2010-08-03 07:49:30 +08:00
|
|
|
//===- ScalarEvolutionsTest.cpp - ScalarEvolution unit tests --------------===//
|
|
|
|
|
//
|
|
|
|
|
// The LLVM Compiler Infrastructure
|
|
|
|
|
//
|
|
|
|
|
// This file is distributed under the University of Illinois Open Source
|
|
|
|
|
// License. See LICENSE.TXT for details.
|
|
|
|
|
//
|
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
|
|
2017-05-27 11:22:55 +08:00
|
|
|
#include "llvm/ADT/SmallVector.h"
|
2016-12-19 16:22:17 +08:00
|
|
|
#include "llvm/Analysis/AssumptionCache.h"
|
[PM] Port ScalarEvolution to the new pass manager.
This change makes ScalarEvolution a stand-alone object and just produces
one from a pass as needed. Making this work well requires making the
object movable, using references instead of overwritten pointers in
a number of places, and other refactorings.
I've also wired it up to the new pass manager and added a RUN line to
a test to exercise it under the new pass manager. This includes basic
printing support much like with other analyses.
But there is a big and somewhat scary change here. Prior to this patch
ScalarEvolution was never *actually* invalidated!!! Re-running the pass
just re-wired up the various other analyses and didn't remove any of the
existing entries in the SCEV caches or clear out anything at all. This
might seem OK as everything in SCEV that can uses ValueHandles to track
updates to the values that serve as SCEV keys. However, this still means
that as we ran SCEV over each function in the module, we kept
accumulating more and more SCEVs into the cache. At the end, we would
have a SCEV cache with every value that we ever needed a SCEV for in the
entire module!!! Yowzers. The releaseMemory routine would dump all of
this, but that isn't realy called during normal runs of the pipeline as
far as I can see.
To make matters worse, there *is* actually a key that we don't update
with value handles -- there is a map keyed off of Loop*s. Because
LoopInfo *does* release its memory from run to run, it is entirely
possible to run SCEV over one function, then over another function, and
then lookup a Loop* from the second function but find an entry inserted
for the first function! Ouch.
To make matters still worse, there are plenty of updates that *don't*
trip a value handle. It seems incredibly unlikely that today GVN or
another pass that invalidates SCEV can update values in *just* such
a way that a subsequent run of SCEV will incorrectly find lookups in
a cache, but it is theoretically possible and would be a nightmare to
debug.
With this refactoring, I've fixed all this by actually destroying and
recreating the ScalarEvolution object from run to run. Technically, this
could increase the amount of malloc traffic we see, but then again it is
also technically correct. ;] I don't actually think we're suffering from
tons of malloc traffic from SCEV because if we were, the fact that we
never clear the memory would seem more likely to have come up as an
actual problem before now. So, I've made the simple fix here. If in fact
there are serious issues with too much allocation and deallocation,
I can work on a clever fix that preserves the allocations (while
clearing the data) between each run, but I'd prefer to do that kind of
optimization with a test case / benchmark that shows why we need such
cleverness (and that can test that we actually make it faster). It's
possible that this will make some things faster by making the SCEV
caches have higher locality (due to being significantly smaller) so
until there is a clear benchmark, I think the simple change is best.
Differential Revision: http://reviews.llvm.org/D12063
llvm-svn: 245193
2015-08-17 10:08:17 +08:00
|
|
|
#include "llvm/Analysis/LoopInfo.h"
|
2012-09-16 02:45:38 +08:00
|
|
|
#include "llvm/Analysis/LoopInfo.h"
|
2017-05-27 11:22:55 +08:00
|
|
|
#include "llvm/Analysis/ScalarEvolutionExpander.h"
|
|
|
|
|
#include "llvm/Analysis/ScalarEvolutionExpressions.h"
|
|
|
|
|
#include "llvm/Analysis/TargetLibraryInfo.h"
|
2016-10-19 01:45:16 +08:00
|
|
|
#include "llvm/AsmParser/Parser.h"
|
2013-01-02 19:36:10 +08:00
|
|
|
#include "llvm/IR/Constants.h"
|
[PM] Port ScalarEvolution to the new pass manager.
This change makes ScalarEvolution a stand-alone object and just produces
one from a pass as needed. Making this work well requires making the
object movable, using references instead of overwritten pointers in
a number of places, and other refactorings.
I've also wired it up to the new pass manager and added a RUN line to
a test to exercise it under the new pass manager. This includes basic
printing support much like with other analyses.
But there is a big and somewhat scary change here. Prior to this patch
ScalarEvolution was never *actually* invalidated!!! Re-running the pass
just re-wired up the various other analyses and didn't remove any of the
existing entries in the SCEV caches or clear out anything at all. This
might seem OK as everything in SCEV that can uses ValueHandles to track
updates to the values that serve as SCEV keys. However, this still means
that as we ran SCEV over each function in the module, we kept
accumulating more and more SCEVs into the cache. At the end, we would
have a SCEV cache with every value that we ever needed a SCEV for in the
entire module!!! Yowzers. The releaseMemory routine would dump all of
this, but that isn't realy called during normal runs of the pipeline as
far as I can see.
To make matters worse, there *is* actually a key that we don't update
with value handles -- there is a map keyed off of Loop*s. Because
LoopInfo *does* release its memory from run to run, it is entirely
possible to run SCEV over one function, then over another function, and
then lookup a Loop* from the second function but find an entry inserted
for the first function! Ouch.
To make matters still worse, there are plenty of updates that *don't*
trip a value handle. It seems incredibly unlikely that today GVN or
another pass that invalidates SCEV can update values in *just* such
a way that a subsequent run of SCEV will incorrectly find lookups in
a cache, but it is theoretically possible and would be a nightmare to
debug.
With this refactoring, I've fixed all this by actually destroying and
recreating the ScalarEvolution object from run to run. Technically, this
could increase the amount of malloc traffic we see, but then again it is
also technically correct. ;] I don't actually think we're suffering from
tons of malloc traffic from SCEV because if we were, the fact that we
never clear the memory would seem more likely to have come up as an
actual problem before now. So, I've made the simple fix here. If in fact
there are serious issues with too much allocation and deallocation,
I can work on a clever fix that preserves the allocations (while
clearing the data) between each run, but I'd prefer to do that kind of
optimization with a test case / benchmark that shows why we need such
cleverness (and that can test that we actually make it faster). It's
possible that this will make some things faster by making the SCEV
caches have higher locality (due to being significantly smaller) so
until there is a clear benchmark, I think the simple change is best.
Differential Revision: http://reviews.llvm.org/D12063
llvm-svn: 245193
2015-08-17 10:08:17 +08:00
|
|
|
#include "llvm/IR/Dominators.h"
|
2013-01-02 19:36:10 +08:00
|
|
|
#include "llvm/IR/GlobalVariable.h"
|
2017-05-27 11:22:55 +08:00
|
|
|
#include "llvm/IR/IRBuilder.h"
|
2016-10-19 01:45:16 +08:00
|
|
|
#include "llvm/IR/InstIterator.h"
|
2013-01-02 19:36:10 +08:00
|
|
|
#include "llvm/IR/LLVMContext.h"
|
2015-02-13 18:01:29 +08:00
|
|
|
#include "llvm/IR/LegacyPassManager.h"
|
2017-05-27 11:22:55 +08:00
|
|
|
#include "llvm/IR/Module.h"
|
2016-10-19 01:45:16 +08:00
|
|
|
#include "llvm/IR/Verifier.h"
|
|
|
|
|
#include "llvm/Support/SourceMgr.h"
|
2010-08-03 07:49:30 +08:00
|
|
|
#include "gtest/gtest.h"
|
|
|
|
|
|
|
|
|
|
namespace llvm {
|
|
|
|
|
namespace {
|
|
|
|
|
|
2011-10-04 14:51:26 +08:00
|
|
|
// We use this fixture to ensure that we clean up ScalarEvolution before
|
|
|
|
|
// deleting the PassManager.
|
|
|
|
|
class ScalarEvolutionsTest : public testing::Test {
|
|
|
|
|
protected:
|
2010-08-03 07:49:30 +08:00
|
|
|
LLVMContext Context;
|
2011-10-04 14:51:26 +08:00
|
|
|
Module M;
|
[PM] Port ScalarEvolution to the new pass manager.
This change makes ScalarEvolution a stand-alone object and just produces
one from a pass as needed. Making this work well requires making the
object movable, using references instead of overwritten pointers in
a number of places, and other refactorings.
I've also wired it up to the new pass manager and added a RUN line to
a test to exercise it under the new pass manager. This includes basic
printing support much like with other analyses.
But there is a big and somewhat scary change here. Prior to this patch
ScalarEvolution was never *actually* invalidated!!! Re-running the pass
just re-wired up the various other analyses and didn't remove any of the
existing entries in the SCEV caches or clear out anything at all. This
might seem OK as everything in SCEV that can uses ValueHandles to track
updates to the values that serve as SCEV keys. However, this still means
that as we ran SCEV over each function in the module, we kept
accumulating more and more SCEVs into the cache. At the end, we would
have a SCEV cache with every value that we ever needed a SCEV for in the
entire module!!! Yowzers. The releaseMemory routine would dump all of
this, but that isn't realy called during normal runs of the pipeline as
far as I can see.
To make matters worse, there *is* actually a key that we don't update
with value handles -- there is a map keyed off of Loop*s. Because
LoopInfo *does* release its memory from run to run, it is entirely
possible to run SCEV over one function, then over another function, and
then lookup a Loop* from the second function but find an entry inserted
for the first function! Ouch.
To make matters still worse, there are plenty of updates that *don't*
trip a value handle. It seems incredibly unlikely that today GVN or
another pass that invalidates SCEV can update values in *just* such
a way that a subsequent run of SCEV will incorrectly find lookups in
a cache, but it is theoretically possible and would be a nightmare to
debug.
