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

684 lines
22 KiB
C++
Raw Normal View History

Add the PPCCTRLoops pass: a PPC machine-code-level optimization pass to form CTR-based loop branching code. This pass is derived from the Hexagon HardwareLoops pass. The only significant enhancement over the Hexagon pass is that PPCCTRLoops will also attempt to delete the replaced add and compare operations if they are no longer otherwise used. Also, invalid preheader DebugLoc is not used. llvm-svn: 158204
2012-06-08 23:38:21 +08:00
//===-- PPCCTRLoops.cpp - Identify and generate CTR loops -----------------===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This pass identifies loops where we can generate the PPC branch instructions
// that decrement and test the count register (CTR) (bdnz and friends).
//
// The pattern that defines the induction variable can changed depending on
// prior optimizations. For example, the IndVarSimplify phase run by 'opt'
// normalizes induction variables, and the Loop Strength Reduction pass
// run by 'llc' may also make changes to the induction variable.
//
// Criteria for CTR loops:
// - Countable loops (w/ ind. var for a trip count)
// - Try inner-most loops first
// - No nested CTR loops.
// - No function calls in loops.
//
//===----------------------------------------------------------------------===//
Implement PPC counter loops as a late IR-level pass The old PPCCTRLoops pass, like the Hexagon pass version from which it was derived, could only handle some simple loops in canonical form. We cannot directly adapt the new Hexagon hardware loops pass, however, because the Hexagon pass contains a fundamental assumption that non-constant-trip-count loops will contain a guard, and this is not always true (the result being that incorrect negative counts can be generated). With this commit, we replace the pass with a late IR-level pass which makes use of SE to calculate the backedge-taken counts and safely generate the loop-count expressions (including any necessary max() parts). This IR level pass inserts custom intrinsics that are lowered into the desired decrement-and-branch instructions. The most fragile part of this new implementation is that interfering uses of the counter register must be detected on the IR level (and, on PPC, this also includes any indirect branches in addition to function calls). Also, to make all of this work, we need a variant of the mtctr instruction that is marked as having side effects. Without this, machine-code level CSE, DCE, etc. illegally transform the resulting code. Hopefully, this can be improved in the future. This new pass is smaller than the original (and much smaller than the new Hexagon hardware loops pass), and can handle many additional cases correctly. In addition, the preheader-creation code has been copied from LoopSimplify, and after we decide on where it belongs, this code will be refactored so that it can be explicitly shared (making this implementation even smaller). The new test-case files ctrloop-{le,lt,ne}.ll have been adapted from tests for the new Hexagon pass. There are a few classes of loops that this pass does not transform (noted by FIXMEs in the files), but these deficiencies can be addressed within the SE infrastructure (thus helping many other passes as well). llvm-svn: 181927
2013-05-16 05:37:41 +08:00
#include "llvm/Transforms/Scalar.h"
Re-sort all of the includes with ./utils/sort_includes.py so that subsequent changes are easier to review. About to fix some layering issues, and wanted to separate out the necessary churn. Also comment and sink the include of "Windows.h" in three .inc files to match the usage in Memory.inc. llvm-svn: 198685
2014-01-07 19:48:04 +08:00
#include "PPC.h"
#include "PPCTargetMachine.h"
Implement PPC counter loops as a late IR-level pass The old PPCCTRLoops pass, like the Hexagon pass version from which it was derived, could only handle some simple loops in canonical form. We cannot directly adapt the new Hexagon hardware loops pass, however, because the Hexagon pass contains a fundamental assumption that non-constant-trip-count loops will contain a guard, and this is not always true (the result being that incorrect negative counts can be generated). With this commit, we replace the pass with a late IR-level pass which makes use of SE to calculate the backedge-taken counts and safely generate the loop-count expressions (including any necessary max() parts). This IR level pass inserts custom intrinsics that are lowered into the desired decrement-and-branch instructions. The most fragile part of this new implementation is that interfering uses of the counter register must be detected on the IR level (and, on PPC, this also includes any indirect branches in addition to function calls). Also, to make all of this work, we need a variant of the mtctr instruction that is marked as having side effects. Without this, machine-code level CSE, DCE, etc. illegally transform the resulting code. Hopefully, this can be improved in the future. This new pass is smaller than the original (and much smaller than the new Hexagon hardware loops pass), and can handle many additional cases correctly. In addition, the preheader-creation code has been copied from LoopSimplify, and after we decide on where it belongs, this code will be refactored so that it can be explicitly shared (making this implementation even smaller). The new test-case files ctrloop-{le,lt,ne}.ll have been adapted from tests for the new Hexagon pass. There are a few classes of loops that this pass does not transform (noted by FIXMEs in the files), but these deficiencies can be addressed within the SE infrastructure (thus helping many other passes as well). llvm-svn: 181927
2013-05-16 05:37:41 +08:00
#include "llvm/ADT/STLExtras.h"
Re-sort all of the includes with ./utils/sort_includes.py so that subsequent changes are easier to review. About to fix some layering issues, and wanted to separate out the necessary churn. Also comment and sink the include of "Windows.h" in three .inc files to match the usage in Memory.inc. llvm-svn: 198685
2014-01-07 19:48:04 +08:00
#include "llvm/ADT/Statistic.h"
Implement PPC counter loops as a late IR-level pass The old PPCCTRLoops pass, like the Hexagon pass version from which it was derived, could only handle some simple loops in canonical form. We cannot directly adapt the new Hexagon hardware loops pass, however, because the Hexagon pass contains a fundamental assumption that non-constant-trip-count loops will contain a guard, and this is not always true (the result being that incorrect negative counts can be generated). With this commit, we replace the pass with a late IR-level pass which makes use of SE to calculate the backedge-taken counts and safely generate the loop-count expressions (including any necessary max() parts). This IR level pass inserts custom intrinsics that are lowered into the desired decrement-and-branch instructions. The most fragile part of this new implementation is that interfering uses of the counter register must be detected on the IR level (and, on PPC, this also includes any indirect branches in addition to function calls). Also, to make all of this work, we need a variant of the mtctr instruction that is marked as having side effects. Without this, machine-code level CSE, DCE, etc. illegally transform the resulting code. Hopefully, this can be improved in the future. This new pass is smaller than the original (and much smaller than the new Hexagon hardware loops pass), and can handle many additional cases correctly. In addition, the preheader-creation code has been copied from LoopSimplify, and after we decide on where it belongs, this code will be refactored so that it can be explicitly shared (making this implementation even smaller). The new test-case files ctrloop-{le,lt,ne}.ll have been adapted from tests for the new Hexagon pass. There are a few classes of loops that this pass does not transform (noted by FIXMEs in the files), but these deficiencies can be addressed within the SE infrastructure (thus helping many other passes as well). llvm-svn: 181927
2013-05-16 05:37:41 +08:00
#include "llvm/Analysis/LoopInfo.h"
#include "llvm/Analysis/ScalarEvolutionExpander.h"
[PM] Move TargetLibraryInfo into the Analysis library. While the term "Target" is in the name, it doesn't really have to do with the LLVM Target library -- this isn't an abstraction which LLVM targets generally need to implement or extend. It has much more to do with modeling the various runtime libraries on different OSes and with different runtime environments. The "target" in this sense is the more general sense of a target of cross compilation. This is in preparation for porting this analysis to the new pass manager. No functionality changed, and updates inbound for Clang and Polly. llvm-svn: 226078
2015-01-15 10:16:27 +08:00
#include "llvm/Analysis/TargetLibraryInfo.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/Constants.h"
Implement PPC counter loops as a late IR-level pass The old PPCCTRLoops pass, like the Hexagon pass version from which it was derived, could only handle some simple loops in canonical form. We cannot directly adapt the new Hexagon hardware loops pass, however, because the Hexagon pass contains a fundamental assumption that non-constant-trip-count loops will contain a guard, and this is not always true (the result being that incorrect negative counts can be generated). With this commit, we replace the pass with a late IR-level pass which makes use of SE to calculate the backedge-taken counts and safely generate the loop-count expressions (including any necessary max() parts). This IR level pass inserts custom intrinsics that are lowered into the desired decrement-and-branch instructions. The most fragile part of this new implementation is that interfering uses of the counter register must be detected on the IR level (and, on PPC, this also includes any indirect branches in addition to function calls). Also, to make all of this work, we need a variant of the mtctr instruction that is marked as having side effects. Without this, machine-code level CSE, DCE, etc. illegally transform the resulting code. Hopefully, this can be improved in the future. This new pass is smaller than the original (and much smaller than the new Hexagon hardware loops pass), and can handle many additional cases correctly. In addition, the preheader-creation code has been copied from LoopSimplify, and after we decide on where it belongs, this code will be refactored so that it can be explicitly shared (making this implementation even smaller). The new test-case files ctrloop-{le,lt,ne}.ll have been adapted from tests for the new Hexagon pass. There are a few classes of loops that this pass does not transform (noted by FIXMEs in the files), but these deficiencies can be addressed within the SE infrastructure (thus helping many other passes as well). llvm-svn: 181927
2013-05-16 05:37:41 +08:00
#include "llvm/IR/DerivedTypes.h"
[cleanup] Move the Dominators.h and Verifier.h headers into the IR directory. These passes are already defined in the IR library, and it doesn't make any sense to have the headers in Analysis. Long term, I think there is going to be a much better way to divide these matters. The dominators code should be fully separated into the abstract graph algorithm and have that put in Support where it becomes obvious that evn Clang's CFGBlock's can use it. Then the verifier can manually construct dominance information from the Support-driven interface while the Analysis library can provide a pass which both caches, reconstructs, and supports a nice update API. But those are very long term, and so I don't want to leave the really confusing structure until that day arrives. llvm-svn: 199082
2014-01-13 17:26:24 +08:00
#include "llvm/IR/Dominators.h"
Check InlineAsm clobbers in PPCCTRLoops We don't need to reject all inline asm as using the counter register (most does not). Only those that explicitly clobber the counter register need to prevent the transformation. llvm-svn: 182191
2013-05-18 17:20:39 +08:00
#include "llvm/IR/InlineAsm.h"
Implement PPC counter loops as a late IR-level pass The old PPCCTRLoops pass, like the Hexagon pass version from which it was derived, could only handle some simple loops in canonical form. We cannot directly adapt the new Hexagon hardware loops pass, however, because the Hexagon pass contains a fundamental assumption that non-constant-trip-count loops will contain a guard, and this is not always true (the result being that incorrect negative counts can be generated). With this commit, we replace the pass with a late IR-level pass which makes use of SE to calculate the backedge-taken counts and safely generate the loop-count expressions (including any necessary max() parts). This IR level pass inserts custom intrinsics that are lowered into the desired decrement-and-branch instructions. The most fragile part of this new implementation is that interfering uses of the counter register must be detected on the IR level (and, on PPC, this also includes any indirect branches in addition to function calls). Also, to make all of this work, we need a variant of the mtctr instruction that is marked as having side effects. Without this, machine-code level CSE, DCE, etc. illegally transform the resulting code. Hopefully, this can be improved in the future. This new pass is smaller than the original (and much smaller than the new Hexagon hardware loops pass), and can handle many additional cases correctly. In addition, the preheader-creation code has been copied from LoopSimplify, and after we decide on where it belongs, this code will be refactored so that it can be explicitly shared (making this implementation even smaller). The new test-case files ctrloop-{le,lt,ne}.ll have been adapted from tests for the new Hexagon pass. There are a few classes of loops that this pass does not transform (noted by FIXMEs in the files), but these deficiencies can be addressed within the SE infrastructure (thus helping many other passes as well). llvm-svn: 181927
2013-05-16 05:37:41 +08:00
#include "llvm/IR/Instructions.h"
#include "llvm/IR/IntrinsicInst.h"
#include "llvm/IR/Module.h"
[Modules] Move ValueHandle into the IR library where Value itself lives. Move the test for this class into the IR unittests as well. This uncovers that ValueMap too is in the IR library. Ironically, the unittest for ValueMap is useless in the Support library (honestly, so was the ValueHandle test) and so it already lives in the IR unittests. Mmmm, tasty layering. llvm-svn: 202821
2014-03-04 19:17:44 +08:00
#include "llvm/IR/ValueHandle.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/PassSupport.h"
Implement PPC counter loops as a late IR-level pass The old PPCCTRLoops pass, like the Hexagon pass version from which it was derived, could only handle some simple loops in canonical form. We cannot directly adapt the new Hexagon hardware loops pass, however, because the Hexagon pass contains a fundamental assumption that non-constant-trip-count loops will contain a guard, and this is not always true (the result being that incorrect negative counts can be generated). With this commit, we replace the pass with a late IR-level pass which makes use of SE to calculate the backedge-taken counts and safely generate the loop-count expressions (including any necessary max() parts). This IR level pass inserts custom intrinsics that are lowered into the desired decrement-and-branch instructions. The most fragile part of this new implementation is that interfering uses of the counter register must be detected on the IR level (and, on PPC, this also includes any indirect branches in addition to function calls). Also, to make all of this work, we need a variant of the mtctr instruction that is marked as having side effects. Without this, machine-code level CSE, DCE, etc. illegally transform the resulting code. Hopefully, this can be improved in the future. This new pass is smaller than the original (and much smaller than the new Hexagon hardware loops pass), and can handle many additional cases correctly. In addition, the preheader-creation code has been copied from LoopSimplify, and after we decide on where it belongs, this code will be refactored so that it can be explicitly shared (making this implementation even smaller). The new test-case files ctrloop-{le,lt,ne}.ll have been adapted from tests for the new Hexagon pass. There are a few classes of loops that this pass does not transform (noted by FIXMEs in the files), but these deficiencies can be addressed within the SE infrastructure (thus helping many other passes as well). llvm-svn: 181927
2013-05-16 05:37:41 +08:00
#include "llvm/Support/CommandLine.h"
Add the PPCCTRLoops pass: a PPC machine-code-level optimization pass to form CTR-based loop branching code. This pass is derived from the Hexagon HardwareLoops pass. The only significant enhancement over the Hexagon pass is that PPCCTRLoops will also attempt to delete the replaced add and compare operations if they are no longer otherwise used. Also, invalid preheader DebugLoc is not used. llvm-svn: 158204
2012-06-08 23:38:21 +08:00
#include "llvm/Support/Debug.h"
#include "llvm/Support/raw_ostream.h"
Implement PPC counter loops as a late IR-level pass The old PPCCTRLoops pass, like the Hexagon pass version from which it was derived, could only handle some simple loops in canonical form. We cannot directly adapt the new Hexagon hardware loops pass, however, because the Hexagon pass contains a fundamental assumption that non-constant-trip-count loops will contain a guard, and this is not always true (the result being that incorrect negative counts can be generated). With this commit, we replace the pass with a late IR-level pass which makes use of SE to calculate the backedge-taken counts and safely generate the loop-count expressions (including any necessary max() parts). This IR level pass inserts custom intrinsics that are lowered into the desired decrement-and-branch instructions. The most fragile part of this new implementation is that interfering uses of the counter register must be detected on the IR level (and, on PPC, this also includes any indirect branches in addition to function calls). Also, to make all of this work, we need a variant of the mtctr instruction that is marked as having side effects. Without this, machine-code level CSE, DCE, etc. illegally transform the resulting code. Hopefully, this can be improved in the future. This new pass is smaller than the original (and much smaller than the new Hexagon hardware loops pass), and can handle many additional cases correctly. In addition, the preheader-creation code has been copied from LoopSimplify, and after we decide on where it belongs, this code will be refactored so that it can be explicitly shared (making this implementation even smaller). The new test-case files ctrloop-{le,lt,ne}.ll have been adapted from tests for the new Hexagon pass. There are a few classes of loops that this pass does not transform (noted by FIXMEs in the files), but these deficiencies can be addressed within the SE infrastructure (thus helping many other passes as well). llvm-svn: 181927
2013-05-16 05:37:41 +08:00
#include "llvm/Transforms/Utils/BasicBlockUtils.h"
#include "llvm/Transforms/Utils/Local.h"
Rename LoopSimplify.h to LoopUtils.h As discussed, LoopUtils.h is a better name. llvm-svn: 182314
2013-05-21 04:46:30 +08:00
#include "llvm/Transforms/Utils/LoopUtils.h"
Implement PPC counter loops as a late IR-level pass The old PPCCTRLoops pass, like the Hexagon pass version from which it was derived, could only handle some simple loops in canonical form. We cannot directly adapt the new Hexagon hardware loops pass, however, because the Hexagon pass contains a fundamental assumption that non-constant-trip-count loops will contain a guard, and this is not always true (the result being that incorrect negative counts can be generated). With this commit, we replace the pass with a late IR-level pass which makes use of SE to calculate the backedge-taken counts and safely generate the loop-count expressions (including any necessary max() parts). This IR level pass inserts custom intrinsics that are lowered into the desired decrement-and-branch instructions. The most fragile part of this new implementation is that interfering uses of the counter register must be detected on the IR level (and, on PPC, this also includes any indirect branches in addition to function calls). Also, to make all of this work, we need a variant of the mtctr instruction that is marked as having side effects. Without this, machine-code level CSE, DCE, etc. illegally transform the resulting code. Hopefully, this can be improved in the future. This new pass is smaller than the original (and much smaller than the new Hexagon hardware loops pass), and can handle many additional cases correctly. In addition, the preheader-creation code has been copied from LoopSimplify, and after we decide on where it belongs, this code will be refactored so that it can be explicitly shared (making this implementation even smaller). The new test-case files ctrloop-{le,lt,ne}.ll have been adapted from tests for the new Hexagon pass. There are a few classes of loops that this pass does not transform (noted by FIXMEs in the files), but these deficiencies can be addressed within the SE infrastructure (thus helping many other passes as well). llvm-svn: 181927
