "\t C1 = " << *C1 << "\n");
DEBUG(dbgs() << "\t C2 = " << *C2 << "\n");
const SCEV *N1 = collectUpperBound(Loop1, A1->getType());
const SCEV *N2 = collectUpperBound(Loop2, A1->getType());
DEBUG(if (N1) dbgs() << "\t N1 = " << *N1 << "\n");
DEBUG(if (N2) dbgs() << "\t N2 = " << *N2 << "\n");
const SCEV *C2_C1 = SE->getMinusSCEV(C2, C1);
const SCEV *C1_C2 = SE->getMinusSCEV(C1, C2);
DEBUG(dbgs() << "\t C2 - C1 = " << *C2_C1 << "\n");
DEBUG(dbgs() << "\t C1 - C2 = " << *C1_C2 << "\n");
if (SE->isKnownNonNegative(A1)) {
if (SE->isKnownNonNegative(A2)) {
// A1 >= 0 && A2 >= 0
if (N1) {
// make sure that c2 - c1 <= a1*N1
const SCEV *A1N1 = SE->getMulExpr(A1, N1);
DEBUG(dbgs() << "\t A1*N1 = " << *A1N1 << "\n");
if (isKnownPredicate(CmpInst::ICMP_SGT, C2_C1, A1N1)) {
++SymbolicRDIVindependence;
return true;
}
}
if (N2) {
// make sure that -a2*N2 <= c2 - c1, or a2*N2 >= c1 - c2
const SCEV *A2N2 = SE->getMulExpr(A2, N2);
DEBUG(dbgs() << "\t A2*N2 = " << *A2N2 << "\n");
if (isKnownPredicate(CmpInst::ICMP_SLT, A2N2, C1_C2)) {
++SymbolicRDIVindependence;
return true;
}
}
}
else if (SE->isKnownNonPositive(A2)) {
// a1 >= 0 && a2 <= 0
if (N1 && N2) {
// make sure that c2 - c1 <= a1*N1 - a2*N2
const SCEV *A1N1 = SE->getMulExpr(A1, N1);
const SCEV *A2N2 = SE->getMulExpr(A2, N2);
const SCEV *A1N1_A2N2 = SE->getMinusSCEV(A1N1, A2N2);
DEBUG(dbgs() << "\t A1*N1 - A2*N2 = " << *A1N1_A2N2 << "\n");
if (isKnownPredicate(CmpInst::ICMP_SGT, C2_C1, A1N1_A2N2)) {
++SymbolicRDIVindependence;
return true;
}
}
// make sure that 0 <= c2 - c1
if (SE->isKnownNegative(C2_C1)) {
++SymbolicRDIVindependence;
return true;
}
}
}
else if (SE->isKnownNonPositive(A1)) {
if (SE->isKnownNonNegative(A2)) {
// a1 <= 0 && a2 >= 0
if (N1 && N2) {
// make sure that a1*N1 - a2*N2 <= c2 - c1
const SCEV *A1N1 = SE->getMulExpr(A1, N1);
const SCEV *A2N2 = SE->getMulExpr(A2, N2);
const SCEV *A1N1_A2N2 = SE->getMinusSCEV(A1N1, A2N2);
DEBUG(dbgs() << "\t A1*N1 - A2*N2 = " << *A1N1_A2N2 << "\n");
if (isKnownPredicate(CmpInst::ICMP_SGT, A1N1_A2N2, C2_C1)) {
++SymbolicRDIVindependence;
return true;
}
}
// make sure that c2 - c1 <= 0
if (SE->isKnownPositive(C2_C1)) {
++SymbolicRDIVindependence;
return true;
}
}
else if (SE->isKnownNonPositive(A2)) {
// a1 <= 0 && a2 <= 0
if (N1) {
// make sure that a1*N1 <= c2 - c1
const SCEV *A1N1 = SE->getMulExpr(A1, N1);
DEBUG(dbgs() << "\t A1*N1 = " << *A1N1 << "\n");
if (isKnownPredicate(CmpInst::ICMP_SGT, A1N1, C2_C1)) {
++SymbolicRDIVindependence;
return true;
}
}
if (N2) {
// make sure that c2 - c1 <= -a2*N2, or c1 - c2 >= a2*N2
const SCEV *A2N2 = SE->getMulExpr(A2, N2);
DEBUG(dbgs() << "\t A2*N2 = " << *A2N2 << "\n");
if (isKnownPredicate(CmpInst::ICMP_SLT, C1_C2, A2N2)) {
++SymbolicRDIVindependence;
return true;
}
}
}
}
return false;
}
// testSIV -
// When we have a pair of subscripts of the form [c1 + a1*i] and [c2 - a2*i]
// where i is an induction variable, c1 and c2 are loop invariant, and a1 and
// a2 are constant, we attack it with an SIV test. While they can all be
// solved with the Exact SIV test, it's worthwhile to use simpler tests when
// they apply; they're cheaper and sometimes more precise.
//
// Return true if dependence disproved.
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
bool DependenceInfo::testSIV(const SCEV *Src, const SCEV *Dst, unsigned &Level,
FullDependence &Result, Constraint &NewConstraint,
const SCEV *&SplitIter) const {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
DEBUG(dbgs() << " src = " << *Src << "\n");
DEBUG(dbgs() << " dst = " << *Dst << "\n");
const SCEVAddRecExpr *SrcAddRec = dyn_cast<SCEVAddRecExpr>(Src);
const SCEVAddRecExpr *DstAddRec = dyn_cast<SCEVAddRecExpr>(Dst);
if (SrcAddRec && DstAddRec) {
const SCEV *SrcConst = SrcAddRec->getStart();
const SCEV *DstConst = DstAddRec->getStart();
const SCEV *SrcCoeff = SrcAddRec->getStepRecurrence(*SE);
const SCEV *DstCoeff = DstAddRec->getStepRecurrence(*SE);
const Loop *CurLoop = SrcAddRec->getLoop();
assert(CurLoop == DstAddRec->getLoop() &&
"both loops in SIV should be same");
Level = mapSrcLoop(CurLoop);
bool disproven;
if (SrcCoeff == DstCoeff)
disproven = strongSIVtest(SrcCoeff, SrcConst, DstConst, CurLoop,
Level, Result, NewConstraint);
else if (SrcCoeff == SE->getNegativeSCEV(DstCoeff))
disproven = weakCrossingSIVtest(SrcCoeff, SrcConst, DstConst, CurLoop,
Level, Result, NewConstraint, SplitIter);
else
disproven = exactSIVtest(SrcCoeff, DstCoeff, SrcConst, DstConst, CurLoop,
Level, Result, NewConstraint);
return disproven ||
gcdMIVtest(Src, Dst, Result) ||
symbolicRDIVtest(SrcCoeff, DstCoeff, SrcConst, DstConst, CurLoop, CurLoop);
}
if (SrcAddRec) {
const SCEV *SrcConst = SrcAddRec->getStart();
const SCEV *SrcCoeff = SrcAddRec->getStepRecurrence(*SE);
const SCEV *DstConst = Dst;
const Loop *CurLoop = SrcAddRec->getLoop();
Level = mapSrcLoop(CurLoop);
return weakZeroDstSIVtest(SrcCoeff, SrcConst, DstConst, CurLoop,
Level, Result, NewConstraint) ||
gcdMIVtest(Src, Dst, Result);
}
if (DstAddRec) {
const SCEV *DstConst = DstAddRec->getStart();
const SCEV *DstCoeff = DstAddRec->getStepRecurrence(*SE);
const SCEV *SrcConst = Src;
const Loop *CurLoop = DstAddRec->getLoop();
Level = mapDstLoop(CurLoop);
return weakZeroSrcSIVtest(DstCoeff, SrcConst, DstConst,
CurLoop, Level, Result, NewConstraint) ||
gcdMIVtest(Src, Dst, Result);
}
llvm_unreachable("SIV test expected at least one AddRec");
return false;
}
// testRDIV -
// When we have a pair of subscripts of the form [c1 + a1*i] and [c2 + a2*j]
// where i and j are induction variables, c1 and c2 are loop invariant,
// and a1 and a2 are constant, we can solve it exactly with an easy adaptation
// of the Exact SIV test, the Restricted Double Index Variable (RDIV) test.
// It doesn't make sense to talk about distance or direction in this case,
// so there's no point in making special versions of the Strong SIV test or
// the Weak-crossing SIV test.
//
// With minor algebra, this test can also be used for things like
// [c1 + a1*i + a2*j][c2].
//
// Return true if dependence disproved.
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
bool DependenceInfo::testRDIV(const SCEV *Src, const SCEV *Dst,
FullDependence &Result) const {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
// we have 3 possible situations here:
// 1) [a*i + b] and [c*j + d]
// 2) [a*i + c*j + b] and [d]
// 3) [b] and [a*i + c*j + d]
// We need to find what we've got and get organized
const SCEV *SrcConst, *DstConst;
const SCEV *SrcCoeff, *DstCoeff;
const Loop *SrcLoop, *DstLoop;
DEBUG(dbgs() << " src = " << *Src << "\n");
DEBUG(dbgs() << " dst = " << *Dst << "\n");
const SCEVAddRecExpr *SrcAddRec = dyn_cast<SCEVAddRecExpr>(Src);
const SCEVAddRecExpr *DstAddRec = dyn_cast<SCEVAddRecExpr>(Dst);
if (SrcAddRec && DstAddRec) {
SrcConst = SrcAddRec->getStart();
SrcCoeff = SrcAddRec->getStepRecurrence(*SE);
SrcLoop = SrcAddRec->getLoop();
DstConst = DstAddRec->getStart();
DstCoeff = DstAddRec->getStepRecurrence(*SE);
DstLoop = DstAddRec->getLoop();
}
else if (SrcAddRec) {
if (const SCEVAddRecExpr *tmpAddRec =
dyn_cast<SCEVAddRecExpr>(SrcAddRec->getStart())) {
SrcConst = tmpAddRec->getStart();
SrcCoeff = tmpAddRec->getStepRecurrence(*SE);
SrcLoop = tmpAddRec->getLoop();
DstConst = Dst;
DstCoeff = SE->getNegativeSCEV(SrcAddRec->getStepRecurrence(*SE));
DstLoop = SrcAddRec->getLoop();
}
else
llvm_unreachable("RDIV reached by surprising SCEVs");
}
else if (DstAddRec) {
if (const SCEVAddRecExpr *tmpAddRec =
dyn_cast<SCEVAddRecExpr>(DstAddRec->getStart())) {
DstConst = tmpAddRec->getStart();
DstCoeff = tmpAddRec->getStepRecurrence(*SE);
DstLoop = tmpAddRec->getLoop();
SrcConst = Src;
SrcCoeff = SE->getNegativeSCEV(DstAddRec->getStepRecurrence(*SE));
SrcLoop = DstAddRec->getLoop();
}
else
llvm_unreachable("RDIV reached by surprising SCEVs");
}
else
llvm_unreachable("RDIV expected at least one AddRec");
return exactRDIVtest(SrcCoeff, DstCoeff,
SrcConst, DstConst,
SrcLoop, DstLoop,
Result) ||
gcdMIVtest(Src, Dst, Result) ||
symbolicRDIVtest(SrcCoeff, DstCoeff,
SrcConst, DstConst,
SrcLoop, DstLoop);
}
// Tests the single-subscript MIV pair (Src and Dst) for dependence.
// Return true if dependence disproved.
// Can sometimes refine direction vectors.
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
bool DependenceInfo::testMIV(const SCEV *Src, const SCEV *Dst,
const SmallBitVector &Loops,
FullDependence &Result) const {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
DEBUG(dbgs() << " src = " << *Src << "\n");
DEBUG(dbgs() << " dst = " << *Dst << "\n");
Result.Consistent = false;
return gcdMIVtest(Src, Dst, Result) ||
banerjeeMIVtest(Src, Dst, Loops, Result);
}
// Given a product, e.g., 10*X*Y, returns the first constant operand,
// in this case 10. If there is no constant part, returns NULL.
static
[DependenceAnalysis] Refactor uses of getConstantPart. NFC. Rather than checking for the SCEV type prior to calling getContantPart, perform the checks in the function. This reduces the number of places where the checks are needed. Differential Revision: http://reviews.llvm.org/D19241 llvm-svn: 266759
2016-04-20 00:46:57 +08:00
const SCEVConstant *getConstantPart(const SCEV *Expr) {
if (const auto *Constant = dyn_cast<SCEVConstant>(Expr))
return Constant;
else if (const auto *Product = dyn_cast<SCEVMulExpr>(Expr))
if (const auto *Constant = dyn_cast<SCEVConstant>(Product->getOperand(0)))
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
return Constant;
[C++11] More 'nullptr' conversion. In some cases just using a boolean check instead of comparing to nullptr. llvm-svn: 206243
2014-04-15 12:59:12 +08:00
return nullptr;
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
}
//===----------------------------------------------------------------------===//
// gcdMIVtest -
// Tests an MIV subscript pair for dependence.
// Returns true if any possible dependence is disproved.
Fix a couple of comment typos. llvm-svn: 167113
2012-10-31 19:25:32 +08:00
// Marks the result as inconsistent.
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
// Can sometimes disprove the equal direction for 1 or more loops,
// as discussed in Michael Wolfe's book,
// High Performance Compilers for Parallel Computing, page 235.
//
// We spend some effort (code!) to handle cases like
// [10*i + 5*N*j + 15*M + 6], where i and j are induction variables,
// but M and N are just loop-invariant variables.
// This should help us handle linearized subscripts;
// also makes this test a useful backup to the various SIV tests.
//
// It occurs to me that the presence of loop-invariant variables
// changes the nature of the test from "greatest common divisor"
Cleaned up a couple of comments. llvm-svn: 168854
2012-11-29 12:30:52 +08:00
// to "a common divisor".
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
bool DependenceInfo::gcdMIVtest(const SCEV *Src, const SCEV *Dst,
FullDependence &Result) const {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
DEBUG(dbgs() << "starting gcd\n");
++GCDapplications;
Corrects a problem where we reply exclusively of GEPs to drive analysis. Better is to look for cases with useful GEPs and use them when possible. When a pair of useful GEPs is not available, use the raw SCEVs directly. This approach supports better analysis of pointer dereferencing. In parallel, all the test cases are updated appropriately. Cases where we have a store to *B++ can now be analyzed! llvm-svn: 168474
2012-11-22 07:50:04 +08:00
unsigned BitWidth = SE->getTypeSizeInBits(Src->getType());
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
APInt RunningGCD = APInt::getNullValue(BitWidth);
// Examine Src coefficients.
// Compute running GCD and record source constant.
// Because we're looking for the constant at the end of the chain,
// we can't quit the loop just because the GCD == 1.
const SCEV *Coefficients = Src;
while (const SCEVAddRecExpr *AddRec =
dyn_cast<SCEVAddRecExpr>(Coefficients)) {
const SCEV *Coeff = AddRec->getStepRecurrence(*SE);
[DependenceAnalysis] Refactor uses of getConstantPart. NFC. Rather than checking for the SCEV type prior to calling getContantPart, perform the checks in the function. This reduces the number of places where the checks are needed. Differential Revision: http://reviews.llvm.org/D19241 llvm-svn: 266759
2016-04-20 00:46:57 +08:00
// If the coefficient is the product of a constant and other stuff,
// we can use the constant in the GCD computation.
const auto *Constant = getConstantPart(Coeff);
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
if (!Constant)
return false;
[SCEV] Add and use SCEVConstant::getAPInt; NFCI llvm-svn: 255921
2015-12-18 04:28:46 +08:00
APInt ConstCoeff = Constant->getAPInt();
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
RunningGCD = APIntOps::GreatestCommonDivisor(RunningGCD, ConstCoeff.abs());
Coefficients = AddRec->getStart();
}
const SCEV *SrcConst = Coefficients;
// Examine Dst coefficients.
// Compute running GCD and record destination constant.
// Because we're looking for the constant at the end of the chain,
// we can't quit the loop just because the GCD == 1.
Coefficients = Dst;
while (const SCEVAddRecExpr *AddRec =
dyn_cast<SCEVAddRecExpr>(Coefficients)) {
const SCEV *Coeff = AddRec->getStepRecurrence(*SE);
[DependenceAnalysis] Refactor uses of getConstantPart. NFC. Rather than checking for the SCEV type prior to calling getContantPart, perform the checks in the function. This reduces the number of places where the checks are needed. Differential Revision: http://reviews.llvm.org/D19241 llvm-svn: 266759
2016-04-20 00:46:57 +08:00
// If the coefficient is the product of a constant and other stuff,
// we can use the constant in the GCD computation.
const auto *Constant = getConstantPart(Coeff);
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
if (!Constant)
return false;
[SCEV] Add and use SCEVConstant::getAPInt; NFCI llvm-svn: 255921
2015-12-18 04:28:46 +08:00
APInt ConstCoeff = Constant->getAPInt();
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
RunningGCD = APIntOps::GreatestCommonDivisor(RunningGCD, ConstCoeff.abs());
Coefficients = AddRec->getStart();
}
const SCEV *DstConst = Coefficients;
APInt ExtraGCD = APInt::getNullValue(BitWidth);
const SCEV *Delta = SE->getMinusSCEV(DstConst, SrcConst);
DEBUG(dbgs() << " Delta = " << *Delta << "\n");
const SCEVConstant *Constant = dyn_cast<SCEVConstant>(Delta);
if (const SCEVAddExpr *Sum = dyn_cast<SCEVAddExpr>(Delta)) {
// If Delta is a sum of products, we may be able to make further progress.
for (unsigned Op = 0, Ops = Sum->getNumOperands(); Op < Ops; Op++) {
const SCEV *Operand = Sum->getOperand(Op);
if (isa<SCEVConstant>(Operand)) {
assert(!Constant && "Surprised to find multiple constants");
Constant = cast<SCEVConstant>(Operand);
}
DependenceAnalysis: Don't crash if there is no constant operand. This makes the code match the comments. Resolves a crash in loop idiom (PR14219). llvm-svn: 167110
2012-10-31 17:20:38 +08:00
else if (const SCEVMulExpr *Product = dyn_cast<SCEVMulExpr>(Operand)) {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
// Search for constant operand to participate in GCD;
// If none found; return false.