With this refactoring, I've fixed all this by actually destroying and
recreating the ScalarEvolution object from run to run. Technically, this
could increase the amount of malloc traffic we see, but then again it is
also technically correct. ;] I don't actually think we're suffering from
tons of malloc traffic from SCEV because if we were, the fact that we
never clear the memory would seem more likely to have come up as an
actual problem before now. So, I've made the simple fix here. If in fact
there are serious issues with too much allocation and deallocation,
I can work on a clever fix that preserves the allocations (while
clearing the data) between each run, but I'd prefer to do that kind of
optimization with a test case / benchmark that shows why we need such
cleverness (and that can test that we actually make it faster). It's
possible that this will make some things faster by making the SCEV
caches have higher locality (due to being significantly smaller) so
until there is a clear benchmark, I think the simple change is best.
Differential Revision: http://reviews.llvm.org/D12063
llvm-svn: 245193
2015-08-17 10:08:17 +08:00
|
|
|
TargetLibraryInfoImpl TLII;
|
|
|
|
|
TargetLibraryInfo TLI;
|
|
|
|
|
|
2016-12-19 16:22:17 +08:00
|
|
|
std::unique_ptr<AssumptionCache> AC;
|
[PM] Port ScalarEvolution to the new pass manager.
This change makes ScalarEvolution a stand-alone object and just produces
one from a pass as needed. Making this work well requires making the
object movable, using references instead of overwritten pointers in
a number of places, and other refactorings.
I've also wired it up to the new pass manager and added a RUN line to
a test to exercise it under the new pass manager. This includes basic
printing support much like with other analyses.
But there is a big and somewhat scary change here. Prior to this patch
ScalarEvolution was never *actually* invalidated!!! Re-running the pass
just re-wired up the various other analyses and didn't remove any of the
existing entries in the SCEV caches or clear out anything at all. This
might seem OK as everything in SCEV that can uses ValueHandles to track
updates to the values that serve as SCEV keys. However, this still means
that as we ran SCEV over each function in the module, we kept
accumulating more and more SCEVs into the cache. At the end, we would
have a SCEV cache with every value that we ever needed a SCEV for in the
entire module!!! Yowzers. The releaseMemory routine would dump all of
this, but that isn't realy called during normal runs of the pipeline as
far as I can see.
To make matters worse, there *is* actually a key that we don't update
with value handles -- there is a map keyed off of Loop*s. Because
LoopInfo *does* release its memory from run to run, it is entirely
possible to run SCEV over one function, then over another function, and
then lookup a Loop* from the second function but find an entry inserted
for the first function! Ouch.
To make matters still worse, there are plenty of updates that *don't*
trip a value handle. It seems incredibly unlikely that today GVN or
another pass that invalidates SCEV can update values in *just* such
a way that a subsequent run of SCEV will incorrectly find lookups in
a cache, but it is theoretically possible and would be a nightmare to
debug.
With this refactoring, I've fixed all this by actually destroying and
recreating the ScalarEvolution object from run to run. Technically, this
could increase the amount of malloc traffic we see, but then again it is
also technically correct. ;] I don't actually think we're suffering from
tons of malloc traffic from SCEV because if we were, the fact that we
never clear the memory would seem more likely to have come up as an
actual problem before now. So, I've made the simple fix here. If in fact
there are serious issues with too much allocation and deallocation,
I can work on a clever fix that preserves the allocations (while
clearing the data) between each run, but I'd prefer to do that kind of
optimization with a test case / benchmark that shows why we need such
cleverness (and that can test that we actually make it faster). It's
possible that this will make some things faster by making the SCEV
caches have higher locality (due to being significantly smaller) so
until there is a clear benchmark, I think the simple change is best.
Differential Revision: http://reviews.llvm.org/D12063
llvm-svn: 245193
2015-08-17 10:08:17 +08:00
|
|
|
std::unique_ptr<DominatorTree> DT;
|
|
|
|
|
std::unique_ptr<LoopInfo> LI;
|
|
|
|
|
|
|
|
|
|
ScalarEvolutionsTest() : M("", Context), TLII(), TLI(TLII) {}
|
|
|
|
|
|
|
|
|
|
ScalarEvolution buildSE(Function &F) {
|
2016-12-19 16:22:17 +08:00
|
|
|
AC.reset(new AssumptionCache(F));
|
[PM] Port ScalarEvolution to the new pass manager.
This change makes ScalarEvolution a stand-alone object and just produces
one from a pass as needed. Making this work well requires making the
object movable, using references instead of overwritten pointers in
a number of places, and other refactorings.
I've also wired it up to the new pass manager and added a RUN line to
a test to exercise it under the new pass manager. This includes basic
printing support much like with other analyses.
But there is a big and somewhat scary change here. Prior to this patch
ScalarEvolution was never *actually* invalidated!!! Re-running the pass
just re-wired up the various other analyses and didn't remove any of the
existing entries in the SCEV caches or clear out anything at all. This
might seem OK as everything in SCEV that can uses ValueHandles to track
updates to the values that serve as SCEV keys. However, this still means
that as we ran SCEV over each function in the module, we kept
accumulating more and more SCEVs into the cache. At the end, we would
have a SCEV cache with every value that we ever needed a SCEV for in the
entire module!!! Yowzers. The releaseMemory routine would dump all of
this, but that isn't realy called during normal runs of the pipeline as
far as I can see.
To make matters worse, there *is* actually a key that we don't update
with value handles -- there is a map keyed off of Loop*s. Because
LoopInfo *does* release its memory from run to run, it is entirely
possible to run SCEV over one function, then over another function, and
then lookup a Loop* from the second function but find an entry inserted
for the first function! Ouch.
To make matters still worse, there are plenty of updates that *don't*
trip a value handle. It seems incredibly unlikely that today GVN or
another pass that invalidates SCEV can update values in *just* such
a way that a subsequent run of SCEV will incorrectly find lookups in
a cache, but it is theoretically possible and would be a nightmare to
debug.
With this refactoring, I've fixed all this by actually destroying and
recreating the ScalarEvolution object from run to run. Technically, this
could increase the amount of malloc traffic we see, but then again it is
also technically correct. ;] I don't actually think we're suffering from
tons of malloc traffic from SCEV because if we were, the fact that we
never clear the memory would seem more likely to have come up as an
actual problem before now. So, I've made the simple fix here. If in fact
there are serious issues with too much allocation and deallocation,
I can work on a clever fix that preserves the allocations (while
clearing the data) between each run, but I'd prefer to do that kind of
optimization with a test case / benchmark that shows why we need such
cleverness (and that can test that we actually make it faster). It's
possible that this will make some things faster by making the SCEV
caches have higher locality (due to being significantly smaller) so
until there is a clear benchmark, I think the simple change is best.
Differential Revision: http://reviews.llvm.org/D12063
llvm-svn: 245193
2015-08-17 10:08:17 +08:00
|
|
|
DT.reset(new DominatorTree(F));
|
|
|
|
|
LI.reset(new LoopInfo(*DT));
|
2016-12-19 16:22:17 +08:00
|
|
|
return ScalarEvolution(F, TLI, *AC, *DT, *LI);
|
[PM] Port ScalarEvolution to the new pass manager.
This change makes ScalarEvolution a stand-alone object and just produces
one from a pass as needed. Making this work well requires making the
object movable, using references instead of overwritten pointers in
a number of places, and other refactorings.
I've also wired it up to the new pass manager and added a RUN line to
a test to exercise it under the new pass manager. This includes basic
printing support much like with other analyses.
But there is a big and somewhat scary change here. Prior to this patch
ScalarEvolution was never *actually* invalidated!!! Re-running the pass
just re-wired up the various other analyses and didn't remove any of the
existing entries in the SCEV caches or clear out anything at all. This
might seem OK as everything in SCEV that can uses ValueHandles to track
updates to the values that serve as SCEV keys. However, this still means
that as we ran SCEV over each function in the module, we kept
accumulating more and more SCEVs into the cache. At the end, we would
have a SCEV cache with every value that we ever needed a SCEV for in the
entire module!!! Yowzers. The releaseMemory routine would dump all of
this, but that isn't realy called during normal runs of the pipeline as
far as I can see.
To make matters worse, there *is* actually a key that we don't update
with value handles -- there is a map keyed off of Loop*s. Because
LoopInfo *does* release its memory from run to run, it is entirely
possible to run SCEV over one function, then over another function, and
then lookup a Loop* from the second function but find an entry inserted
for the first function! Ouch.
To make matters still worse, there are plenty of updates that *don't*
trip a value handle. It seems incredibly unlikely that today GVN or
another pass that invalidates SCEV can update values in *just* such
a way that a subsequent run of SCEV will incorrectly find lookups in
a cache, but it is theoretically possible and would be a nightmare to
debug.
With this refactoring, I've fixed all this by actually destroying and
recreating the ScalarEvolution object from run to run. Technically, this
could increase the amount of malloc traffic we see, but then again it is
also technically correct. ;] I don't actually think we're suffering from
tons of malloc traffic from SCEV because if we were, the fact that we
never clear the memory would seem more likely to have come up as an
actual problem before now. So, I've made the simple fix here. If in fact
there are serious issues with too much allocation and deallocation,
I can work on a clever fix that preserves the allocations (while
clearing the data) between each run, but I'd prefer to do that kind of
optimization with a test case / benchmark that shows why we need such
cleverness (and that can test that we actually make it faster). It's
possible that this will make some things faster by making the SCEV
caches have higher locality (due to being significantly smaller) so
until there is a clear benchmark, I think the simple change is best.