2013-05-16 05:37:41 +08:00
Add a PPCCTRLoops verification pass When asserts are enabled, this adds a verification pass for PPC counter-loop formation. Unfortunately, without sacrificing code quality, there is no better way of forming counter-based loops except at the (late) IR level. This means that we need to recognize, at the IR level, anything which might turn into a function call (or indirect branch). Because this is currently a finite set of things, and because SelectionDAG lowering is basic-block local, this can be done. Nevertheless, it is fragile, and failure results in a miscompile. This verification pass checks that all (reachable) counter-based branches are dominated by a loop mtctr instruction, and that no instructions in between clobber the counter register. If these conditions are not satisfied, then an ICE will be triggered. In short, this is to help us sleep better at night. llvm-svn: 182295
2013-05-21 00:08:17 +08:00
#ifndef NDEBUG
#include "llvm/CodeGen/MachineDominators.h"
#include "llvm/CodeGen/MachineFunction.h"
#include "llvm/CodeGen/MachineFunctionPass.h"
#include "llvm/CodeGen/MachineRegisterInfo.h"
#endif
Add the PPCCTRLoops pass: a PPC machine-code-level optimization pass to form CTR-based loop branching code. This pass is derived from the Hexagon HardwareLoops pass. The only significant enhancement over the Hexagon pass is that PPCCTRLoops will also attempt to delete the replaced add and compare operations if they are no longer otherwise used. Also, invalid preheader DebugLoc is not used. llvm-svn: 158204
2012-06-08 23:38:21 +08:00
#include <algorithm>
Implement PPC counter loops as a late IR-level pass The old PPCCTRLoops pass, like the Hexagon pass version from which it was derived, could only handle some simple loops in canonical form. We cannot directly adapt the new Hexagon hardware loops pass, however, because the Hexagon pass contains a fundamental assumption that non-constant-trip-count loops will contain a guard, and this is not always true (the result being that incorrect negative counts can be generated). With this commit, we replace the pass with a late IR-level pass which makes use of SE to calculate the backedge-taken counts and safely generate the loop-count expressions (including any necessary max() parts). This IR level pass inserts custom intrinsics that are lowered into the desired decrement-and-branch instructions. The most fragile part of this new implementation is that interfering uses of the counter register must be detected on the IR level (and, on PPC, this also includes any indirect branches in addition to function calls). Also, to make all of this work, we need a variant of the mtctr instruction that is marked as having side effects. Without this, machine-code level CSE, DCE, etc. illegally transform the resulting code. Hopefully, this can be improved in the future. This new pass is smaller than the original (and much smaller than the new Hexagon hardware loops pass), and can handle many additional cases correctly. In addition, the preheader-creation code has been copied from LoopSimplify, and after we decide on where it belongs, this code will be refactored so that it can be explicitly shared (making this implementation even smaller). The new test-case files ctrloop-{le,lt,ne}.ll have been adapted from tests for the new Hexagon pass. There are a few classes of loops that this pass does not transform (noted by FIXMEs in the files), but these deficiencies can be addressed within the SE infrastructure (thus helping many other passes as well). llvm-svn: 181927
2013-05-16 05:37:41 +08:00
#include <vector>
Add the PPCCTRLoops pass: a PPC machine-code-level optimization pass to form CTR-based loop branching code. This pass is derived from the Hexagon HardwareLoops pass. The only significant enhancement over the Hexagon pass is that PPCCTRLoops will also attempt to delete the replaced add and compare operations if they are no longer otherwise used. Also, invalid preheader DebugLoc is not used. llvm-svn: 158204
2012-06-08 23:38:21 +08:00
using namespace llvm;
[Modules] Fix potential ODR violations by sinking the DEBUG_TYPE definition below all of the header #include lines, lib/Target/... edition. llvm-svn: 206842
2014-04-22 10:41:26 +08:00
#define DEBUG_TYPE "ctrloops"
Implement PPC counter loops as a late IR-level pass The old PPCCTRLoops pass, like the Hexagon pass version from which it was derived, could only handle some simple loops in canonical form. We cannot directly adapt the new Hexagon hardware loops pass, however, because the Hexagon pass contains a fundamental assumption that non-constant-trip-count loops will contain a guard, and this is not always true (the result being that incorrect negative counts can be generated). With this commit, we replace the pass with a late IR-level pass which makes use of SE to calculate the backedge-taken counts and safely generate the loop-count expressions (including any necessary max() parts). This IR level pass inserts custom intrinsics that are lowered into the desired decrement-and-branch instructions. The most fragile part of this new implementation is that interfering uses of the counter register must be detected on the IR level (and, on PPC, this also includes any indirect branches in addition to function calls). Also, to make all of this work, we need a variant of the mtctr instruction that is marked as having side effects. Without this, machine-code level CSE, DCE, etc. illegally transform the resulting code. Hopefully, this can be improved in the future. This new pass is smaller than the original (and much smaller than the new Hexagon hardware loops pass), and can handle many additional cases correctly. In addition, the preheader-creation code has been copied from LoopSimplify, and after we decide on where it belongs, this code will be refactored so that it can be explicitly shared (making this implementation even smaller). The new test-case files ctrloop-{le,lt,ne}.ll have been adapted from tests for the new Hexagon pass. There are a few classes of loops that this pass does not transform (noted by FIXMEs in the files), but these deficiencies can be addressed within the SE infrastructure (thus helping many other passes as well). llvm-svn: 181927
2013-05-16 05:37:41 +08:00
#ifndef NDEBUG
static cl::opt<int> CTRLoopLimit("ppc-max-ctrloop", cl::Hidden, cl::init(-1));
#endif
Add the PPCCTRLoops pass: a PPC machine-code-level optimization pass to form CTR-based loop branching code. This pass is derived from the Hexagon HardwareLoops pass. The only significant enhancement over the Hexagon pass is that PPCCTRLoops will also attempt to delete the replaced add and compare operations if they are no longer otherwise used. Also, invalid preheader DebugLoc is not used. llvm-svn: 158204
2012-06-08 23:38:21 +08:00
STATISTIC(NumCTRLoops, "Number of loops converted to CTR loops");
Add registration for PPC-specific passes to allow the IR to be dumped via -print-after-all. llvm-svn: 175058
2013-02-14 01:40:07 +08:00
namespace llvm {
void initializePPCCTRLoopsPass(PassRegistry&);
Add a PPCCTRLoops verification pass When asserts are enabled, this adds a verification pass for PPC counter-loop formation. Unfortunately, without sacrificing code quality, there is no better way of forming counter-based loops except at the (late) IR level. This means that we need to recognize, at the IR level, anything which might turn into a function call (or indirect branch). Because this is currently a finite set of things, and because SelectionDAG lowering is basic-block local, this can be done. Nevertheless, it is fragile, and failure results in a miscompile. This verification pass checks that all (reachable) counter-based branches are dominated by a loop mtctr instruction, and that no instructions in between clobber the counter register. If these conditions are not satisfied, then an ICE will be triggered. In short, this is to help us sleep better at night. llvm-svn: 182295
2013-05-21 00:08:17 +08:00
#ifndef NDEBUG
void initializePPCCTRLoopsVerifyPass(PassRegistry&);
#endif
Add registration for PPC-specific passes to allow the IR to be dumped via -print-after-all. llvm-svn: 175058
2013-02-14 01:40:07 +08:00
}
Add the PPCCTRLoops pass: a PPC machine-code-level optimization pass to form CTR-based loop branching code. This pass is derived from the Hexagon HardwareLoops pass. The only significant enhancement over the Hexagon pass is that PPCCTRLoops will also attempt to delete the replaced add and compare operations if they are no longer otherwise used. Also, invalid preheader DebugLoc is not used. llvm-svn: 158204
2012-06-08 23:38:21 +08:00
namespace {
Implement PPC counter loops as a late IR-level pass The old PPCCTRLoops pass, like the Hexagon pass version from which it was derived, could only handle some simple loops in canonical form. We cannot directly adapt the new Hexagon hardware loops pass, however, because the Hexagon pass contains a fundamental assumption that non-constant-trip-count loops will contain a guard, and this is not always true (the result being that incorrect negative counts can be generated). With this commit, we replace the pass with a late IR-level pass which makes use of SE to calculate the backedge-taken counts and safely generate the loop-count expressions (including any necessary max() parts). This IR level pass inserts custom intrinsics that are lowered into the desired decrement-and-branch instructions. The most fragile part of this new implementation is that interfering uses of the counter register must be detected on the IR level (and, on PPC, this also includes any indirect branches in addition to function calls). Also, to make all of this work, we need a variant of the mtctr instruction that is marked as having side effects. Without this, machine-code level CSE, DCE, etc. illegally transform the resulting code. Hopefully, this can be improved in the future. This new pass is smaller than the original (and much smaller than the new Hexagon hardware loops pass), and can handle many additional cases correctly. In addition, the preheader-creation code has been copied from LoopSimplify, and after we decide on where it belongs, this code will be refactored so that it can be explicitly shared (making this implementation even smaller). The new test-case files ctrloop-{le,lt,ne}.ll have been adapted from tests for the new Hexagon pass. There are a few classes of loops that this pass does not transform (noted by FIXMEs in the files), but these deficiencies can be addressed within the SE infrastructure (thus helping many other passes as well). llvm-svn: 181927
2013-05-16 05:37:41 +08:00
struct PPCCTRLoops : public FunctionPass {
#ifndef NDEBUG
static int Counter;
#endif
Add the PPCCTRLoops pass: a PPC machine-code-level optimization pass to form CTR-based loop branching code. This pass is derived from the Hexagon HardwareLoops pass. The only significant enhancement over the Hexagon pass is that PPCCTRLoops will also attempt to delete the replaced add and compare operations if they are no longer otherwise used. Also, invalid preheader DebugLoc is not used. llvm-svn: 158204
2012-06-08 23:38:21 +08:00
public:
Implement PPC counter loops as a late IR-level pass The old PPCCTRLoops pass, like the Hexagon pass version from which it was derived, could only handle some simple loops in canonical form. We cannot directly adapt the new Hexagon hardware loops pass, however, because the Hexagon pass contains a fundamental assumption that non-constant-trip-count loops will contain a guard, and this is not always true (the result being that incorrect negative counts can be generated). With this commit, we replace the pass with a late IR-level pass which makes use of SE to calculate the backedge-taken counts and safely generate the loop-count expressions (including any necessary max() parts). This IR level pass inserts custom intrinsics that are lowered into the desired decrement-and-branch instructions. The most fragile part of this new implementation is that interfering uses of the counter register must be detected on the IR level (and, on PPC, this also includes any indirect branches in addition to function calls). Also, to make all of this work, we need a variant of the mtctr instruction that is marked as having side effects. Without this, machine-code level CSE, DCE, etc. illegally transform the resulting code. Hopefully, this can be improved in the future. This new pass is smaller than the original (and much smaller than the new Hexagon hardware loops pass), and can handle many additional cases correctly. In addition, the preheader-creation code has been copied from LoopSimplify, and after we decide on where it belongs, this code will be refactored so that it can be explicitly shared (making this implementation even smaller). The new test-case files ctrloop-{le,lt,ne}.ll have been adapted from tests for the new Hexagon pass. There are a few classes of loops that this pass does not transform (noted by FIXMEs in the files), but these deficiencies can be addressed within the SE infrastructure (thus helping many other passes as well). llvm-svn: 181927
2013-05-16 05:37:41 +08:00
static char ID;
Add the PPCCTRLoops pass: a PPC machine-code-level optimization pass to form CTR-based loop branching code. This pass is derived from the Hexagon HardwareLoops pass. The only significant enhancement over the Hexagon pass is that PPCCTRLoops will also attempt to delete the replaced add and compare operations if they are no longer otherwise used. Also, invalid preheader DebugLoc is not used. llvm-svn: 158204
2012-06-08 23:38:21 +08:00
[C++] Use 'nullptr'. Target edition. llvm-svn: 207197
2014-04-25 13:30:21 +08:00
PPCCTRLoops() : FunctionPass(ID), TM(nullptr) {
Implement PPC counter loops as a late IR-level pass The old PPCCTRLoops pass, like the Hexagon pass version from which it was derived, could only handle some simple loops in canonical form. We cannot directly adapt the new Hexagon hardware loops pass, however, because the Hexagon pass contains a fundamental assumption that non-constant-trip-count loops will contain a guard, and this is not always true (the result being that incorrect negative counts can be generated). With this commit, we replace the pass with a late IR-level pass which makes use of SE to calculate the backedge-taken counts and safely generate the loop-count expressions (including any necessary max() parts). This IR level pass inserts custom intrinsics that are lowered into the desired decrement-and-branch instructions. The most fragile part of this new implementation is that interfering uses of the counter register must be detected on the IR level (and, on PPC, this also includes any indirect branches in addition to function calls). Also, to make all of this work, we need a variant of the mtctr instruction that is marked as having side effects. Without this, machine-code level CSE, DCE, etc. illegally transform the resulting code. Hopefully, this can be improved in the future. This new pass is smaller than the original (and much smaller than the new Hexagon hardware loops pass), and can handle many additional cases correctly. In addition, the preheader-creation code has been copied from LoopSimplify, and after we decide on where it belongs, this code will be refactored so that it can be explicitly shared (making this implementation even smaller). The new test-case files ctrloop-{le,lt,ne}.ll have been adapted from tests for the new Hexagon pass. There are a few classes of loops that this pass does not transform (noted by FIXMEs in the files), but these deficiencies can be addressed within the SE infrastructure (thus helping many other passes as well). llvm-svn: 181927
2013-05-16 05:37:41 +08:00
initializePPCCTRLoopsPass(*PassRegistry::getPassRegistry());
}
PPCCTRLoops(PPCTargetMachine &TM) : FunctionPass(ID), TM(&TM) {
Add registration for PPC-specific passes to allow the IR to be dumped via -print-after-all. llvm-svn: 175058
2013-02-14 01:40:07 +08:00
initializePPCCTRLoopsPass(*PassRegistry::getPassRegistry());
}
Add the PPCCTRLoops pass: a PPC machine-code-level optimization pass to form CTR-based loop branching code. This pass is derived from the Hexagon HardwareLoops pass. The only significant enhancement over the Hexagon pass is that PPCCTRLoops will also attempt to delete the replaced add and compare operations if they are no longer otherwise used. Also, invalid preheader DebugLoc is not used. llvm-svn: 158204
2012-06-08 23:38:21 +08:00
[C++11] Add 'override' keywords and remove 'virtual'. Additionally add 'final' and leave 'virtual' on some methods that are marked virtual without overriding anything and have no obvious overrides themselves. PowerPC edition llvm-svn: 207504
2014-04-29 15:57:37 +08:00
bool runOnFunction(Function &F) override;
Add the PPCCTRLoops pass: a PPC machine-code-level optimization pass to form CTR-based loop branching code. This pass is derived from the Hexagon HardwareLoops pass. The only significant enhancement over the Hexagon pass is that PPCCTRLoops will also attempt to delete the replaced add and compare operations if they are no longer otherwise used. Also, invalid preheader DebugLoc is not used. llvm-svn: 158204
2012-06-08 23:38:21 +08:00
[C++11] Add 'override' keywords and remove 'virtual'. Additionally add 'final' and leave 'virtual' on some methods that are marked virtual without overriding anything and have no obvious overrides themselves. PowerPC edition llvm-svn: 207504
2014-04-29 15:57:37 +08:00
void getAnalysisUsage(AnalysisUsage &AU) const override {
[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.addRequired<LoopInfoWrapperPass>();
AU.addPreserved<LoopInfoWrapperPass>();
[PM] Split DominatorTree into a concrete analysis result object which can be used by both the new pass manager and the old. This removes it from any of the virtual mess of the pass interfaces and lets it derive cleanly from the DominatorTreeBase<> template. In turn, tons of boilerplate interface can be nuked and it turns into a very straightforward extension of the base DominatorTree interface. The old analysis pass is now a simple wrapper. The names and style of this split should match the split between CallGraph and CallGraphWrapperPass. All of the users of DominatorTree have been updated to match using many of the same tricks as with CallGraph. The goal is that the common type remains the resulting DominatorTree rather than the pass. This will make subsequent work toward the new pass manager significantly easier. Also in numerous places things became cleaner because I switched from re-running the pass (!!! mid way through some other passes run!!!) to directly recomputing the domtree. llvm-svn: 199104
2014-01-13 21:07:17 +08:00
AU.addRequired<DominatorTreeWrapperPass>();
AU.addPreserved<DominatorTreeWrapperPass>();
Implement PPC counter loops as a late IR-level pass The old PPCCTRLoops pass, like the Hexagon pass version from which it was derived, could only handle some simple loops in canonical form. We cannot directly adapt the new Hexagon hardware loops pass, however, because the Hexagon pass contains a fundamental assumption that non-constant-trip-count loops will contain a guard, and this is not always true (the result being that incorrect negative counts can be generated). With this commit, we replace the pass with a late IR-level pass which makes use of SE to calculate the backedge-taken counts and safely generate the loop-count expressions (including any necessary max() parts). This IR level pass inserts custom intrinsics that are lowered into the desired decrement-and-branch instructions. The most fragile part of this new implementation is that interfering uses of the counter register must be detected on the IR level (and, on PPC, this also includes any indirect branches in addition to function calls). Also, to make all of this work, we need a variant of the mtctr instruction that is marked as having side effects. Without this, machine-code level CSE, DCE, etc. illegally transform the resulting code. Hopefully, this can be improved in the future. This new pass is smaller than the original (and much smaller than the new Hexagon hardware loops pass), and can handle many additional cases correctly. In addition, the preheader-creation code has been copied from LoopSimplify, and after we decide on where it belongs, this code will be refactored so that it can be explicitly shared (making this implementation even smaller). The new test-case files ctrloop-{le,lt,ne}.ll have been adapted from tests for the new Hexagon pass. There are a few classes of loops that this pass does not transform (noted by FIXMEs in the files), but these deficiencies can be addressed within the SE infrastructure (thus helping many other passes as well). llvm-svn: 181927