DependenceAnalysis: Don't crash if there is no constant operand. This makes the code match the comments. Resolves a crash in loop idiom (PR14219). llvm-svn: 167110
2012-10-31 17:20:38 +08:00
const SCEVConstant *ConstOp = getConstantPart(Product);
if (!ConstOp)
return false;
[SCEV] Add and use SCEVConstant::getAPInt; NFCI llvm-svn: 255921
2015-12-18 04:28:46 +08:00
APInt ConstOpValue = ConstOp->getAPInt();
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
ExtraGCD = APIntOps::GreatestCommonDivisor(ExtraGCD,
ConstOpValue.abs());
}
else
return false;
}
}
if (!Constant)
return false;
[SCEV] Add and use SCEVConstant::getAPInt; NFCI llvm-svn: 255921
2015-12-18 04:28:46 +08:00
APInt ConstDelta = cast<SCEVConstant>(Constant)->getAPInt();
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
DEBUG(dbgs() << " ConstDelta = " << ConstDelta << "\n");
if (ConstDelta == 0)
return false;
RunningGCD = APIntOps::GreatestCommonDivisor(RunningGCD, ExtraGCD);
DEBUG(dbgs() << " RunningGCD = " << RunningGCD << "\n");
APInt Remainder = ConstDelta.srem(RunningGCD);
if (Remainder != 0) {
++GCDindependence;
return true;
}
// Try to disprove equal directions.
// For example, given a subscript pair [3*i + 2*j] and [i' + 2*j' - 1],
// the code above can't disprove the dependence because the GCD = 1.
// So we consider what happen if i = i' and what happens if j = j'.
// If i = i', we can simplify the subscript to [2*i + 2*j] and [2*j' - 1],
// which is infeasible, so we can disallow the = direction for the i level.
// Setting j = j' doesn't help matters, so we end up with a direction vector
// of [<>, *]
//
// Given A[5*i + 10*j*M + 9*M*N] and A[15*i + 20*j*M - 21*N*M + 5],
// we need to remember that the constant part is 5 and the RunningGCD should
// be initialized to ExtraGCD = 30.
DEBUG(dbgs() << " ExtraGCD = " << ExtraGCD << '\n');
bool Improved = false;
Coefficients = Src;
while (const SCEVAddRecExpr *AddRec =
dyn_cast<SCEVAddRecExpr>(Coefficients)) {
Coefficients = AddRec->getStart();
const Loop *CurLoop = AddRec->getLoop();
RunningGCD = ExtraGCD;
const SCEV *SrcCoeff = AddRec->getStepRecurrence(*SE);
const SCEV *DstCoeff = SE->getMinusSCEV(SrcCoeff, SrcCoeff);
const SCEV *Inner = Src;
while (RunningGCD != 1 && isa<SCEVAddRecExpr>(Inner)) {
AddRec = cast<SCEVAddRecExpr>(Inner);
const SCEV *Coeff = AddRec->getStepRecurrence(*SE);
if (CurLoop == AddRec->getLoop())
; // SrcCoeff == Coeff
else {
[DependenceAnalysis] Refactor uses of getConstantPart. NFC. Rather than checking for the SCEV type prior to calling getContantPart, perform the checks in the function. This reduces the number of places where the checks are needed. Differential Revision: http://reviews.llvm.org/D19241 llvm-svn: 266759
2016-04-20 00:46:57 +08:00
// If the coefficient is the product of a constant and other stuff,
// we can use the constant in the GCD computation.
Constant = getConstantPart(Coeff);
[DependenceAnalysis] Check if result of getConstantPart is null A seg-fault occurs due to a reference of a null pointer, which is the value returned by getConstantPart. This function returns null if the constant part is not found. The code that calls this function needs to check for the null return value. Differential Revision: http://reviews.llvm.org/D18718 llvm-svn: 265319
2016-04-05 02:13:18 +08:00
if (!Constant)
return false;
[SCEV] Add and use SCEVConstant::getAPInt; NFCI llvm-svn: 255921
2015-12-18 04:28:46 +08:00
APInt ConstCoeff = Constant->getAPInt();
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
RunningGCD = APIntOps::GreatestCommonDivisor(RunningGCD, ConstCoeff.abs());
}
Inner = AddRec->getStart();
}
Inner = Dst;
while (RunningGCD != 1 && isa<SCEVAddRecExpr>(Inner)) {
AddRec = cast<SCEVAddRecExpr>(Inner);
const SCEV *Coeff = AddRec->getStepRecurrence(*SE);
if (CurLoop == AddRec->getLoop())
DstCoeff = Coeff;
else {
[DependenceAnalysis] Refactor uses of getConstantPart. NFC. Rather than checking for the SCEV type prior to calling getContantPart, perform the checks in the function. This reduces the number of places where the checks are needed. Differential Revision: http://reviews.llvm.org/D19241 llvm-svn: 266759
2016-04-20 00:46:57 +08:00
// If the coefficient is the product of a constant and other stuff,
// we can use the constant in the GCD computation.
Constant = getConstantPart(Coeff);
[DependenceAnalysis] Check if result of getConstantPart is null A seg-fault occurs due to a reference of a null pointer, which is the value returned by getConstantPart. This function returns null if the constant part is not found. The code that calls this function needs to check for the null return value. Differential Revision: http://reviews.llvm.org/D18718 llvm-svn: 265319
2016-04-05 02:13:18 +08:00
if (!Constant)
return false;
[SCEV] Add and use SCEVConstant::getAPInt; NFCI llvm-svn: 255921
2015-12-18 04:28:46 +08:00
APInt ConstCoeff = Constant->getAPInt();
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
RunningGCD = APIntOps::GreatestCommonDivisor(RunningGCD, ConstCoeff.abs());
}
Inner = AddRec->getStart();
}
Delta = SE->getMinusSCEV(SrcCoeff, DstCoeff);
[DependenceAnalysis] Refactor uses of getConstantPart. NFC. Rather than checking for the SCEV type prior to calling getContantPart, perform the checks in the function. This reduces the number of places where the checks are needed. Differential Revision: http://reviews.llvm.org/D19241 llvm-svn: 266759
2016-04-20 00:46:57 +08:00
// If the coefficient is the product of a constant and other stuff,
// we can use the constant in the GCD computation.
Constant = getConstantPart(Delta);
if (!Constant)
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
// The difference of the two coefficients might not be a product
// or constant, in which case we give up on this direction.
continue;
[SCEV] Add and use SCEVConstant::getAPInt; NFCI llvm-svn: 255921
2015-12-18 04:28:46 +08:00
APInt ConstCoeff = Constant->getAPInt();
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
RunningGCD = APIntOps::GreatestCommonDivisor(RunningGCD, ConstCoeff.abs());
DEBUG(dbgs() << "\tRunningGCD = " << RunningGCD << "\n");
if (RunningGCD != 0) {
Remainder = ConstDelta.srem(RunningGCD);
DEBUG(dbgs() << "\tRemainder = " << Remainder << "\n");
if (Remainder != 0) {
unsigned Level = mapSrcLoop(CurLoop);
fix warning DependenceAnalysis.cpp:1164:32: warning: implicit truncation from 'int' to bitfield changes value from -5 to 3 [-Wconstant-conversion] Result.DV[Level].Direction &= ~Dependence::DVEntry::GT; ^ ~~~~~~~~~~~~~~~~~~~~~~~~ Patch from Preston Briggs <preston.briggs@gmail.com>. llvm-svn: 165784
2012-10-12 10:04:32 +08:00
Result.DV[Level - 1].Direction &= unsigned(~Dependence::DVEntry::EQ);
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
Improved = true;
}
}
}
if (Improved)
++GCDsuccesses;
DEBUG(dbgs() << "all done\n");
return false;
}
//===----------------------------------------------------------------------===//
// banerjeeMIVtest -
// Use Banerjee's Inequalities to test an MIV subscript pair.
// (Wolfe, in the race-car book, calls this the Extreme Value Test.)
// Generally follows the discussion in Section 2.5.2 of
//
// Optimizing Supercompilers for Supercomputers
// Michael Wolfe
//
// The inequalities given on page 25 are simplified in that loops are
// normalized so that the lower bound is always 0 and the stride is always 1.
// For example, Wolfe gives
//
// LB^<_k = (A^-_k - B_k)^- (U_k - L_k - N_k) + (A_k - B_k)L_k - B_k N_k
//
// where A_k is the coefficient of the kth index in the source subscript,
// B_k is the coefficient of the kth index in the destination subscript,
// U_k is the upper bound of the kth index, L_k is the lower bound of the Kth
// index, and N_k is the stride of the kth index. Since all loops are normalized
// by the SCEV package, N_k = 1 and L_k = 0, allowing us to simplify the
// equation to
//
// LB^<_k = (A^-_k - B_k)^- (U_k - 0 - 1) + (A_k - B_k)0 - B_k 1
// = (A^-_k - B_k)^- (U_k - 1) - B_k
//
// Similar simplifications are possible for the other equations.
//
// When we can't determine the number of iterations for a loop,
// we use NULL as an indicator for the worst case, infinity.
// When computing the upper bound, NULL denotes +inf;
// for the lower bound, NULL denotes -inf.
//
// Return true if dependence disproved.
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
bool DependenceInfo::banerjeeMIVtest(const SCEV *Src, const SCEV *Dst,
const SmallBitVector &Loops,
FullDependence &Result) const {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
DEBUG(dbgs() << "starting Banerjee\n");
++BanerjeeApplications;
DEBUG(dbgs() << " Src = " << *Src << '\n');
const SCEV *A0;
Revert "Analysis: unique_ptr-ify DependenceAnalysis::collectCoeffInfo" This reverts commit r216358. llvm-svn: 216431
2014-08-26 10:03:38 +08:00
CoefficientInfo *A = collectCoeffInfo(Src, true, A0);
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
DEBUG(dbgs() << " Dst = " << *Dst << '\n');
const SCEV *B0;
Revert "Analysis: unique_ptr-ify DependenceAnalysis::collectCoeffInfo" This reverts commit r216358. llvm-svn: 216431
2014-08-26 10:03:38 +08:00
CoefficientInfo *B = collectCoeffInfo(Dst, false, B0);
BoundInfo *Bound = new BoundInfo[MaxLevels + 1];
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
const SCEV *Delta = SE->getMinusSCEV(B0, A0);
DEBUG(dbgs() << "\tDelta = " << *Delta << '\n');
// Compute bounds for all the * directions.
DEBUG(dbgs() << "\tBounds[*]\n");
for (unsigned K = 1; K <= MaxLevels; ++K) {
Bound[K].Iterations = A[K].Iterations ? A[K].Iterations : B[K].Iterations;
Bound[K].Direction = Dependence::DVEntry::ALL;
Bound[K].DirSet = Dependence::DVEntry::NONE;
findBoundsALL(A, B, Bound, K);
#ifndef NDEBUG
DEBUG(dbgs() << "\t " << K << '\t');
if (Bound[K].Lower[Dependence::DVEntry::ALL])
DEBUG(dbgs() << *Bound[K].Lower[Dependence::DVEntry::ALL] << '\t');
else
DEBUG(dbgs() << "-inf\t");
if (Bound[K].Upper[Dependence::DVEntry::ALL])
DEBUG(dbgs() << *Bound[K].Upper[Dependence::DVEntry::ALL] << '\n');
else
DEBUG(dbgs() << "+inf\n");
#endif
}
// Test the *, *, *, ... case.
bool Disproved = false;
if (testBounds(Dependence::DVEntry::ALL, 0, Bound, Delta)) {
// Explore the direction vector hierarchy.
unsigned DepthExpanded = 0;
unsigned NewDeps = exploreDirections(1, A, B, Bound,
Loops, DepthExpanded, Delta);
if (NewDeps > 0) {
bool Improved = false;
for (unsigned K = 1; K <= CommonLevels; ++K) {
if (Loops[K]) {
unsigned Old = Result.DV[K - 1].Direction;
Result.DV[K - 1].Direction = Old & Bound[K].DirSet;
Improved |= Old != Result.DV[K - 1].Direction;
if (!Result.DV[K - 1].Direction) {
Improved = false;
Disproved = true;
break;
}
}
}
if (Improved)
++BanerjeeSuccesses;
}
else {
++BanerjeeIndependence;
Disproved = true;
}
}
else {
++BanerjeeIndependence;
Disproved = true;
}
Revert "Analysis: unique_ptr-ify DependenceAnalysis::collectCoeffInfo" This reverts commit r216358. llvm-svn: 216431
2014-08-26 10:03:38 +08:00
delete [] Bound;
delete [] A;
delete [] B;
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
return Disproved;
}
// Hierarchically expands the direction vector
// search space, combining the directions of discovered dependences
// in the DirSet field of Bound. Returns the number of distinct
// dependences discovered. If the dependence is disproved,
// it will return 0.
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
unsigned DependenceInfo::exploreDirections(unsigned Level, CoefficientInfo *A,
CoefficientInfo *B, BoundInfo *Bound,
const SmallBitVector &Loops,
unsigned &DepthExpanded,
const SCEV *Delta) const {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
if (Level > CommonLevels) {
// record result
DEBUG(dbgs() << "\t[");
for (unsigned K = 1; K <= CommonLevels; ++K) {
if (Loops[K]) {
Bound[K].DirSet |= Bound[K].Direction;
#ifndef NDEBUG
switch (Bound[K].Direction) {
case Dependence::DVEntry::LT:
DEBUG(dbgs() << " <");
break;
case Dependence::DVEntry::EQ:
DEBUG(dbgs() << " =");
break;
case Dependence::DVEntry::GT:
DEBUG(dbgs() << " >");
break;
case Dependence::DVEntry::ALL:
DEBUG(dbgs() << " *");
break;
default:
llvm_unreachable("unexpected Bound[K].Direction");
}
#endif
}
}
DEBUG(dbgs() << " ]\n");
return 1;
}
if (Loops[Level]) {
if (Level > DepthExpanded) {
DepthExpanded = Level;
// compute bounds for <, =, > at current level
findBoundsLT(A, B, Bound, Level);
findBoundsGT(A, B, Bound, Level);
findBoundsEQ(A, B, Bound, Level);
#ifndef NDEBUG
DEBUG(dbgs() << "\tBound for level = " << Level << '\n');
DEBUG(dbgs() << "\t <\t");
if (Bound[Level].Lower[Dependence::DVEntry::LT])
DEBUG(dbgs() << *Bound[Level].Lower[Dependence::DVEntry::LT] << '\t');
else
DEBUG(dbgs() << "-inf\t");
if (Bound[Level].Upper[Dependence::DVEntry::LT])
DEBUG(dbgs() << *Bound[Level].Upper[Dependence::DVEntry::LT] << '\n');
else
DEBUG(dbgs() << "+inf\n");
DEBUG(dbgs() << "\t =\t");
if (Bound[Level].Lower[Dependence::DVEntry::EQ])
DEBUG(dbgs() << *Bound[Level].Lower[Dependence::DVEntry::EQ] << '\t');
else
DEBUG(dbgs() << "-inf\t");
if (Bound[Level].Upper[Dependence::DVEntry::EQ])
DEBUG(dbgs() << *Bound[Level].Upper[Dependence::DVEntry::EQ] << '\n');
else
DEBUG(dbgs() << "+inf\n");
DEBUG(dbgs() << "\t >\t");
if (Bound[Level].Lower[Dependence::DVEntry::GT])
DEBUG(dbgs() << *Bound[Level].Lower[Dependence::DVEntry::GT] << '\t');
else
DEBUG(dbgs() << "-inf\t");
if (Bound[Level].Upper[Dependence::DVEntry::GT])
DEBUG(dbgs() << *Bound[Level].Upper[Dependence::DVEntry::GT] << '\n');
else
DEBUG(dbgs() << "+inf\n");
#endif
}
unsigned NewDeps = 0;
// test bounds for <, *, *, ...
if (testBounds(Dependence::DVEntry::LT, Level, Bound, Delta))
NewDeps += exploreDirections(Level + 1, A, B, Bound,
Loops, DepthExpanded, Delta);
// Test bounds for =, *, *, ...
if (testBounds(Dependence::DVEntry::EQ, Level, Bound, Delta))
NewDeps += exploreDirections(Level + 1, A, B, Bound,
Loops, DepthExpanded, Delta);
// test bounds for >, *, *, ...
if (testBounds(Dependence::DVEntry::GT, Level, Bound, Delta))
NewDeps += exploreDirections(Level + 1, A, B, Bound,
Loops, DepthExpanded, Delta);
Bound[Level].Direction = Dependence::DVEntry::ALL;
return NewDeps;
}
else
return exploreDirections(Level + 1, A, B, Bound, Loops, DepthExpanded, Delta);
}
// Returns true iff the current bounds are plausible.
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
bool DependenceInfo::testBounds(unsigned char DirKind, unsigned Level,
BoundInfo *Bound, const SCEV *Delta) const {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
Bound[Level].Direction = DirKind;
if (const SCEV *LowerBound = getLowerBound(Bound))
if (isKnownPredicate(CmpInst::ICMP_SGT, LowerBound, Delta))
return false;
if (const SCEV *UpperBound = getUpperBound(Bound))
if (isKnownPredicate(CmpInst::ICMP_SGT, Delta, UpperBound))
return false;
return true;
}
// Computes the upper and lower bounds for level K
// using the * direction. Records them in Bound.
// Wolfe gives the equations
//
// LB^*_k = (A^-_k - B^+_k)(U_k - L_k) + (A_k - B_k)L_k
// UB^*_k = (A^+_k - B^-_k)(U_k - L_k) + (A_k - B_k)L_k
//
// Since we normalize loops, we can simplify these equations to
//
// LB^*_k = (A^-_k - B^+_k)U_k
// UB^*_k = (A^+_k - B^-_k)U_k
//
// We must be careful to handle the case where the upper bound is unknown.