Differential Revision: http://reviews.llvm.org/D12063
llvm-svn: 245193
2015-08-17 10:08:17 +08:00
|
|
|
}
|
2016-11-10 15:56:05 +08:00
|
|
|
|
2017-04-15 07:47:53 +08:00
|
|
|
void runWithSE(
|
2016-12-12 22:57:11 +08:00
|
|
|
Module &M, StringRef FuncName,
|
2017-04-15 07:47:53 +08:00
|
|
|
function_ref<void(Function &F, LoopInfo &LI, ScalarEvolution &SE)> Test) {
|
2016-12-13 02:52:32 +08:00
|
|
|
auto *F = M.getFunction(FuncName);
|
|
|
|
|
ASSERT_NE(F, nullptr) << "Could not find " << FuncName;
|
|
|
|
|
ScalarEvolution SE = buildSE(*F);
|
2017-04-15 07:47:53 +08:00
|
|
|
Test(*F, *LI, SE);
|
2016-11-10 15:56:05 +08:00
|
|
|
}
|
2011-10-04 14:51:26 +08:00
|
|
|
};
|
2010-08-03 07:49:30 +08:00
|
|
|
|
2011-10-04 14:51:26 +08:00
|
|
|
TEST_F(ScalarEvolutionsTest, SCEVUnknownRAUW) {
|
2011-07-18 12:54:35 +08:00
|
|
|
FunctionType *FTy = FunctionType::get(Type::getVoidTy(Context),
|
2011-07-12 22:06:48 +08:00
|
|
|
std::vector<Type *>(), false);
|
2010-08-03 07:49:30 +08:00
|
|
|
Function *F = cast<Function>(M.getOrInsertFunction("f", FTy));
|
|
|
|
|
BasicBlock *BB = BasicBlock::Create(Context, "entry", F);
|
2014-06-09 06:29:17 +08:00
|
|
|
ReturnInst::Create(Context, nullptr, BB);
|
2010-08-03 07:49:30 +08:00
|
|
|
|
2011-07-18 12:54:35 +08:00
|
|
|
Type *Ty = Type::getInt1Ty(Context);
|
2010-08-03 07:49:30 +08:00
|
|
|
Constant *Init = Constant::getNullValue(Ty);
|
|
|
|
|
Value *V0 = new GlobalVariable(M, Ty, false, GlobalValue::ExternalLinkage, Init, "V0");
|
|
|
|
|
Value *V1 = new GlobalVariable(M, Ty, false, GlobalValue::ExternalLinkage, Init, "V1");
|
|
|
|
|
Value *V2 = new GlobalVariable(M, Ty, false, GlobalValue::ExternalLinkage, Init, "V2");
|
|
|
|
|
|
[PM] Port ScalarEvolution to the new pass manager.
This change makes ScalarEvolution a stand-alone object and just produces
one from a pass as needed. Making this work well requires making the
object movable, using references instead of overwritten pointers in
a number of places, and other refactorings.
I've also wired it up to the new pass manager and added a RUN line to
a test to exercise it under the new pass manager. This includes basic
printing support much like with other analyses.
But there is a big and somewhat scary change here. Prior to this patch
ScalarEvolution was never *actually* invalidated!!! Re-running the pass
just re-wired up the various other analyses and didn't remove any of the
existing entries in the SCEV caches or clear out anything at all. This
might seem OK as everything in SCEV that can uses ValueHandles to track
updates to the values that serve as SCEV keys. However, this still means
that as we ran SCEV over each function in the module, we kept
accumulating more and more SCEVs into the cache. At the end, we would
have a SCEV cache with every value that we ever needed a SCEV for in the
entire module!!! Yowzers. The releaseMemory routine would dump all of
this, but that isn't realy called during normal runs of the pipeline as
far as I can see.
To make matters worse, there *is* actually a key that we don't update
with value handles -- there is a map keyed off of Loop*s. Because
LoopInfo *does* release its memory from run to run, it is entirely
possible to run SCEV over one function, then over another function, and
then lookup a Loop* from the second function but find an entry inserted
for the first function! Ouch.
To make matters still worse, there are plenty of updates that *don't*
trip a value handle. It seems incredibly unlikely that today GVN or
another pass that invalidates SCEV can update values in *just* such
a way that a subsequent run of SCEV will incorrectly find lookups in
a cache, but it is theoretically possible and would be a nightmare to
debug.
With this refactoring, I've fixed all this by actually destroying and
recreating the ScalarEvolution object from run to run. Technically, this
could increase the amount of malloc traffic we see, but then again it is
also technically correct. ;] I don't actually think we're suffering from
tons of malloc traffic from SCEV because if we were, the fact that we
never clear the memory would seem more likely to have come up as an
actual problem before now. So, I've made the simple fix here. If in fact
there are serious issues with too much allocation and deallocation,
I can work on a clever fix that preserves the allocations (while
clearing the data) between each run, but I'd prefer to do that kind of
optimization with a test case / benchmark that shows why we need such
cleverness (and that can test that we actually make it faster). It's
possible that this will make some things faster by making the SCEV
caches have higher locality (due to being significantly smaller) so
until there is a clear benchmark, I think the simple change is best.
Differential Revision: http://reviews.llvm.org/D12063
llvm-svn: 245193
2015-08-17 10:08:17 +08:00
|
|
|
ScalarEvolution SE = buildSE(*F);
|
2010-08-03 07:49:30 +08:00
|
|
|
|
|
|
|
|
const SCEV *S0 = SE.getSCEV(V0);
|
|
|
|
|
const SCEV *S1 = SE.getSCEV(V1);
|
|
|
|
|
const SCEV *S2 = SE.getSCEV(V2);
|
|
|
|
|
|
|
|
|
|
const SCEV *P0 = SE.getAddExpr(S0, S0);
|
|
|
|
|
const SCEV *P1 = SE.getAddExpr(S1, S1);
|
|
|
|
|
const SCEV *P2 = SE.getAddExpr(S2, S2);
|
|
|
|
|
|
|
|
|
|
const SCEVMulExpr *M0 = cast<SCEVMulExpr>(P0);
|
|
|
|
|
const SCEVMulExpr *M1 = cast<SCEVMulExpr>(P1);
|
|
|
|
|
const SCEVMulExpr *M2 = cast<SCEVMulExpr>(P2);
|
|
|
|
|
|
|
|
|
|
EXPECT_EQ(cast<SCEVConstant>(M0->getOperand(0))->getValue()->getZExtValue(),
|
|
|
|
|
2u);
|
|
|
|
|
EXPECT_EQ(cast<SCEVConstant>(M1->getOperand(0))->getValue()->getZExtValue(),
|
|
|
|
|
2u);
|
|
|
|
|
EXPECT_EQ(cast<SCEVConstant>(M2->getOperand(0))->getValue()->getZExtValue(),
|
|
|
|
|
2u);
|
|
|
|
|
|
|
|
|
|
// Before the RAUWs, these are all pointing to separate values.
|
|
|
|
|
EXPECT_EQ(cast<SCEVUnknown>(M0->getOperand(1))->getValue(), V0);
|
|
|
|
|
EXPECT_EQ(cast<SCEVUnknown>(M1->getOperand(1))->getValue(), V1);
|
|
|
|
|
EXPECT_EQ(cast<SCEVUnknown>(M2->getOperand(1))->getValue(), V2);
|
|
|
|
|
|
|
|
|
|
// Do some RAUWs.
|
|
|
|
|
V2->replaceAllUsesWith(V1);
|
|
|
|
|
V1->replaceAllUsesWith(V0);
|
|
|
|
|
|
|
|
|
|
// After the RAUWs, these should all be pointing to V0.
|
|
|
|
|
EXPECT_EQ(cast<SCEVUnknown>(M0->getOperand(1))->getValue(), V0);
|
|
|
|
|
EXPECT_EQ(cast<SCEVUnknown>(M1->getOperand(1))->getValue(), V0);
|
|
|
|
|
EXPECT_EQ(cast<SCEVUnknown>(M2->getOperand(1))->getValue(), V0);
|
2011-10-04 14:51:26 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
TEST_F(ScalarEvolutionsTest, SCEVMultiplyAddRecs) {
|
|
|
|
|
Type *Ty = Type::getInt32Ty(Context);
|
|
|
|
|
SmallVector<Type *, 10> Types;
|
|
|
|
|
Types.append(10, Ty);
|
|
|
|
|
FunctionType *FTy = FunctionType::get(Type::getVoidTy(Context), Types, false);
|
|
|
|
|
Function *F = cast<Function>(M.getOrInsertFunction("f", FTy));
|
|
|
|
|
BasicBlock *BB = BasicBlock::Create(Context, "entry", F);
|
2014-06-09 06:29:17 +08:00
|
|
|
ReturnInst::Create(Context, nullptr, BB);
|
2011-10-04 14:51:26 +08:00
|
|
|
|
[PM] Port ScalarEvolution to the new pass manager.
This change makes ScalarEvolution a stand-alone object and just produces
one from a pass as needed. Making this work well requires making the
object movable, using references instead of overwritten pointers in
a number of places, and other refactorings.
I've also wired it up to the new pass manager and added a RUN line to
a test to exercise it under the new pass manager. This includes basic
printing support much like with other analyses.
But there is a big and somewhat scary change here. Prior to this patch
ScalarEvolution was never *actually* invalidated!!! Re-running the pass
just re-wired up the various other analyses and didn't remove any of the
existing entries in the SCEV caches or clear out anything at all. This
might seem OK as everything in SCEV that can uses ValueHandles to track
updates to the values that serve as SCEV keys. However, this still means
that as we ran SCEV over each function in the module, we kept
accumulating more and more SCEVs into the cache. At the end, we would
have a SCEV cache with every value that we ever needed a SCEV for in the
entire module!!! Yowzers. The releaseMemory routine would dump all of
this, but that isn't realy called during normal runs of the pipeline as
far as I can see.