2013-05-16 05:37:41 +08:00
AU.addRequired<ScalarEvolution>();
Add the PPCCTRLoops pass: a PPC machine-code-level optimization pass to form CTR-based loop branching code. This pass is derived from the Hexagon HardwareLoops pass. The only significant enhancement over the Hexagon pass is that PPCCTRLoops will also attempt to delete the replaced add and compare operations if they are no longer otherwise used. Also, invalid preheader DebugLoc is not used. llvm-svn: 158204
2012-06-08 23:38:21 +08:00
}
private:
Create an new preheader in PPCCTRLoops to avoid counter register clobbers Some IR-level instructions (such as FP <-> i64 conversions) are not chained w.r.t. the mtctr intrinsic and yet may become function calls that clobber the counter register. At the selection-DAG level, these might be reordered with the mtctr intrinsic causing miscompiles. To avoid this situation, if an existing preheader has instructions that might use the counter register, create a new preheader for the mtctr intrinsic. This extra block will be remerged with the old preheader at the MI level, but will prevent unwanted reordering at the selection-DAG level. llvm-svn: 182045
2013-05-17 03:58:38 +08:00
bool mightUseCTR(const Triple &TT, BasicBlock *BB);
Implement PPC counter loops as a late IR-level pass The old PPCCTRLoops pass, like the Hexagon pass version from which it was derived, could only handle some simple loops in canonical form. We cannot directly adapt the new Hexagon hardware loops pass, however, because the Hexagon pass contains a fundamental assumption that non-constant-trip-count loops will contain a guard, and this is not always true (the result being that incorrect negative counts can be generated). With this commit, we replace the pass with a late IR-level pass which makes use of SE to calculate the backedge-taken counts and safely generate the loop-count expressions (including any necessary max() parts). This IR level pass inserts custom intrinsics that are lowered into the desired decrement-and-branch instructions. The most fragile part of this new implementation is that interfering uses of the counter register must be detected on the IR level (and, on PPC, this also includes any indirect branches in addition to function calls). Also, to make all of this work, we need a variant of the mtctr instruction that is marked as having side effects. Without this, machine-code level CSE, DCE, etc. illegally transform the resulting code. Hopefully, this can be improved in the future. This new pass is smaller than the original (and much smaller than the new Hexagon hardware loops pass), and can handle many additional cases correctly. In addition, the preheader-creation code has been copied from LoopSimplify, and after we decide on where it belongs, this code will be refactored so that it can be explicitly shared (making this implementation even smaller). The new test-case files ctrloop-{le,lt,ne}.ll have been adapted from tests for the new Hexagon pass. There are a few classes of loops that this pass does not transform (noted by FIXMEs in the files), but these deficiencies can be addressed within the SE infrastructure (thus helping many other passes as well). llvm-svn: 181927
2013-05-16 05:37:41 +08:00
bool convertToCTRLoop(Loop *L);
Remove copied preheader insertion logic from PPCCTRLoops Now that the preheader insertion logic in LoopSimplify is externally exposed, use it, and remove the copy-and-pasted version. No functionality change intended. llvm-svn: 182300
2013-05-21 00:47:10 +08:00
Add the PPCCTRLoops pass: a PPC machine-code-level optimization pass to form CTR-based loop branching code. This pass is derived from the Hexagon HardwareLoops pass. The only significant enhancement over the Hexagon pass is that PPCCTRLoops will also attempt to delete the replaced add and compare operations if they are no longer otherwise used. Also, invalid preheader DebugLoc is not used. llvm-svn: 158204
2012-06-08 23:38:21 +08:00
private:
Implement PPC counter loops as a late IR-level pass The old PPCCTRLoops pass, like the Hexagon pass version from which it was derived, could only handle some simple loops in canonical form. We cannot directly adapt the new Hexagon hardware loops pass, however, because the Hexagon pass contains a fundamental assumption that non-constant-trip-count loops will contain a guard, and this is not always true (the result being that incorrect negative counts can be generated). With this commit, we replace the pass with a late IR-level pass which makes use of SE to calculate the backedge-taken counts and safely generate the loop-count expressions (including any necessary max() parts). This IR level pass inserts custom intrinsics that are lowered into the desired decrement-and-branch instructions. The most fragile part of this new implementation is that interfering uses of the counter register must be detected on the IR level (and, on PPC, this also includes any indirect branches in addition to function calls). Also, to make all of this work, we need a variant of the mtctr instruction that is marked as having side effects. Without this, machine-code level CSE, DCE, etc. illegally transform the resulting code. Hopefully, this can be improved in the future. This new pass is smaller than the original (and much smaller than the new Hexagon hardware loops pass), and can handle many additional cases correctly. In addition, the preheader-creation code has been copied from LoopSimplify, and after we decide on where it belongs, this code will be refactored so that it can be explicitly shared (making this implementation even smaller). The new test-case files ctrloop-{le,lt,ne}.ll have been adapted from tests for the new Hexagon pass. There are a few classes of loops that this pass does not transform (noted by FIXMEs in the files), but these deficiencies can be addressed within the SE infrastructure (thus helping many other passes as well). llvm-svn: 181927
2013-05-16 05:37:41 +08:00
PPCTargetMachine *TM;
LoopInfo *LI;
ScalarEvolution *SE;
Make some DataLayout pointers const. No functionality change. Just reduces the noise of an upcoming patch. llvm-svn: 202087
2014-02-25 07:12:18 +08:00
const DataLayout *DL;
Implement PPC counter loops as a late IR-level pass The old PPCCTRLoops pass, like the Hexagon pass version from which it was derived, could only handle some simple loops in canonical form. We cannot directly adapt the new Hexagon hardware loops pass, however, because the Hexagon pass contains a fundamental assumption that non-constant-trip-count loops will contain a guard, and this is not always true (the result being that incorrect negative counts can be generated). With this commit, we replace the pass with a late IR-level pass which makes use of SE to calculate the backedge-taken counts and safely generate the loop-count expressions (including any necessary max() parts). This IR level pass inserts custom intrinsics that are lowered into the desired decrement-and-branch instructions. The most fragile part of this new implementation is that interfering uses of the counter register must be detected on the IR level (and, on PPC, this also includes any indirect branches in addition to function calls). Also, to make all of this work, we need a variant of the mtctr instruction that is marked as having side effects. Without this, machine-code level CSE, DCE, etc. illegally transform the resulting code. Hopefully, this can be improved in the future. This new pass is smaller than the original (and much smaller than the new Hexagon hardware loops pass), and can handle many additional cases correctly. In addition, the preheader-creation code has been copied from LoopSimplify, and after we decide on where it belongs, this code will be refactored so that it can be explicitly shared (making this implementation even smaller). The new test-case files ctrloop-{le,lt,ne}.ll have been adapted from tests for the new Hexagon pass. There are a few classes of loops that this pass does not transform (noted by FIXMEs in the files), but these deficiencies can be addressed within the SE infrastructure (thus helping many other passes as well). llvm-svn: 181927
2013-05-16 05:37:41 +08:00
DominatorTree *DT;
const TargetLibraryInfo *LibInfo;
Add the PPCCTRLoops pass: a PPC machine-code-level optimization pass to form CTR-based loop branching code. This pass is derived from the Hexagon HardwareLoops pass. The only significant enhancement over the Hexagon pass is that PPCCTRLoops will also attempt to delete the replaced add and compare operations if they are no longer otherwise used. Also, invalid preheader DebugLoc is not used. llvm-svn: 158204
2012-06-08 23:38:21 +08:00
};
Implement PPC counter loops as a late IR-level pass The old PPCCTRLoops pass, like the Hexagon pass version from which it was derived, could only handle some simple loops in canonical form. We cannot directly adapt the new Hexagon hardware loops pass, however, because the Hexagon pass contains a fundamental assumption that non-constant-trip-count loops will contain a guard, and this is not always true (the result being that incorrect negative counts can be generated). With this commit, we replace the pass with a late IR-level pass which makes use of SE to calculate the backedge-taken counts and safely generate the loop-count expressions (including any necessary max() parts). This IR level pass inserts custom intrinsics that are lowered into the desired decrement-and-branch instructions. The most fragile part of this new implementation is that interfering uses of the counter register must be detected on the IR level (and, on PPC, this also includes any indirect branches in addition to function calls). Also, to make all of this work, we need a variant of the mtctr instruction that is marked as having side effects. Without this, machine-code level CSE, DCE, etc. illegally transform the resulting code. Hopefully, this can be improved in the future. This new pass is smaller than the original (and much smaller than the new Hexagon hardware loops pass), and can handle many additional cases correctly. In addition, the preheader-creation code has been copied from LoopSimplify, and after we decide on where it belongs, this code will be refactored so that it can be explicitly shared (making this implementation even smaller). The new test-case files ctrloop-{le,lt,ne}.ll have been adapted from tests for the new Hexagon pass. There are a few classes of loops that this pass does not transform (noted by FIXMEs in the files), but these deficiencies can be addressed within the SE infrastructure (thus helping many other passes as well). llvm-svn: 181927
2013-05-16 05:37:41 +08:00
char PPCCTRLoops::ID = 0;
#ifndef NDEBUG
int PPCCTRLoops::Counter = 0;
#endif
Add a PPCCTRLoops verification pass When asserts are enabled, this adds a verification pass for PPC counter-loop formation. Unfortunately, without sacrificing code quality, there is no better way of forming counter-based loops except at the (late) IR level. This means that we need to recognize, at the IR level, anything which might turn into a function call (or indirect branch). Because this is currently a finite set of things, and because SelectionDAG lowering is basic-block local, this can be done. Nevertheless, it is fragile, and failure results in a miscompile. This verification pass checks that all (reachable) counter-based branches are dominated by a loop mtctr instruction, and that no instructions in between clobber the counter register. If these conditions are not satisfied, then an ICE will be triggered. In short, this is to help us sleep better at night. llvm-svn: 182295
2013-05-21 00:08:17 +08:00
#ifndef NDEBUG
struct PPCCTRLoopsVerify : public MachineFunctionPass {
public:
static char ID;
PPCCTRLoopsVerify() : MachineFunctionPass(ID) {
initializePPCCTRLoopsVerifyPass(*PassRegistry::getPassRegistry());
}
[C++11] Add 'override' keywords and remove 'virtual'. Additionally add 'final' and leave 'virtual' on some methods that are marked virtual without overriding anything and have no obvious overrides themselves. PowerPC edition llvm-svn: 207504
2014-04-29 15:57:37 +08:00
void getAnalysisUsage(AnalysisUsage &AU) const override {
Add a PPCCTRLoops verification pass When asserts are enabled, this adds a verification pass for PPC counter-loop formation. Unfortunately, without sacrificing code quality, there is no better way of forming counter-based loops except at the (late) IR level. This means that we need to recognize, at the IR level, anything which might turn into a function call (or indirect branch). Because this is currently a finite set of things, and because SelectionDAG lowering is basic-block local, this can be done. Nevertheless, it is fragile, and failure results in a miscompile. This verification pass checks that all (reachable) counter-based branches are dominated by a loop mtctr instruction, and that no instructions in between clobber the counter register. If these conditions are not satisfied, then an ICE will be triggered. In short, this is to help us sleep better at night. llvm-svn: 182295
2013-05-21 00:08:17 +08:00
AU.addRequired<MachineDominatorTree>();
MachineFunctionPass::getAnalysisUsage(AU);
}
[C++11] Add 'override' keywords and remove 'virtual'. Additionally add 'final' and leave 'virtual' on some methods that are marked virtual without overriding anything and have no obvious overrides themselves. PowerPC edition llvm-svn: 207504
2014-04-29 15:57:37 +08:00
bool runOnMachineFunction(MachineFunction &MF) override;
Add a PPCCTRLoops verification pass When asserts are enabled, this adds a verification pass for PPC counter-loop formation. Unfortunately, without sacrificing code quality, there is no better way of forming counter-based loops except at the (late) IR level. This means that we need to recognize, at the IR level, anything which might turn into a function call (or indirect branch). Because this is currently a finite set of things, and because SelectionDAG lowering is basic-block local, this can be done. Nevertheless, it is fragile, and failure results in a miscompile. This verification pass checks that all (reachable) counter-based branches are dominated by a loop mtctr instruction, and that no instructions in between clobber the counter register. If these conditions are not satisfied, then an ICE will be triggered. In short, this is to help us sleep better at night. llvm-svn: 182295
2013-05-21 00:08:17 +08:00
private:
MachineDominatorTree *MDT;
};
char PPCCTRLoopsVerify::ID = 0;
#endif // NDEBUG
Add the PPCCTRLoops pass: a PPC machine-code-level optimization pass to form CTR-based loop branching code. This pass is derived from the Hexagon HardwareLoops pass. The only significant enhancement over the Hexagon pass is that PPCCTRLoops will also attempt to delete the replaced add and compare operations if they are no longer otherwise used. Also, invalid preheader DebugLoc is not used. llvm-svn: 158204
2012-06-08 23:38:21 +08:00
} // end anonymous namespace
Add registration for PPC-specific passes to allow the IR to be dumped via -print-after-all. llvm-svn: 175058
2013-02-14 01:40:07 +08:00
INITIALIZE_PASS_BEGIN(PPCCTRLoops, "ppc-ctr-loops", "PowerPC CTR Loops",
false, false)
[PM] Split DominatorTree into a concrete analysis result object which can be used by both the new pass manager and the old. This removes it from any of the virtual mess of the pass interfaces and lets it derive cleanly from the DominatorTreeBase<> template. In turn, tons of boilerplate interface can be nuked and it turns into a very straightforward extension of the base DominatorTree interface. The old analysis pass is now a simple wrapper. The names and style of this split should match the split between CallGraph and CallGraphWrapperPass. All of the users of DominatorTree have been updated to match using many of the same tricks as with CallGraph. The goal is that the common type remains the resulting DominatorTree rather than the pass. This will make subsequent work toward the new pass manager significantly easier. Also in numerous places things became cleaner because I switched from re-running the pass (!!! mid way through some other passes run!!!) to directly recomputing the domtree. llvm-svn: 199104
2014-01-13 21:07:17 +08:00
INITIALIZE_PASS_DEPENDENCY(DominatorTreeWrapperPass)
[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)
Implement PPC counter loops as a late IR-level pass The old PPCCTRLoops pass, like the Hexagon pass version from which it was derived, could only handle some simple loops in canonical form. We cannot directly adapt the new Hexagon hardware loops pass, however, because the Hexagon pass contains a fundamental assumption that non-constant-trip-count loops will contain a guard, and this is not always true (the result being that incorrect negative counts can be generated). With this commit, we replace the pass with a late IR-level pass which makes use of SE to calculate the backedge-taken counts and safely generate the loop-count expressions (including any necessary max() parts). This IR level pass inserts custom intrinsics that are lowered into the desired decrement-and-branch instructions. The most fragile part of this new implementation is that interfering uses of the counter register must be detected on the IR level (and, on PPC, this also includes any indirect branches in addition to function calls). Also, to make all of this work, we need a variant of the mtctr instruction that is marked as having side effects. Without this, machine-code level CSE, DCE, etc. illegally transform the resulting code. Hopefully, this can be improved in the future. This new pass is smaller than the original (and much smaller than the new Hexagon hardware loops pass), and can handle many additional cases correctly. In addition, the preheader-creation code has been copied from LoopSimplify, and after we decide on where it belongs, this code will be refactored so that it can be explicitly shared (making this implementation even smaller). The new test-case files ctrloop-{le,lt,ne}.ll have been adapted from tests for the new Hexagon pass. There are a few classes of loops that this pass does not transform (noted by FIXMEs in the files), but these deficiencies can be addressed within the SE infrastructure (thus helping many other passes as well). llvm-svn: 181927
2013-05-16 05:37:41 +08:00
INITIALIZE_PASS_DEPENDENCY(ScalarEvolution)
Add registration for PPC-specific passes to allow the IR to be dumped via -print-after-all. llvm-svn: 175058
2013-02-14 01:40:07 +08:00
INITIALIZE_PASS_END(PPCCTRLoops, "ppc-ctr-loops", "PowerPC CTR Loops",
false, false)
Add the PPCCTRLoops pass: a PPC machine-code-level optimization pass to form CTR-based loop branching code. This pass is derived from the Hexagon HardwareLoops pass. The only significant enhancement over the Hexagon pass is that PPCCTRLoops will also attempt to delete the replaced add and compare operations if they are no longer otherwise used. Also, invalid preheader DebugLoc is not used. llvm-svn: 158204
2012-06-08 23:38:21 +08:00
Implement PPC counter loops as a late IR-level pass The old PPCCTRLoops pass, like the Hexagon pass version from which it was derived, could only handle some simple loops in canonical form. We cannot directly adapt the new Hexagon hardware loops pass, however, because the Hexagon pass contains a fundamental assumption that non-constant-trip-count loops will contain a guard, and this is not always true (the result being that incorrect negative counts can be generated). With this commit, we replace the pass with a late IR-level pass which makes use of SE to calculate the backedge-taken counts and safely generate the loop-count expressions (including any necessary max() parts). This IR level pass inserts custom intrinsics that are lowered into the desired decrement-and-branch instructions. The most fragile part of this new implementation is that interfering uses of the counter register must be detected on the IR level (and, on PPC, this also includes any indirect branches in addition to function calls). Also, to make all of this work, we need a variant of the mtctr instruction that is marked as having side effects. Without this, machine-code level CSE, DCE, etc. illegally transform the resulting code. Hopefully, this can be improved in the future. This new pass is smaller than the original (and much smaller than the new Hexagon hardware loops pass), and can handle many additional cases correctly. In addition, the preheader-creation code has been copied from LoopSimplify, and after we decide on where it belongs, this code will be refactored so that it can be explicitly shared (making this implementation even smaller). The new test-case files ctrloop-{le,lt,ne}.ll have been adapted from tests for the new Hexagon pass. There are a few classes of loops that this pass does not transform (noted by FIXMEs in the files), but these deficiencies can be addressed within the SE infrastructure (thus helping many other passes as well). llvm-svn: 181927