// Note that the lower bound is always <= 0
// and the upper bound is always >= 0.
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
void DependenceInfo::findBoundsALL(CoefficientInfo *A, CoefficientInfo *B,
BoundInfo *Bound, unsigned K) const {
[C++11] More 'nullptr' conversion. In some cases just using a boolean check instead of comparing to nullptr. llvm-svn: 206243
2014-04-15 12:59:12 +08:00
Bound[K].Lower[Dependence::DVEntry::ALL] = nullptr; // Default value = -infinity.
Bound[K].Upper[Dependence::DVEntry::ALL] = nullptr; // Default value = +infinity.
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
if (Bound[K].Iterations) {
Bound[K].Lower[Dependence::DVEntry::ALL] =
SE->getMulExpr(SE->getMinusSCEV(A[K].NegPart, B[K].PosPart),
Bound[K].Iterations);
Bound[K].Upper[Dependence::DVEntry::ALL] =
SE->getMulExpr(SE->getMinusSCEV(A[K].PosPart, B[K].NegPart),
Bound[K].Iterations);
}
else {
// If the difference is 0, we won't need to know the number of iterations.
if (isKnownPredicate(CmpInst::ICMP_EQ, A[K].NegPart, B[K].PosPart))
Bound[K].Lower[Dependence::DVEntry::ALL] =
[SCEV] Introduce ScalarEvolution::getOne and getZero. Summary: It is fairly common to call SE->getConstant(Ty, 0) or SE->getConstant(Ty, 1); this change makes such uses a little bit briefer. I've refactored the call sites I could find easily to use getZero / getOne. Reviewers: hfinkel, majnemer, reames Subscribers: sanjoy, llvm-commits Differential Revision: http://reviews.llvm.org/D12947 llvm-svn: 248362
2015-09-23 09:59:04 +08:00
SE->getZero(A[K].Coeff->getType());
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
if (isKnownPredicate(CmpInst::ICMP_EQ, A[K].PosPart, B[K].NegPart))
Bound[K].Upper[Dependence::DVEntry::ALL] =
[SCEV] Introduce ScalarEvolution::getOne and getZero. Summary: It is fairly common to call SE->getConstant(Ty, 0) or SE->getConstant(Ty, 1); this change makes such uses a little bit briefer. I've refactored the call sites I could find easily to use getZero / getOne. Reviewers: hfinkel, majnemer, reames Subscribers: sanjoy, llvm-commits Differential Revision: http://reviews.llvm.org/D12947 llvm-svn: 248362
2015-09-23 09:59:04 +08:00
SE->getZero(A[K].Coeff->getType());
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
}
}
// Computes the upper and lower bounds for level K
// using the = direction. Records them in Bound.
// Wolfe gives the equations
//
// LB^=_k = (A_k - B_k)^- (U_k - L_k) + (A_k - B_k)L_k
// UB^=_k = (A_k - B_k)^+ (U_k - L_k) + (A_k - B_k)L_k
//
// Since we normalize loops, we can simplify these equations to
//
// LB^=_k = (A_k - B_k)^- U_k
// UB^=_k = (A_k - B_k)^+ U_k
//
// We must be careful to handle the case where the upper bound is unknown.
// Note that the lower bound is always <= 0
// and the upper bound is always >= 0.
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
void DependenceInfo::findBoundsEQ(CoefficientInfo *A, CoefficientInfo *B,
BoundInfo *Bound, unsigned K) const {
[C++11] More 'nullptr' conversion. In some cases just using a boolean check instead of comparing to nullptr. llvm-svn: 206243
2014-04-15 12:59:12 +08:00
Bound[K].Lower[Dependence::DVEntry::EQ] = nullptr; // Default value = -infinity.
Bound[K].Upper[Dependence::DVEntry::EQ] = nullptr; // Default value = +infinity.
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
if (Bound[K].Iterations) {
const SCEV *Delta = SE->getMinusSCEV(A[K].Coeff, B[K].Coeff);
const SCEV *NegativePart = getNegativePart(Delta);
Bound[K].Lower[Dependence::DVEntry::EQ] =
SE->getMulExpr(NegativePart, Bound[K].Iterations);
const SCEV *PositivePart = getPositivePart(Delta);
Bound[K].Upper[Dependence::DVEntry::EQ] =
SE->getMulExpr(PositivePart, Bound[K].Iterations);
}
else {
// If the positive/negative part of the difference is 0,
// we won't need to know the number of iterations.
const SCEV *Delta = SE->getMinusSCEV(A[K].Coeff, B[K].Coeff);
const SCEV *NegativePart = getNegativePart(Delta);
if (NegativePart->isZero())
Bound[K].Lower[Dependence::DVEntry::EQ] = NegativePart; // Zero
const SCEV *PositivePart = getPositivePart(Delta);
if (PositivePart->isZero())
Bound[K].Upper[Dependence::DVEntry::EQ] = PositivePart; // Zero
}
}
// Computes the upper and lower bounds for level K
// using the < direction. Records them in Bound.
// Wolfe gives the equations
//
// LB^<_k = (A^-_k - B_k)^- (U_k - L_k - N_k) + (A_k - B_k)L_k - B_k N_k
// UB^<_k = (A^+_k - B_k)^+ (U_k - L_k - N_k) + (A_k - B_k)L_k - B_k N_k
//
// Since we normalize loops, we can simplify these equations to
//
// LB^<_k = (A^-_k - B_k)^- (U_k - 1) - B_k
// UB^<_k = (A^+_k - B_k)^+ (U_k - 1) - B_k
//
// We must be careful to handle the case where the upper bound is unknown.
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
void DependenceInfo::findBoundsLT(CoefficientInfo *A, CoefficientInfo *B,
BoundInfo *Bound, unsigned K) const {
[C++11] More 'nullptr' conversion. In some cases just using a boolean check instead of comparing to nullptr. llvm-svn: 206243
2014-04-15 12:59:12 +08:00
Bound[K].Lower[Dependence::DVEntry::LT] = nullptr; // Default value = -infinity.
Bound[K].Upper[Dependence::DVEntry::LT] = nullptr; // Default value = +infinity.
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
if (Bound[K].Iterations) {
[SCEV] Introduce ScalarEvolution::getOne and getZero. Summary: It is fairly common to call SE->getConstant(Ty, 0) or SE->getConstant(Ty, 1); this change makes such uses a little bit briefer. I've refactored the call sites I could find easily to use getZero / getOne. Reviewers: hfinkel, majnemer, reames Subscribers: sanjoy, llvm-commits Differential Revision: http://reviews.llvm.org/D12947 llvm-svn: 248362
2015-09-23 09:59:04 +08:00
const SCEV *Iter_1 = SE->getMinusSCEV(
Bound[K].Iterations, SE->getOne(Bound[K].Iterations->getType()));
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
const SCEV *NegPart =
getNegativePart(SE->getMinusSCEV(A[K].NegPart, B[K].Coeff));
Bound[K].Lower[Dependence::DVEntry::LT] =
SE->getMinusSCEV(SE->getMulExpr(NegPart, Iter_1), B[K].Coeff);
const SCEV *PosPart =
getPositivePart(SE->getMinusSCEV(A[K].PosPart, B[K].Coeff));
Bound[K].Upper[Dependence::DVEntry::LT] =
SE->getMinusSCEV(SE->getMulExpr(PosPart, Iter_1), B[K].Coeff);
}
else {
// If the positive/negative part of the difference is 0,
// we won't need to know the number of iterations.
const SCEV *NegPart =
getNegativePart(SE->getMinusSCEV(A[K].NegPart, B[K].Coeff));
if (NegPart->isZero())
Bound[K].Lower[Dependence::DVEntry::LT] = SE->getNegativeSCEV(B[K].Coeff);
const SCEV *PosPart =
getPositivePart(SE->getMinusSCEV(A[K].PosPart, B[K].Coeff));
if (PosPart->isZero())
Bound[K].Upper[Dependence::DVEntry::LT] = SE->getNegativeSCEV(B[K].Coeff);
}
}
// Computes the upper and lower bounds for level K
// using the > direction. Records them in Bound.
// Wolfe gives the equations
//
// LB^>_k = (A_k - B^+_k)^- (U_k - L_k - N_k) + (A_k - B_k)L_k + A_k N_k
// UB^>_k = (A_k - B^-_k)^+ (U_k - L_k - N_k) + (A_k - B_k)L_k + A_k N_k
//
// Since we normalize loops, we can simplify these equations to
//
// LB^>_k = (A_k - B^+_k)^- (U_k - 1) + A_k
// UB^>_k = (A_k - B^-_k)^+ (U_k - 1) + A_k
//
// We must be careful to handle the case where the upper bound is unknown.
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
void DependenceInfo::findBoundsGT(CoefficientInfo *A, CoefficientInfo *B,
BoundInfo *Bound, unsigned K) const {
[C++11] More 'nullptr' conversion. In some cases just using a boolean check instead of comparing to nullptr. llvm-svn: 206243
2014-04-15 12:59:12 +08:00
Bound[K].Lower[Dependence::DVEntry::GT] = nullptr; // Default value = -infinity.
Bound[K].Upper[Dependence::DVEntry::GT] = nullptr; // Default value = +infinity.
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
if (Bound[K].Iterations) {
[SCEV] Introduce ScalarEvolution::getOne and getZero. Summary: It is fairly common to call SE->getConstant(Ty, 0) or SE->getConstant(Ty, 1); this change makes such uses a little bit briefer. I've refactored the call sites I could find easily to use getZero / getOne. Reviewers: hfinkel, majnemer, reames Subscribers: sanjoy, llvm-commits Differential Revision: http://reviews.llvm.org/D12947 llvm-svn: 248362
2015-09-23 09:59:04 +08:00
const SCEV *Iter_1 = SE->getMinusSCEV(
Bound[K].Iterations, SE->getOne(Bound[K].Iterations->getType()));
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
const SCEV *NegPart =
getNegativePart(SE->getMinusSCEV(A[K].Coeff, B[K].PosPart));
Bound[K].Lower[Dependence::DVEntry::GT] =
SE->getAddExpr(SE->getMulExpr(NegPart, Iter_1), A[K].Coeff);
const SCEV *PosPart =
getPositivePart(SE->getMinusSCEV(A[K].Coeff, B[K].NegPart));
Bound[K].Upper[Dependence::DVEntry::GT] =
SE->getAddExpr(SE->getMulExpr(PosPart, Iter_1), A[K].Coeff);
}
else {
// If the positive/negative part of the difference is 0,
// we won't need to know the number of iterations.
const SCEV *NegPart = getNegativePart(SE->getMinusSCEV(A[K].Coeff, B[K].PosPart));
if (NegPart->isZero())
Bound[K].Lower[Dependence::DVEntry::GT] = A[K].Coeff;
const SCEV *PosPart = getPositivePart(SE->getMinusSCEV(A[K].Coeff, B[K].NegPart));
if (PosPart->isZero())
Bound[K].Upper[Dependence::DVEntry::GT] = A[K].Coeff;
}
}
// X^+ = max(X, 0)
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
const SCEV *DependenceInfo::getPositivePart(const SCEV *X) const {
[SCEV] Introduce ScalarEvolution::getOne and getZero. Summary: It is fairly common to call SE->getConstant(Ty, 0) or SE->getConstant(Ty, 1); this change makes such uses a little bit briefer. I've refactored the call sites I could find easily to use getZero / getOne. Reviewers: hfinkel, majnemer, reames Subscribers: sanjoy, llvm-commits Differential Revision: http://reviews.llvm.org/D12947 llvm-svn: 248362
2015-09-23 09:59:04 +08:00
return SE->getSMaxExpr(X, SE->getZero(X->getType()));
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
}
// X^- = min(X, 0)
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
const SCEV *DependenceInfo::getNegativePart(const SCEV *X) const {
[SCEV] Introduce ScalarEvolution::getOne and getZero. Summary: It is fairly common to call SE->getConstant(Ty, 0) or SE->getConstant(Ty, 1); this change makes such uses a little bit briefer. I've refactored the call sites I could find easily to use getZero / getOne. Reviewers: hfinkel, majnemer, reames Subscribers: sanjoy, llvm-commits Differential Revision: http://reviews.llvm.org/D12947 llvm-svn: 248362
2015-09-23 09:59:04 +08:00
return SE->getSMinExpr(X, SE->getZero(X->getType()));
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
}
// Walks through the subscript,
// collecting each coefficient, the associated loop bounds,
// and recording its positive and negative parts for later use.
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
DependenceInfo::CoefficientInfo *
DependenceInfo::collectCoeffInfo(const SCEV *Subscript, bool SrcFlag,
const SCEV *&Constant) const {
[SCEV] Introduce ScalarEvolution::getOne and getZero. Summary: It is fairly common to call SE->getConstant(Ty, 0) or SE->getConstant(Ty, 1); this change makes such uses a little bit briefer. I've refactored the call sites I could find easily to use getZero / getOne. Reviewers: hfinkel, majnemer, reames Subscribers: sanjoy, llvm-commits Differential Revision: http://reviews.llvm.org/D12947 llvm-svn: 248362
2015-09-23 09:59:04 +08:00
const SCEV *Zero = SE->getZero(Subscript->getType());
Revert "Analysis: unique_ptr-ify DependenceAnalysis::collectCoeffInfo" This reverts commit r216358. llvm-svn: 216431
2014-08-26 10:03:38 +08:00
CoefficientInfo *CI = new CoefficientInfo[MaxLevels + 1];
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
for (unsigned K = 1; K <= MaxLevels; ++K) {
CI[K].Coeff = Zero;
CI[K].PosPart = Zero;
CI[K].NegPart = Zero;
[C++11] More 'nullptr' conversion. In some cases just using a boolean check instead of comparing to nullptr. llvm-svn: 206243
2014-04-15 12:59:12 +08:00
CI[K].Iterations = nullptr;
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
}
while (const SCEVAddRecExpr *AddRec = dyn_cast<SCEVAddRecExpr>(Subscript)) {
const Loop *L = AddRec->getLoop();
unsigned K = SrcFlag ? mapSrcLoop(L) : mapDstLoop(L);
CI[K].Coeff = AddRec->getStepRecurrence(*SE);
CI[K].PosPart = getPositivePart(CI[K].Coeff);
CI[K].NegPart = getNegativePart(CI[K].Coeff);
CI[K].Iterations = collectUpperBound(L, Subscript->getType());
Subscript = AddRec->getStart();
}
Constant = Subscript;
#ifndef NDEBUG
DEBUG(dbgs() << "\tCoefficient Info\n");
for (unsigned K = 1; K <= MaxLevels; ++K) {
DEBUG(dbgs() << "\t " << K << "\t" << *CI[K].Coeff);
DEBUG(dbgs() << "\tPos Part = ");
DEBUG(dbgs() << *CI[K].PosPart);
DEBUG(dbgs() << "\tNeg Part = ");
DEBUG(dbgs() << *CI[K].NegPart);
DEBUG(dbgs() << "\tUpper Bound = ");
if (CI[K].Iterations)
DEBUG(dbgs() << *CI[K].Iterations);
else
DEBUG(dbgs() << "+inf");
DEBUG(dbgs() << '\n');
}
DEBUG(dbgs() << "\t Constant = " << *Subscript << '\n');
#endif
return CI;
}
// Looks through all the bounds info and
// computes the lower bound given the current direction settings
// at each level. If the lower bound for any level is -inf,
// the result is -inf.
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
const SCEV *DependenceInfo::getLowerBound(BoundInfo *Bound) const {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
const SCEV *Sum = Bound[1].Lower[Bound[1].Direction];
for (unsigned K = 2; Sum && K <= MaxLevels; ++K) {
if (Bound[K].Lower[Bound[K].Direction])
Sum = SE->getAddExpr(Sum, Bound[K].Lower[Bound[K].Direction]);
else
[C++11] More 'nullptr' conversion. In some cases just using a boolean check instead of comparing to nullptr. llvm-svn: 206243
2014-04-15 12:59:12 +08:00
Sum = nullptr;
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
}
return Sum;
}
// Looks through all the bounds info and
// computes the upper bound given the current direction settings
// at each level. If the upper bound at any level is +inf,
// the result is +inf.
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
const SCEV *DependenceInfo::getUpperBound(BoundInfo *Bound) const {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
const SCEV *Sum = Bound[1].Upper[Bound[1].Direction];
for (unsigned K = 2; Sum && K <= MaxLevels; ++K) {
if (Bound[K].Upper[Bound[K].Direction])
Sum = SE->getAddExpr(Sum, Bound[K].Upper[Bound[K].Direction]);
else
[C++11] More 'nullptr' conversion. In some cases just using a boolean check instead of comparing to nullptr. llvm-svn: 206243
2014-04-15 12:59:12 +08:00
Sum = nullptr;
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
}
return Sum;
}
//===----------------------------------------------------------------------===//
// Constraint manipulation for Delta test.
// Given a linear SCEV,
// return the coefficient (the step)
// corresponding to the specified loop.
// If there isn't one, return 0.
[DependenceAnalysis] Extend unifySubscriptType for handling coupled subscript groups. Summary: In continuation to an earlier commit to DependenceAnalysis.cpp by jingyue (r222100), the type for all subscripts in a coupled group need to be the same since constraints from one subscript may be propagated to another during testing. During testing, new SCEVs may be created and the operands for these need to be the same. This patch extends unifySubscriptType() to work on lists of subscript pairs, ensuring a common extended type for all of them. Test Plan: Added a test case to NonCanonicalizedSubscript.ll which causes dependence analysis to crash without this fix. All regression tests pass. Reviewers: spop, sebpop, jingyue Reviewed By: jingyue Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9698 llvm-svn: 238573
2015-05-30 00:58:08 +08:00
// For example, given a*i + b*j + c*k, finding the coefficient
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
// corresponding to the j loop would yield b.