To make matters worse, there *is* actually a key that we don't update
with value handles -- there is a map keyed off of Loop*s. Because
LoopInfo *does* release its memory from run to run, it is entirely
possible to run SCEV over one function, then over another function, and
then lookup a Loop* from the second function but find an entry inserted
for the first function! Ouch.
To make matters still worse, there are plenty of updates that *don't*
trip a value handle. It seems incredibly unlikely that today GVN or
another pass that invalidates SCEV can update values in *just* such
a way that a subsequent run of SCEV will incorrectly find lookups in
a cache, but it is theoretically possible and would be a nightmare to
debug.
With this refactoring, I've fixed all this by actually destroying and
recreating the ScalarEvolution object from run to run. Technically, this
could increase the amount of malloc traffic we see, but then again it is
also technically correct. ;] I don't actually think we're suffering from
tons of malloc traffic from SCEV because if we were, the fact that we
never clear the memory would seem more likely to have come up as an
actual problem before now. So, I've made the simple fix here. If in fact
there are serious issues with too much allocation and deallocation,
I can work on a clever fix that preserves the allocations (while
clearing the data) between each run, but I'd prefer to do that kind of
optimization with a test case / benchmark that shows why we need such
cleverness (and that can test that we actually make it faster). It's
possible that this will make some things faster by making the SCEV
caches have higher locality (due to being significantly smaller) so
until there is a clear benchmark, I think the simple change is best.
Differential Revision: http://reviews.llvm.org/D12063
llvm-svn: 245193
2015-08-17 10:08:17 +08:00
|
|
|
ScalarEvolution SE = buildSE(*F);
|
2011-10-04 14:51:26 +08:00
|
|
|
|
|
|
|
|
// It's possible to produce an empty loop through the default constructor,
|
|
|
|
|
// but you can't add any blocks to it without a LoopInfo pass.
|
|
|
|
|
Loop L;
|
|
|
|
|
const_cast<std::vector<BasicBlock*>&>(L.getBlocks()).push_back(BB);
|
|
|
|
|
|
|
|
|
|
Function::arg_iterator AI = F->arg_begin();
|
|
|
|
|
SmallVector<const SCEV *, 5> A;
|
|
|
|
|
A.push_back(SE.getSCEV(&*AI++));
|
|
|
|
|
A.push_back(SE.getSCEV(&*AI++));
|
|
|
|
|
A.push_back(SE.getSCEV(&*AI++));
|
|
|
|
|
A.push_back(SE.getSCEV(&*AI++));
|
|
|
|
|
A.push_back(SE.getSCEV(&*AI++));
|
|
|
|
|
const SCEV *A_rec = SE.getAddRecExpr(A, &L, SCEV::FlagAnyWrap);
|
|
|
|
|
|
|
|
|
|
SmallVector<const SCEV *, 5> B;
|
|
|
|
|
B.push_back(SE.getSCEV(&*AI++));
|
|
|
|
|
B.push_back(SE.getSCEV(&*AI++));
|
|
|
|
|
B.push_back(SE.getSCEV(&*AI++));
|
|
|
|
|
B.push_back(SE.getSCEV(&*AI++));
|
|
|
|
|
B.push_back(SE.getSCEV(&*AI++));
|
|
|
|
|
const SCEV *B_rec = SE.getAddRecExpr(B, &L, SCEV::FlagAnyWrap);
|
|
|
|
|
|
|
|
|
|
/* Spot check that we perform this transformation:
|
|
|
|
|
{A0,+,A1,+,A2,+,A3,+,A4} * {B0,+,B1,+,B2,+,B3,+,B4} =
|
|
|
|
|
{A0*B0,+,
|
|
|
|
|
A1*B0 + A0*B1 + A1*B1,+,
|
|
|
|
|
A2*B0 + 2A1*B1 + A0*B2 + 2A2*B1 + 2A1*B2 + A2*B2,+,
|
|
|
|
|
A3*B0 + 3A2*B1 + 3A1*B2 + A0*B3 + 3A3*B1 + 6A2*B2 + 3A1*B3 + 3A3*B2 +
|
|
|
|
|
3A2*B3 + A3*B3,+,
|
|
|
|
|
A4*B0 + 4A3*B1 + 6A2*B2 + 4A1*B3 + A0*B4 + 4A4*B1 + 12A3*B2 + 12A2*B3 +
|
|
|
|
|
4A1*B4 + 6A4*B2 + 12A3*B3 + 6A2*B4 + 4A4*B3 + 4A3*B4 + A4*B4,+,
|
|
|
|
|
5A4*B1 + 10A3*B2 + 10A2*B3 + 5A1*B4 + 20A4*B2 + 30A3*B3 + 20A2*B4 +
|
|
|
|
|
30A4*B3 + 30A3*B4 + 20A4*B4,+,
|
|
|
|
|
15A4*B2 + 20A3*B3 + 15A2*B4 + 60A4*B3 + 60A3*B4 + 90A4*B4,+,
|
|
|
|
|
35A4*B3 + 35A3*B4 + 140A4*B4,+,
|
|
|
|
|
70A4*B4}
|
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
const SCEVAddRecExpr *Product =
|
|
|
|
|
dyn_cast<SCEVAddRecExpr>(SE.getMulExpr(A_rec, B_rec));
|
|
|
|
|
ASSERT_TRUE(Product);
|
|
|
|
|
ASSERT_EQ(Product->getNumOperands(), 9u);
|
|
|
|
|
|
|
|
|
|
SmallVector<const SCEV *, 16> Sum;
|
|
|
|
|
Sum.push_back(SE.getMulExpr(A[0], B[0]));
|
|
|
|
|
EXPECT_EQ(Product->getOperand(0), SE.getAddExpr(Sum));
|
|
|
|
|
Sum.clear();
|
|
|
|
|
|
|
|
|
|
// SCEV produces different an equal but different expression for these.
|
|
|
|
|
// Re-enable when PR11052 is fixed.
|
|
|
|
|
#if 0
|
|
|
|
|
Sum.push_back(SE.getMulExpr(A[1], B[0]));
|
|
|
|
|
Sum.push_back(SE.getMulExpr(A[0], B[1]));
|
|
|
|
|
Sum.push_back(SE.getMulExpr(A[1], B[1]));
|
|
|
|
|
EXPECT_EQ(Product->getOperand(1), SE.getAddExpr(Sum));
|
|
|
|
|
Sum.clear();
|
|
|
|
|
|
|
|
|
|
Sum.push_back(SE.getMulExpr(A[2], B[0]));
|
|
|
|
|
Sum.push_back(SE.getMulExpr(SE.getConstant(Ty, 2), A[1], B[1]));
|
|
|
|
|
Sum.push_back(SE.getMulExpr(A[0], B[2]));
|
|
|
|
|
Sum.push_back(SE.getMulExpr(SE.getConstant(Ty, 2), A[2], B[1]));
|
|
|
|
|
Sum.push_back(SE.getMulExpr(SE.getConstant(Ty, 2), A[1], B[2]));
|
|
|
|
|
Sum.push_back(SE.getMulExpr(A[2], B[2]));
|
|
|
|
|
EXPECT_EQ(Product->getOperand(2), SE.getAddExpr(Sum));
|
|
|
|
|
Sum.clear();
|
|
|
|
|
|
|
|
|
|
Sum.push_back(SE.getMulExpr(A[3], B[0]));
|
|
|
|
|
Sum.push_back(SE.getMulExpr(SE.getConstant(Ty, 3), A[2], B[1]));
|
|
|
|
|
Sum.push_back(SE.getMulExpr(SE.getConstant(Ty, 3), A[1], B[2]));
|
|
|
|
|
Sum.push_back(SE.getMulExpr(A[0], B[3]));
|
|
|
|
|
Sum.push_back(SE.getMulExpr(SE.getConstant(Ty, 3), A[3], B[1]));
|
|
|
|
|