2013-05-16 05:37:41 +08:00
FunctionPass *llvm::createPPCCTRLoops(PPCTargetMachine &TM) {
return new PPCCTRLoops(TM);
Add the PPCCTRLoops pass: a PPC machine-code-level optimization pass to form CTR-based loop branching code. This pass is derived from the Hexagon HardwareLoops pass. The only significant enhancement over the Hexagon pass is that PPCCTRLoops will also attempt to delete the replaced add and compare operations if they are no longer otherwise used. Also, invalid preheader DebugLoc is not used. llvm-svn: 158204
2012-06-08 23:38:21 +08:00
}
Add a PPCCTRLoops verification pass When asserts are enabled, this adds a verification pass for PPC counter-loop formation. Unfortunately, without sacrificing code quality, there is no better way of forming counter-based loops except at the (late) IR level. This means that we need to recognize, at the IR level, anything which might turn into a function call (or indirect branch). Because this is currently a finite set of things, and because SelectionDAG lowering is basic-block local, this can be done. Nevertheless, it is fragile, and failure results in a miscompile. This verification pass checks that all (reachable) counter-based branches are dominated by a loop mtctr instruction, and that no instructions in between clobber the counter register. If these conditions are not satisfied, then an ICE will be triggered. In short, this is to help us sleep better at night. llvm-svn: 182295
2013-05-21 00:08:17 +08:00
#ifndef NDEBUG
INITIALIZE_PASS_BEGIN(PPCCTRLoopsVerify, "ppc-ctr-loops-verify",
"PowerPC CTR Loops Verify", false, false)
INITIALIZE_PASS_DEPENDENCY(MachineDominatorTree)
INITIALIZE_PASS_END(PPCCTRLoopsVerify, "ppc-ctr-loops-verify",
"PowerPC CTR Loops Verify", false, false)
FunctionPass *llvm::createPPCCTRLoopsVerify() {
return new PPCCTRLoopsVerify();
}
#endif // NDEBUG
Implement PPC counter loops as a late IR-level pass The old PPCCTRLoops pass, like the Hexagon pass version from which it was derived, could only handle some simple loops in canonical form. We cannot directly adapt the new Hexagon hardware loops pass, however, because the Hexagon pass contains a fundamental assumption that non-constant-trip-count loops will contain a guard, and this is not always true (the result being that incorrect negative counts can be generated). With this commit, we replace the pass with a late IR-level pass which makes use of SE to calculate the backedge-taken counts and safely generate the loop-count expressions (including any necessary max() parts). This IR level pass inserts custom intrinsics that are lowered into the desired decrement-and-branch instructions. The most fragile part of this new implementation is that interfering uses of the counter register must be detected on the IR level (and, on PPC, this also includes any indirect branches in addition to function calls). Also, to make all of this work, we need a variant of the mtctr instruction that is marked as having side effects. Without this, machine-code level CSE, DCE, etc. illegally transform the resulting code. Hopefully, this can be improved in the future. This new pass is smaller than the original (and much smaller than the new Hexagon hardware loops pass), and can handle many additional cases correctly. In addition, the preheader-creation code has been copied from LoopSimplify, and after we decide on where it belongs, this code will be refactored so that it can be explicitly shared (making this implementation even smaller). The new test-case files ctrloop-{le,lt,ne}.ll have been adapted from tests for the new Hexagon pass. There are a few classes of loops that this pass does not transform (noted by FIXMEs in the files), but these deficiencies can be addressed within the SE infrastructure (thus helping many other passes as well). llvm-svn: 181927
2013-05-16 05:37:41 +08:00
bool PPCCTRLoops::runOnFunction(Function &F) {
[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
LI = &getAnalysis<LoopInfoWrapperPass>().getLoopInfo();
Implement PPC counter loops as a late IR-level pass The old PPCCTRLoops pass, like the Hexagon pass version from which it was derived, could only handle some simple loops in canonical form. We cannot directly adapt the new Hexagon hardware loops pass, however, because the Hexagon pass contains a fundamental assumption that non-constant-trip-count loops will contain a guard, and this is not always true (the result being that incorrect negative counts can be generated). With this commit, we replace the pass with a late IR-level pass which makes use of SE to calculate the backedge-taken counts and safely generate the loop-count expressions (including any necessary max() parts). This IR level pass inserts custom intrinsics that are lowered into the desired decrement-and-branch instructions. The most fragile part of this new implementation is that interfering uses of the counter register must be detected on the IR level (and, on PPC, this also includes any indirect branches in addition to function calls). Also, to make all of this work, we need a variant of the mtctr instruction that is marked as having side effects. Without this, machine-code level CSE, DCE, etc. illegally transform the resulting code. Hopefully, this can be improved in the future. This new pass is smaller than the original (and much smaller than the new Hexagon hardware loops pass), and can handle many additional cases correctly. In addition, the preheader-creation code has been copied from LoopSimplify, and after we decide on where it belongs, this code will be refactored so that it can be explicitly shared (making this implementation even smaller). The new test-case files ctrloop-{le,lt,ne}.ll have been adapted from tests for the new Hexagon pass. There are a few classes of loops that this pass does not transform (noted by FIXMEs in the files), but these deficiencies can be addressed within the SE infrastructure (thus helping many other passes as well). llvm-svn: 181927
2013-05-16 05:37:41 +08:00
SE = &getAnalysis<ScalarEvolution>();
[PM] Split DominatorTree into a concrete analysis result object which can be used by both the new pass manager and the old. This removes it from any of the virtual mess of the pass interfaces and lets it derive cleanly from the DominatorTreeBase<> template. In turn, tons of boilerplate interface can be nuked and it turns into a very straightforward extension of the base DominatorTree interface. The old analysis pass is now a simple wrapper. The names and style of this split should match the split between CallGraph and CallGraphWrapperPass. All of the users of DominatorTree have been updated to match using many of the same tricks as with CallGraph. The goal is that the common type remains the resulting DominatorTree rather than the pass. This will make subsequent work toward the new pass manager significantly easier. Also in numerous places things became cleaner because I switched from re-running the pass (!!! mid way through some other passes run!!!) to directly recomputing the domtree. llvm-svn: 199104
2014-01-13 21:07:17 +08:00
DT = &getAnalysis<DominatorTreeWrapperPass>().getDomTree();
Make DataLayout a plain object, not a pass. Instead, have a DataLayoutPass that holds one. This will allow parts of LLVM don't don't handle passes to also use DataLayout. llvm-svn: 202168
2014-02-26 01:30:31 +08:00
DataLayoutPass *DLP = getAnalysisIfAvailable<DataLayoutPass>();
[C++] Use 'nullptr'. Target edition. llvm-svn: 207197
2014-04-25 13:30:21 +08:00
DL = DLP ? &DLP->getDataLayout() : nullptr;
[PM] Separate the TargetLibraryInfo object from the immutable pass. The pass is really just a means of accessing a cached instance of the TargetLibraryInfo object, and this way we can re-use that object for the new pass manager as its result. Lots of delta, but nothing interesting happening here. This is the common pattern that is developing to allow analyses to live in both the old and new pass manager -- a wrapper pass in the old pass manager emulates the separation intrinsic to the new pass manager between the result and pass for analyses. llvm-svn: 226157
2015-01-15 18:41:28 +08:00
auto *TLIP = getAnalysisIfAvailable<TargetLibraryInfoWrapperPass>();
LibInfo = TLIP ? &TLIP->getTLI() : nullptr;
Add the PPCCTRLoops pass: a PPC machine-code-level optimization pass to form CTR-based loop branching code. This pass is derived from the Hexagon HardwareLoops pass. The only significant enhancement over the Hexagon pass is that PPCCTRLoops will also attempt to delete the replaced add and compare operations if they are no longer otherwise used. Also, invalid preheader DebugLoc is not used. llvm-svn: 158204
2012-06-08 23:38:21 +08:00
Implement PPC counter loops as a late IR-level pass The old PPCCTRLoops pass, like the Hexagon pass version from which it was derived, could only handle some simple loops in canonical form. We cannot directly adapt the new Hexagon hardware loops pass, however, because the Hexagon pass contains a fundamental assumption that non-constant-trip-count loops will contain a guard, and this is not always true (the result being that incorrect negative counts can be generated). With this commit, we replace the pass with a late IR-level pass which makes use of SE to calculate the backedge-taken counts and safely generate the loop-count expressions (including any necessary max() parts). This IR level pass inserts custom intrinsics that are lowered into the desired decrement-and-branch instructions. The most fragile part of this new implementation is that interfering uses of the counter register must be detected on the IR level (and, on PPC, this also includes any indirect branches in addition to function calls). Also, to make all of this work, we need a variant of the mtctr instruction that is marked as having side effects. Without this, machine-code level CSE, DCE, etc. illegally transform the resulting code. Hopefully, this can be improved in the future. This new pass is smaller than the original (and much smaller than the new Hexagon hardware loops pass), and can handle many additional cases correctly. In addition, the preheader-creation code has been copied from LoopSimplify, and after we decide on where it belongs, this code will be refactored so that it can be explicitly shared (making this implementation even smaller). The new test-case files ctrloop-{le,lt,ne}.ll have been adapted from tests for the new Hexagon pass. There are a few classes of loops that this pass does not transform (noted by FIXMEs in the files), but these deficiencies can be addressed within the SE infrastructure (thus helping many other passes as well). llvm-svn: 181927
2013-05-16 05:37:41 +08:00
bool MadeChange = false;
Add the PPCCTRLoops pass: a PPC machine-code-level optimization pass to form CTR-based loop branching code. This pass is derived from the Hexagon HardwareLoops pass. The only significant enhancement over the Hexagon pass is that PPCCTRLoops will also attempt to delete the replaced add and compare operations if they are no longer otherwise used. Also, invalid preheader DebugLoc is not used. llvm-svn: 158204
2012-06-08 23:38:21 +08:00
Implement PPC counter loops as a late IR-level pass The old PPCCTRLoops pass, like the Hexagon pass version from which it was derived, could only handle some simple loops in canonical form. We cannot directly adapt the new Hexagon hardware loops pass, however, because the Hexagon pass contains a fundamental assumption that non-constant-trip-count loops will contain a guard, and this is not always true (the result being that incorrect negative counts can be generated). With this commit, we replace the pass with a late IR-level pass which makes use of SE to calculate the backedge-taken counts and safely generate the loop-count expressions (including any necessary max() parts). This IR level pass inserts custom intrinsics that are lowered into the desired decrement-and-branch instructions. The most fragile part of this new implementation is that interfering uses of the counter register must be detected on the IR level (and, on PPC, this also includes any indirect branches in addition to function calls). Also, to make all of this work, we need a variant of the mtctr instruction that is marked as having side effects. Without this, machine-code level CSE, DCE, etc. illegally transform the resulting code. Hopefully, this can be improved in the future. This new pass is smaller than the original (and much smaller than the new Hexagon hardware loops pass), and can handle many additional cases correctly. In addition, the preheader-creation code has been copied from LoopSimplify, and after we decide on where it belongs, this code will be refactored so that it can be explicitly shared (making this implementation even smaller). The new test-case files ctrloop-{le,lt,ne}.ll have been adapted from tests for the new Hexagon pass. There are a few classes of loops that this pass does not transform (noted by FIXMEs in the files), but these deficiencies can be addressed within the SE infrastructure (thus helping many other passes as well). llvm-svn: 181927
2013-05-16 05:37:41 +08:00
for (LoopInfo::iterator I = LI->begin(), E = LI->end();
Add the PPCCTRLoops pass: a PPC machine-code-level optimization pass to form CTR-based loop branching code. This pass is derived from the Hexagon HardwareLoops pass. The only significant enhancement over the Hexagon pass is that PPCCTRLoops will also attempt to delete the replaced add and compare operations if they are no longer otherwise used. Also, invalid preheader DebugLoc is not used. llvm-svn: 158204
2012-06-08 23:38:21 +08:00
I != E; ++I) {
Implement PPC counter loops as a late IR-level pass The old PPCCTRLoops pass, like the Hexagon pass version from which it was derived, could only handle some simple loops in canonical form. We cannot directly adapt the new Hexagon hardware loops pass, however, because the Hexagon pass contains a fundamental assumption that non-constant-trip-count loops will contain a guard, and this is not always true (the result being that incorrect negative counts can be generated). With this commit, we replace the pass with a late IR-level pass which makes use of SE to calculate the backedge-taken counts and safely generate the loop-count expressions (including any necessary max() parts). This IR level pass inserts custom intrinsics that are lowered into the desired decrement-and-branch instructions. The most fragile part of this new implementation is that interfering uses of the counter register must be detected on the IR level (and, on PPC, this also includes any indirect branches in addition to function calls). Also, to make all of this work, we need a variant of the mtctr instruction that is marked as having side effects. Without this, machine-code level CSE, DCE, etc. illegally transform the resulting code. Hopefully, this can be improved in the future. This new pass is smaller than the original (and much smaller than the new Hexagon hardware loops pass), and can handle many additional cases correctly. In addition, the preheader-creation code has been copied from LoopSimplify, and after we decide on where it belongs, this code will be refactored so that it can be explicitly shared (making this implementation even smaller). The new test-case files ctrloop-{le,lt,ne}.ll have been adapted from tests for the new Hexagon pass. There are a few classes of loops that this pass does not transform (noted by FIXMEs in the files), but these deficiencies can be addressed within the SE infrastructure (thus helping many other passes as well). llvm-svn: 181927
2013-05-16 05:37:41 +08:00
Loop *L = *I;
if (!L->getParentLoop())
MadeChange |= convertToCTRLoop(L);
Add the PPCCTRLoops pass: a PPC machine-code-level optimization pass to form CTR-based loop branching code. This pass is derived from the Hexagon HardwareLoops pass. The only significant enhancement over the Hexagon pass is that PPCCTRLoops will also attempt to delete the replaced add and compare operations if they are no longer otherwise used. Also, invalid preheader DebugLoc is not used. llvm-svn: 158204
2012-06-08 23:38:21 +08:00
}
Implement PPC counter loops as a late IR-level pass The old PPCCTRLoops pass, like the Hexagon pass version from which it was derived, could only handle some simple loops in canonical form. We cannot directly adapt the new Hexagon hardware loops pass, however, because the Hexagon pass contains a fundamental assumption that non-constant-trip-count loops will contain a guard, and this is not always true (the result being that incorrect negative counts can be generated). With this commit, we replace the pass with a late IR-level pass which makes use of SE to calculate the backedge-taken counts and safely generate the loop-count expressions (including any necessary max() parts). This IR level pass inserts custom intrinsics that are lowered into the desired decrement-and-branch instructions. The most fragile part of this new implementation is that interfering uses of the counter register must be detected on the IR level (and, on PPC, this also includes any indirect branches in addition to function calls). Also, to make all of this work, we need a variant of the mtctr instruction that is marked as having side effects. Without this, machine-code level CSE, DCE, etc. illegally transform the resulting code. Hopefully, this can be improved in the future. This new pass is smaller than the original (and much smaller than the new Hexagon hardware loops pass), and can handle many additional cases correctly. In addition, the preheader-creation code has been copied from LoopSimplify, and after we decide on where it belongs, this code will be refactored so that it can be explicitly shared (making this implementation even smaller). The new test-case files ctrloop-{le,lt,ne}.ll have been adapted from tests for the new Hexagon pass. There are a few classes of loops that this pass does not transform (noted by FIXMEs in the files), but these deficiencies can be addressed within the SE infrastructure (thus helping many other passes as well). llvm-svn: 181927
2013-05-16 05:37:41 +08:00
return MadeChange;
Add the PPCCTRLoops pass: a PPC machine-code-level optimization pass to form CTR-based loop branching code. This pass is derived from the Hexagon HardwareLoops pass. The only significant enhancement over the Hexagon pass is that PPCCTRLoops will also attempt to delete the replaced add and compare operations if they are no longer otherwise used. Also, invalid preheader DebugLoc is not used. llvm-svn: 158204
2012-06-08 23:38:21 +08:00
}
Account for 128-bit integer operations in PPCCTRLoops We need to abort the formation of counter-register-based loops where there are 128-bit integer operations that might become function calls. llvm-svn: 202192
2014-02-26 04:51:50 +08:00
static bool isLargeIntegerTy(bool Is32Bit, Type *Ty) {
if (IntegerType *ITy = dyn_cast<IntegerType>(Ty))
Silencing an MSVC signed comparison warning. llvm-svn: 202295
2014-02-27 04:22:20 +08:00
return ITy->getBitWidth() > (Is32Bit ? 32U : 64U);
Account for 128-bit integer operations in PPCCTRLoops We need to abort the formation of counter-register-based loops where there are 128-bit integer operations that might become function calls. llvm-svn: 202192
2014-02-26 04:51:50 +08:00
return false;
}
PowerPC: CTR shouldn't fire if a TLS call is in the loop Determining the address of a TLS variable results in a function call in certain TLS models. This means that a simple ICmpInst might actually result in invalidating the CTR register. In such cases, do not attempt to rely on the CTR register for loop optimization purposes. This fixes PR22034. Differential Revision: http://reviews.llvm.org/D6786 llvm-svn: 224890
2014-12-28 03:45:38 +08:00
// Determining the address of a TLS variable results in a function call in
// certain TLS models.