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
const SCEV *DependenceInfo::findCoefficient(const SCEV *Expr,
const Loop *TargetLoop) const {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
const SCEVAddRecExpr *AddRec = dyn_cast<SCEVAddRecExpr>(Expr);
if (!AddRec)
[SCEV] Introduce ScalarEvolution::getOne and getZero. Summary: It is fairly common to call SE->getConstant(Ty, 0) or SE->getConstant(Ty, 1); this change makes such uses a little bit briefer. I've refactored the call sites I could find easily to use getZero / getOne. Reviewers: hfinkel, majnemer, reames Subscribers: sanjoy, llvm-commits Differential Revision: http://reviews.llvm.org/D12947 llvm-svn: 248362
2015-09-23 09:59:04 +08:00
return SE->getZero(Expr->getType());
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
if (AddRec->getLoop() == TargetLoop)
return AddRec->getStepRecurrence(*SE);
return findCoefficient(AddRec->getStart(), TargetLoop);
}
// Given a linear SCEV,
// return the SCEV given by zeroing out the coefficient
// corresponding to the specified loop.
// For example, given a*i + b*j + c*k, zeroing the coefficient
// corresponding to the j loop would yield a*i + c*k.
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
const SCEV *DependenceInfo::zeroCoefficient(const SCEV *Expr,
const Loop *TargetLoop) const {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
const SCEVAddRecExpr *AddRec = dyn_cast<SCEVAddRecExpr>(Expr);
if (!AddRec)
return Expr; // ignore
if (AddRec->getLoop() == TargetLoop)
return AddRec->getStart();
return SE->getAddRecExpr(zeroCoefficient(AddRec->getStart(), TargetLoop),
AddRec->getStepRecurrence(*SE),
AddRec->getLoop(),
AddRec->getNoWrapFlags());
}
// Given a linear SCEV Expr,
// return the SCEV given by adding some Value to the
// coefficient corresponding to the specified TargetLoop.
// For example, given a*i + b*j + c*k, adding 1 to the coefficient
// corresponding to the j loop would yield a*i + (b+1)*j + c*k.
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
const SCEV *DependenceInfo::addToCoefficient(const SCEV *Expr,
const Loop *TargetLoop,
const SCEV *Value) const {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
const SCEVAddRecExpr *AddRec = dyn_cast<SCEVAddRecExpr>(Expr);
if (!AddRec) // create a new addRec
return SE->getAddRecExpr(Expr,
Value,
TargetLoop,
SCEV::FlagAnyWrap); // Worst case, with no info.
if (AddRec->getLoop() == TargetLoop) {
const SCEV *Sum = SE->getAddExpr(AddRec->getStepRecurrence(*SE), Value);
if (Sum->isZero())
return AddRec->getStart();
return SE->getAddRecExpr(AddRec->getStart(),
Sum,
AddRec->getLoop(),
AddRec->getNoWrapFlags());
}
(no commit message) llvm-svn: 185187
2013-06-29 02:44:48 +08:00
if (SE->isLoopInvariant(AddRec, TargetLoop))
Reformat partially, where I touched for whitespace changes. llvm-svn: 220773
2014-10-28 19:54:52 +08:00
return SE->getAddRecExpr(AddRec, Value, TargetLoop, SCEV::FlagAnyWrap);
return SE->getAddRecExpr(
addToCoefficient(AddRec->getStart(), TargetLoop, Value),
AddRec->getStepRecurrence(*SE), AddRec->getLoop(),
AddRec->getNoWrapFlags());
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
}
// Review the constraints, looking for opportunities
// to simplify a subscript pair (Src and Dst).
// Return true if some simplification occurs.
// If the simplification isn't exact (that is, if it is conservative
// in terms of dependence), set consistent to false.
// Corresponds to Figure 5 from the paper
//
// Practical Dependence Testing
// Goff, Kennedy, Tseng
// PLDI 1991
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
bool DependenceInfo::propagate(const SCEV *&Src, const SCEV *&Dst,
SmallBitVector &Loops,
SmallVectorImpl<Constraint> &Constraints,
bool &Consistent) {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
bool Result = false;
for (int LI = Loops.find_first(); LI >= 0; LI = Loops.find_next(LI)) {
DEBUG(dbgs() << "\t Constraint[" << LI << "] is");
DEBUG(Constraints[LI].dump(dbgs()));
if (Constraints[LI].isDistance())
Result |= propagateDistance(Src, Dst, Constraints[LI], Consistent);
else if (Constraints[LI].isLine())
Result |= propagateLine(Src, Dst, Constraints[LI], Consistent);
else if (Constraints[LI].isPoint())
Result |= propagatePoint(Src, Dst, Constraints[LI]);
}
return Result;
}
// Attempt to propagate a distance
// constraint into a subscript pair (Src and Dst).
// Return true if some simplification occurs.
// If the simplification isn't exact (that is, if it is conservative
// in terms of dependence), set consistent to false.
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
bool DependenceInfo::propagateDistance(const SCEV *&Src, const SCEV *&Dst,
Constraint &CurConstraint,
bool &Consistent) {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
const Loop *CurLoop = CurConstraint.getAssociatedLoop();
DEBUG(dbgs() << "\t\tSrc is " << *Src << "\n");
const SCEV *A_K = findCoefficient(Src, CurLoop);
if (A_K->isZero())
return false;
const SCEV *DA_K = SE->getMulExpr(A_K, CurConstraint.getD());
Src = SE->getMinusSCEV(Src, DA_K);
Src = zeroCoefficient(Src, CurLoop);
DEBUG(dbgs() << "\t\tnew Src is " << *Src << "\n");
DEBUG(dbgs() << "\t\tDst is " << *Dst << "\n");
Dst = addToCoefficient(Dst, CurLoop, SE->getNegativeSCEV(A_K));
DEBUG(dbgs() << "\t\tnew Dst is " << *Dst << "\n");
if (!findCoefficient(Dst, CurLoop)->isZero())
Consistent = false;
return true;
}
// Attempt to propagate a line
// constraint into a subscript pair (Src and Dst).
// Return true if some simplification occurs.
// If the simplification isn't exact (that is, if it is conservative
// in terms of dependence), set consistent to false.
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
bool DependenceInfo::propagateLine(const SCEV *&Src, const SCEV *&Dst,
Constraint &CurConstraint,
bool &Consistent) {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
const Loop *CurLoop = CurConstraint.getAssociatedLoop();
const SCEV *A = CurConstraint.getA();
const SCEV *B = CurConstraint.getB();
const SCEV *C = CurConstraint.getC();
DEBUG(dbgs() << "\t\tA = " << *A << ", B = " << *B << ", C = " << *C << "\n");
DEBUG(dbgs() << "\t\tSrc = " << *Src << "\n");
DEBUG(dbgs() << "\t\tDst = " << *Dst << "\n");
if (A->isZero()) {
const SCEVConstant *Bconst = dyn_cast<SCEVConstant>(B);
const SCEVConstant *Cconst = dyn_cast<SCEVConstant>(C);
if (!Bconst || !Cconst) return false;
[SCEV] Add and use SCEVConstant::getAPInt; NFCI llvm-svn: 255921
2015-12-18 04:28:46 +08:00
APInt Beta = Bconst->getAPInt();
APInt Charlie = Cconst->getAPInt();
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
APInt CdivB = Charlie.sdiv(Beta);
assert(Charlie.srem(Beta) == 0 && "C should be evenly divisible by B");
const SCEV *AP_K = findCoefficient(Dst, CurLoop);
// Src = SE->getAddExpr(Src, SE->getMulExpr(AP_K, SE->getConstant(CdivB)));
Src = SE->getMinusSCEV(Src, SE->getMulExpr(AP_K, SE->getConstant(CdivB)));
Dst = zeroCoefficient(Dst, CurLoop);
if (!findCoefficient(Src, CurLoop)->isZero())
Consistent = false;
}
else if (B->isZero()) {
const SCEVConstant *Aconst = dyn_cast<SCEVConstant>(A);
const SCEVConstant *Cconst = dyn_cast<SCEVConstant>(C);
if (!Aconst || !Cconst) return false;
[SCEV] Add and use SCEVConstant::getAPInt; NFCI llvm-svn: 255921
2015-12-18 04:28:46 +08:00
APInt Alpha = Aconst->getAPInt();
APInt Charlie = Cconst->getAPInt();
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
APInt CdivA = Charlie.sdiv(Alpha);
assert(Charlie.srem(Alpha) == 0 && "C should be evenly divisible by A");
const SCEV *A_K = findCoefficient(Src, CurLoop);
Src = SE->getAddExpr(Src, SE->getMulExpr(A_K, SE->getConstant(CdivA)));
Src = zeroCoefficient(Src, CurLoop);
if (!findCoefficient(Dst, CurLoop)->isZero())
Consistent = false;
}
else if (isKnownPredicate(CmpInst::ICMP_EQ, A, B)) {
const SCEVConstant *Aconst = dyn_cast<SCEVConstant>(A);
const SCEVConstant *Cconst = dyn_cast<SCEVConstant>(C);
if (!Aconst || !Cconst) return false;
[SCEV] Add and use SCEVConstant::getAPInt; NFCI llvm-svn: 255921
2015-12-18 04:28:46 +08:00
APInt Alpha = Aconst->getAPInt();
APInt Charlie = Cconst->getAPInt();
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
APInt CdivA = Charlie.sdiv(Alpha);
assert(Charlie.srem(Alpha) == 0 && "C should be evenly divisible by A");
const SCEV *A_K = findCoefficient(Src, CurLoop);
Src = SE->getAddExpr(Src, SE->getMulExpr(A_K, SE->getConstant(CdivA)));
Src = zeroCoefficient(Src, CurLoop);
Dst = addToCoefficient(Dst, CurLoop, A_K);
if (!findCoefficient(Dst, CurLoop)->isZero())
Consistent = false;
}
else {
// paper is incorrect here, or perhaps just misleading
const SCEV *A_K = findCoefficient(Src, CurLoop);
Src = SE->getMulExpr(Src, A);
Dst = SE->getMulExpr(Dst, A);
Src = SE->getAddExpr(Src, SE->getMulExpr(A_K, C));
Src = zeroCoefficient(Src, CurLoop);
Dst = addToCoefficient(Dst, CurLoop, SE->getMulExpr(A_K, B));
if (!findCoefficient(Dst, CurLoop)->isZero())
Consistent = false;
}
DEBUG(dbgs() << "\t\tnew Src = " << *Src << "\n");
DEBUG(dbgs() << "\t\tnew Dst = " << *Dst << "\n");
return true;
}
// Attempt to propagate a point
// constraint into a subscript pair (Src and Dst).
// Return true if some simplification occurs.
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
bool DependenceInfo::propagatePoint(const SCEV *&Src, const SCEV *&Dst,
Constraint &CurConstraint) {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
const Loop *CurLoop = CurConstraint.getAssociatedLoop();
const SCEV *A_K = findCoefficient(Src, CurLoop);
const SCEV *AP_K = findCoefficient(Dst, CurLoop);
const SCEV *XA_K = SE->getMulExpr(A_K, CurConstraint.getX());
const SCEV *YAP_K = SE->getMulExpr(AP_K, CurConstraint.getY());
DEBUG(dbgs() << "\t\tSrc is " << *Src << "\n");
Src = SE->getAddExpr(Src, SE->getMinusSCEV(XA_K, YAP_K));
Src = zeroCoefficient(Src, CurLoop);
DEBUG(dbgs() << "\t\tnew Src is " << *Src << "\n");
DEBUG(dbgs() << "\t\tDst is " << *Dst << "\n");
Dst = zeroCoefficient(Dst, CurLoop);
DEBUG(dbgs() << "\t\tnew Dst is " << *Dst << "\n");
return true;
}
// Update direction vector entry based on the current constraint.
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
void DependenceInfo::updateDirection(Dependence::DVEntry &Level,
const Constraint &CurConstraint) const {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
DEBUG(dbgs() << "\tUpdate direction, constraint =");
DEBUG(CurConstraint.dump(dbgs()));
if (CurConstraint.isAny())
; // use defaults
else if (CurConstraint.isDistance()) {
// this one is consistent, the others aren't
Level.Scalar = false;
Level.Distance = CurConstraint.getD();
unsigned NewDirection = Dependence::DVEntry::NONE;
if (!SE->isKnownNonZero(Level.Distance)) // if may be zero
NewDirection = Dependence::DVEntry::EQ;
if (!SE->isKnownNonPositive(Level.Distance)) // if may be positive
NewDirection |= Dependence::DVEntry::LT;
if (!SE->isKnownNonNegative(Level.Distance)) // if may be negative
NewDirection |= Dependence::DVEntry::GT;
Level.Direction &= NewDirection;
}
else if (CurConstraint.isLine()) {
Level.Scalar = false;
[C++11] More 'nullptr' conversion. In some cases just using a boolean check instead of comparing to nullptr. llvm-svn: 206243
2014-04-15 12:59:12 +08:00
Level.Distance = nullptr;
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
// direction should be accurate
}
else if (CurConstraint.isPoint()) {
Level.Scalar = false;
[C++11] More 'nullptr' conversion. In some cases just using a boolean check instead of comparing to nullptr. llvm-svn: 206243
2014-04-15 12:59:12 +08:00
Level.Distance = nullptr;
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
unsigned NewDirection = Dependence::DVEntry::NONE;
if (!isKnownPredicate(CmpInst::ICMP_NE,
CurConstraint.getY(),
CurConstraint.getX()))
// if X may be = Y
NewDirection |= Dependence::DVEntry::EQ;
if (!isKnownPredicate(CmpInst::ICMP_SLE,
CurConstraint.getY(),
CurConstraint.getX()))
// if Y may be > X
NewDirection |= Dependence::DVEntry::LT;
if (!isKnownPredicate(CmpInst::ICMP_SGE,
CurConstraint.getY(),
CurConstraint.getX()))
// if Y may be < X
NewDirection |= Dependence::DVEntry::GT;
Level.Direction &= NewDirection;
}
else
llvm_unreachable("constraint has unexpected kind");
}
delinearization of arrays llvm-svn: 194527
2013-11-13 06:47:20 +08:00
/// Check if we can delinearize the subscripts. If the SCEVs representing the
/// source and destination array references are recurrences on a nested loop,
Fix known typos Sweep the codebase for common typos. Includes some changes to visible function names that were misspelt. llvm-svn: 200018
2014-01-25 01:20:08 +08:00
/// this function flattens the nested recurrences into separate recurrences
delinearization of arrays llvm-svn: 194527
2013-11-13 06:47:20 +08:00
/// for each loop level.
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
bool DependenceInfo::tryDelinearize(Instruction *Src, Instruction *Dst,
SmallVectorImpl<Subscript> &Pair) {
Fix how DependenceAnalysis calls delinearization Fix how DependenceAnalysis calls delinearization, mirroring what is done in Delinearization.cpp (mostly by making sure to call getSCEVAtScope before delinearizing, and by removing the unnecessary 'Pairs == 1' check). Patch by Vaivaswatha Nagaraj! llvm-svn: 245408
2015-08-19 10:56:36 +08:00
Value *SrcPtr = getPointerOperand(Src);
Value *DstPtr = getPointerOperand(Dst);
Loop *SrcLoop = LI->getLoopFor(Src->getParent());
Loop *DstLoop = LI->getLoopFor(Dst->getParent());
// Below code mimics the code in Delinearization.cpp
const SCEV *SrcAccessFn =
SE->getSCEVAtScope(SrcPtr, SrcLoop);
const SCEV *DstAccessFn =
SE->getSCEVAtScope(DstPtr, DstLoop);
remove BasePointer before delinearizing No functional change is intended: instead of relying on the delinearization to come up with the base pointer as a remainder of the divisions in the delinearization, we just compute it from the array access and use that value. We substract the base pointer from the SCEV to be delinearized and that simplifies the work of the delinearizer. llvm-svn: 209692
2014-05-28 06:41:51 +08:00
const SCEVUnknown *SrcBase =
Fix how DependenceAnalysis calls delinearization Fix how DependenceAnalysis calls delinearization, mirroring what is done in Delinearization.cpp (mostly by making sure to call getSCEVAtScope before delinearizing, and by removing the unnecessary 'Pairs == 1' check). Patch by Vaivaswatha Nagaraj! llvm-svn: 245408
2015-08-19 10:56:36 +08:00
dyn_cast<SCEVUnknown>(SE->getPointerBase(SrcAccessFn));
remove BasePointer before delinearizing No functional change is intended: instead of relying on the delinearization to come up with the base pointer as a remainder of the divisions in the delinearization, we just compute it from the array access and use that value. We substract the base pointer from the SCEV to be delinearized and that simplifies the work of the delinearizer. llvm-svn: 209692
2014-05-28 06:41:51 +08:00
const SCEVUnknown *DstBase =
Fix how DependenceAnalysis calls delinearization Fix how DependenceAnalysis calls delinearization, mirroring what is done in Delinearization.cpp (mostly by making sure to call getSCEVAtScope before delinearizing, and by removing the unnecessary 'Pairs == 1' check). Patch by Vaivaswatha Nagaraj! llvm-svn: 245408
2015-08-19 10:56:36 +08:00
dyn_cast<SCEVUnknown>(SE->getPointerBase(DstAccessFn));
remove BasePointer before delinearizing No functional change is intended: instead of relying on the delinearization to come up with the base pointer as a remainder of the divisions in the delinearization, we just compute it from the array access and use that value. We substract the base pointer from the SCEV to be delinearized and that simplifies the work of the delinearizer. llvm-svn: 209692
2014-05-28 06:41:51 +08:00
if (!SrcBase || !DstBase || SrcBase != DstBase)
return false;
Fix how DependenceAnalysis calls delinearization Fix how DependenceAnalysis calls delinearization, mirroring what is done in Delinearization.cpp (mostly by making sure to call getSCEVAtScope before delinearizing, and by removing the unnecessary 'Pairs == 1' check). Patch by Vaivaswatha Nagaraj! llvm-svn: 245408
2015-08-19 10:56:36 +08:00
const SCEV *ElementSize = SE->getElementSize(Src);
if (ElementSize != SE->getElementSize(Dst))
return false;
const SCEV *SrcSCEV = SE->getMinusSCEV(SrcAccessFn, SrcBase);
const SCEV *DstSCEV = SE->getMinusSCEV(DstAccessFn, DstBase);
remove BasePointer before delinearizing No functional change is intended: instead of relying on the delinearization to come up with the base pointer as a remainder of the divisions in the delinearization, we just compute it from the array access and use that value. We substract the base pointer from the SCEV to be delinearized and that simplifies the work of the delinearizer. llvm-svn: 209692
2014-05-28 06:41:51 +08:00
delinearization of arrays llvm-svn: 194527
2013-11-13 06:47:20 +08:00
const SCEVAddRecExpr *SrcAR = dyn_cast<SCEVAddRecExpr>(SrcSCEV);
const SCEVAddRecExpr *DstAR = dyn_cast<SCEVAddRecExpr>(DstSCEV);
if (!SrcAR || !DstAR || !SrcAR->isAffine() || !DstAR->isAffine())
return false;
split delinearization pass in 3 steps To compute the dimensions of the array in a unique way, we split the delinearization analysis in three steps: - find parametric terms in all memory access functions - compute the array dimensions from the set of terms - compute the delinearized access functions for each dimension The first step is executed on all the memory access functions such that we gather all the patterns in which an array is accessed. The second step reduces all this information in a unique description of the sizes of the array. The third step is delinearizing each memory access function following the common description of the shape of the array computed in step 2. This rewrite of the delinearization pass also solves a problem we had with the previous implementation: because the previous algorithm was by induction on the structure of the SCEV, it would not correctly recognize the shape of the array when the memory access was not following the nesting of the loops: for example, see polly/test/ScopInfo/multidim_only_ivs_3d_reverse.ll ; void foo(long n, long m, long o, double A[n][m][o]) { ; ; for (long i = 0; i < n; i++) ; for (long j = 0; j < m; j++) ; for (long k = 0; k < o; k++) ; A[i][k][j] = 1.0; Starting with this patch we no longer delinearize access functions that do not contain parameters, for example in test/Analysis/DependenceAnalysis/GCD.ll ;; for (long int i = 0; i < 100; i++) ;; for (long int j = 0; j < 100; j++) { ;; A[2*i - 4*j] = i; ;; *B++ = A[6*i + 8*j]; these accesses will not be delinearized as the upper bound of the loops are constants, and their access functions do not contain SCEVUnknown parameters. llvm-svn: 208232
2014-05-08 02:01:20 +08:00
// First step: collect parametric terms in both array references.