Sum.push_back(SE.getMulExpr(SE.getConstant(Ty, 6), A[2], B[2]));
|
|
|
|
|
Sum.push_back(SE.getMulExpr(SE.getConstant(Ty, 3), A[1], B[3]));
|
|
|
|
|
Sum.push_back(SE.getMulExpr(SE.getConstant(Ty, 3), A[3], B[2]));
|
|
|
|
|
Sum.push_back(SE.getMulExpr(SE.getConstant(Ty, 3), A[2], B[3]));
|
|
|
|
|
Sum.push_back(SE.getMulExpr(A[3], B[3]));
|
|
|
|
|
EXPECT_EQ(Product->getOperand(3), SE.getAddExpr(Sum));
|
|
|
|
|
Sum.clear();
|
|
|
|
|
|
|
|
|
|
Sum.push_back(SE.getMulExpr(A[4], B[0]));
|
|
|
|
|
Sum.push_back(SE.getMulExpr(SE.getConstant(Ty, 4), A[3], B[1]));
|
|
|
|
|
Sum.push_back(SE.getMulExpr(SE.getConstant(Ty, 6), A[2], B[2]));
|
|
|
|
|
Sum.push_back(SE.getMulExpr(SE.getConstant(Ty, 4), A[1], B[3]));
|
|
|
|
|
Sum.push_back(SE.getMulExpr(A[0], B[4]));
|
|
|
|
|
Sum.push_back(SE.getMulExpr(SE.getConstant(Ty, 4), A[4], B[1]));
|
|
|
|
|
Sum.push_back(SE.getMulExpr(SE.getConstant(Ty, 12), A[3], B[2]));
|
|
|
|
|
Sum.push_back(SE.getMulExpr(SE.getConstant(Ty, 12), A[2], B[3]));
|
|
|
|
|
Sum.push_back(SE.getMulExpr(SE.getConstant(Ty, 4), A[1], B[4]));
|
|
|
|
|
Sum.push_back(SE.getMulExpr(SE.getConstant(Ty, 6), A[4], B[2]));
|
|
|
|
|
Sum.push_back(SE.getMulExpr(SE.getConstant(Ty, 12), A[3], B[3]));
|
|
|
|
|
Sum.push_back(SE.getMulExpr(SE.getConstant(Ty, 6), A[2], B[4]));
|
|
|
|
|
Sum.push_back(SE.getMulExpr(SE.getConstant(Ty, 4), A[4], B[3]));
|
|
|
|
|
Sum.push_back(SE.getMulExpr(SE.getConstant(Ty, 4), A[3], B[4]));
|
|
|
|
|
Sum.push_back(SE.getMulExpr(A[4], B[4]));
|
|
|
|
|
EXPECT_EQ(Product->getOperand(4), SE.getAddExpr(Sum));
|
|
|
|
|
Sum.clear();
|
|
|
|
|
|
|
|
|
|
Sum.push_back(SE.getMulExpr(SE.getConstant(Ty, 5), A[4], B[1]));
|
|
|
|
|
Sum.push_back(SE.getMulExpr(SE.getConstant(Ty, 10), A[3], B[2]));
|
|
|
|
|
Sum.push_back(SE.getMulExpr(SE.getConstant(Ty, 10), A[2], B[3]));
|
|
|
|
|
Sum.push_back(SE.getMulExpr(SE.getConstant(Ty, 5), A[1], B[4]));
|
|
|
|
|
Sum.push_back(SE.getMulExpr(SE.getConstant(Ty, 20), A[4], B[2]));
|
|
|
|
|
Sum.push_back(SE.getMulExpr(SE.getConstant(Ty, 30), A[3], B[3]));
|
|
|
|
|
Sum.push_back(SE.getMulExpr(SE.getConstant(Ty, 20), A[2], B[4]));
|
|
|
|
|
Sum.push_back(SE.getMulExpr(SE.getConstant(Ty, 30), A[4], B[3]));
|
|
|
|
|
Sum.push_back(SE.getMulExpr(SE.getConstant(Ty, 30), A[3], B[4]));
|
|
|
|
|
Sum.push_back(SE.getMulExpr(SE.getConstant(Ty, 20), A[4], B[4]));
|
|
|
|
|
EXPECT_EQ(Product->getOperand(5), SE.getAddExpr(Sum));
|
|
|
|
|
Sum.clear();
|
|
|
|
|
|
|
|
|
|
Sum.push_back(SE.getMulExpr(SE.getConstant(Ty, 15), A[4], B[2]));
|
|
|
|
|
Sum.push_back(SE.getMulExpr(SE.getConstant(Ty, 20), A[3], B[3]));
|
|
|
|
|
Sum.push_back(SE.getMulExpr(SE.getConstant(Ty, 15), A[2], B[4]));
|
|
|
|
|
Sum.push_back(SE.getMulExpr(SE.getConstant(Ty, 60), A[4], B[3]));
|
|
|
|
|
Sum.push_back(SE.getMulExpr(SE.getConstant(Ty, 60), A[3], B[4]));
|
|
|
|
|
Sum.push_back(SE.getMulExpr(SE.getConstant(Ty, 90), A[4], B[4]));
|
|
|
|
|
EXPECT_EQ(Product->getOperand(6), SE.getAddExpr(Sum));
|
|
|
|
|
Sum.clear();
|
|
|
|
|
|
|
|
|
|
Sum.push_back(SE.getMulExpr(SE.getConstant(Ty, 35), A[4], B[3]));
|
|
|
|
|
Sum.push_back(SE.getMulExpr(SE.getConstant(Ty, 35), A[3], B[4]));
|
|
|
|
|
Sum.push_back(SE.getMulExpr(SE.getConstant(Ty, 140), A[4], B[4]));
|
|
|
|
|
EXPECT_EQ(Product->getOperand(7), SE.getAddExpr(Sum));
|
|
|
|
|
Sum.clear();
|
|
|
|
|
#endif
|
2010-08-03 07:49:30 +08:00
|
|
|
|
2011-10-04 14:51:26 +08:00
|
|
|
Sum.push_back(SE.getMulExpr(SE.getConstant(Ty, 70), A[4], B[4]));
|
|
|
|
|
EXPECT_EQ(Product->getOperand(8), SE.getAddExpr(Sum));
|
2010-08-03 07:49:30 +08:00
|
|
|
}
|
|
|
|
|
|
2016-02-22 01:42:10 +08:00
|
|
|
TEST_F(ScalarEvolutionsTest, SimplifiedPHI) {
|
|
|
|
|
FunctionType *FTy = FunctionType::get(Type::getVoidTy(Context),
|
|
|
|
|
std::vector<Type *>(), false);
|
|
|
|
|
Function *F = cast<Function>(M.getOrInsertFunction("f", FTy));
|
|
|
|
|
BasicBlock *EntryBB = BasicBlock::Create(Context, "entry", F);
|
|
|
|
|
BasicBlock *LoopBB = BasicBlock::Create(Context, "loop", F);
|
|
|
|
|
BasicBlock *ExitBB = BasicBlock::Create(Context, "exit", F);
|
|
|
|
|
BranchInst::Create(LoopBB, EntryBB);
|
|
|
|
|
BranchInst::Create(LoopBB, ExitBB, UndefValue::get(Type::getInt1Ty(Context)),
|
|
|
|
|
LoopBB);
|
|
|
|
|
ReturnInst::Create(Context, nullptr, ExitBB);
|
|
|
|
|
auto *Ty = Type::getInt32Ty(Context);
|
|
|
|
|
auto *PN = PHINode::Create(Ty, 2, "", &*LoopBB->begin());
|
|
|
|
|
PN->addIncoming(Constant::getNullValue(Ty), EntryBB);
|
|
|
|
|
PN->addIncoming(UndefValue::get(Ty), LoopBB);
|
|
|
|
|
ScalarEvolution SE = buildSE(*F);
|
|
|
|
|
auto *S1 = SE.getSCEV(PN);
|
|
|
|
|
auto *S2 = SE.getSCEV(PN);
|
2016-02-22 15:20:40 +08:00
|
|
|
auto *ZeroConst = SE.getConstant(Ty, 0);
|
2016-02-22 01:42:10 +08:00
|
|
|
|
|
|
|
|
// At some point, only the first call to getSCEV returned the simplified
|
|
|
|
|
// SCEVConstant and later calls just returned a SCEVUnknown referencing the
|
|
|
|
|
// PHI node.
|
2016-02-22 15:20:40 +08:00
|
|
|
EXPECT_EQ(S1, ZeroConst);
|
|
|
|
|
EXPECT_EQ(S1, S2);
|
2016-02-22 01:42:10 +08:00
|
|
|
}
|
|
|
|
|
|
2016-09-15 12:06:44 +08:00
|
|
|
TEST_F(ScalarEvolutionsTest, ExpandPtrTypeSCEV) {
|
|
|
|
|
// It is to test the fix for PR30213. It exercises the branch in scev
|
|
|
|
|
// expansion when the value in ValueOffsetPair is a ptr and the offset
|
|
|
|
|
// is not divisible by the elem type size of value.