static bool memAddrUsesCTR(const PPCTargetMachine *TM,
const llvm::Value *MemAddr) {
const auto *GV = dyn_cast<GlobalValue>(MemAddr);
if (!GV)
return false;
if (!GV->isThreadLocal())
return false;
if (!TM)
return true;
TLSModel::Model Model = TM->getTLSModel(GV);
return Model == TLSModel::GeneralDynamic || Model == TLSModel::LocalDynamic;
}
Create an new preheader in PPCCTRLoops to avoid counter register clobbers Some IR-level instructions (such as FP <-> i64 conversions) are not chained w.r.t. the mtctr intrinsic and yet may become function calls that clobber the counter register. At the selection-DAG level, these might be reordered with the mtctr intrinsic causing miscompiles. To avoid this situation, if an existing preheader has instructions that might use the counter register, create a new preheader for the mtctr intrinsic. This extra block will be remerged with the old preheader at the MI level, but will prevent unwanted reordering at the selection-DAG level. llvm-svn: 182045
2013-05-17 03:58:38 +08:00
bool PPCCTRLoops::mightUseCTR(const Triple &TT, BasicBlock *BB) {
for (BasicBlock::iterator J = BB->begin(), JE = BB->end();
J != JE; ++J) {
if (CallInst *CI = dyn_cast<CallInst>(J)) {
Check InlineAsm clobbers in PPCCTRLoops We don't need to reject all inline asm as using the counter register (most does not). Only those that explicitly clobber the counter register need to prevent the transformation. llvm-svn: 182191
2013-05-18 17:20:39 +08:00
if (InlineAsm *IA = dyn_cast<InlineAsm>(CI->getCalledValue())) {
// Inline ASM is okay, unless it clobbers the ctr register.
InlineAsm::ConstraintInfoVector CIV = IA->ParseConstraints();
for (unsigned i = 0, ie = CIV.size(); i < ie; ++i) {
InlineAsm::ConstraintInfo &C = CIV[i];
if (C.Type != InlineAsm::isInput)
for (unsigned j = 0, je = C.Codes.size(); j < je; ++j)
if (StringRef(C.Codes[j]).equals_lower("{ctr}"))
return true;
}
continue;
}
Create an new preheader in PPCCTRLoops to avoid counter register clobbers Some IR-level instructions (such as FP <-> i64 conversions) are not chained w.r.t. the mtctr intrinsic and yet may become function calls that clobber the counter register. At the selection-DAG level, these might be reordered with the mtctr intrinsic causing miscompiles. To avoid this situation, if an existing preheader has instructions that might use the counter register, create a new preheader for the mtctr intrinsic. This extra block will be remerged with the old preheader at the MI level, but will prevent unwanted reordering at the selection-DAG level. llvm-svn: 182045
2013-05-17 03:58:38 +08:00
if (!TM)
return true;
Migrate some of PPC away from the use of bare getSubtarget/getSubtargetImpl. llvm-svn: 227547
2015-01-30 10:11:24 +08:00
const TargetLowering *TLI =
TM->getSubtargetImpl(*BB->getParent())->getTargetLowering();
Create an new preheader in PPCCTRLoops to avoid counter register clobbers Some IR-level instructions (such as FP <-> i64 conversions) are not chained w.r.t. the mtctr intrinsic and yet may become function calls that clobber the counter register. At the selection-DAG level, these might be reordered with the mtctr intrinsic causing miscompiles. To avoid this situation, if an existing preheader has instructions that might use the counter register, create a new preheader for the mtctr intrinsic. This extra block will be remerged with the old preheader at the MI level, but will prevent unwanted reordering at the selection-DAG level. llvm-svn: 182045
2013-05-17 03:58:38 +08:00
if (Function *F = CI->getCalledFunction()) {
// Most intrinsics don't become function calls, but some might.
// sin, cos, exp and log are always calls.
unsigned Opcode;
if (F->getIntrinsicID() != Intrinsic::not_intrinsic) {
switch (F->getIntrinsicID()) {
default: continue;
// VisualStudio defines setjmp as _setjmp
#if defined(_MSC_VER) && defined(setjmp) && \
!defined(setjmp_undefined_for_msvc)
# pragma push_macro("setjmp")
# undef setjmp
# define setjmp_undefined_for_msvc
#endif
case Intrinsic::setjmp:
#if defined(_MSC_VER) && defined(setjmp_undefined_for_msvc)
// let's return it to _setjmp state
# pragma pop_macro("setjmp")
# undef setjmp_undefined_for_msvc
#endif
case Intrinsic::longjmp:
PPC: Add CTR-register clobber to builtin setjmp Because the builtin longjmp implementation uses a CTR-based indirect jump, when the control flow arrives at the builtin setjmp call, the CTR register has necessarily been clobbered. Correspondingly, this adds CTR to the list of implicit definitions of the builtin setjmp pseudo instruction. We don't need to add CTR to the implicit definitions of builtin longjmp because, even though it does clobber the CTR register, the control flow cannot return to inside the loop unless there is also a builtin setjmp call. llvm-svn: 186488
2013-07-17 13:35:44 +08:00
// Exclude eh_sjlj_setjmp; we don't need to exclude eh_sjlj_longjmp
// because, although it does clobber the counter register, the
// control can't then return to inside the loop unless there is also
// an eh_sjlj_setjmp.
case Intrinsic::eh_sjlj_setjmp:
Create an new preheader in PPCCTRLoops to avoid counter register clobbers Some IR-level instructions (such as FP <-> i64 conversions) are not chained w.r.t. the mtctr intrinsic and yet may become function calls that clobber the counter register. At the selection-DAG level, these might be reordered with the mtctr intrinsic causing miscompiles. To avoid this situation, if an existing preheader has instructions that might use the counter register, create a new preheader for the mtctr intrinsic. This extra block will be remerged with the old preheader at the MI level, but will prevent unwanted reordering at the selection-DAG level. llvm-svn: 182045
2013-05-17 03:58:38 +08:00
case Intrinsic::memcpy:
case Intrinsic::memmove:
case Intrinsic::memset:
case Intrinsic::powi:
case Intrinsic::log:
case Intrinsic::log2:
case Intrinsic::log10:
case Intrinsic::exp:
case Intrinsic::exp2:
case Intrinsic::pow:
case Intrinsic::sin:
case Intrinsic::cos:
return true;
Add a llvm.copysign intrinsic This adds a llvm.copysign intrinsic; We already have Libfunc recognition for copysign (which is turned into the FCOPYSIGN SDAG node). In order to autovectorize calls to copysign in the loop vectorizer, we need a corresponding intrinsic as well. In addition to the expected changes to the language reference, the loop vectorizer, BasicTTI, and the SDAG builder (the intrinsic is transformed into an FCOPYSIGN node, just like the function call), this also adds FCOPYSIGN to a few lists in LegalizeVector{Ops,Types} so that vector copysigns can be expanded. In TargetLoweringBase::initActions, I've made the default action for FCOPYSIGN be Expand for vector types. This seems correct for all in-tree targets, and I think is the right thing to do because, previously, there was no way to generate vector-values FCOPYSIGN nodes (and most targets don't specify an action for vector-typed FCOPYSIGN). llvm-svn: 188728
2013-08-20 07:35:46 +08:00
case Intrinsic::copysign:
if (CI->getArgOperand(0)->getType()->getScalarType()->
isPPC_FP128Ty())
return true;
else
continue; // ISD::FCOPYSIGN is never a library call.
Create an new preheader in PPCCTRLoops to avoid counter register clobbers Some IR-level instructions (such as FP <-> i64 conversions) are not chained w.r.t. the mtctr intrinsic and yet may become function calls that clobber the counter register. At the selection-DAG level, these might be reordered with the mtctr intrinsic causing miscompiles. To avoid this situation, if an existing preheader has instructions that might use the counter register, create a new preheader for the mtctr intrinsic. This extra block will be remerged with the old preheader at the MI level, but will prevent unwanted reordering at the selection-DAG level. llvm-svn: 182045
2013-05-17 03:58:38 +08:00
case Intrinsic::sqrt: Opcode = ISD::FSQRT; break;
case Intrinsic::floor: Opcode = ISD::FFLOOR; break;
case Intrinsic::ceil: Opcode = ISD::FCEIL; break;
case Intrinsic::trunc: Opcode = ISD::FTRUNC; break;
case Intrinsic::rint: Opcode = ISD::FRINT; break;
case Intrinsic::nearbyint: Opcode = ISD::FNEARBYINT; break;
Add ISD::FROUND for libm round() All libm floating-point rounding functions, except for round(), had their own ISD nodes. Recent PowerPC cores have an instruction for round(), and so here I'm adding ISD::FROUND so that round() can be custom lowered as well. For the most part, this is straightforward. I've added an intrinsic and a matching ISD node just like those for nearbyint() and friends. The SelectionDAG pattern I've named frnd (because ISD::FP_ROUND has already claimed fround). This will be used by the PowerPC backend in a follow-up commit. llvm-svn: 187926
2013-08-08 06:49:12 +08:00
case Intrinsic::round: Opcode = ISD::FROUND; break;
Create an new preheader in PPCCTRLoops to avoid counter register clobbers Some IR-level instructions (such as FP <-> i64 conversions) are not chained w.r.t. the mtctr intrinsic and yet may become function calls that clobber the counter register. At the selection-DAG level, these might be reordered with the mtctr intrinsic causing miscompiles. To avoid this situation, if an existing preheader has instructions that might use the counter register, create a new preheader for the mtctr intrinsic. This extra block will be remerged with the old preheader at the MI level, but will prevent unwanted reordering at the selection-DAG level. llvm-svn: 182045
2013-05-17 03:58:38 +08:00
}
}
// PowerPC does not use [US]DIVREM or other library calls for
// operations on regular types which are not otherwise library calls
// (i.e. soft float or atomics). If adapting for targets that do,
// additional care is required here.
LibFunc::Func Func;
if (!F->hasLocalLinkage() && F->hasName() && LibInfo &&
LibInfo->getLibFunc(F->getName(), Func) &&
LibInfo->hasOptimizedCodeGen(Func)) {
// Non-read-only functions are never treated as intrinsics.
if (!CI->onlyReadsMemory())
return true;
// Conversion happens only for FP calls.
if (!CI->getArgOperand(0)->getType()->isFloatingPointTy())
return true;
switch (Func) {
default: return true;
case LibFunc::copysign:
case LibFunc::copysignf:
continue; // ISD::FCOPYSIGN is never a library call.
Don't form PPC CTR-based loops around a copysignl call copysign/copysignf never become function calls (because the SDAG expansion code does not lower to the corresponding function call, but rather directly implements the associated logic), but copysignl almost always is lowered into a call to the requested libm functon (and, thus, might clobber CTR). llvm-svn: 188727
2013-08-20 07:35:24 +08:00
case LibFunc::copysignl:
return true;
Create an new preheader in PPCCTRLoops to avoid counter register clobbers Some IR-level instructions (such as FP <-> i64 conversions) are not chained w.r.t. the mtctr intrinsic and yet may become function calls that clobber the counter register. At the selection-DAG level, these might be reordered with the mtctr intrinsic causing miscompiles. To avoid this situation, if an existing preheader has instructions that might use the counter register, create a new preheader for the mtctr intrinsic. This extra block will be remerged with the old preheader at the MI level, but will prevent unwanted reordering at the selection-DAG level. llvm-svn: 182045
2013-05-17 03:58:38 +08:00
case LibFunc::fabs:
case LibFunc::fabsf:
case LibFunc::fabsl:
continue; // ISD::FABS is never a library call.
case LibFunc::sqrt:
case LibFunc::sqrtf:
case LibFunc::sqrtl:
Opcode = ISD::FSQRT; break;
case LibFunc::floor:
case LibFunc::floorf:
case LibFunc::floorl:
Opcode = ISD::FFLOOR; break;
case LibFunc::nearbyint:
case LibFunc::nearbyintf:
case LibFunc::nearbyintl:
Opcode = ISD::FNEARBYINT; break;
case LibFunc::ceil:
case LibFunc::ceilf:
case LibFunc::ceill:
Opcode = ISD::FCEIL; break;
case LibFunc::rint:
case LibFunc::rintf:
case LibFunc::rintl:
Opcode = ISD::FRINT; break;
Add ISD::FROUND for libm round() All libm floating-point rounding functions, except for round(), had their own ISD nodes. Recent PowerPC cores have an instruction for round(), and so here I'm adding ISD::FROUND so that round() can be custom lowered as well. For the most part, this is straightforward. I've added an intrinsic and a matching ISD node just like those for nearbyint() and friends. The SelectionDAG pattern I've named frnd (because ISD::FP_ROUND has already claimed fround). This will be used by the PowerPC backend in a follow-up commit. llvm-svn: 187926
2013-08-08 06:49:12 +08:00
case LibFunc::round:
case LibFunc::roundf:
case LibFunc::roundl:
Opcode = ISD::FROUND; break;
Create an new preheader in PPCCTRLoops to avoid counter register clobbers Some IR-level instructions (such as FP <-> i64 conversions) are not chained w.r.t. the mtctr intrinsic and yet may become function calls that clobber the counter register. At the selection-DAG level, these might be reordered with the mtctr intrinsic causing miscompiles. To avoid this situation, if an existing preheader has instructions that might use the counter register, create a new preheader for the mtctr intrinsic. This extra block will be remerged with the old preheader at the MI level, but will prevent unwanted reordering at the selection-DAG level. llvm-svn: 182045
2013-05-17 03:58:38 +08:00
case LibFunc::trunc:
case LibFunc::truncf:
case LibFunc::truncl:
Opcode = ISD::FTRUNC; break;
}
MVT VTy =
TLI->getSimpleValueType(CI->getArgOperand(0)->getType(), true);
if (VTy == MVT::Other)
return true;
if (TLI->isOperationLegalOrCustom(Opcode, VTy))
continue;
else if (VTy.isVector() &&
TLI->isOperationLegalOrCustom(Opcode, VTy.getScalarType()))
continue;
return true;
}
}
return true;
} else if (isa<BinaryOperator>(J) &&
J->getType()->getScalarType()->isPPC_FP128Ty()) {
// Most operations on ppc_f128 values become calls.