SmallVector<const SCEV *, 4> Terms;
Move delinearization from SCEVAddRecExpr to ScalarEvolution The expressions we delinearize do not necessarily have to have a SCEVAddRecExpr at the outermost level. At this moment, the additional flexibility is not exploited in LLVM itself, but in Polly we will soon soonish use this functionality. For LLVM, this change should not affect existing functionality (which is covered by test/Analysis/Delinearization/) llvm-svn: 240952
2015-06-29 22:42:48 +08:00
SE->collectParametricTerms(SrcAR, Terms);
SE->collectParametricTerms(DstAR, Terms);
delinearization of arrays llvm-svn: 194527
2013-11-13 06:47:20 +08:00
split delinearization pass in 3 steps To compute the dimensions of the array in a unique way, we split the delinearization analysis in three steps: - find parametric terms in all memory access functions - compute the array dimensions from the set of terms - compute the delinearized access functions for each dimension The first step is executed on all the memory access functions such that we gather all the patterns in which an array is accessed. The second step reduces all this information in a unique description of the sizes of the array. The third step is delinearizing each memory access function following the common description of the shape of the array computed in step 2. This rewrite of the delinearization pass also solves a problem we had with the previous implementation: because the previous algorithm was by induction on the structure of the SCEV, it would not correctly recognize the shape of the array when the memory access was not following the nesting of the loops: for example, see polly/test/ScopInfo/multidim_only_ivs_3d_reverse.ll ; void foo(long n, long m, long o, double A[n][m][o]) { ; ; for (long i = 0; i < n; i++) ; for (long j = 0; j < m; j++) ; for (long k = 0; k < o; k++) ; A[i][k][j] = 1.0; Starting with this patch we no longer delinearize access functions that do not contain parameters, for example in test/Analysis/DependenceAnalysis/GCD.ll ;; for (long int i = 0; i < 100; i++) ;; for (long int j = 0; j < 100; j++) { ;; A[2*i - 4*j] = i; ;; *B++ = A[6*i + 8*j]; these accesses will not be delinearized as the upper bound of the loops are constants, and their access functions do not contain SCEVUnknown parameters. llvm-svn: 208232
2014-05-08 02:01:20 +08:00
// Second step: find subscript sizes.
SmallVector<const SCEV *, 4> Sizes;
remove constant terms The delinearization is needed only to remove the non linearity induced by expressions involving multiplications of parameters and induction variables. There is no problem in dealing with constant times parameters, or constant times an induction variable. For this reason, the current patch discards all constant terms and multipliers before running the delinearization algorithm on the terms. The only thing remaining in the term expressions are parameters and multiply expressions of parameters: these simplified term expressions are passed to the array shape recognizer that will not recognize constant dimensions anymore: these will be recognized as different strides in parametric subscripts. The only important special case of a constant dimension is the size of elements. Instead of relying on the delinearization to infer the size of an element, compute the element size from the base address type. This is a much more precise way of computing the element size than before, as we would have mixed together the size of an element with the strides of the innermost dimension. llvm-svn: 209691
2014-05-28 06:41:45 +08:00
SE->findArrayDimensions(Terms, Sizes, ElementSize);
fail delinearization when the size of subscripts differs Because the delinearization is not a global analysis pass, it will compute the delinearization independently of knowledge about the way the delinearization happened for other data accesses to the same array: the dependence analysis will only trigger the delinearization on a tuple of access functions, and thus delinearization may compute different subscripts sizes for a same array. When that happens the safest is to discard the delinearized information. llvm-svn: 201866
2014-02-22 02:15:07 +08:00
split delinearization pass in 3 steps To compute the dimensions of the array in a unique way, we split the delinearization analysis in three steps: - find parametric terms in all memory access functions - compute the array dimensions from the set of terms - compute the delinearized access functions for each dimension The first step is executed on all the memory access functions such that we gather all the patterns in which an array is accessed. The second step reduces all this information in a unique description of the sizes of the array. The third step is delinearizing each memory access function following the common description of the shape of the array computed in step 2. This rewrite of the delinearization pass also solves a problem we had with the previous implementation: because the previous algorithm was by induction on the structure of the SCEV, it would not correctly recognize the shape of the array when the memory access was not following the nesting of the loops: for example, see polly/test/ScopInfo/multidim_only_ivs_3d_reverse.ll ; void foo(long n, long m, long o, double A[n][m][o]) { ; ; for (long i = 0; i < n; i++) ; for (long j = 0; j < m; j++) ; for (long k = 0; k < o; k++) ; A[i][k][j] = 1.0; Starting with this patch we no longer delinearize access functions that do not contain parameters, for example in test/Analysis/DependenceAnalysis/GCD.ll ;; for (long int i = 0; i < 100; i++) ;; for (long int j = 0; j < 100; j++) { ;; A[2*i - 4*j] = i; ;; *B++ = A[6*i + 8*j]; these accesses will not be delinearized as the upper bound of the loops are constants, and their access functions do not contain SCEVUnknown parameters. llvm-svn: 208232
2014-05-08 02:01:20 +08:00
// Third step: compute the access functions for each subscript.
SmallVector<const SCEV *, 4> SrcSubscripts, DstSubscripts;
Move delinearization from SCEVAddRecExpr to ScalarEvolution The expressions we delinearize do not necessarily have to have a SCEVAddRecExpr at the outermost level. At this moment, the additional flexibility is not exploited in LLVM itself, but in Polly we will soon soonish use this functionality. For LLVM, this change should not affect existing functionality (which is covered by test/Analysis/Delinearization/) llvm-svn: 240952
2015-06-29 22:42:48 +08:00
SE->computeAccessFunctions(SrcAR, SrcSubscripts, Sizes);
SE->computeAccessFunctions(DstAR, DstSubscripts, Sizes);
delinearization of arrays llvm-svn: 194527
2013-11-13 06:47:20 +08:00
split delinearization pass in 3 steps To compute the dimensions of the array in a unique way, we split the delinearization analysis in three steps: - find parametric terms in all memory access functions - compute the array dimensions from the set of terms - compute the delinearized access functions for each dimension The first step is executed on all the memory access functions such that we gather all the patterns in which an array is accessed. The second step reduces all this information in a unique description of the sizes of the array. The third step is delinearizing each memory access function following the common description of the shape of the array computed in step 2. This rewrite of the delinearization pass also solves a problem we had with the previous implementation: because the previous algorithm was by induction on the structure of the SCEV, it would not correctly recognize the shape of the array when the memory access was not following the nesting of the loops: for example, see polly/test/ScopInfo/multidim_only_ivs_3d_reverse.ll ; void foo(long n, long m, long o, double A[n][m][o]) { ; ; for (long i = 0; i < n; i++) ; for (long j = 0; j < m; j++) ; for (long k = 0; k < o; k++) ; A[i][k][j] = 1.0; Starting with this patch we no longer delinearize access functions that do not contain parameters, for example in test/Analysis/DependenceAnalysis/GCD.ll ;; for (long int i = 0; i < 100; i++) ;; for (long int j = 0; j < 100; j++) { ;; A[2*i - 4*j] = i; ;; *B++ = A[6*i + 8*j]; these accesses will not be delinearized as the upper bound of the loops are constants, and their access functions do not contain SCEVUnknown parameters. llvm-svn: 208232
2014-05-08 02:01:20 +08:00
// Fail when there is only a subscript: that's a linearized access function.
if (SrcSubscripts.size() < 2 || DstSubscripts.size() < 2 ||
SrcSubscripts.size() != DstSubscripts.size())
return false;
fail delinearization when the size of subscripts differs Because the delinearization is not a global analysis pass, it will compute the delinearization independently of knowledge about the way the delinearization happened for other data accesses to the same array: the dependence analysis will only trigger the delinearization on a tuple of access functions, and thus delinearization may compute different subscripts sizes for a same array. When that happens the safest is to discard the delinearized information. llvm-svn: 201866
2014-02-22 02:15:07 +08:00
split delinearization pass in 3 steps To compute the dimensions of the array in a unique way, we split the delinearization analysis in three steps: - find parametric terms in all memory access functions - compute the array dimensions from the set of terms - compute the delinearized access functions for each dimension The first step is executed on all the memory access functions such that we gather all the patterns in which an array is accessed. The second step reduces all this information in a unique description of the sizes of the array. The third step is delinearizing each memory access function following the common description of the shape of the array computed in step 2. This rewrite of the delinearization pass also solves a problem we had with the previous implementation: because the previous algorithm was by induction on the structure of the SCEV, it would not correctly recognize the shape of the array when the memory access was not following the nesting of the loops: for example, see polly/test/ScopInfo/multidim_only_ivs_3d_reverse.ll ; void foo(long n, long m, long o, double A[n][m][o]) { ; ; for (long i = 0; i < n; i++) ; for (long j = 0; j < m; j++) ; for (long k = 0; k < o; k++) ; A[i][k][j] = 1.0; Starting with this patch we no longer delinearize access functions that do not contain parameters, for example in test/Analysis/DependenceAnalysis/GCD.ll ;; for (long int i = 0; i < 100; i++) ;; for (long int j = 0; j < 100; j++) { ;; A[2*i - 4*j] = i; ;; *B++ = A[6*i + 8*j]; these accesses will not be delinearized as the upper bound of the loops are constants, and their access functions do not contain SCEVUnknown parameters. llvm-svn: 208232
2014-05-08 02:01:20 +08:00
int size = SrcSubscripts.size();
normalize the last delinearized dimension in the dependence test, we used to discard some information that the delinearization provides: the size of the innermost dimension of an array, i.e., the size of scalars stored in the array, and the remainder of the delinearization that provides the offset from which the array reads start, i.e., the base address of the array. To avoid losing this data in the rest of the data dependence analysis, the fix is to multiply the access function in the last delinearized dimension by its size, effectively making the size of the last dimension to always be in bytes, and then add the remainder of delinearization to the last subscript, effectively making the last subscript start at the base address of the array. llvm-svn: 201867
2014-02-22 02:15:11 +08:00
split delinearization pass in 3 steps To compute the dimensions of the array in a unique way, we split the delinearization analysis in three steps: - find parametric terms in all memory access functions - compute the array dimensions from the set of terms - compute the delinearized access functions for each dimension The first step is executed on all the memory access functions such that we gather all the patterns in which an array is accessed. The second step reduces all this information in a unique description of the sizes of the array. The third step is delinearizing each memory access function following the common description of the shape of the array computed in step 2. This rewrite of the delinearization pass also solves a problem we had with the previous implementation: because the previous algorithm was by induction on the structure of the SCEV, it would not correctly recognize the shape of the array when the memory access was not following the nesting of the loops: for example, see polly/test/ScopInfo/multidim_only_ivs_3d_reverse.ll ; void foo(long n, long m, long o, double A[n][m][o]) { ; ; for (long i = 0; i < n; i++) ; for (long j = 0; j < m; j++) ; for (long k = 0; k < o; k++) ; A[i][k][j] = 1.0; Starting with this patch we no longer delinearize access functions that do not contain parameters, for example in test/Analysis/DependenceAnalysis/GCD.ll ;; for (long int i = 0; i < 100; i++) ;; for (long int j = 0; j < 100; j++) { ;; A[2*i - 4*j] = i; ;; *B++ = A[6*i + 8*j]; these accesses will not be delinearized as the upper bound of the loops are constants, and their access functions do not contain SCEVUnknown parameters. llvm-svn: 208232
2014-05-08 02:01:20 +08:00
DEBUG({
dbgs() << "\nSrcSubscripts: ";
for (int i = 0; i < size; i++)
dbgs() << *SrcSubscripts[i];
dbgs() << "\nDstSubscripts: ";
for (int i = 0; i < size; i++)
dbgs() << *DstSubscripts[i];
});
delinearization of arrays llvm-svn: 194527
2013-11-13 06:47:20 +08:00
add more comments around the delinearization of arrays llvm-svn: 194612
2013-11-14 06:37:58 +08:00
// The delinearization transforms a single-subscript MIV dependence test into
// a multi-subscript SIV dependence test that is easier to compute. So we
// resize Pair to contain as many pairs of subscripts as the delinearization
// has found, and then initialize the pairs following the delinearization.
delinearization of arrays llvm-svn: 194527
2013-11-13 06:47:20 +08:00
Pair.resize(size);
for (int i = 0; i < size; ++i) {
Pair[i].Src = SrcSubscripts[i];
Pair[i].Dst = DstSubscripts[i];
[DependenceAnalysis] Allow subscripts of different types Summary: Several places in DependenceAnalysis assumes both SCEVs in a subscript pair share the same integer type. For instance, isKnownPredicate calls SE->getMinusSCEV(X, Y) which asserts X and Y share the same type. However, DependenceAnalysis fails to ensure this assumption when producing a subscript pair, causing tests such as NonCanonicalizedSubscript to crash. With this patch, DependenceAnalysis runs unifySubscriptType before producing any subscript pair, ensuring the assumption. Test Plan: Added NonCanonicalizedSubscript.ll on which DependenceAnalysis before the fix crashed because subscripts have different types. Reviewers: spop, sebpop, jingyue Reviewed By: jingyue Subscribers: eliben, meheff, llvm-commits Differential Revision: http://reviews.llvm.org/D6289 llvm-svn: 222100
2014-11-17 00:52:44 +08:00
unifySubscriptType(&Pair[i]);
add more comments around the delinearization of arrays llvm-svn: 194612
2013-11-14 06:37:58 +08:00
// FIXME: we should record the bounds SrcSizes[i] and DstSizes[i] that the
// delinearization has found, and add these constraints to the dependence
// check to avoid memory accesses overflow from one dimension into another.
// This is related to the problem of determining the existence of data
// dependences in array accesses using a different number of subscripts: in
// C one can access an array A[100][100]; as A[0][9999], *A[9999], etc.
delinearization of arrays llvm-svn: 194527
2013-11-13 06:47:20 +08:00
}
return true;
}
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
//===----------------------------------------------------------------------===//
#ifndef NDEBUG
// For debugging purposes, dump a small bit vector to dbgs().
static void dumpSmallBitVector(SmallBitVector &BV) {
dbgs() << "{";
for (int VI = BV.find_first(); VI >= 0; VI = BV.find_next(VI)) {
dbgs() << VI;
if (BV.find_next(VI) >= 0)
dbgs() << ' ';
}
dbgs() << "}\n";
}
#endif
// depends -
// Returns NULL if there is no dependence.
// Otherwise, return a Dependence with as many details as possible.
// Corresponds to Section 3.1 in the paper
//
// Practical Dependence Testing
// Goff, Kennedy, Tseng
// PLDI 1991
//
Corrects a problem where we reply exclusively of GEPs to drive analysis. Better is to look for cases with useful GEPs and use them when possible. When a pair of useful GEPs is not available, use the raw SCEVs directly. This approach supports better analysis of pointer dereferencing. In parallel, all the test cases are updated appropriately. Cases where we have a store to *B++ can now be analyzed! llvm-svn: 168474
2012-11-22 07:50:04 +08:00
// Care is required to keep the routine below, getSplitIteration(),
// up to date with respect to this routine.