|
|
|
|
|
auto *I8Ty = Type::getInt8Ty(Context);
|
|
|
|
|
auto *I8PtrTy = Type::getInt8PtrTy(Context);
|
|
|
|
|
auto *I32Ty = Type::getInt32Ty(Context);
|
|
|
|
|
auto *I32PtrTy = Type::getInt32PtrTy(Context);
|
|
|
|
|
FunctionType *FTy =
|
|
|
|
|
FunctionType::get(Type::getVoidTy(Context), std::vector<Type *>(), false);
|
|
|
|
|
Function *F = cast<Function>(M.getOrInsertFunction("f", FTy));
|
|
|
|
|
BasicBlock *EntryBB = BasicBlock::Create(Context, "entry", F);
|
|
|
|
|
BasicBlock *LoopBB = BasicBlock::Create(Context, "loop", F);
|
|
|
|
|
BasicBlock *ExitBB = BasicBlock::Create(Context, "exit", F);
|
|
|
|
|
BranchInst::Create(LoopBB, EntryBB);
|
|
|
|
|
ReturnInst::Create(Context, nullptr, ExitBB);
|
|
|
|
|
|
|
|
|
|
// loop: ; preds = %loop, %entry
|
|
|
|
|
// %alloca = alloca i32
|
|
|
|
|
// %gep0 = getelementptr i32, i32* %alloca, i32 1
|
|
|
|
|
// %bitcast1 = bitcast i32* %gep0 to i8*
|
|
|
|
|
// %gep1 = getelementptr i8, i8* %bitcast1, i32 1
|
|
|
|
|
// %gep2 = getelementptr i8, i8* undef, i32 1
|
|
|
|
|
// %cmp = icmp ult i8* undef, %bitcast1
|
|
|
|
|
// %select = select i1 %cmp, i8* %gep1, i8* %gep2
|
|
|
|
|
// %bitcast2 = bitcast i8* %select to i32*
|
|
|
|
|
// br i1 undef, label %loop, label %exit
|
|
|
|
|
|
2017-04-11 06:27:50 +08:00
|
|
|
const DataLayout &DL = F->getParent()->getDataLayout();
|
2016-09-15 12:06:44 +08:00
|
|
|
BranchInst *Br = BranchInst::Create(
|
|
|
|
|
LoopBB, ExitBB, UndefValue::get(Type::getInt1Ty(Context)), LoopBB);
|
2017-04-11 06:27:50 +08:00
|
|
|
AllocaInst *Alloca = new AllocaInst(I32Ty, DL.getAllocaAddrSpace(),
|
|
|
|
|
"alloca", Br);
|
2016-09-15 12:06:44 +08:00
|
|
|
ConstantInt *Ci32 = ConstantInt::get(Context, APInt(32, 1));
|
|
|
|
|
GetElementPtrInst *Gep0 =
|
|
|
|
|
GetElementPtrInst::Create(I32Ty, Alloca, Ci32, "gep0", Br);
|
|
|
|
|
CastInst *CastA =
|
|
|
|
|
CastInst::CreateBitOrPointerCast(Gep0, I8PtrTy, "bitcast1", Br);
|
|
|
|
|
GetElementPtrInst *Gep1 =
|
|
|
|
|
GetElementPtrInst::Create(I8Ty, CastA, Ci32, "gep1", Br);
|
|
|
|
|
GetElementPtrInst *Gep2 = GetElementPtrInst::Create(
|
|
|
|
|
I8Ty, UndefValue::get(I8PtrTy), Ci32, "gep2", Br);
|
|
|
|
|
CmpInst *Cmp = CmpInst::Create(Instruction::ICmp, CmpInst::ICMP_ULT,
|
|
|
|
|
UndefValue::get(I8PtrTy), CastA, "cmp", Br);
|
|
|
|
|
SelectInst *Sel = SelectInst::Create(Cmp, Gep1, Gep2, "select", Br);
|
|
|
|
|
CastInst *CastB =
|
|
|
|
|
CastInst::CreateBitOrPointerCast(Sel, I32PtrTy, "bitcast2", Br);
|
|
|
|
|
|
|
|
|
|
ScalarEvolution SE = buildSE(*F);
|
|
|
|
|
auto *S = SE.getSCEV(CastB);
|
|
|
|
|
SCEVExpander Exp(SE, M.getDataLayout(), "expander");
|
|
|
|
|
Value *V =
|
|
|
|
|
Exp.expandCodeFor(cast<SCEVAddExpr>(S)->getOperand(1), nullptr, Br);
|
|
|
|
|
|
|
|
|
|
// Expect the expansion code contains:
|
|
|
|
|
// %0 = bitcast i32* %bitcast2 to i8*
|
|
|
|
|
// %uglygep = getelementptr i8, i8* %0, i64 -1
|
|
|
|
|
// %1 = bitcast i8* %uglygep to i32*
|
|
|
|
|
EXPECT_TRUE(isa<BitCastInst>(V));
|
|
|
|
|
Instruction *Gep = cast<Instruction>(V)->getPrevNode();
|
|
|
|
|
EXPECT_TRUE(isa<GetElementPtrInst>(Gep));
|
|
|
|
|
EXPECT_TRUE(isa<ConstantInt>(Gep->getOperand(1)));
|
|
|
|
|
EXPECT_EQ(cast<ConstantInt>(Gep->getOperand(1))->getSExtValue(), -1);
|
|
|
|
|
EXPECT_TRUE(isa<BitCastInst>(Gep->getPrevNode()));
|
|
|
|
|
}
|
|
|
|
|
|
2016-10-31 07:52:50 +08:00
|
|
|
static Instruction *getInstructionByName(Function &F, StringRef Name) {
|
|
|
|
|
for (auto &I : instructions(F))
|
|
|
|
|
if (I.getName() == Name)
|
|
|
|
|
return &I;
|
2016-10-19 01:45:16 +08:00
|
|
|
llvm_unreachable("Expected to find instruction!");
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
TEST_F(ScalarEvolutionsTest, CommutativeExprOperandOrder) {
|
|
|
|
|
LLVMContext C;
|
|
|
|
|
SMDiagnostic Err;
|
|
|
|
|
std::unique_ptr<Module> M = parseAssemblyString(
|
|
|
|
|
"target datalayout = \"e-m:e-p:32:32-f64:32:64-f80:32-n8:16:32-S128\" "
|
2016-10-31 07:52:50 +08:00
|
|
|
" "
|
2016-10-31 07:52:56 +08:00
|
|
|
"@var_0 = external global i32, align 4"
|
|
|
|
|
"@var_1 = external global i32, align 4"
|
2016-10-31 11:32:45 +08:00
|
|
|
"@var_2 = external global i32, align 4"
|
2016-10-31 07:52:56 +08:00
|
|
|
" "
|
2016-10-31 11:32:43 +08:00
|
|
|
"declare i32 @unknown(i32, i32, i32)"
|
|
|
|
|
" "
|
2016-10-31 07:52:50 +08:00
|
|
|
"define void @f_1(i8* nocapture %arr, i32 %n, i32* %A, i32* %B) "
|
2016-10-19 01:45:16 +08:00
|
|
|
" local_unnamed_addr { "
|
|
|
|
|
"entry: "
|
|
|
|
|
" %entrycond = icmp sgt i32 %n, 0 "
|
|
|
|
|
" br i1 %entrycond, label %loop.ph, label %for.end "
|
|
|
|
|
" "
|
|
|
|
|
"loop.ph: "
|
|
|
|
|
" %a = load i32, i32* %A, align 4 "
|
|
|
|
|
" %b = load i32, i32* %B, align 4 "
|
|
|
|
|
" %mul = mul nsw i32 %b, %a "
|
|
|
|
|
" %iv0.init = getelementptr inbounds i8, i8* %arr, i32 %mul "
|
|
|
|
|
" br label %loop "
|
|
|
|
|
" "
|
|
|
|
|
"loop: "
|
|
|
|
|
" %iv0 = phi i8* [ %iv0.inc, %loop ], [ %iv0.init, %loop.ph ] "
|
|
|
|
|
" %iv1 = phi i32 [ %iv1.inc, %loop ], [ 0, %loop.ph ] "
|
|
|
|
|
" %conv = trunc i32 %iv1 to i8 "
|
|
|
|
|
" store i8 %conv, i8* %iv0, align 1 "
|
|
|
|
|
" %iv0.inc = getelementptr inbounds i8, i8* %iv0, i32 %b "
|
|
|
|
|
" %iv1.inc = add nuw nsw i32 %iv1, 1 "
|
|
|
|
|
" %exitcond = icmp eq i32 %iv1.inc, %n "
|
|
|
|
|
" br i1 %exitcond, label %for.end.loopexit, label %loop "
|
|
|
|
|
" "
|
|
|
|
|
"for.end.loopexit: "
|
|
|
|
|
" br label %for.end "
|
|
|
|
|
" "
|
|
|
|
|
"for.end: "
|
|
|
|
|
" ret void "
|
|
|
|
|
"} "
|
|
|
|
|
" "
|
2016-10-31 07:52:50 +08:00
|
|
|
"define void @f_2(i32* %X, i32* %Y, i32* %Z) { "
|
2016-10-19 01:45:16 +08:00
|
|
|
" %x = load i32, i32* %X "
|
|
|
|
|
" %y = load i32, i32* %Y "
|
|
|
|
|
" %z = load i32, i32* %Z "
|
|
|
|
|
" ret void "
|
2016-10-31 07:52:56 +08:00
|
|
|
"} "
|
|
|
|
|
" "
|
|
|
|
|
"define void @f_3() { "
|
|
|
|
|
" %x = load i32, i32* @var_0"
|
|
|
|
|
" %y = load i32, i32* @var_1"
|
2016-10-31 11:32:45 +08:00
|
|
|
" %z = load i32, i32* @var_2"
|
2016-10-31 07:52:56 +08:00
|
|
|
" ret void"
|
|
|
|
|
"} "
|
2016-10-31 11:32:43 +08:00
|
|
|
" "
|
|
|
|
|
"define void @f_4(i32 %a, i32 %b, i32 %c) { "
|
|
|
|
|
" %x = call i32 @unknown(i32 %a, i32 %b, i32 %c)"
|
|
|
|
|
" %y = call i32 @unknown(i32 %b, i32 %c, i32 %a)"
|
|
|
|
|
" %z = call i32 @unknown(i32 %c, i32 %a, i32 %b)"
|
|
|
|
|
" ret void"
|
|
|
|
|
"} "
|
2016-10-31 07:52:56 +08:00
|
|
|
,
|
2016-10-19 01:45:16 +08:00
|
|
|
Err, C);
|
|
|
|
|
|
|
|
|
|
assert(M && "Could not parse module?");
|
|
|
|
|
assert(!verifyModule(*M) && "Must have been well formed!");
|
|
|
|
|
|
2017-04-15 07:47:53 +08:00
|
|
|
runWithSE(*M, "f_1", [&](Function &F, LoopInfo &LI, ScalarEvolution &SE) {
|
2016-10-31 11:32:39 +08:00
|
|
|
auto *IV0 = getInstructionByName(F, "iv0");
|
|
|
|
|
auto *IV0Inc = getInstructionByName(F, "iv0.inc");
|
2016-10-19 01:45:16 +08:00
|
|
|
|
|
|
|
|
auto *FirstExprForIV0 = SE.getSCEV(IV0);
|
|
|
|
|
auto *FirstExprForIV0Inc = SE.getSCEV(IV0Inc);
|
|
|
|
|
auto *SecondExprForIV0 = SE.getSCEV(IV0);
|
|
|
|
|
|
|
|
|
|
EXPECT_TRUE(isa<SCEVAddRecExpr>(FirstExprForIV0));
|
|
|
|
|
EXPECT_TRUE(isa<SCEVAddRecExpr>(FirstExprForIV0Inc));
|
|
|
|
|
EXPECT_TRUE(isa<SCEVAddRecExpr>(SecondExprForIV0));