return true;
} else if (isa<UIToFPInst>(J) || isa<SIToFPInst>(J) ||
isa<FPToUIInst>(J) || isa<FPToSIInst>(J)) {
CastInst *CI = cast<CastInst>(J);
if (CI->getSrcTy()->getScalarType()->isPPC_FP128Ty() ||
CI->getDestTy()->getScalarType()->isPPC_FP128Ty() ||
Account for 128-bit integer operations in PPCCTRLoops We need to abort the formation of counter-register-based loops where there are 128-bit integer operations that might become function calls. llvm-svn: 202192
2014-02-26 04:51:50 +08:00
isLargeIntegerTy(TT.isArch32Bit(), CI->getSrcTy()->getScalarType()) ||
isLargeIntegerTy(TT.isArch32Bit(), CI->getDestTy()->getScalarType()))
Create an new preheader in PPCCTRLoops to avoid counter register clobbers Some IR-level instructions (such as FP <-> i64 conversions) are not chained w.r.t. the mtctr intrinsic and yet may become function calls that clobber the counter register. At the selection-DAG level, these might be reordered with the mtctr intrinsic causing miscompiles. To avoid this situation, if an existing preheader has instructions that might use the counter register, create a new preheader for the mtctr intrinsic. This extra block will be remerged with the old preheader at the MI level, but will prevent unwanted reordering at the selection-DAG level. llvm-svn: 182045
2013-05-17 03:58:38 +08:00
return true;
Account for 128-bit integer operations in PPCCTRLoops We need to abort the formation of counter-register-based loops where there are 128-bit integer operations that might become function calls. llvm-svn: 202192
2014-02-26 04:51:50 +08:00
} else if (isLargeIntegerTy(TT.isArch32Bit(),
J->getType()->getScalarType()) &&
Disallow i64 div/rem in PPC32 counter loops On PPC32, [su]div,rem on i64 types are transformed into runtime library function calls. As a result, they are not allowed in counter-based loops (the counter-loops verification pass caught this error; this change fixes PR16169). llvm-svn: 183581
2013-06-08 06:16:19 +08:00
(J->getOpcode() == Instruction::UDiv ||
J->getOpcode() == Instruction::SDiv ||
J->getOpcode() == Instruction::URem ||
J->getOpcode() == Instruction::SRem)) {
return true;
[PowerPC] On PPC32, 128-bit shifts might be runtime calls The counter-loops formation pass needs to know what operations might be function calls (because they can't appear in counter-based loops). On PPC32, 128-bit shifts might be runtime calls (even though you can't use __int128 on PPC32, it seems that SROA might form them). Fixes PR19709. llvm-svn: 208501
2014-05-12 00:23:29 +08:00
} else if (TT.isArch32Bit() &&
isLargeIntegerTy(false, J->getType()->getScalarType()) &&
(J->getOpcode() == Instruction::Shl ||
J->getOpcode() == Instruction::AShr ||
J->getOpcode() == Instruction::LShr)) {
// Only on PPC32, for 128-bit integers (specifically not 64-bit
// integers), these might be runtime calls.
return true;
Create an new preheader in PPCCTRLoops to avoid counter register clobbers Some IR-level instructions (such as FP <-> i64 conversions) are not chained w.r.t. the mtctr intrinsic and yet may become function calls that clobber the counter register. At the selection-DAG level, these might be reordered with the mtctr intrinsic causing miscompiles. To avoid this situation, if an existing preheader has instructions that might use the counter register, create a new preheader for the mtctr intrinsic. This extra block will be remerged with the old preheader at the MI level, but will prevent unwanted reordering at the selection-DAG level. llvm-svn: 182045
2013-05-17 03:58:38 +08:00
} else if (isa<IndirectBrInst>(J) || isa<InvokeInst>(J)) {
// On PowerPC, indirect jumps use the counter register.
return true;
} else if (SwitchInst *SI = dyn_cast<SwitchInst>(J)) {
if (!TM)
return true;
Use the cached subtargets and remove calls to getSubtarget/getSubtargetImpl without a Function argument. llvm-svn: 227622
2015-01-31 06:02:31 +08:00
const TargetLowering *TLI =
TM->getSubtargetImpl(*BB->getParent())->getTargetLowering();
Create an new preheader in PPCCTRLoops to avoid counter register clobbers Some IR-level instructions (such as FP <-> i64 conversions) are not chained w.r.t. the mtctr intrinsic and yet may become function calls that clobber the counter register. At the selection-DAG level, these might be reordered with the mtctr intrinsic causing miscompiles. To avoid this situation, if an existing preheader has instructions that might use the counter register, create a new preheader for the mtctr intrinsic. This extra block will be remerged with the old preheader at the MI level, but will prevent unwanted reordering at the selection-DAG level. llvm-svn: 182045
2013-05-17 03:58:38 +08:00
Reinstate "Nuke the old JIT." Approved by Jim Grosbach, Lang Hames, Rafael Espindola. This reinstates commits r215111, 215115, 215116, 215117, 215136. llvm-svn: 216982
2014-09-03 06:28:02 +08:00
if (SI->getNumCases() + 1 >= (unsigned)TLI->getMinimumJumpTableEntries())
Create an new preheader in PPCCTRLoops to avoid counter register clobbers Some IR-level instructions (such as FP <-> i64 conversions) are not chained w.r.t. the mtctr intrinsic and yet may become function calls that clobber the counter register. At the selection-DAG level, these might be reordered with the mtctr intrinsic causing miscompiles. To avoid this situation, if an existing preheader has instructions that might use the counter register, create a new preheader for the mtctr intrinsic. This extra block will be remerged with the old preheader at the MI level, but will prevent unwanted reordering at the selection-DAG level. llvm-svn: 182045
2013-05-17 03:58:38 +08:00
return true;
}
PowerPC: CTR shouldn't fire if a TLS call is in the loop Determining the address of a TLS variable results in a function call in certain TLS models. This means that a simple ICmpInst might actually result in invalidating the CTR register. In such cases, do not attempt to rely on the CTR register for loop optimization purposes. This fixes PR22034. Differential Revision: http://reviews.llvm.org/D6786 llvm-svn: 224890
2014-12-28 03:45:38 +08:00
for (Value *Operand : J->operands())
if (memAddrUsesCTR(TM, Operand))
return true;
Create an new preheader in PPCCTRLoops to avoid counter register clobbers Some IR-level instructions (such as FP <-> i64 conversions) are not chained w.r.t. the mtctr intrinsic and yet may become function calls that clobber the counter register. At the selection-DAG level, these might be reordered with the mtctr intrinsic causing miscompiles. To avoid this situation, if an existing preheader has instructions that might use the counter register, create a new preheader for the mtctr intrinsic. This extra block will be remerged with the old preheader at the MI level, but will prevent unwanted reordering at the selection-DAG level. llvm-svn: 182045
2013-05-17 03:58:38 +08:00
}
return false;
}
Implement PPC counter loops as a late IR-level pass The old PPCCTRLoops pass, like the Hexagon pass version from which it was derived, could only handle some simple loops in canonical form. We cannot directly adapt the new Hexagon hardware loops pass, however, because the Hexagon pass contains a fundamental assumption that non-constant-trip-count loops will contain a guard, and this is not always true (the result being that incorrect negative counts can be generated). With this commit, we replace the pass with a late IR-level pass which makes use of SE to calculate the backedge-taken counts and safely generate the loop-count expressions (including any necessary max() parts). This IR level pass inserts custom intrinsics that are lowered into the desired decrement-and-branch instructions. The most fragile part of this new implementation is that interfering uses of the counter register must be detected on the IR level (and, on PPC, this also includes any indirect branches in addition to function calls). Also, to make all of this work, we need a variant of the mtctr instruction that is marked as having side effects. Without this, machine-code level CSE, DCE, etc. illegally transform the resulting code. Hopefully, this can be improved in the future. This new pass is smaller than the original (and much smaller than the new Hexagon hardware loops pass), and can handle many additional cases correctly. In addition, the preheader-creation code has been copied from LoopSimplify, and after we decide on where it belongs, this code will be refactored so that it can be explicitly shared (making this implementation even smaller). The new test-case files ctrloop-{le,lt,ne}.ll have been adapted from tests for the new Hexagon pass. There are a few classes of loops that this pass does not transform (noted by FIXMEs in the files), but these deficiencies can be addressed within the SE infrastructure (thus helping many other passes as well). llvm-svn: 181927
2013-05-16 05:37:41 +08:00
bool PPCCTRLoops::convertToCTRLoop(Loop *L) {
bool MadeChange = false;
Add the PPCCTRLoops pass: a PPC machine-code-level optimization pass to form CTR-based loop branching code. This pass is derived from the Hexagon HardwareLoops pass. The only significant enhancement over the Hexagon pass is that PPCCTRLoops will also attempt to delete the replaced add and compare operations if they are no longer otherwise used. Also, invalid preheader DebugLoc is not used. llvm-svn: 158204
2012-06-08 23:38:21 +08:00
Implement PPC counter loops as a late IR-level pass The old PPCCTRLoops pass, like the Hexagon pass version from which it was derived, could only handle some simple loops in canonical form. We cannot directly adapt the new Hexagon hardware loops pass, however, because the Hexagon pass contains a fundamental assumption that non-constant-trip-count loops will contain a guard, and this is not always true (the result being that incorrect negative counts can be generated). With this commit, we replace the pass with a late IR-level pass which makes use of SE to calculate the backedge-taken counts and safely generate the loop-count expressions (including any necessary max() parts). This IR level pass inserts custom intrinsics that are lowered into the desired decrement-and-branch instructions. The most fragile part of this new implementation is that interfering uses of the counter register must be detected on the IR level (and, on PPC, this also includes any indirect branches in addition to function calls). Also, to make all of this work, we need a variant of the mtctr instruction that is marked as having side effects. Without this, machine-code level CSE, DCE, etc. illegally transform the resulting code. Hopefully, this can be improved in the future. This new pass is smaller than the original (and much smaller than the new Hexagon hardware loops pass), and can handle many additional cases correctly. In addition, the preheader-creation code has been copied from LoopSimplify, and after we decide on where it belongs, this code will be refactored so that it can be explicitly shared (making this implementation even smaller). The new test-case files ctrloop-{le,lt,ne}.ll have been adapted from tests for the new Hexagon pass. There are a few classes of loops that this pass does not transform (noted by FIXMEs in the files), but these deficiencies can be addressed within the SE infrastructure (thus helping many other passes as well). llvm-svn: 181927
2013-05-16 05:37:41 +08:00
Triple TT = Triple(L->getHeader()->getParent()->getParent()->
getTargetTriple());
if (!TT.isArch32Bit() && !TT.isArch64Bit())
return MadeChange; // Unknown arch. type.
Cleanup initial-value constants in PPCCTRLoops Because the initial-value constants had not been added to the list of instructions considered for DCE the resulting code had redundant constant-materialization instructions. llvm-svn: 177294
2013-03-19 01:40:27 +08:00
Implement PPC counter loops as a late IR-level pass The old PPCCTRLoops pass, like the Hexagon pass version from which it was derived, could only handle some simple loops in canonical form. We cannot directly adapt the new Hexagon hardware loops pass, however, because the Hexagon pass contains a fundamental assumption that non-constant-trip-count loops will contain a guard, and this is not always true (the result being that incorrect negative counts can be generated). With this commit, we replace the pass with a late IR-level pass which makes use of SE to calculate the backedge-taken counts and safely generate the loop-count expressions (including any necessary max() parts). This IR level pass inserts custom intrinsics that are lowered into the desired decrement-and-branch instructions. The most fragile part of this new implementation is that interfering uses of the counter register must be detected on the IR level (and, on PPC, this also includes any indirect branches in addition to function calls). Also, to make all of this work, we need a variant of the mtctr instruction that is marked as having side effects. Without this, machine-code level CSE, DCE, etc. illegally transform the resulting code. Hopefully, this can be improved in the future. This new pass is smaller than the original (and much smaller than the new Hexagon hardware loops pass), and can handle many additional cases correctly. In addition, the preheader-creation code has been copied from LoopSimplify, and after we decide on where it belongs, this code will be refactored so that it can be explicitly shared (making this implementation even smaller). The new test-case files ctrloop-{le,lt,ne}.ll have been adapted from tests for the new Hexagon pass. There are a few classes of loops that this pass does not transform (noted by FIXMEs in the files), but these deficiencies can be addressed within the SE infrastructure (thus helping many other passes as well). llvm-svn: 181927
2013-05-16 05:37:41 +08:00
// Process nested loops first.
for (Loop::iterator I = L->begin(), E = L->end(); I != E; ++I) {
MadeChange |= convertToCTRLoop(*I);
}
Cleanup initial-value constants in PPCCTRLoops Because the initial-value constants had not been added to the list of instructions considered for DCE the resulting code had redundant constant-materialization instructions. llvm-svn: 177294
2013-03-19 01:40:27 +08:00
Implement PPC counter loops as a late IR-level pass The old PPCCTRLoops pass, like the Hexagon pass version from which it was derived, could only handle some simple loops in canonical form. We cannot directly adapt the new Hexagon hardware loops pass, however, because the Hexagon pass contains a fundamental assumption that non-constant-trip-count loops will contain a guard, and this is not always true (the result being that incorrect negative counts can be generated). With this commit, we replace the pass with a late IR-level pass which makes use of SE to calculate the backedge-taken counts and safely generate the loop-count expressions (including any necessary max() parts). This IR level pass inserts custom intrinsics that are lowered into the desired decrement-and-branch instructions. The most fragile part of this new implementation is that interfering uses of the counter register must be detected on the IR level (and, on PPC, this also includes any indirect branches in addition to function calls). Also, to make all of this work, we need a variant of the mtctr instruction that is marked as having side effects. Without this, machine-code level CSE, DCE, etc. illegally transform the resulting code. Hopefully, this can be improved in the future. This new pass is smaller than the original (and much smaller than the new Hexagon hardware loops pass), and can handle many additional cases correctly. In addition, the preheader-creation code has been copied from LoopSimplify, and after we decide on where it belongs, this code will be refactored so that it can be explicitly shared (making this implementation even smaller). The new test-case files ctrloop-{le,lt,ne}.ll have been adapted from tests for the new Hexagon pass. There are a few classes of loops that this pass does not transform (noted by FIXMEs in the files), but these deficiencies can be addressed within the SE infrastructure (thus helping many other passes as well). llvm-svn: 181927
2013-05-16 05:37:41 +08:00
// If a nested loop has been converted, then we can't convert this loop.
if (MadeChange)
return MadeChange;
#ifndef NDEBUG
// Stop trying after reaching the limit (if any).
int Limit = CTRLoopLimit;
if (Limit >= 0) {
if (Counter >= CTRLoopLimit)
return false;
Counter++;
}
#endif
// We don't want to spill/restore the counter register, and so we don't
// want to use the counter register if the loop contains calls.