Analysis: unique_ptr-ify DependenceAnalysis::depends llvm-svn: 216357
2014-08-25 08:28:39 +08:00
std::unique_ptr<Dependence>
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
DependenceInfo::depends(Instruction *Src, Instruction *Dst,
bool PossiblyLoopIndependent) {
Modify depends(Src, Dst, PossiblyLoopIndependent). If the Src and Dst are the same instruction, no loop-independent dependence is possible, so we force the PossiblyLoopIndependent flag to false. The test case results are updated appropriately. llvm-svn: 168678
2012-11-27 14:41:46 +08:00
if (Src == Dst)
PossiblyLoopIndependent = false;
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
if ((!Src->mayReadFromMemory() && !Src->mayWriteToMemory()) ||
(!Dst->mayReadFromMemory() && !Dst->mayWriteToMemory()))
// if both instructions don't reference memory, there's no dependence
[C++11] More 'nullptr' conversion. In some cases just using a boolean check instead of comparing to nullptr. llvm-svn: 206243
2014-04-15 12:59:12 +08:00
return nullptr;
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
Corrects a problem where we reply exclusively of GEPs to drive analysis. Better is to look for cases with useful GEPs and use them when possible. When a pair of useful GEPs is not available, use the raw SCEVs directly. This approach supports better analysis of pointer dereferencing. In parallel, all the test cases are updated appropriately. Cases where we have a store to *B++ can now be analyzed! llvm-svn: 168474
2012-11-22 07:50:04 +08:00
if (!isLoadOrStore(Src) || !isLoadOrStore(Dst)) {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
// can only analyze simple loads and stores, i.e., no calls, invokes, etc.
Corrects a problem where we reply exclusively of GEPs to drive analysis. Better is to look for cases with useful GEPs and use them when possible. When a pair of useful GEPs is not available, use the raw SCEVs directly. This approach supports better analysis of pointer dereferencing. In parallel, all the test cases are updated appropriately. Cases where we have a store to *B++ can now be analyzed! llvm-svn: 168474
2012-11-22 07:50:04 +08:00
DEBUG(dbgs() << "can only handle simple loads and stores\n");
Analysis: unique_ptr-ify DependenceAnalysis::depends llvm-svn: 216357
2014-08-25 08:28:39 +08:00
return make_unique<Dependence>(Src, Dst);
Corrects a problem where we reply exclusively of GEPs to drive analysis. Better is to look for cases with useful GEPs and use them when possible. When a pair of useful GEPs is not available, use the raw SCEVs directly. This approach supports better analysis of pointer dereferencing. In parallel, all the test cases are updated appropriately. Cases where we have a store to *B++ can now be analyzed! llvm-svn: 168474
2012-11-22 07:50:04 +08:00
}
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
removes a few "const" qualifiers so that I can (someday) call SE->getSCEV without complaint. No semantic change intended. Patch from Preston Briggs <preston.briggs@gmail.com>. llvm-svn: 168391
2012-11-21 06:28:04 +08:00
Value *SrcPtr = getPointerOperand(Src);
Value *DstPtr = getPointerOperand(Dst);
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
DataLayout is mandatory, update the API to reflect it with references. Summary: Now that the DataLayout is a mandatory part of the module, let's start cleaning the codebase. This patch is a first attempt at doing that. This patch is not exactly NFC as for instance some places were passing a nullptr instead of the DataLayout, possibly just because there was a default value on the DataLayout argument to many functions in the API. Even though it is not purely NFC, there is no change in the validation. I turned as many pointer to DataLayout to references, this helped figuring out all the places where a nullptr could come up. I had initially a local version of this patch broken into over 30 independant, commits but some later commit were cleaning the API and touching part of the code modified in the previous commits, so it seemed cleaner without the intermediate state. Test Plan: Reviewers: echristo Subscribers: llvm-commits From: Mehdi Amini <mehdi.amini@apple.com> llvm-svn: 231740
2015-03-10 10:37:25 +08:00
switch (underlyingObjectsAlias(AA, F->getParent()->getDataLayout(), DstPtr,
SrcPtr)) {
[PM/AA] Hoist the AliasResult enum out of the AliasAnalysis class. This will allow classes to implement the AA interface without deriving from the class or referencing an internal enum of some other class as their return types. Also, to a pretty fundamental extent, concepts such as 'NoAlias', 'MayAlias', and 'MustAlias' are first class concepts in LLVM and we aren't saving anything by scoping them heavily. My mild preference would have been to use a scoped enum, but that feature is essentially completely broken AFAICT. I'm extremely disappointed. For example, we cannot through any reasonable[1] means construct an enum class (or analog) which has scoped names but converts to a boolean in order to test for the possibility of aliasing. [1]: Richard Smith came up with a "solution", but it requires class templates, and lots of boilerplate setting up the enumeration multiple times. Something like Boost.PP could potentially bundle this up, but even that would be quite painful and it doesn't seem realistically worth it. The enum class solution would probably work without the need for a bool conversion. Differential Revision: http://reviews.llvm.org/D10495 llvm-svn: 240255
2015-06-22 10:16:51 +08:00
case MayAlias:
case PartialAlias:
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
// cannot analyse objects if we don't understand their aliasing.
Corrects a problem where we reply exclusively of GEPs to drive analysis. Better is to look for cases with useful GEPs and use them when possible. When a pair of useful GEPs is not available, use the raw SCEVs directly. This approach supports better analysis of pointer dereferencing. In parallel, all the test cases are updated appropriately. Cases where we have a store to *B++ can now be analyzed! llvm-svn: 168474
2012-11-22 07:50:04 +08:00
DEBUG(dbgs() << "can't analyze may or partial alias\n");
Analysis: unique_ptr-ify DependenceAnalysis::depends llvm-svn: 216357
2014-08-25 08:28:39 +08:00
return make_unique<Dependence>(Src, Dst);
[PM/AA] Hoist the AliasResult enum out of the AliasAnalysis class. This will allow classes to implement the AA interface without deriving from the class or referencing an internal enum of some other class as their return types. Also, to a pretty fundamental extent, concepts such as 'NoAlias', 'MayAlias', and 'MustAlias' are first class concepts in LLVM and we aren't saving anything by scoping them heavily. My mild preference would have been to use a scoped enum, but that feature is essentially completely broken AFAICT. I'm extremely disappointed. For example, we cannot through any reasonable[1] means construct an enum class (or analog) which has scoped names but converts to a boolean in order to test for the possibility of aliasing. [1]: Richard Smith came up with a "solution", but it requires class templates, and lots of boilerplate setting up the enumeration multiple times. Something like Boost.PP could potentially bundle this up, but even that would be quite painful and it doesn't seem realistically worth it. The enum class solution would probably work without the need for a bool conversion. Differential Revision: http://reviews.llvm.org/D10495 llvm-svn: 240255
2015-06-22 10:16:51 +08:00
case NoAlias:
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
// If the objects noalias, they are distinct, accesses are independent.
Corrects a problem where we reply exclusively of GEPs to drive analysis. Better is to look for cases with useful GEPs and use them when possible. When a pair of useful GEPs is not available, use the raw SCEVs directly. This approach supports better analysis of pointer dereferencing. In parallel, all the test cases are updated appropriately. Cases where we have a store to *B++ can now be analyzed! llvm-svn: 168474
2012-11-22 07:50:04 +08:00
DEBUG(dbgs() << "no alias\n");
[C++11] More 'nullptr' conversion. In some cases just using a boolean check instead of comparing to nullptr. llvm-svn: 206243
2014-04-15 12:59:12 +08:00
return nullptr;
[PM/AA] Hoist the AliasResult enum out of the AliasAnalysis class. This will allow classes to implement the AA interface without deriving from the class or referencing an internal enum of some other class as their return types. Also, to a pretty fundamental extent, concepts such as 'NoAlias', 'MayAlias', and 'MustAlias' are first class concepts in LLVM and we aren't saving anything by scoping them heavily. My mild preference would have been to use a scoped enum, but that feature is essentially completely broken AFAICT. I'm extremely disappointed. For example, we cannot through any reasonable[1] means construct an enum class (or analog) which has scoped names but converts to a boolean in order to test for the possibility of aliasing. [1]: Richard Smith came up with a "solution", but it requires class templates, and lots of boilerplate setting up the enumeration multiple times. Something like Boost.PP could potentially bundle this up, but even that would be quite painful and it doesn't seem realistically worth it. The enum class solution would probably work without the need for a bool conversion. Differential Revision: http://reviews.llvm.org/D10495 llvm-svn: 240255
2015-06-22 10:16:51 +08:00
case MustAlias:
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
break; // The underlying objects alias; test accesses for dependence.
}
// establish loop nesting levels
establishNestingLevels(Src, Dst);
DEBUG(dbgs() << " common nesting levels = " << CommonLevels << "\n");
DEBUG(dbgs() << " maximum nesting levels = " << MaxLevels << "\n");
Revert r231103, "FullDependenceAnalysis: Avoid using the (deprecated in C++11) copy ctor" It is miscompiled on msc18. llvm-svn: 231335
2015-03-05 09:25:12 +08:00
FullDependence Result(Src, Dst, PossiblyLoopIndependent, CommonLevels);
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
++TotalArrayPairs;
Corrects a problem where we reply exclusively of GEPs to drive analysis. Better is to look for cases with useful GEPs and use them when possible. When a pair of useful GEPs is not available, use the raw SCEVs directly. This approach supports better analysis of pointer dereferencing. In parallel, all the test cases are updated appropriately. Cases where we have a store to *B++ can now be analyzed! llvm-svn: 168474
2012-11-22 07:50:04 +08:00
// See if there are GEPs we can use.
bool UsefulGEP = false;
GEPOperator *SrcGEP = dyn_cast<GEPOperator>(SrcPtr);
GEPOperator *DstGEP = dyn_cast<GEPOperator>(DstPtr);
if (SrcGEP && DstGEP &&
SrcGEP->getPointerOperandType() == DstGEP->getPointerOperandType()) {
const SCEV *SrcPtrSCEV = SE->getSCEV(SrcGEP->getPointerOperand());
const SCEV *DstPtrSCEV = SE->getSCEV(DstGEP->getPointerOperand());
DEBUG(dbgs() << " SrcPtrSCEV = " << *SrcPtrSCEV << "\n");
DEBUG(dbgs() << " DstPtrSCEV = " << *DstPtrSCEV << "\n");
Fix a crash in Dependency Analysis. This crash in Dependency analysis is because we assume here that in case of UsefulGEP both source and destination have the same number of operands which may not be true. This incorrect assumption results in crash while populating Pairs. Fix the same. This crash was observed during lnt regression for code such as- struct s{ int A[10][10]; int C[10][10][10]; } S; void dep_constraint_crash_test(int k,int N) { for( int i=0;i<N;i++) for( int j=0;j<N;j++) S.A[0][0] = S.C[0][0][k]; } Review: http://reviews.llvm.org/D8162 llvm-svn: 231784
2015-03-10 21:31:03 +08:00
UsefulGEP = isLoopInvariant(SrcPtrSCEV, LI->getLoopFor(Src->getParent())) &&
isLoopInvariant(DstPtrSCEV, LI->getLoopFor(Dst->getParent())) &&
(SrcGEP->getNumOperands() == DstGEP->getNumOperands());
Corrects a problem where we reply exclusively of GEPs to drive analysis. Better is to look for cases with useful GEPs and use them when possible. When a pair of useful GEPs is not available, use the raw SCEVs directly. This approach supports better analysis of pointer dereferencing. In parallel, all the test cases are updated appropriately. Cases where we have a store to *B++ can now be analyzed! llvm-svn: 168474
2012-11-22 07:50:04 +08:00
}
unsigned Pairs = UsefulGEP ? SrcGEP->idx_end() - SrcGEP->idx_begin() : 1;
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
SmallVector<Subscript, 4> Pair(Pairs);
Corrects a problem where we reply exclusively of GEPs to drive analysis. Better is to look for cases with useful GEPs and use them when possible. When a pair of useful GEPs is not available, use the raw SCEVs directly. This approach supports better analysis of pointer dereferencing. In parallel, all the test cases are updated appropriately. Cases where we have a store to *B++ can now be analyzed! llvm-svn: 168474
2012-11-22 07:50:04 +08:00
if (UsefulGEP) {
DEBUG(dbgs() << " using GEPs\n");
unsigned P = 0;
for (GEPOperator::const_op_iterator SrcIdx = SrcGEP->idx_begin(),
SrcEnd = SrcGEP->idx_end(),
DstIdx = DstGEP->idx_begin();
SrcIdx != SrcEnd;
++SrcIdx, ++DstIdx, ++P) {
Pair[P].Src = SE->getSCEV(*SrcIdx);
Pair[P].Dst = SE->getSCEV(*DstIdx);
[DependenceAnalysis] Allow subscripts of different types Summary: Several places in DependenceAnalysis assumes both SCEVs in a subscript pair share the same integer type. For instance, isKnownPredicate calls SE->getMinusSCEV(X, Y) which asserts X and Y share the same type. However, DependenceAnalysis fails to ensure this assumption when producing a subscript pair, causing tests such as NonCanonicalizedSubscript to crash. With this patch, DependenceAnalysis runs unifySubscriptType before producing any subscript pair, ensuring the assumption. Test Plan: Added NonCanonicalizedSubscript.ll on which DependenceAnalysis before the fix crashed because subscripts have different types. Reviewers: spop, sebpop, jingyue Reviewed By: jingyue Subscribers: eliben, meheff, llvm-commits Differential Revision: http://reviews.llvm.org/D6289 llvm-svn: 222100
2014-11-17 00:52:44 +08:00
unifySubscriptType(&Pair[P]);
Corrects a problem where we reply exclusively of GEPs to drive analysis. Better is to look for cases with useful GEPs and use them when possible. When a pair of useful GEPs is not available, use the raw SCEVs directly. This approach supports better analysis of pointer dereferencing. In parallel, all the test cases are updated appropriately. Cases where we have a store to *B++ can now be analyzed! llvm-svn: 168474
2012-11-22 07:50:04 +08:00
}
}
else {
DEBUG(dbgs() << " ignoring GEPs\n");
const SCEV *SrcSCEV = SE->getSCEV(SrcPtr);
const SCEV *DstSCEV = SE->getSCEV(DstPtr);
DEBUG(dbgs() << " SrcSCEV = " << *SrcSCEV << "\n");
DEBUG(dbgs() << " DstSCEV = " << *DstSCEV << "\n");
Pair[0].Src = SrcSCEV;
Pair[0].Dst = DstSCEV;
}
Fix how DependenceAnalysis calls delinearization Fix how DependenceAnalysis calls delinearization, mirroring what is done in Delinearization.cpp (mostly by making sure to call getSCEVAtScope before delinearizing, and by removing the unnecessary 'Pairs == 1' check). Patch by Vaivaswatha Nagaraj! llvm-svn: 245408
2015-08-19 10:56:36 +08:00
if (Delinearize && CommonLevels > 1) {
if (tryDelinearize(Src, Dst, Pair)) {
DEBUG(dbgs() << " delinerized GEP\n");
Pairs = Pair.size();
}
delinearization of arrays llvm-svn: 194527
2013-11-13 06:47:20 +08:00
}
Corrects a problem where we reply exclusively of GEPs to drive analysis. Better is to look for cases with useful GEPs and use them when possible. When a pair of useful GEPs is not available, use the raw SCEVs directly. This approach supports better analysis of pointer dereferencing. In parallel, all the test cases are updated appropriately. Cases where we have a store to *B++ can now be analyzed! llvm-svn: 168474
2012-11-22 07:50:04 +08:00
for (unsigned P = 0; P < Pairs; ++P) {
Pair[P].Loops.resize(MaxLevels + 1);
Pair[P].GroupLoops.resize(MaxLevels + 1);
Pair[P].Group.resize(Pairs);
removeMatchingExtensions(&Pair[P]);
Pair[P].Classification =
classifyPair(Pair[P].Src, LI->getLoopFor(Src->getParent()),
Pair[P].Dst, LI->getLoopFor(Dst->getParent()),
Pair[P].Loops);
Pair[P].GroupLoops = Pair[P].Loops;
Pair[P].Group.set(P);
DEBUG(dbgs() << " subscript " << P << "\n");
DEBUG(dbgs() << "\tsrc = " << *Pair[P].Src << "\n");
DEBUG(dbgs() << "\tdst = " << *Pair[P].Dst << "\n");
DEBUG(dbgs() << "\tclass = " << Pair[P].Classification << "\n");
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
DEBUG(dbgs() << "\tloops = ");
Corrects a problem where we reply exclusively of GEPs to drive analysis. Better is to look for cases with useful GEPs and use them when possible. When a pair of useful GEPs is not available, use the raw SCEVs directly. This approach supports better analysis of pointer dereferencing. In parallel, all the test cases are updated appropriately. Cases where we have a store to *B++ can now be analyzed! llvm-svn: 168474
2012-11-22 07:50:04 +08:00
DEBUG(dumpSmallBitVector(Pair[P].Loops));
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
}
SmallBitVector Separable(Pairs);
SmallBitVector Coupled(Pairs);
// Partition subscripts into separable and minimally-coupled groups
// Algorithm in paper is algorithmically better;
// this may be faster in practice. Check someday.
//
// Here's an example of how it works. Consider this code:
//
// for (i = ...) {
// for (j = ...) {
// for (k = ...) {
// for (l = ...) {
// for (m = ...) {
// A[i][j][k][m] = ...;
// ... = A[0][j][l][i + j];
// }
// }
// }
// }
// }
//
// There are 4 subscripts here:
// 0 [i] and [0]
// 1 [j] and [j]
// 2 [k] and [l]
// 3 [m] and [i + j]
//
// We've already classified each subscript pair as ZIV, SIV, etc.,
// and collected all the loops mentioned by pair P in Pair[P].Loops.
// In addition, we've initialized Pair[P].GroupLoops to Pair[P].Loops
// and set Pair[P].Group = {P}.
//
// Src Dst Classification Loops GroupLoops Group
// 0 [i] [0] SIV {1} {1} {0}
// 1 [j] [j] SIV {2} {2} {1}
// 2 [k] [l] RDIV {3,4} {3,4} {2}
// 3 [m] [i + j] MIV {1,2,5} {1,2,5} {3}
//
// For each subscript SI 0 .. 3, we consider each remaining subscript, SJ.
// So, 0 is compared against 1, 2, and 3; 1 is compared against 2 and 3, etc.
//
// We begin by comparing 0 and 1. The intersection of the GroupLoops is empty.
// Next, 0 and 2. Again, the intersection of their GroupLoops is empty.