|
2016-10-31 11:32:39 +08:00
|
|
|
});
|
2016-10-19 01:45:16 +08:00
|
|
|
|
2016-10-31 11:32:43 +08:00
|
|
|
auto CheckCommutativeMulExprs = [&](ScalarEvolution &SE, const SCEV *A,
|
|
|
|
|
const SCEV *B, const SCEV *C) {
|
|
|
|
|
EXPECT_EQ(SE.getMulExpr(A, B), SE.getMulExpr(B, A));
|
|
|
|
|
EXPECT_EQ(SE.getMulExpr(B, C), SE.getMulExpr(C, B));
|
|
|
|
|
EXPECT_EQ(SE.getMulExpr(A, C), SE.getMulExpr(C, A));
|
2016-10-19 01:45:16 +08:00
|
|
|
|
2016-10-31 11:32:43 +08:00
|
|
|
SmallVector<const SCEV *, 3> Ops0 = {A, B, C};
|
|
|
|
|
SmallVector<const SCEV *, 3> Ops1 = {A, C, B};
|
|
|
|
|
SmallVector<const SCEV *, 3> Ops2 = {B, A, C};
|
|
|
|
|
SmallVector<const SCEV *, 3> Ops3 = {B, C, A};
|
|
|
|
|
SmallVector<const SCEV *, 3> Ops4 = {C, B, A};
|
|
|
|
|
SmallVector<const SCEV *, 3> Ops5 = {C, A, B};
|
2016-10-19 01:45:16 +08:00
|
|
|
|
|
|
|
|
auto *Mul0 = SE.getMulExpr(Ops0);
|
|
|
|
|
auto *Mul1 = SE.getMulExpr(Ops1);
|
|
|
|
|
auto *Mul2 = SE.getMulExpr(Ops2);
|
|
|
|
|
auto *Mul3 = SE.getMulExpr(Ops3);
|
|
|
|
|
auto *Mul4 = SE.getMulExpr(Ops4);
|
|
|
|
|
auto *Mul5 = SE.getMulExpr(Ops5);
|
|
|
|
|
|
2016-10-31 11:32:43 +08:00
|
|
|
EXPECT_EQ(Mul0, Mul1) << "Expected " << *Mul0 << " == " << *Mul1;
|
|
|
|
|
EXPECT_EQ(Mul1, Mul2) << "Expected " << *Mul1 << " == " << *Mul2;
|
|
|
|
|
EXPECT_EQ(Mul2, Mul3) << "Expected " << *Mul2 << " == " << *Mul3;
|
|
|
|
|
EXPECT_EQ(Mul3, Mul4) << "Expected " << *Mul3 << " == " << *Mul4;
|
|
|
|
|
EXPECT_EQ(Mul4, Mul5) << "Expected " << *Mul4 << " == " << *Mul5;
|
|
|
|
|
};
|
|
|
|
|
|
2016-10-31 11:32:45 +08:00
|
|
|
for (StringRef FuncName : {"f_2", "f_3", "f_4"})
|
2017-04-15 07:47:53 +08:00
|
|
|
runWithSE(
|
|
|
|
|
*M, FuncName, [&](Function &F, LoopInfo &LI, ScalarEvolution &SE) {
|
|
|
|
|
CheckCommutativeMulExprs(SE, SE.getSCEV(getInstructionByName(F, "x")),
|
|
|
|
|
SE.getSCEV(getInstructionByName(F, "y")),
|
|
|
|
|
SE.getSCEV(getInstructionByName(F, "z")));
|
|
|
|
|
});
|
2016-10-19 01:45:16 +08:00
|
|
|
}
|
|
|
|
|
|
2017-03-06 07:49:17 +08:00
|
|
|
TEST_F(ScalarEvolutionsTest, CompareSCEVComplexity) {
|
2016-11-18 00:07:52 +08:00
|
|
|
FunctionType *FTy =
|
|
|
|
|
FunctionType::get(Type::getVoidTy(Context), std::vector<Type *>(), false);
|
|
|
|
|
Function *F = cast<Function>(M.getOrInsertFunction("f", FTy));
|
|
|
|
|
BasicBlock *EntryBB = BasicBlock::Create(Context, "entry", F);
|
|
|
|
|
BasicBlock *LoopBB = BasicBlock::Create(Context, "bb1", F);
|
|
|
|
|
BranchInst::Create(LoopBB, EntryBB);
|
|
|
|
|
|
|
|
|
|
auto *Ty = Type::getInt32Ty(Context);
|
|
|
|
|
SmallVector<Instruction*, 8> Muls(8), Acc(8), NextAcc(8);
|
|
|
|
|
|
|
|
|
|
Acc[0] = PHINode::Create(Ty, 2, "", LoopBB);
|
|
|
|
|
Acc[1] = PHINode::Create(Ty, 2, "", LoopBB);
|
|
|
|
|
Acc[2] = PHINode::Create(Ty, 2, "", LoopBB);
|
|
|
|
|
Acc[3] = PHINode::Create(Ty, 2, "", LoopBB);
|
|
|
|
|
Acc[4] = PHINode::Create(Ty, 2, "", LoopBB);
|
|
|
|
|
Acc[5] = PHINode::Create(Ty, 2, "", LoopBB);
|
|
|
|
|
Acc[6] = PHINode::Create(Ty, 2, "", LoopBB);
|
|
|
|
|
Acc[7] = PHINode::Create(Ty, 2, "", LoopBB);
|
|
|
|
|
|
|
|
|
|
for (int i = 0; i < 20; i++) {
|
|
|
|
|
Muls[0] = BinaryOperator::CreateMul(Acc[0], Acc[0], "", LoopBB);
|
|
|
|
|
NextAcc[0] = BinaryOperator::CreateAdd(Muls[0], Acc[4], "", LoopBB);
|
|
|
|
|
Muls[1] = BinaryOperator::CreateMul(Acc[1], Acc[1], "", LoopBB);
|
|
|
|
|
NextAcc[1] = BinaryOperator::CreateAdd(Muls[1], Acc[5], "", LoopBB);
|
|
|
|
|
Muls[2] = BinaryOperator::CreateMul(Acc[2], Acc[2], "", LoopBB);
|
|
|
|
|
NextAcc[2] = BinaryOperator::CreateAdd(Muls[2], Acc[6], "", LoopBB);
|
|
|
|
|
Muls[3] = BinaryOperator::CreateMul(Acc[3], Acc[3], "", LoopBB);
|
|
|
|
|
NextAcc[3] = BinaryOperator::CreateAdd(Muls[3], Acc[7], "", LoopBB);
|
|
|
|
|
|
|
|
|
|
Muls[4] = BinaryOperator::CreateMul(Acc[4], Acc[4], "", LoopBB);
|
|
|
|
|
NextAcc[4] = BinaryOperator::CreateAdd(Muls[4], Acc[0], "", LoopBB);
|
|
|
|
|
Muls[5] = BinaryOperator::CreateMul(Acc[5], Acc[5], "", LoopBB);
|
|
|
|
|
NextAcc[5] = BinaryOperator::CreateAdd(Muls[5], Acc[1], "", LoopBB);
|
|
|
|
|
Muls[6] = BinaryOperator::CreateMul(Acc[6], Acc[6], "", LoopBB);
|
|
|
|
|
NextAcc[6] = BinaryOperator::CreateAdd(Muls[6], Acc[2], "", LoopBB);
|
|
|
|
|
Muls[7] = BinaryOperator::CreateMul(Acc[7], Acc[7], "", LoopBB);
|
|
|
|
|
NextAcc[7] = BinaryOperator::CreateAdd(Muls[7], Acc[3], "", LoopBB);
|
|
|
|
|
Acc = NextAcc;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
auto II = LoopBB->begin();
|
|
|
|
|
for (int i = 0; i < 8; i++) {
|
|
|
|
|
PHINode *Phi = cast<PHINode>(&*II++);
|
|
|
|
|
Phi->addIncoming(Acc[i], LoopBB);
|
|
|
|
|
Phi->addIncoming(UndefValue::get(Ty), EntryBB);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
BasicBlock *ExitBB = BasicBlock::Create(Context, "bb2", F);
|
|
|
|
|
BranchInst::Create(LoopBB, ExitBB, UndefValue::get(Type::getInt1Ty(Context)),
|
|
|
|
|
LoopBB);
|
|
|
|
|
|
|
|
|
|
Acc[0] = BinaryOperator::CreateAdd(Acc[0], Acc[1], "", ExitBB);
|
|
|
|
|
Acc[1] = BinaryOperator::CreateAdd(Acc[2], Acc[3], "", ExitBB);
|
|
|
|
|
Acc[2] = BinaryOperator::CreateAdd(Acc[4], Acc[5], "", ExitBB);
|
|
|
|
|
Acc[3] = BinaryOperator::CreateAdd(Acc[6], Acc[7], "", ExitBB);
|
|
|
|
|
Acc[0] = BinaryOperator::CreateAdd(Acc[0], Acc[1], "", ExitBB);
|
|
|
|
|
Acc[1] = BinaryOperator::CreateAdd(Acc[2], Acc[3], "", ExitBB);
|
|
|
|
|
Acc[0] = BinaryOperator::CreateAdd(Acc[0], Acc[1], "", ExitBB);
|
|
|
|
|
|
|
|
|
|
ReturnInst::Create(Context, nullptr, ExitBB);
|
|
|
|
|
|
|
|
|
|
ScalarEvolution SE = buildSE(*F);
|
|
|
|
|
|
|
|
|
|
EXPECT_NE(nullptr, SE.getSCEV(Acc[0]));
|
|
|
|
|
}
|
|
|
|
|
|
2017-03-06 07:49:17 +08:00
|
|
|
TEST_F(ScalarEvolutionsTest, CompareValueComplexity) {
|
|
|
|
|
IntegerType *IntPtrTy = M.getDataLayout().getIntPtrType(Context);
|
|
|
|
|
PointerType *IntPtrPtrTy = IntPtrTy->getPointerTo();
|
|
|
|
|
|
|
|
|
|
FunctionType *FTy =
|
|
|
|
|
FunctionType::get(Type::getVoidTy(Context), {IntPtrTy, IntPtrTy}, false);
|
|
|
|
|
Function *F = cast<Function>(M.getOrInsertFunction("f", FTy));
|
|
|
|
|
BasicBlock *EntryBB = BasicBlock::Create(Context, "entry", F);
|
|
|
|
|
|
|
|
|
|
Value *X = &*F->arg_begin();
|
|
|
|
|
Value *Y = &*std::next(F->arg_begin());
|
|
|
|
|
|
|
|
|
|
const int ValueDepth = 10;
|
|
|
|
|
for (int i = 0; i < ValueDepth; i++) {
|
|
|
|
|
X = new LoadInst(new IntToPtrInst(X, IntPtrPtrTy, "", EntryBB), "",
|
|
|
|
|
/*isVolatile*/ false, EntryBB);
|
|
|
|
|
Y = new LoadInst(new IntToPtrInst(Y, IntPtrPtrTy, "", EntryBB), "",
|
|
|
|
|
/*isVolatile*/ false, EntryBB);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
auto *MulA = BinaryOperator::CreateMul(X, Y, "", EntryBB);
|
|
|
|
|
auto *MulB = BinaryOperator::CreateMul(Y, X, "", EntryBB);
|
|
|
|
|
ReturnInst::Create(Context, nullptr, EntryBB);
|
|
|
|
|
|
|
|
|
|
// This test isn't checking for correctness. Today making A and B resolve to
|
|
|
|
|
// the same SCEV would require deeper searching in CompareValueComplexity,
|
|
|
|
|
// which will slow down compilation. However, this test can fail (with LLVM's
|
|
|
|
|
// behavior still being correct) if we ever have a smarter
|
|
|
|
|
// CompareValueComplexity that is both fast and more accurate.