for (Loop::block_iterator I = L->block_begin(), IE = L->block_end();
Create an new preheader in PPCCTRLoops to avoid counter register clobbers Some IR-level instructions (such as FP <-> i64 conversions) are not chained w.r.t. the mtctr intrinsic and yet may become function calls that clobber the counter register. At the selection-DAG level, these might be reordered with the mtctr intrinsic causing miscompiles. To avoid this situation, if an existing preheader has instructions that might use the counter register, create a new preheader for the mtctr intrinsic. This extra block will be remerged with the old preheader at the MI level, but will prevent unwanted reordering at the selection-DAG level. llvm-svn: 182045
2013-05-17 03:58:38 +08:00
I != IE; ++I)
if (mightUseCTR(TT, *I))
return MadeChange;
Add the PPCCTRLoops pass: a PPC machine-code-level optimization pass to form CTR-based loop branching code. This pass is derived from the Hexagon HardwareLoops pass. The only significant enhancement over the Hexagon pass is that PPCCTRLoops will also attempt to delete the replaced add and compare operations if they are no longer otherwise used. Also, invalid preheader DebugLoc is not used. llvm-svn: 158204
2012-06-08 23:38:21 +08:00
Implement PPC counter loops as a late IR-level pass The old PPCCTRLoops pass, like the Hexagon pass version from which it was derived, could only handle some simple loops in canonical form. We cannot directly adapt the new Hexagon hardware loops pass, however, because the Hexagon pass contains a fundamental assumption that non-constant-trip-count loops will contain a guard, and this is not always true (the result being that incorrect negative counts can be generated). With this commit, we replace the pass with a late IR-level pass which makes use of SE to calculate the backedge-taken counts and safely generate the loop-count expressions (including any necessary max() parts). This IR level pass inserts custom intrinsics that are lowered into the desired decrement-and-branch instructions. The most fragile part of this new implementation is that interfering uses of the counter register must be detected on the IR level (and, on PPC, this also includes any indirect branches in addition to function calls). Also, to make all of this work, we need a variant of the mtctr instruction that is marked as having side effects. Without this, machine-code level CSE, DCE, etc. illegally transform the resulting code. Hopefully, this can be improved in the future. This new pass is smaller than the original (and much smaller than the new Hexagon hardware loops pass), and can handle many additional cases correctly. In addition, the preheader-creation code has been copied from LoopSimplify, and after we decide on where it belongs, this code will be refactored so that it can be explicitly shared (making this implementation even smaller). The new test-case files ctrloop-{le,lt,ne}.ll have been adapted from tests for the new Hexagon pass. There are a few classes of loops that this pass does not transform (noted by FIXMEs in the files), but these deficiencies can be addressed within the SE infrastructure (thus helping many other passes as well). llvm-svn: 181927
2013-05-16 05:37:41 +08:00
SmallVector<BasicBlock*, 4> ExitingBlocks;
L->getExitingBlocks(ExitingBlocks);
[C++] Use 'nullptr'. Target edition. llvm-svn: 207197
2014-04-25 13:30:21 +08:00
BasicBlock *CountedExitBlock = nullptr;
const SCEV *ExitCount = nullptr;
BranchInst *CountedExitBranch = nullptr;
Use SmallVectorImpl::iterator/const_iterator instead of SmallVector to avoid specifying the vector size. llvm-svn: 185606
2013-07-04 09:31:24 +08:00
for (SmallVectorImpl<BasicBlock *>::iterator I = ExitingBlocks.begin(),
Implement PPC counter loops as a late IR-level pass The old PPCCTRLoops pass, like the Hexagon pass version from which it was derived, could only handle some simple loops in canonical form. We cannot directly adapt the new Hexagon hardware loops pass, however, because the Hexagon pass contains a fundamental assumption that non-constant-trip-count loops will contain a guard, and this is not always true (the result being that incorrect negative counts can be generated). With this commit, we replace the pass with a late IR-level pass which makes use of SE to calculate the backedge-taken counts and safely generate the loop-count expressions (including any necessary max() parts). This IR level pass inserts custom intrinsics that are lowered into the desired decrement-and-branch instructions. The most fragile part of this new implementation is that interfering uses of the counter register must be detected on the IR level (and, on PPC, this also includes any indirect branches in addition to function calls). Also, to make all of this work, we need a variant of the mtctr instruction that is marked as having side effects. Without this, machine-code level CSE, DCE, etc. illegally transform the resulting code. Hopefully, this can be improved in the future. This new pass is smaller than the original (and much smaller than the new Hexagon hardware loops pass), and can handle many additional cases correctly. In addition, the preheader-creation code has been copied from LoopSimplify, and after we decide on where it belongs, this code will be refactored so that it can be explicitly shared (making this implementation even smaller). The new test-case files ctrloop-{le,lt,ne}.ll have been adapted from tests for the new Hexagon pass. There are a few classes of loops that this pass does not transform (noted by FIXMEs in the files), but these deficiencies can be addressed within the SE infrastructure (thus helping many other passes as well). llvm-svn: 181927
2013-05-16 05:37:41 +08:00
IE = ExitingBlocks.end(); I != IE; ++I) {
const SCEV *EC = SE->getExitCount(L, *I);
DEBUG(dbgs() << "Exit Count for " << *L << " from block " <<
(*I)->getName() << ": " << *EC << "\n");
if (isa<SCEVCouldNotCompute>(EC))
continue;
if (const SCEVConstant *ConstEC = dyn_cast<SCEVConstant>(EC)) {
if (ConstEC->getValue()->isZero())
continue;
} else if (!SE->isLoopInvariant(EC, L))
continue;
Don't form PPC CTR loops for over-sized exit counts Although you can't generate this from C on PPC64, if you have a loop using a 64-bit counter on PPC32 then you can't form a CTR-based loop for it. This had been cauing the PPCCTRLoops pass to assert. Thanks to Joerg Sonnenberger for providing a test case! llvm-svn: 185361
2013-07-02 03:34:59 +08:00
if (SE->getTypeSizeInBits(EC->getType()) > (TT.isArch64Bit() ? 64 : 32))
continue;
Implement PPC counter loops as a late IR-level pass The old PPCCTRLoops pass, like the Hexagon pass version from which it was derived, could only handle some simple loops in canonical form. We cannot directly adapt the new Hexagon hardware loops pass, however, because the Hexagon pass contains a fundamental assumption that non-constant-trip-count loops will contain a guard, and this is not always true (the result being that incorrect negative counts can be generated). With this commit, we replace the pass with a late IR-level pass which makes use of SE to calculate the backedge-taken counts and safely generate the loop-count expressions (including any necessary max() parts). This IR level pass inserts custom intrinsics that are lowered into the desired decrement-and-branch instructions. The most fragile part of this new implementation is that interfering uses of the counter register must be detected on the IR level (and, on PPC, this also includes any indirect branches in addition to function calls). Also, to make all of this work, we need a variant of the mtctr instruction that is marked as having side effects. Without this, machine-code level CSE, DCE, etc. illegally transform the resulting code. Hopefully, this can be improved in the future. This new pass is smaller than the original (and much smaller than the new Hexagon hardware loops pass), and can handle many additional cases correctly. In addition, the preheader-creation code has been copied from LoopSimplify, and after we decide on where it belongs, this code will be refactored so that it can be explicitly shared (making this implementation even smaller). The new test-case files ctrloop-{le,lt,ne}.ll have been adapted from tests for the new Hexagon pass. There are a few classes of loops that this pass does not transform (noted by FIXMEs in the files), but these deficiencies can be addressed within the SE infrastructure (thus helping many other passes as well). llvm-svn: 181927
2013-05-16 05:37:41 +08:00
// We now have a loop-invariant count of loop iterations (which is not the
// constant zero) for which we know that this loop will not exit via this
// exisiting block.
// We need to make sure that this block will run on every loop iteration.
// For this to be true, we must dominate all blocks with backedges. Such
// blocks are in-loop predecessors to the header block.
bool NotAlways = false;
for (pred_iterator PI = pred_begin(L->getHeader()),
PIE = pred_end(L->getHeader()); PI != PIE; ++PI) {
if (!L->contains(*PI))
continue;
Add the PPCCTRLoops pass: a PPC machine-code-level optimization pass to form CTR-based loop branching code. This pass is derived from the Hexagon HardwareLoops pass. The only significant enhancement over the Hexagon pass is that PPCCTRLoops will also attempt to delete the replaced add and compare operations if they are no longer otherwise used. Also, invalid preheader DebugLoc is not used. llvm-svn: 158204
2012-06-08 23:38:21 +08:00
Implement PPC counter loops as a late IR-level pass The old PPCCTRLoops pass, like the Hexagon pass version from which it was derived, could only handle some simple loops in canonical form. We cannot directly adapt the new Hexagon hardware loops pass, however, because the Hexagon pass contains a fundamental assumption that non-constant-trip-count loops will contain a guard, and this is not always true (the result being that incorrect negative counts can be generated). With this commit, we replace the pass with a late IR-level pass which makes use of SE to calculate the backedge-taken counts and safely generate the loop-count expressions (including any necessary max() parts). This IR level pass inserts custom intrinsics that are lowered into the desired decrement-and-branch instructions. The most fragile part of this new implementation is that interfering uses of the counter register must be detected on the IR level (and, on PPC, this also includes any indirect branches in addition to function calls). Also, to make all of this work, we need a variant of the mtctr instruction that is marked as having side effects. Without this, machine-code level CSE, DCE, etc. illegally transform the resulting code. Hopefully, this can be improved in the future. This new pass is smaller than the original (and much smaller than the new Hexagon hardware loops pass), and can handle many additional cases correctly. In addition, the preheader-creation code has been copied from LoopSimplify, and after we decide on where it belongs, this code will be refactored so that it can be explicitly shared (making this implementation even smaller). The new test-case files ctrloop-{le,lt,ne}.ll have been adapted from tests for the new Hexagon pass. There are a few classes of loops that this pass does not transform (noted by FIXMEs in the files), but these deficiencies can be addressed within the SE infrastructure (thus helping many other passes as well). llvm-svn: 181927
2013-05-16 05:37:41 +08:00
if (!DT->dominates(*I, *PI)) {
NotAlways = true;
break;
Add the PPCCTRLoops pass: a PPC machine-code-level optimization pass to form CTR-based loop branching code. This pass is derived from the Hexagon HardwareLoops pass. The only significant enhancement over the Hexagon pass is that PPCCTRLoops will also attempt to delete the replaced add and compare operations if they are no longer otherwise used. Also, invalid preheader DebugLoc is not used. llvm-svn: 158204
2012-06-08 23:38:21 +08:00
}
}
Implement PPC counter loops as a late IR-level pass The old PPCCTRLoops pass, like the Hexagon pass version from which it was derived, could only handle some simple loops in canonical form. We cannot directly adapt the new Hexagon hardware loops pass, however, because the Hexagon pass contains a fundamental assumption that non-constant-trip-count loops will contain a guard, and this is not always true (the result being that incorrect negative counts can be generated). With this commit, we replace the pass with a late IR-level pass which makes use of SE to calculate the backedge-taken counts and safely generate the loop-count expressions (including any necessary max() parts). This IR level pass inserts custom intrinsics that are lowered into the desired decrement-and-branch instructions. The most fragile part of this new implementation is that interfering uses of the counter register must be detected on the IR level (and, on PPC, this also includes any indirect branches in addition to function calls). Also, to make all of this work, we need a variant of the mtctr instruction that is marked as having side effects. Without this, machine-code level CSE, DCE, etc. illegally transform the resulting code. Hopefully, this can be improved in the future. This new pass is smaller than the original (and much smaller than the new Hexagon hardware loops pass), and can handle many additional cases correctly. In addition, the preheader-creation code has been copied from LoopSimplify, and after we decide on where it belongs, this code will be refactored so that it can be explicitly shared (making this implementation even smaller). The new test-case files ctrloop-{le,lt,ne}.ll have been adapted from tests for the new Hexagon pass. There are a few classes of loops that this pass does not transform (noted by FIXMEs in the files), but these deficiencies can be addressed within the SE infrastructure (thus helping many other passes as well). llvm-svn: 181927
2013-05-16 05:37:41 +08:00
if (NotAlways)
continue;
Add the PPCCTRLoops pass: a PPC machine-code-level optimization pass to form CTR-based loop branching code. This pass is derived from the Hexagon HardwareLoops pass. The only significant enhancement over the Hexagon pass is that PPCCTRLoops will also attempt to delete the replaced add and compare operations if they are no longer otherwise used. Also, invalid preheader DebugLoc is not used. llvm-svn: 158204
2012-06-08 23:38:21 +08:00
Implement PPC counter loops as a late IR-level pass The old PPCCTRLoops pass, like the Hexagon pass version from which it was derived, could only handle some simple loops in canonical form. We cannot directly adapt the new Hexagon hardware loops pass, however, because the Hexagon pass contains a fundamental assumption that non-constant-trip-count loops will contain a guard, and this is not always true (the result being that incorrect negative counts can be generated). With this commit, we replace the pass with a late IR-level pass which makes use of SE to calculate the backedge-taken counts and safely generate the loop-count expressions (including any necessary max() parts). This IR level pass inserts custom intrinsics that are lowered into the desired decrement-and-branch instructions. The most fragile part of this new implementation is that interfering uses of the counter register must be detected on the IR level (and, on PPC, this also includes any indirect branches in addition to function calls). Also, to make all of this work, we need a variant of the mtctr instruction that is marked as having side effects. Without this, machine-code level CSE, DCE, etc. illegally transform the resulting code. Hopefully, this can be improved in the future. This new pass is smaller than the original (and much smaller than the new Hexagon hardware loops pass), and can handle many additional cases correctly. In addition, the preheader-creation code has been copied from LoopSimplify, and after we decide on where it belongs, this code will be refactored so that it can be explicitly shared (making this implementation even smaller). The new test-case files ctrloop-{le,lt,ne}.ll have been adapted from tests for the new Hexagon pass. There are a few classes of loops that this pass does not transform (noted by FIXMEs in the files), but these deficiencies can be addressed within the SE infrastructure (thus helping many other passes as well). llvm-svn: 181927
2013-05-16 05:37:41 +08:00
// Make sure this blocks ends with a conditional branch.
Instruction *TI = (*I)->getTerminator();
if (!TI)
continue;
Add the PPCCTRLoops pass: a PPC machine-code-level optimization pass to form CTR-based loop branching code. This pass is derived from the Hexagon HardwareLoops pass. The only significant enhancement over the Hexagon pass is that PPCCTRLoops will also attempt to delete the replaced add and compare operations if they are no longer otherwise used. Also, invalid preheader DebugLoc is not used. llvm-svn: 158204
2012-06-08 23:38:21 +08:00
Implement PPC counter loops as a late IR-level pass The old PPCCTRLoops pass, like the Hexagon pass version from which it was derived, could only handle some simple loops in canonical form. We cannot directly adapt the new Hexagon hardware loops pass, however, because the Hexagon pass contains a fundamental assumption that non-constant-trip-count loops will contain a guard, and this is not always true (the result being that incorrect negative counts can be generated). With this commit, we replace the pass with a late IR-level pass which makes use of SE to calculate the backedge-taken counts and safely generate the loop-count expressions (including any necessary max() parts). This IR level pass inserts custom intrinsics that are lowered into the desired decrement-and-branch instructions. The most fragile part of this new implementation is that interfering uses of the counter register must be detected on the IR level (and, on PPC, this also includes any indirect branches in addition to function calls). Also, to make all of this work, we need a variant of the mtctr instruction that is marked as having side effects. Without this, machine-code level CSE, DCE, etc. illegally transform the resulting code. Hopefully, this can be improved in the future. This new pass is smaller than the original (and much smaller than the new Hexagon hardware loops pass), and can handle many additional cases correctly. In addition, the preheader-creation code has been copied from LoopSimplify, and after we decide on where it belongs, this code will be refactored so that it can be explicitly shared (making this implementation even smaller). The new test-case files ctrloop-{le,lt,ne}.ll have been adapted from tests for the new Hexagon pass. There are a few classes of loops that this pass does not transform (noted by FIXMEs in the files), but these deficiencies can be addressed within the SE infrastructure (thus helping many other passes as well). llvm-svn: 181927
2013-05-16 05:37:41 +08:00
if (BranchInst *BI = dyn_cast<BranchInst>(TI)) {
if (!BI->isConditional())
Add the PPCCTRLoops pass: a PPC machine-code-level optimization pass to form CTR-based loop branching code. This pass is derived from the Hexagon HardwareLoops pass. The only significant enhancement over the Hexagon pass is that PPCCTRLoops will also attempt to delete the replaced add and compare operations if they are no longer otherwise used. Also, invalid preheader DebugLoc is not used. llvm-svn: 158204
2012-06-08 23:38:21 +08:00
continue;
Implement PPC counter loops as a late IR-level pass The old PPCCTRLoops pass, like the Hexagon pass version from which it was derived, could only handle some simple loops in canonical form. We cannot directly adapt the new Hexagon hardware loops pass, however, because the Hexagon pass contains a fundamental assumption that non-constant-trip-count loops will contain a guard, and this is not always true (the result being that incorrect negative counts can be generated). With this commit, we replace the pass with a late IR-level pass which makes use of SE to calculate the backedge-taken counts and safely generate the loop-count expressions (including any necessary max() parts). This IR level pass inserts custom intrinsics that are lowered into the desired decrement-and-branch instructions. The most fragile part of this new implementation is that interfering uses of the counter register must be detected on the IR level (and, on PPC, this also includes any indirect branches in addition to function calls). Also, to make all of this work, we need a variant of the mtctr instruction that is marked as having side effects. Without this, machine-code level CSE, DCE, etc. illegally transform the resulting code. Hopefully, this can be improved in the future. This new pass is smaller than the original (and much smaller than the new Hexagon hardware loops pass), and can handle many additional cases correctly. In addition, the preheader-creation code has been copied from LoopSimplify, and after we decide on where it belongs, this code will be refactored so that it can be explicitly shared (making this implementation even smaller). The new test-case files ctrloop-{le,lt,ne}.ll have been adapted from tests for the new Hexagon pass. There are a few classes of loops that this pass does not transform (noted by FIXMEs in the files), but these deficiencies can be addressed within the SE infrastructure (thus helping many other passes as well). llvm-svn: 181927
2013-05-16 05:37:41 +08:00
CountedExitBranch = BI;
} else
continue;
Add the PPCCTRLoops pass: a PPC machine-code-level optimization pass to form CTR-based loop branching code. This pass is derived from the Hexagon HardwareLoops pass. The only significant enhancement over the Hexagon pass is that PPCCTRLoops will also attempt to delete the replaced add and compare operations if they are no longer otherwise used. Also, invalid preheader DebugLoc is not used. llvm-svn: 158204
2012-06-08 23:38:21 +08:00
Implement PPC counter loops as a late IR-level pass The old PPCCTRLoops pass, like the Hexagon pass version from which it was derived, could only handle some simple loops in canonical form. We cannot directly adapt the new Hexagon hardware loops pass, however, because the Hexagon pass contains a fundamental assumption that non-constant-trip-count loops will contain a guard, and this is not always true (the result being that incorrect negative counts can be generated). With this commit, we replace the pass with a late IR-level pass which makes use of SE to calculate the backedge-taken counts and safely generate the loop-count expressions (including any necessary max() parts). This IR level pass inserts custom intrinsics that are lowered into the desired decrement-and-branch instructions. The most fragile part of this new implementation is that interfering uses of the counter register must be detected on the IR level (and, on PPC, this also includes any indirect branches in addition to function calls). Also, to make all of this work, we need a variant of the mtctr instruction that is marked as having side effects. Without this, machine-code level CSE, DCE, etc. illegally transform the resulting code. Hopefully, this can be improved in the future. This new pass is smaller than the original (and much smaller than the new Hexagon hardware loops pass), and can handle many additional cases correctly. In addition, the preheader-creation code has been copied from LoopSimplify, and after we decide on where it belongs, this code will be refactored so that it can be explicitly shared (making this implementation even smaller). The new test-case files ctrloop-{le,lt,ne}.ll have been adapted from tests for the new Hexagon pass. There are a few classes of loops that this pass does not transform (noted by FIXMEs in the files), but these deficiencies can be addressed within the SE infrastructure (thus helping many other passes as well). llvm-svn: 181927
2013-05-16 05:37:41 +08:00
// Note that this block may not be the loop latch block, even if the loop
// has a latch block.