// Next 0 and 3. The intersection of their GroupLoop = {1}, not empty,
// so Pair[3].Group = {0,3} and Done = false (that is, 0 will not be added
// to either Separable or Coupled).
//
// Next, we consider 1 and 2. The intersection of the GroupLoops is empty.
// Next, 1 and 3. The intersectionof their GroupLoops = {2}, not empty,
// so Pair[3].Group = {0, 1, 3} and Done = false.
//
// Next, we compare 2 against 3. The intersection of the GroupLoops is empty.
// Since Done remains true, we add 2 to the set of Separable pairs.
//
// Finally, we consider 3. There's nothing to compare it with,
// so Done remains true and we add it to the Coupled set.
// Pair[3].Group = {0, 1, 3} and GroupLoops = {1, 2, 5}.
//
// In the end, we've got 1 separable subscript and 1 coupled group.
for (unsigned SI = 0; SI < Pairs; ++SI) {
if (Pair[SI].Classification == Subscript::NonLinear) {
// ignore these, but collect loops for later
++NonlinearSubscriptPairs;
collectCommonLoops(Pair[SI].Src,
LI->getLoopFor(Src->getParent()),
Pair[SI].Loops);
collectCommonLoops(Pair[SI].Dst,
LI->getLoopFor(Dst->getParent()),
Pair[SI].Loops);
Revert r231103, "FullDependenceAnalysis: Avoid using the (deprecated in C++11) copy ctor" It is miscompiled on msc18. llvm-svn: 231335
2015-03-05 09:25:12 +08:00
Result.Consistent = false;
Reformat. llvm-svn: 231336
2015-03-05 09:25:19 +08:00
} else if (Pair[SI].Classification == Subscript::ZIV) {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
// always separable
Separable.set(SI);
}
else {
// SIV, RDIV, or MIV, so check for coupled group
bool Done = true;
for (unsigned SJ = SI + 1; SJ < Pairs; ++SJ) {
SmallBitVector Intersection = Pair[SI].GroupLoops;
Intersection &= Pair[SJ].GroupLoops;
if (Intersection.any()) {
// accumulate set of all the loops in group
Pair[SJ].GroupLoops |= Pair[SI].GroupLoops;
// accumulate set of all subscripts in group
Pair[SJ].Group |= Pair[SI].Group;
Done = false;
}
}
if (Done) {
if (Pair[SI].Group.count() == 1) {
Separable.set(SI);
++SeparableSubscriptPairs;
}
else {
Coupled.set(SI);
++CoupledSubscriptPairs;
}
}
}
}
DEBUG(dbgs() << " Separable = ");
DEBUG(dumpSmallBitVector(Separable));
DEBUG(dbgs() << " Coupled = ");
DEBUG(dumpSmallBitVector(Coupled));
Constraint NewConstraint;
NewConstraint.setAny(SE);
// test separable subscripts
for (int SI = Separable.find_first(); SI >= 0; SI = Separable.find_next(SI)) {
DEBUG(dbgs() << "testing subscript " << SI);
switch (Pair[SI].Classification) {
case Subscript::ZIV:
DEBUG(dbgs() << ", ZIV\n");
Revert r231103, "FullDependenceAnalysis: Avoid using the (deprecated in C++11) copy ctor" It is miscompiled on msc18. llvm-svn: 231335
2015-03-05 09:25:12 +08:00
if (testZIV(Pair[SI].Src, Pair[SI].Dst, Result))
[C++11] More 'nullptr' conversion. In some cases just using a boolean check instead of comparing to nullptr. llvm-svn: 206243
2014-04-15 12:59:12 +08:00
return nullptr;
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
break;
case Subscript::SIV: {
DEBUG(dbgs() << ", SIV\n");
unsigned Level;
[C++11] More 'nullptr' conversion. In some cases just using a boolean check instead of comparing to nullptr. llvm-svn: 206243
2014-04-15 12:59:12 +08:00
const SCEV *SplitIter = nullptr;
Reformat. llvm-svn: 231336
2015-03-05 09:25:19 +08:00
if (testSIV(Pair[SI].Src, Pair[SI].Dst, Level, Result, NewConstraint,
SplitIter))
[C++11] More 'nullptr' conversion. In some cases just using a boolean check instead of comparing to nullptr. llvm-svn: 206243
2014-04-15 12:59:12 +08:00
return nullptr;
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
break;
}
case Subscript::RDIV:
DEBUG(dbgs() << ", RDIV\n");
Revert r231103, "FullDependenceAnalysis: Avoid using the (deprecated in C++11) copy ctor" It is miscompiled on msc18. llvm-svn: 231335
2015-03-05 09:25:12 +08:00
if (testRDIV(Pair[SI].Src, Pair[SI].Dst, Result))
[C++11] More 'nullptr' conversion. In some cases just using a boolean check instead of comparing to nullptr. llvm-svn: 206243
2014-04-15 12:59:12 +08:00
return nullptr;
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
break;
case Subscript::MIV:
DEBUG(dbgs() << ", MIV\n");
Revert r231103, "FullDependenceAnalysis: Avoid using the (deprecated in C++11) copy ctor" It is miscompiled on msc18. llvm-svn: 231335
2015-03-05 09:25:12 +08:00
if (testMIV(Pair[SI].Src, Pair[SI].Dst, Pair[SI].Loops, Result))
[C++11] More 'nullptr' conversion. In some cases just using a boolean check instead of comparing to nullptr. llvm-svn: 206243
2014-04-15 12:59:12 +08:00
return nullptr;
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
break;
default:
llvm_unreachable("subscript has unexpected classification");
}
}
if (Coupled.count()) {
// test coupled subscript groups
DEBUG(dbgs() << "starting on coupled subscripts\n");
DEBUG(dbgs() << "MaxLevels + 1 = " << MaxLevels + 1 << "\n");
SmallVector<Constraint, 4> Constraints(MaxLevels + 1);
for (unsigned II = 0; II <= MaxLevels; ++II)
Constraints[II].setAny(SE);
for (int SI = Coupled.find_first(); SI >= 0; SI = Coupled.find_next(SI)) {
DEBUG(dbgs() << "testing subscript group " << SI << " { ");
SmallBitVector Group(Pair[SI].Group);
SmallBitVector Sivs(Pairs);
SmallBitVector Mivs(Pairs);
SmallBitVector ConstrainedLevels(MaxLevels + 1);
[DependenceAnalysis] Extend unifySubscriptType for handling coupled subscript groups. Summary: In continuation to an earlier commit to DependenceAnalysis.cpp by jingyue (r222100), the type for all subscripts in a coupled group need to be the same since constraints from one subscript may be propagated to another during testing. During testing, new SCEVs may be created and the operands for these need to be the same. This patch extends unifySubscriptType() to work on lists of subscript pairs, ensuring a common extended type for all of them. Test Plan: Added a test case to NonCanonicalizedSubscript.ll which causes dependence analysis to crash without this fix. All regression tests pass. Reviewers: spop, sebpop, jingyue Reviewed By: jingyue Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9698 llvm-svn: 238573
2015-05-30 00:58:08 +08:00
SmallVector<Subscript *, 4> PairsInGroup;
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
for (int SJ = Group.find_first(); SJ >= 0; SJ = Group.find_next(SJ)) {
DEBUG(dbgs() << SJ << " ");
if (Pair[SJ].Classification == Subscript::SIV)
Sivs.set(SJ);
else
Mivs.set(SJ);
[DependenceAnalysis] Extend unifySubscriptType for handling coupled subscript groups. Summary: In continuation to an earlier commit to DependenceAnalysis.cpp by jingyue (r222100), the type for all subscripts in a coupled group need to be the same since constraints from one subscript may be propagated to another during testing. During testing, new SCEVs may be created and the operands for these need to be the same. This patch extends unifySubscriptType() to work on lists of subscript pairs, ensuring a common extended type for all of them. Test Plan: Added a test case to NonCanonicalizedSubscript.ll which causes dependence analysis to crash without this fix. All regression tests pass. Reviewers: spop, sebpop, jingyue Reviewed By: jingyue Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9698 llvm-svn: 238573
2015-05-30 00:58:08 +08:00
PairsInGroup.push_back(&Pair[SJ]);
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
}
[DependenceAnalysis] Extend unifySubscriptType for handling coupled subscript groups. Summary: In continuation to an earlier commit to DependenceAnalysis.cpp by jingyue (r222100), the type for all subscripts in a coupled group need to be the same since constraints from one subscript may be propagated to another during testing. During testing, new SCEVs may be created and the operands for these need to be the same. This patch extends unifySubscriptType() to work on lists of subscript pairs, ensuring a common extended type for all of them. Test Plan: Added a test case to NonCanonicalizedSubscript.ll which causes dependence analysis to crash without this fix. All regression tests pass. Reviewers: spop, sebpop, jingyue Reviewed By: jingyue Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9698 llvm-svn: 238573
2015-05-30 00:58:08 +08:00
unifySubscriptType(PairsInGroup);
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
DEBUG(dbgs() << "}\n");
while (Sivs.any()) {
bool Changed = false;
for (int SJ = Sivs.find_first(); SJ >= 0; SJ = Sivs.find_next(SJ)) {
DEBUG(dbgs() << "testing subscript " << SJ << ", SIV\n");
// SJ is an SIV subscript that's part of the current coupled group
unsigned Level;
[C++11] More 'nullptr' conversion. In some cases just using a boolean check instead of comparing to nullptr. llvm-svn: 206243
2014-04-15 12:59:12 +08:00
const SCEV *SplitIter = nullptr;
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
DEBUG(dbgs() << "SIV\n");
Reformat. llvm-svn: 231336
2015-03-05 09:25:19 +08:00
if (testSIV(Pair[SJ].Src, Pair[SJ].Dst, Level, Result, NewConstraint,
SplitIter))
[C++11] More 'nullptr' conversion. In some cases just using a boolean check instead of comparing to nullptr. llvm-svn: 206243
2014-04-15 12:59:12 +08:00
return nullptr;
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
ConstrainedLevels.set(Level);
if (intersectConstraints(&Constraints[Level], &NewConstraint)) {
if (Constraints[Level].isEmpty()) {
++DeltaIndependence;
[C++11] More 'nullptr' conversion. In some cases just using a boolean check instead of comparing to nullptr. llvm-svn: 206243
2014-04-15 12:59:12 +08:00
return nullptr;
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
}
Changed = true;
}
Sivs.reset(SJ);
}
if (Changed) {
// propagate, possibly creating new SIVs and ZIVs
DEBUG(dbgs() << " propagating\n");
DEBUG(dbgs() << "\tMivs = ");
DEBUG(dumpSmallBitVector(Mivs));
for (int SJ = Mivs.find_first(); SJ >= 0; SJ = Mivs.find_next(SJ)) {
// SJ is an MIV subscript that's part of the current coupled group
DEBUG(dbgs() << "\tSJ = " << SJ << "\n");
if (propagate(Pair[SJ].Src, Pair[SJ].Dst, Pair[SJ].Loops,
Revert r231103, "FullDependenceAnalysis: Avoid using the (deprecated in C++11) copy ctor" It is miscompiled on msc18. llvm-svn: 231335
2015-03-05 09:25:12 +08:00
Constraints, Result.Consistent)) {
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
DEBUG(dbgs() << "\t Changed\n");
++DeltaPropagations;
Pair[SJ].Classification =
classifyPair(Pair[SJ].Src, LI->getLoopFor(Src->getParent()),
Pair[SJ].Dst, LI->getLoopFor(Dst->getParent()),
Pair[SJ].Loops);
switch (Pair[SJ].Classification) {
case Subscript::ZIV:
DEBUG(dbgs() << "ZIV\n");
Revert r231103, "FullDependenceAnalysis: Avoid using the (deprecated in C++11) copy ctor" It is miscompiled on msc18. llvm-svn: 231335
2015-03-05 09:25:12 +08:00
if (testZIV(Pair[SJ].Src, Pair[SJ].Dst, Result))
[C++11] More 'nullptr' conversion. In some cases just using a boolean check instead of comparing to nullptr. llvm-svn: 206243
2014-04-15 12:59:12 +08:00
return nullptr;
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
Mivs.reset(SJ);
break;
case Subscript::SIV:
Sivs.set(SJ);
Mivs.reset(SJ);
break;
case Subscript::RDIV:
case Subscript::MIV:
break;
default:
llvm_unreachable("bad subscript classification");
}
}
}
}
}
// test & propagate remaining RDIVs
for (int SJ = Mivs.find_first(); SJ >= 0; SJ = Mivs.find_next(SJ)) {
if (Pair[SJ].Classification == Subscript::RDIV) {
DEBUG(dbgs() << "RDIV test\n");
Revert r231103, "FullDependenceAnalysis: Avoid using the (deprecated in C++11) copy ctor" It is miscompiled on msc18. llvm-svn: 231335
2015-03-05 09:25:12 +08:00
if (testRDIV(Pair[SJ].Src, Pair[SJ].Dst, Result))
[C++11] More 'nullptr' conversion. In some cases just using a boolean check instead of comparing to nullptr. llvm-svn: 206243
2014-04-15 12:59:12 +08:00
return nullptr;
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
// I don't yet understand how to propagate RDIV results
Mivs.reset(SJ);
}
}
// test remaining MIVs
// This code is temporary.
// Better to somehow test all remaining subscripts simultaneously.
for (int SJ = Mivs.find_first(); SJ >= 0; SJ = Mivs.find_next(SJ)) {
if (Pair[SJ].Classification == Subscript::MIV) {
DEBUG(dbgs() << "MIV test\n");
Revert r231103, "FullDependenceAnalysis: Avoid using the (deprecated in C++11) copy ctor" It is miscompiled on msc18. llvm-svn: 231335
2015-03-05 09:25:12 +08:00
if (testMIV(Pair[SJ].Src, Pair[SJ].Dst, Pair[SJ].Loops, Result))
[C++11] More 'nullptr' conversion. In some cases just using a boolean check instead of comparing to nullptr. llvm-svn: 206243
2014-04-15 12:59:12 +08:00
return nullptr;
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
}
else
llvm_unreachable("expected only MIV subscripts at this point");
}
Revert r231103, "FullDependenceAnalysis: Avoid using the (deprecated in C++11) copy ctor" It is miscompiled on msc18. llvm-svn: 231335
2015-03-05 09:25:12 +08:00
// update Result.DV from constraint vector
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
DEBUG(dbgs() << " updating\n");
Reformat. llvm-svn: 231336
2015-03-05 09:25:19 +08:00
for (int SJ = ConstrainedLevels.find_first(); SJ >= 0;
SJ = ConstrainedLevels.find_next(SJ)) {
Fix a memory corruption in Dependency Analysis. This crash occurs due to memory corruption when trying to update dependency direction based on Constraints. This crash was observed during lnt regression of Polybench benchmark test case dynprog. Review: http://reviews.llvm.org/D8059 llvm-svn: 231788
2015-03-10 22:32:02 +08:00
if (SJ > (int)CommonLevels)
break;
Revert r231103, "FullDependenceAnalysis: Avoid using the (deprecated in C++11) copy ctor" It is miscompiled on msc18. llvm-svn: 231335
2015-03-05 09:25:12 +08:00
updateDirection(Result.DV[SJ - 1], Constraints[SJ]);
if (Result.DV[SJ - 1].Direction == Dependence::DVEntry::NONE)
[C++11] More 'nullptr' conversion. In some cases just using a boolean check instead of comparing to nullptr. llvm-svn: 206243
2014-04-15 12:59:12 +08:00
return nullptr;
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
}
}
}
Cleaned up a couple of comments. llvm-svn: 168854
2012-11-29 12:30:52 +08:00
// Make sure the Scalar flags are set correctly.
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
SmallBitVector CompleteLoops(MaxLevels + 1);
for (unsigned SI = 0; SI < Pairs; ++SI)
CompleteLoops |= Pair[SI].Loops;
for (unsigned II = 1; II <= CommonLevels; ++II)
if (CompleteLoops[II])
Revert r231103, "FullDependenceAnalysis: Avoid using the (deprecated in C++11) copy ctor" It is miscompiled on msc18. llvm-svn: 231335
2015-03-05 09:25:12 +08:00
Result.DV[II - 1].Scalar = false;
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
if (PossiblyLoopIndependent) {
Modified depends() to recognize that when all levels are "=" and there's no possible loo-independent dependence, then there's no dependence. Updated all test result appropriately. llvm-svn: 168719
2012-11-28 03:12:26 +08:00
// Make sure the LoopIndependent flag is set correctly.
// All directions must include equal, otherwise no
// loop-independent dependence is possible.
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
for (unsigned II = 1; II <= CommonLevels; ++II) {
Revert r231103, "FullDependenceAnalysis: Avoid using the (deprecated in C++11) copy ctor" It is miscompiled on msc18. llvm-svn: 231335
2015-03-05 09:25:12 +08:00
if (!(Result.getDirection(II) & Dependence::DVEntry::EQ)) {
Result.LoopIndependent = false;
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
break;
}
}
}
Modified depends() to recognize that when all levels are "=" and there's no possible loo-independent dependence, then there's no dependence. Updated all test result appropriately. llvm-svn: 168719
2012-11-28 03:12:26 +08:00
else {
// On the other hand, if all directions are equal and there's no
// loop-independent dependence possible, then no dependence exists.
bool AllEqual = true;
for (unsigned II = 1; II <= CommonLevels; ++II) {
Revert r231103, "FullDependenceAnalysis: Avoid using the (deprecated in C++11) copy ctor" It is miscompiled on msc18. llvm-svn: 231335
2015-03-05 09:25:12 +08:00
if (Result.getDirection(II) != Dependence::DVEntry::EQ) {
Cleaned up a couple of comments. llvm-svn: 168854
2012-11-29 12:30:52 +08:00
AllEqual = false;
break;
Modified depends() to recognize that when all levels are "=" and there's no possible loo-independent dependence, then there's no dependence. Updated all test result appropriately. llvm-svn: 168719
2012-11-28 03:12:26 +08:00
}
}
if (AllEqual)
[C++11] More 'nullptr' conversion. In some cases just using a boolean check instead of comparing to nullptr. llvm-svn: 206243
2014-04-15 12:59:12 +08:00
return nullptr;
Modified depends() to recognize that when all levels are "=" and there's no possible loo-independent dependence, then there's no dependence. Updated all test result appropriately. llvm-svn: 168719
2012-11-28 03:12:26 +08:00
}
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
-Wdeprecated-clean: Fix cases of violating the rule of 5 in ways that are deprecated in C++11 llvm-svn: 243788
2015-08-01 05:37:09 +08:00
return make_unique<FullDependence>(std::move(Result));
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
}
//===----------------------------------------------------------------------===//
// getSplitIteration -
// Rather than spend rarely-used space recording the splitting iteration
// during the Weak-Crossing SIV test, we re-compute it on demand.