CountedExitBlock = *I;
ExitCount = EC;
break;
Add the PPCCTRLoops pass: a PPC machine-code-level optimization pass to form CTR-based loop branching code. This pass is derived from the Hexagon HardwareLoops pass. The only significant enhancement over the Hexagon pass is that PPCCTRLoops will also attempt to delete the replaced add and compare operations if they are no longer otherwise used. Also, invalid preheader DebugLoc is not used. llvm-svn: 158204
2012-06-08 23:38:21 +08:00
}
Implement PPC counter loops as a late IR-level pass The old PPCCTRLoops pass, like the Hexagon pass version from which it was derived, could only handle some simple loops in canonical form. We cannot directly adapt the new Hexagon hardware loops pass, however, because the Hexagon pass contains a fundamental assumption that non-constant-trip-count loops will contain a guard, and this is not always true (the result being that incorrect negative counts can be generated). With this commit, we replace the pass with a late IR-level pass which makes use of SE to calculate the backedge-taken counts and safely generate the loop-count expressions (including any necessary max() parts). This IR level pass inserts custom intrinsics that are lowered into the desired decrement-and-branch instructions. The most fragile part of this new implementation is that interfering uses of the counter register must be detected on the IR level (and, on PPC, this also includes any indirect branches in addition to function calls). Also, to make all of this work, we need a variant of the mtctr instruction that is marked as having side effects. Without this, machine-code level CSE, DCE, etc. illegally transform the resulting code. Hopefully, this can be improved in the future. This new pass is smaller than the original (and much smaller than the new Hexagon hardware loops pass), and can handle many additional cases correctly. In addition, the preheader-creation code has been copied from LoopSimplify, and after we decide on where it belongs, this code will be refactored so that it can be explicitly shared (making this implementation even smaller). The new test-case files ctrloop-{le,lt,ne}.ll have been adapted from tests for the new Hexagon pass. There are a few classes of loops that this pass does not transform (noted by FIXMEs in the files), but these deficiencies can be addressed within the SE infrastructure (thus helping many other passes as well). llvm-svn: 181927
2013-05-16 05:37:41 +08:00
if (!CountedExitBlock)
return MadeChange;
BasicBlock *Preheader = L->getLoopPreheader();
Create an new preheader in PPCCTRLoops to avoid counter register clobbers Some IR-level instructions (such as FP <-> i64 conversions) are not chained w.r.t. the mtctr intrinsic and yet may become function calls that clobber the counter register. At the selection-DAG level, these might be reordered with the mtctr intrinsic causing miscompiles. To avoid this situation, if an existing preheader has instructions that might use the counter register, create a new preheader for the mtctr intrinsic. This extra block will be remerged with the old preheader at the MI level, but will prevent unwanted reordering at the selection-DAG level. llvm-svn: 182045
2013-05-17 03:58:38 +08:00
// If we don't have a preheader, then insert one. If we already have a
// preheader, then we can use it (except if the preheader contains a use of
// the CTR register because some such uses might be reordered by the
// selection DAG after the mtctr instruction).
if (!Preheader || mightUseCTR(TT, Preheader))
Remove copied preheader insertion logic from PPCCTRLoops Now that the preheader insertion logic in LoopSimplify is externally exposed, use it, and remove the copy-and-pasted version. No functionality change intended. llvm-svn: 182300
2013-05-21 00:47:10 +08:00
Preheader = InsertPreheaderForLoop(L, this);
Implement PPC counter loops as a late IR-level pass The old PPCCTRLoops pass, like the Hexagon pass version from which it was derived, could only handle some simple loops in canonical form. We cannot directly adapt the new Hexagon hardware loops pass, however, because the Hexagon pass contains a fundamental assumption that non-constant-trip-count loops will contain a guard, and this is not always true (the result being that incorrect negative counts can be generated). With this commit, we replace the pass with a late IR-level pass which makes use of SE to calculate the backedge-taken counts and safely generate the loop-count expressions (including any necessary max() parts). This IR level pass inserts custom intrinsics that are lowered into the desired decrement-and-branch instructions. The most fragile part of this new implementation is that interfering uses of the counter register must be detected on the IR level (and, on PPC, this also includes any indirect branches in addition to function calls). Also, to make all of this work, we need a variant of the mtctr instruction that is marked as having side effects. Without this, machine-code level CSE, DCE, etc. illegally transform the resulting code. Hopefully, this can be improved in the future. This new pass is smaller than the original (and much smaller than the new Hexagon hardware loops pass), and can handle many additional cases correctly. In addition, the preheader-creation code has been copied from LoopSimplify, and after we decide on where it belongs, this code will be refactored so that it can be explicitly shared (making this implementation even smaller). The new test-case files ctrloop-{le,lt,ne}.ll have been adapted from tests for the new Hexagon pass. There are a few classes of loops that this pass does not transform (noted by FIXMEs in the files), but these deficiencies can be addressed within the SE infrastructure (thus helping many other passes as well). llvm-svn: 181927
2013-05-16 05:37:41 +08:00
if (!Preheader)
return MadeChange;
DEBUG(dbgs() << "Preheader for exit count: " << Preheader->getName() << "\n");
// Insert the count into the preheader and replace the condition used by the
// selected branch.
MadeChange = true;
SCEVExpander SCEVE(*SE, "loopcnt");
LLVMContext &C = SE->getContext();
Type *CountType = TT.isArch64Bit() ? Type::getInt64Ty(C) :
Type::getInt32Ty(C);
if (!ExitCount->getType()->isPointerTy() &&
ExitCount->getType() != CountType)
ExitCount = SE->getZeroExtendExpr(ExitCount, CountType);
ExitCount = SE->getAddExpr(ExitCount,
SE->getConstant(CountType, 1));
Value *ECValue = SCEVE.expandCodeFor(ExitCount, CountType,
Preheader->getTerminator());
IRBuilder<> CountBuilder(Preheader->getTerminator());
Module *M = Preheader->getParent()->getParent();
Value *MTCTRFunc = Intrinsic::getDeclaration(M, Intrinsic::ppc_mtctr,
CountType);
CountBuilder.CreateCall(MTCTRFunc, ECValue);
IRBuilder<> CondBuilder(CountedExitBranch);
Value *DecFunc =
Intrinsic::getDeclaration(M, Intrinsic::ppc_is_decremented_ctr_nonzero);
Value *NewCond = CondBuilder.CreateCall(DecFunc);
Value *OldCond = CountedExitBranch->getCondition();
CountedExitBranch->setCondition(NewCond);
// The false branch must exit the loop.
if (!L->contains(CountedExitBranch->getSuccessor(0)))
CountedExitBranch->swapSuccessors();
// The old condition may be dead now, and may have even created a dead PHI
// (the original induction variable).
RecursivelyDeleteTriviallyDeadInstructions(OldCond);
DeleteDeadPHIs(CountedExitBlock);
Fix large count and negative constant count handling in PPCCTRLoops This commit fixes an assert that would occur on loops with large constant counts (like looping for ((uint32_t) -1) iterations on PPC64). The existing code did not handle counts that it computed to be negative (asserting instead), but these can be created with valid inputs. This bug was discovered by bugpoint while I was attempting to isolate a completely different problem. Also, in writing test cases for the negative-count problem, I discovered that the ori/lsi handling was broken (there was a typo which caused the logic that was supposed to detect these pairs and extract the iteration count to always fail). This has now also been corrected (and is covered by one of the new test cases). llvm-svn: 177295
2013-03-19 01:40:44 +08:00
Implement PPC counter loops as a late IR-level pass The old PPCCTRLoops pass, like the Hexagon pass version from which it was derived, could only handle some simple loops in canonical form. We cannot directly adapt the new Hexagon hardware loops pass, however, because the Hexagon pass contains a fundamental assumption that non-constant-trip-count loops will contain a guard, and this is not always true (the result being that incorrect negative counts can be generated). With this commit, we replace the pass with a late IR-level pass which makes use of SE to calculate the backedge-taken counts and safely generate the loop-count expressions (including any necessary max() parts). This IR level pass inserts custom intrinsics that are lowered into the desired decrement-and-branch instructions. The most fragile part of this new implementation is that interfering uses of the counter register must be detected on the IR level (and, on PPC, this also includes any indirect branches in addition to function calls). Also, to make all of this work, we need a variant of the mtctr instruction that is marked as having side effects. Without this, machine-code level CSE, DCE, etc. illegally transform the resulting code. Hopefully, this can be improved in the future. This new pass is smaller than the original (and much smaller than the new Hexagon hardware loops pass), and can handle many additional cases correctly. In addition, the preheader-creation code has been copied from LoopSimplify, and after we decide on where it belongs, this code will be refactored so that it can be explicitly shared (making this implementation even smaller). The new test-case files ctrloop-{le,lt,ne}.ll have been adapted from tests for the new Hexagon pass. There are a few classes of loops that this pass does not transform (noted by FIXMEs in the files), but these deficiencies can be addressed within the SE infrastructure (thus helping many other passes as well). llvm-svn: 181927
2013-05-16 05:37:41 +08:00
++NumCTRLoops;
return MadeChange;
}
Fix large count and negative constant count handling in PPCCTRLoops This commit fixes an assert that would occur on loops with large constant counts (like looping for ((uint32_t) -1) iterations on PPC64). The existing code did not handle counts that it computed to be negative (asserting instead), but these can be created with valid inputs. This bug was discovered by bugpoint while I was attempting to isolate a completely different problem. Also, in writing test cases for the negative-count problem, I discovered that the ori/lsi handling was broken (there was a typo which caused the logic that was supposed to detect these pairs and extract the iteration count to always fail). This has now also been corrected (and is covered by one of the new test cases). llvm-svn: 177295
2013-03-19 01:40:44 +08:00
Add a PPCCTRLoops verification pass When asserts are enabled, this adds a verification pass for PPC counter-loop formation. Unfortunately, without sacrificing code quality, there is no better way of forming counter-based loops except at the (late) IR level. This means that we need to recognize, at the IR level, anything which might turn into a function call (or indirect branch). Because this is currently a finite set of things, and because SelectionDAG lowering is basic-block local, this can be done. Nevertheless, it is fragile, and failure results in a miscompile. This verification pass checks that all (reachable) counter-based branches are dominated by a loop mtctr instruction, and that no instructions in between clobber the counter register. If these conditions are not satisfied, then an ICE will be triggered. In short, this is to help us sleep better at night. llvm-svn: 182295
2013-05-21 00:08:17 +08:00
#ifndef NDEBUG
static bool clobbersCTR(const MachineInstr *MI) {
for (unsigned i = 0, e = MI->getNumOperands(); i != e; ++i) {
const MachineOperand &MO = MI->getOperand(i);
if (MO.isReg()) {
if (MO.isDef() && (MO.getReg() == PPC::CTR || MO.getReg() == PPC::CTR8))
return true;
} else if (MO.isRegMask()) {
if (MO.clobbersPhysReg(PPC::CTR) || MO.clobbersPhysReg(PPC::CTR8))
return true;
}
}
return false;
}
static bool verifyCTRBranch(MachineBasicBlock *MBB,
MachineBasicBlock::iterator I) {
MachineBasicBlock::iterator BI = I;
SmallSet<MachineBasicBlock *, 16> Visited;
SmallVector<MachineBasicBlock *, 8> Preds;
bool CheckPreds;
if (I == MBB->begin()) {
Visited.insert(MBB);
goto queue_preds;
} else
--I;
check_block:
Visited.insert(MBB);
if (I == MBB->end())
goto queue_preds;
CheckPreds = true;
for (MachineBasicBlock::iterator IE = MBB->begin();; --I) {
unsigned Opc = I->getOpcode();
Rename PPC MTCTRse to MTCTRloop As the pairing of this instruction form with the bdnz/bdz branches is now enforced by the verification pass, make it clear from the name that these are used only for counter-based loops. No functionality change intended. llvm-svn: 182296
2013-05-21 00:08:37 +08:00
if (Opc == PPC::MTCTRloop || Opc == PPC::MTCTR8loop) {
Add a PPCCTRLoops verification pass When asserts are enabled, this adds a verification pass for PPC counter-loop formation. Unfortunately, without sacrificing code quality, there is no better way of forming counter-based loops except at the (late) IR level. This means that we need to recognize, at the IR level, anything which might turn into a function call (or indirect branch). Because this is currently a finite set of things, and because SelectionDAG lowering is basic-block local, this can be done. Nevertheless, it is fragile, and failure results in a miscompile. This verification pass checks that all (reachable) counter-based branches are dominated by a loop mtctr instruction, and that no instructions in between clobber the counter register. If these conditions are not satisfied, then an ICE will be triggered. In short, this is to help us sleep better at night. llvm-svn: 182295
2013-05-21 00:08:17 +08:00
CheckPreds = false;
break;
}
if (I != BI && clobbersCTR(I)) {
DEBUG(dbgs() << "BB#" << MBB->getNumber() << " (" <<
MBB->getFullName() << ") instruction " << *I <<
" clobbers CTR, invalidating " << "BB#" <<
BI->getParent()->getNumber() << " (" <<
BI->getParent()->getFullName() << ") instruction " <<
*BI << "\n");
return false;
}
if (I == IE)
break;
}
if (!CheckPreds && Preds.empty())
return true;
if (CheckPreds) {
queue_preds:
if (MachineFunction::iterator(MBB) == MBB->getParent()->begin()) {
DEBUG(dbgs() << "Unable to find a MTCTR instruction for BB#" <<
BI->getParent()->getNumber() << " (" <<
BI->getParent()->getFullName() << ") instruction " <<
*BI << "\n");
return false;
}
for (MachineBasicBlock::pred_iterator PI = MBB->pred_begin(),
PIE = MBB->pred_end(); PI != PIE; ++PI)
Preds.push_back(*PI);
}
do {
MBB = Preds.pop_back_val();
if (!Visited.count(MBB)) {
I = MBB->getLastNonDebugInstr();
goto check_block;
}
} while (!Preds.empty());
return true;
}
bool PPCCTRLoopsVerify::runOnMachineFunction(MachineFunction &MF) {
MDT = &getAnalysis<MachineDominatorTree>();
// Verify that all bdnz/bdz instructions are dominated by a loop mtctr before
// any other instructions that might clobber the ctr register.
for (MachineFunction::iterator I = MF.begin(), IE = MF.end();
I != IE; ++I) {
MachineBasicBlock *MBB = I;
if (!MDT->isReachableFromEntry(MBB))
continue;
for (MachineBasicBlock::iterator MII = MBB->getFirstTerminator(),
MIIE = MBB->end(); MII != MIIE; ++MII) {
unsigned Opc = MII->getOpcode();
if (Opc == PPC::BDNZ8 || Opc == PPC::BDNZ ||
Opc == PPC::BDZ8 || Opc == PPC::BDZ)
if (!verifyCTRBranch(MBB, MII))
llvm_unreachable("Invalid PPC CTR loop!");
}
}
return false;
}
#endif // NDEBUG