// The re-computation is basically a repeat of the entire dependence test,
// though simplified since we know that the dependence exists.
// It's tedious, since we must go through all propagations, etc.
//
Corrects a problem where we reply exclusively of GEPs to drive analysis. Better is to look for cases with useful GEPs and use them when possible. When a pair of useful GEPs is not available, use the raw SCEVs directly. This approach supports better analysis of pointer dereferencing. In parallel, all the test cases are updated appropriately. Cases where we have a store to *B++ can now be analyzed! llvm-svn: 168474
2012-11-22 07:50:04 +08:00
// Care is required to keep this code up to date with respect to the routine
// above, depends().
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
//
// Generally, the dependence analyzer will be used to build
// a dependence graph for a function (basically a map from instructions
// to dependences). Looking for cycles in the graph shows us loops
// that cannot be trivially vectorized/parallelized.
//
// We can try to improve the situation by examining all the dependences
// that make up the cycle, looking for ones we can break.
// Sometimes, peeling the first or last iteration of a loop will break
// dependences, and we've got flags for those possibilities.
// Sometimes, splitting a loop at some other iteration will do the trick,
// and we've got a flag for that case. Rather than waste the space to
// record the exact iteration (since we rarely know), we provide
// a method that calculates the iteration. It's a drag that it must work
// from scratch, but wonderful in that it's possible.
//
// Here's an example:
//
// for (i = 0; i < 10; i++)
// A[i] = ...
// ... = A[11 - i]
//
// There's a loop-carried flow dependence from the store to the load,
// found by the weak-crossing SIV test. The dependence will have a flag,
// indicating that the dependence can be broken by splitting the loop.
// Calling getSplitIteration will return 5.
// Splitting the loop breaks the dependence, like so:
//
// for (i = 0; i <= 5; i++)
// A[i] = ...
// ... = A[11 - i]
// for (i = 6; i < 10; i++)
// A[i] = ...
// ... = A[11 - i]
//
// breaks the dependence and allows us to vectorize/parallelize
// both loops.
[PM] Port of the DepndenceAnalysis to the new PM. Ported DA to the new PM by splitting the former DependenceAnalysis Pass into a DependenceInfo result type and DependenceAnalysisWrapperPass type and adding a new PM-style DependenceAnalysis analysis pass returning the DependenceInfo. Patch by Philip Pfaffe, most of the review by Justin. Differential Revision: http://reviews.llvm.org/D18834 llvm-svn: 269370
2016-05-13 06:19:39 +08:00
const SCEV *DependenceInfo::getSplitIteration(const Dependence &Dep,
unsigned SplitLevel) {
Analysis: take a reference instead of pointer This parameter is never null. llvm-svn: 216356
2014-08-25 08:28:35 +08:00
assert(Dep.isSplitable(SplitLevel) &&
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
"Dep should be splitable at SplitLevel");
Analysis: take a reference instead of pointer This parameter is never null. llvm-svn: 216356
2014-08-25 08:28:35 +08:00
Instruction *Src = Dep.getSrc();
Instruction *Dst = Dep.getDst();
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
assert(Src->mayReadFromMemory() || Src->mayWriteToMemory());
assert(Dst->mayReadFromMemory() || Dst->mayWriteToMemory());
assert(isLoadOrStore(Src));
assert(isLoadOrStore(Dst));
Corrects a problem where we reply exclusively of GEPs to drive analysis. Better is to look for cases with useful GEPs and use them when possible. When a pair of useful GEPs is not available, use the raw SCEVs directly. This approach supports better analysis of pointer dereferencing. In parallel, all the test cases are updated appropriately. Cases where we have a store to *B++ can now be analyzed! llvm-svn: 168474
2012-11-22 07:50:04 +08:00
Value *SrcPtr = getPointerOperand(Src);
Value *DstPtr = getPointerOperand(Dst);
DataLayout is mandatory, update the API to reflect it with references. Summary: Now that the DataLayout is a mandatory part of the module, let's start cleaning the codebase. This patch is a first attempt at doing that. This patch is not exactly NFC as for instance some places were passing a nullptr instead of the DataLayout, possibly just because there was a default value on the DataLayout argument to many functions in the API. Even though it is not purely NFC, there is no change in the validation. I turned as many pointer to DataLayout to references, this helped figuring out all the places where a nullptr could come up. I had initially a local version of this patch broken into over 30 independant, commits but some later commit were cleaning the API and touching part of the code modified in the previous commits, so it seemed cleaner without the intermediate state. Test Plan: Reviewers: echristo Subscribers: llvm-commits From: Mehdi Amini <mehdi.amini@apple.com> llvm-svn: 231740
2015-03-10 10:37:25 +08:00
assert(underlyingObjectsAlias(AA, F->getParent()->getDataLayout(), DstPtr,
[PM/AA] Hoist the AliasResult enum out of the AliasAnalysis class. This will allow classes to implement the AA interface without deriving from the class or referencing an internal enum of some other class as their return types. Also, to a pretty fundamental extent, concepts such as 'NoAlias', 'MayAlias', and 'MustAlias' are first class concepts in LLVM and we aren't saving anything by scoping them heavily. My mild preference would have been to use a scoped enum, but that feature is essentially completely broken AFAICT. I'm extremely disappointed. For example, we cannot through any reasonable[1] means construct an enum class (or analog) which has scoped names but converts to a boolean in order to test for the possibility of aliasing. [1]: Richard Smith came up with a "solution", but it requires class templates, and lots of boilerplate setting up the enumeration multiple times. Something like Boost.PP could potentially bundle this up, but even that would be quite painful and it doesn't seem realistically worth it. The enum class solution would probably work without the need for a bool conversion. Differential Revision: http://reviews.llvm.org/D10495 llvm-svn: 240255
2015-06-22 10:16:51 +08:00
SrcPtr) == MustAlias);
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
// establish loop nesting levels
establishNestingLevels(Src, Dst);
FullDependence Result(Src, Dst, false, CommonLevels);
Corrects a problem where we reply exclusively of GEPs to drive analysis. Better is to look for cases with useful GEPs and use them when possible. When a pair of useful GEPs is not available, use the raw SCEVs directly. This approach supports better analysis of pointer dereferencing. In parallel, all the test cases are updated appropriately. Cases where we have a store to *B++ can now be analyzed! llvm-svn: 168474
2012-11-22 07:50:04 +08:00
// See if there are GEPs we can use.
bool UsefulGEP = false;
GEPOperator *SrcGEP = dyn_cast<GEPOperator>(SrcPtr);
GEPOperator *DstGEP = dyn_cast<GEPOperator>(DstPtr);
if (SrcGEP && DstGEP &&
SrcGEP->getPointerOperandType() == DstGEP->getPointerOperandType()) {
const SCEV *SrcPtrSCEV = SE->getSCEV(SrcGEP->getPointerOperand());
const SCEV *DstPtrSCEV = SE->getSCEV(DstGEP->getPointerOperand());
Fix a crash in Dependency Analysis. This crash in Dependency analysis is because we assume here that in case of UsefulGEP both source and destination have the same number of operands which may not be true. This incorrect assumption results in crash while populating Pairs. Fix the same. This crash was observed during lnt regression for code such as- struct s{ int A[10][10]; int C[10][10][10]; } S; void dep_constraint_crash_test(int k,int N) { for( int i=0;i<N;i++) for( int j=0;j<N;j++) S.A[0][0] = S.C[0][0][k]; } Review: http://reviews.llvm.org/D8162 llvm-svn: 231784
2015-03-10 21:31:03 +08:00
UsefulGEP = isLoopInvariant(SrcPtrSCEV, LI->getLoopFor(Src->getParent())) &&
isLoopInvariant(DstPtrSCEV, LI->getLoopFor(Dst->getParent())) &&
(SrcGEP->getNumOperands() == DstGEP->getNumOperands());
Corrects a problem where we reply exclusively of GEPs to drive analysis. Better is to look for cases with useful GEPs and use them when possible. When a pair of useful GEPs is not available, use the raw SCEVs directly. This approach supports better analysis of pointer dereferencing. In parallel, all the test cases are updated appropriately. Cases where we have a store to *B++ can now be analyzed! llvm-svn: 168474
2012-11-22 07:50:04 +08:00
}
unsigned Pairs = UsefulGEP ? SrcGEP->idx_end() - SrcGEP->idx_begin() : 1;
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
SmallVector<Subscript, 4> Pair(Pairs);
Corrects a problem where we reply exclusively of GEPs to drive analysis. Better is to look for cases with useful GEPs and use them when possible. When a pair of useful GEPs is not available, use the raw SCEVs directly. This approach supports better analysis of pointer dereferencing. In parallel, all the test cases are updated appropriately. Cases where we have a store to *B++ can now be analyzed! llvm-svn: 168474
2012-11-22 07:50:04 +08:00
if (UsefulGEP) {
unsigned P = 0;
for (GEPOperator::const_op_iterator SrcIdx = SrcGEP->idx_begin(),
SrcEnd = SrcGEP->idx_end(),
DstIdx = DstGEP->idx_begin();
SrcIdx != SrcEnd;
++SrcIdx, ++DstIdx, ++P) {
Pair[P].Src = SE->getSCEV(*SrcIdx);
Pair[P].Dst = SE->getSCEV(*DstIdx);
}
}
else {
const SCEV *SrcSCEV = SE->getSCEV(SrcPtr);
const SCEV *DstSCEV = SE->getSCEV(DstPtr);
Pair[0].Src = SrcSCEV;
Pair[0].Dst = DstSCEV;
}
Fix how DependenceAnalysis calls delinearization Fix how DependenceAnalysis calls delinearization, mirroring what is done in Delinearization.cpp (mostly by making sure to call getSCEVAtScope before delinearizing, and by removing the unnecessary 'Pairs == 1' check). Patch by Vaivaswatha Nagaraj! llvm-svn: 245408
2015-08-19 10:56:36 +08:00
if (Delinearize && CommonLevels > 1) {
if (tryDelinearize(Src, Dst, Pair)) {
DEBUG(dbgs() << " delinerized GEP\n");
Pairs = Pair.size();
}
delinearization of arrays llvm-svn: 194527
2013-11-13 06:47:20 +08:00
}
Corrects a problem where we reply exclusively of GEPs to drive analysis. Better is to look for cases with useful GEPs and use them when possible. When a pair of useful GEPs is not available, use the raw SCEVs directly. This approach supports better analysis of pointer dereferencing. In parallel, all the test cases are updated appropriately. Cases where we have a store to *B++ can now be analyzed! llvm-svn: 168474
2012-11-22 07:50:04 +08:00
for (unsigned P = 0; P < Pairs; ++P) {
Pair[P].Loops.resize(MaxLevels + 1);
Pair[P].GroupLoops.resize(MaxLevels + 1);
Pair[P].Group.resize(Pairs);
removeMatchingExtensions(&Pair[P]);
Pair[P].Classification =
classifyPair(Pair[P].Src, LI->getLoopFor(Src->getParent()),
Pair[P].Dst, LI->getLoopFor(Dst->getParent()),
Pair[P].Loops);
Pair[P].GroupLoops = Pair[P].Loops;
Pair[P].Group.set(P);
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
}
SmallBitVector Separable(Pairs);
SmallBitVector Coupled(Pairs);
// partition subscripts into separable and minimally-coupled groups
for (unsigned SI = 0; SI < Pairs; ++SI) {
if (Pair[SI].Classification == Subscript::NonLinear) {
// ignore these, but collect loops for later
collectCommonLoops(Pair[SI].Src,
LI->getLoopFor(Src->getParent()),
Pair[SI].Loops);
collectCommonLoops(Pair[SI].Dst,
LI->getLoopFor(Dst->getParent()),
Pair[SI].Loops);
Result.Consistent = false;
}
else if (Pair[SI].Classification == Subscript::ZIV)
Separable.set(SI);
else {
// SIV, RDIV, or MIV, so check for coupled group
bool Done = true;
for (unsigned SJ = SI + 1; SJ < Pairs; ++SJ) {
SmallBitVector Intersection = Pair[SI].GroupLoops;
Intersection &= Pair[SJ].GroupLoops;
if (Intersection.any()) {
// accumulate set of all the loops in group
Pair[SJ].GroupLoops |= Pair[SI].GroupLoops;
// accumulate set of all subscripts in group
Pair[SJ].Group |= Pair[SI].Group;
Done = false;
}
}
if (Done) {
if (Pair[SI].Group.count() == 1)
Separable.set(SI);
else
Coupled.set(SI);
}
}
}
Constraint NewConstraint;
NewConstraint.setAny(SE);
// test separable subscripts
for (int SI = Separable.find_first(); SI >= 0; SI = Separable.find_next(SI)) {
switch (Pair[SI].Classification) {
case Subscript::SIV: {
unsigned Level;
[C++11] More 'nullptr' conversion. In some cases just using a boolean check instead of comparing to nullptr. llvm-svn: 206243
2014-04-15 12:59:12 +08:00
const SCEV *SplitIter = nullptr;
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
(void) testSIV(Pair[SI].Src, Pair[SI].Dst, Level,
Result, NewConstraint, SplitIter);
if (Level == SplitLevel) {
[C++11] More 'nullptr' conversion. In some cases just using a boolean check instead of comparing to nullptr. llvm-svn: 206243
2014-04-15 12:59:12 +08:00
assert(SplitIter != nullptr);
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
return SplitIter;
}
break;
}
case Subscript::ZIV:
case Subscript::RDIV:
case Subscript::MIV:
break;
default:
llvm_unreachable("subscript has unexpected classification");
}
}
if (Coupled.count()) {
// test coupled subscript groups
SmallVector<Constraint, 4> Constraints(MaxLevels + 1);
for (unsigned II = 0; II <= MaxLevels; ++II)
Constraints[II].setAny(SE);
for (int SI = Coupled.find_first(); SI >= 0; SI = Coupled.find_next(SI)) {
SmallBitVector Group(Pair[SI].Group);
SmallBitVector Sivs(Pairs);
SmallBitVector Mivs(Pairs);
SmallBitVector ConstrainedLevels(MaxLevels + 1);
for (int SJ = Group.find_first(); SJ >= 0; SJ = Group.find_next(SJ)) {
if (Pair[SJ].Classification == Subscript::SIV)
Sivs.set(SJ);
else
Mivs.set(SJ);
}
while (Sivs.any()) {
bool Changed = false;
for (int SJ = Sivs.find_first(); SJ >= 0; SJ = Sivs.find_next(SJ)) {
// SJ is an SIV subscript that's part of the current coupled group
unsigned Level;
[C++11] More 'nullptr' conversion. In some cases just using a boolean check instead of comparing to nullptr. llvm-svn: 206243
2014-04-15 12:59:12 +08:00
const SCEV *SplitIter = nullptr;
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
(void) testSIV(Pair[SJ].Src, Pair[SJ].Dst, Level,
Result, NewConstraint, SplitIter);
if (Level == SplitLevel && SplitIter)
return SplitIter;
ConstrainedLevels.set(Level);
if (intersectConstraints(&Constraints[Level], &NewConstraint))
Changed = true;
Sivs.reset(SJ);
}
if (Changed) {
// propagate, possibly creating new SIVs and ZIVs
for (int SJ = Mivs.find_first(); SJ >= 0; SJ = Mivs.find_next(SJ)) {
// SJ is an MIV subscript that's part of the current coupled group
if (propagate(Pair[SJ].Src, Pair[SJ].Dst,
Pair[SJ].Loops, Constraints, Result.Consistent)) {
Pair[SJ].Classification =
classifyPair(Pair[SJ].Src, LI->getLoopFor(Src->getParent()),
Pair[SJ].Dst, LI->getLoopFor(Dst->getParent()),
Pair[SJ].Loops);
switch (Pair[SJ].Classification) {
case Subscript::ZIV:
Mivs.reset(SJ);
break;
case Subscript::SIV:
Sivs.set(SJ);
Mivs.reset(SJ);
break;
case Subscript::RDIV:
case Subscript::MIV:
break;
default:
llvm_unreachable("bad subscript classification");
}
}
}
}
}
}
}
llvm_unreachable("somehow reached end of routine");
[C++11] More 'nullptr' conversion. In some cases just using a boolean check instead of comparing to nullptr. llvm-svn: 206243
2014-04-15 12:59:12 +08:00
return nullptr;
dependence analysis Patch from Preston Briggs <preston.briggs@gmail.com>. This is an updated version of the dependence-analysis patch, including an MIV test based on Banerjee's inequalities. It's a fairly complete implementation of the paper Practical Dependence Testing Gina Goff, Ken Kennedy, and Chau-Wen Tseng PLDI 1991 It cannot yet propagate constraints between coupled RDIV subscripts (discussed in Section 5.3.2 of the paper). It's organized as a FunctionPass with a single entry point that supports testing for dependence between two instructions in a function. If there's no dependence, it returns null. If there's a dependence, it returns a pointer to a Dependence which can be queried about details (what kind of dependence, is it loop independent, direction and distance vector entries, etc). I haven't included every imaginable feature, but there's a good selection that should be adequate for supporting many loop transformations. Of course, it can be extended as necessary. Included in the patch file are many test cases, commented with C code showing the loops and array references. llvm-svn: 165708
2012-10-11 15:32:34 +08:00
}