|
|
|
|
|
|
|
|
|
|
ScalarEvolution SE = buildSE(*F);
|
|
|
|
|
auto *A = SE.getSCEV(MulA);
|
|
|
|
|
auto *B = SE.getSCEV(MulB);
|
|
|
|
|
EXPECT_NE(A, B);
|
|
|
|
|
}
|
|
|
|
|
|
2017-02-06 20:38:06 +08:00
|
|
|
TEST_F(ScalarEvolutionsTest, SCEVAddExpr) {
|
|
|
|
|
Type *Ty32 = Type::getInt32Ty(Context);
|
|
|
|
|
Type *ArgTys[] = {Type::getInt64Ty(Context), Ty32};
|
|
|
|
|
|
|
|
|
|
FunctionType *FTy =
|
|
|
|
|
FunctionType::get(Type::getVoidTy(Context), ArgTys, false);
|
|
|
|
|
Function *F = cast<Function>(M.getOrInsertFunction("f", FTy));
|
|
|
|
|
|
|
|
|
|
Argument *A1 = &*F->arg_begin();
|
|
|
|
|
Argument *A2 = &*(std::next(F->arg_begin()));
|
|
|
|
|
BasicBlock *EntryBB = BasicBlock::Create(Context, "entry", F);
|
|
|
|
|
|
|
|
|
|
Instruction *Trunc = CastInst::CreateTruncOrBitCast(A1, Ty32, "", EntryBB);
|
|
|
|
|
Instruction *Mul1 = BinaryOperator::CreateMul(Trunc, A2, "", EntryBB);
|
|
|
|
|
Instruction *Add1 = BinaryOperator::CreateAdd(Mul1, Trunc, "", EntryBB);
|
|
|
|
|
Mul1 = BinaryOperator::CreateMul(Add1, Trunc, "", EntryBB);
|
|
|
|
|
Instruction *Add2 = BinaryOperator::CreateAdd(Mul1, Add1, "", EntryBB);
|
2017-02-07 05:27:12 +08:00
|
|
|
// FIXME: The size of this is arbitrary and doesn't seem to change the
|
|
|
|
|
// result, but SCEV will do quadratic work for these so a large number here
|
|
|
|
|
// will be extremely slow. We should revisit what and how this is testing
|
|
|
|
|
// SCEV.
|
|
|
|
|
for (int i = 0; i < 10; i++) {
|
2017-02-06 20:38:06 +08:00
|
|
|
Mul1 = BinaryOperator::CreateMul(Add2, Add1, "", EntryBB);
|
|
|
|
|
Add1 = Add2;
|
|
|
|
|
Add2 = BinaryOperator::CreateAdd(Mul1, Add1, "", EntryBB);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
ReturnInst::Create(Context, nullptr, EntryBB);
|
|
|
|
|
ScalarEvolution SE = buildSE(*F);
|
|
|
|
|
EXPECT_NE(nullptr, SE.getSCEV(Mul1));
|
|
|
|
|
}
|
|
|
|
|
|
2017-04-14 23:50:04 +08:00
|
|
|
static Instruction &GetInstByName(Function &F, StringRef Name) {
|
|
|
|
|
for (auto &I : instructions(F))
|
|
|
|
|
if (I.getName() == Name)
|
|
|
|
|
return I;
|
|
|
|
|
llvm_unreachable("Could not find instructions!");
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
TEST_F(ScalarEvolutionsTest, SCEVNormalization) {
|
|
|
|
|
LLVMContext C;
|
|
|
|
|
SMDiagnostic Err;
|
|
|
|
|
std::unique_ptr<Module> M = parseAssemblyString(
|
|
|
|
|
"target datalayout = \"e-m:e-p:32:32-f64:32:64-f80:32-n8:16:32-S128\" "
|
|
|
|
|
" "
|
|
|
|
|
"@var_0 = external global i32, align 4"
|
|
|
|
|
"@var_1 = external global i32, align 4"
|
|
|
|
|
"@var_2 = external global i32, align 4"
|
|
|
|
|
" "
|
|
|
|
|
"declare i32 @unknown(i32, i32, i32)"
|
|
|
|
|
" "
|
|
|
|
|
"define void @f_1(i8* nocapture %arr, i32 %n, i32* %A, i32* %B) "
|
|
|
|
|
" local_unnamed_addr { "
|
|
|
|
|
"entry: "
|
|
|
|
|
" br label %loop.ph "
|
|
|
|
|
" "
|
|
|
|
|
"loop.ph: "
|
|
|
|
|
" br label %loop "
|
|
|
|
|
" "
|
|
|
|
|
"loop: "
|
|
|
|
|
" %iv0 = phi i32 [ %iv0.inc, %loop ], [ 0, %loop.ph ] "
|
|
|
|
|
" %iv1 = phi i32 [ %iv1.inc, %loop ], [ -2147483648, %loop.ph ] "
|
|
|
|
|
" %iv0.inc = add i32 %iv0, 1 "
|
|
|
|
|
" %iv1.inc = add i32 %iv1, 3 "
|
|
|
|
|
" br i1 undef, label %for.end.loopexit, label %loop "
|
|
|
|
|
" "
|
|
|
|
|
"for.end.loopexit: "
|
|
|
|
|
" ret void "
|
|
|
|
|
"} "
|
2017-04-25 08:09:19 +08:00
|
|
|
" "
|
|
|
|
|
"define void @f_2(i32 %a, i32 %b, i32 %c, i32 %d) "
|
|
|
|
|
" local_unnamed_addr { "
|
|
|
|
|
"entry: "
|
|
|
|
|
" br label %loop_0 "
|
|
|
|
|
" "
|
|
|
|
|
"loop_0: "
|
|
|
|
|
" br i1 undef, label %loop_0, label %loop_1 "
|
|
|
|
|
" "
|
|
|
|
|
"loop_1: "
|
|
|
|
|
" br i1 undef, label %loop_2, label %loop_1 "
|
|
|
|
|
" "
|
|
|
|
|
" "
|
|
|
|
|
"loop_2: "
|
|
|
|
|
" br i1 undef, label %end, label %loop_2 "
|
|
|
|
|
" "
|
|
|
|
|
"end: "
|
|
|
|
|
" ret void "
|
|
|
|
|
"} "
|
2017-04-14 23:50:04 +08:00
|
|
|
,
|
|
|
|
|
Err, C);
|
|
|
|
|
|
|
|
|
|
assert(M && "Could not parse module?");
|
|
|
|
|
assert(!verifyModule(*M) && "Must have been well formed!");
|
|
|
|
|
|
2017-04-15 07:47:53 +08:00
|
|
|
runWithSE(*M, "f_1", [&](Function &F, LoopInfo &LI, ScalarEvolution &SE) {
|
2017-04-14 23:50:04 +08:00
|
|
|
auto &I0 = GetInstByName(F, "iv0");
|
|
|
|
|
auto &I1 = *I0.getNextNode();
|
|
|
|
|
|
|
|
|
|
auto *S0 = cast<SCEVAddRecExpr>(SE.getSCEV(&I0));
|
|
|
|
|
PostIncLoopSet Loops;
|
|
|
|
|
Loops.insert(S0->getLoop());
|
|
|
|
|
auto *N0 = normalizeForPostIncUse(S0, Loops, SE);
|
|
|
|
|
auto *D0 = denormalizeForPostIncUse(N0, Loops, SE);
|
|
|
|
|
EXPECT_EQ(S0, D0) << *S0 << " " << *D0;
|
|
|
|
|
|
|
|
|
|
auto *S1 = cast<SCEVAddRecExpr>(SE.getSCEV(&I1));
|
|
|
|
|
Loops.clear();
|
|
|
|
|
Loops.insert(S1->getLoop());
|
|
|
|
|
auto *N1 = normalizeForPostIncUse(S1, Loops, SE);
|
|
|
|
|
auto *D1 = denormalizeForPostIncUse(N1, Loops, SE);
|
|
|
|
|
EXPECT_EQ(S1, D1) << *S1 << " " << *D1;
|
|
|
|
|
});
|
2017-04-25 08:09:19 +08:00
|
|
|
|
|
|
|
|
runWithSE(*M, "f_2", [&](Function &F, LoopInfo &LI, ScalarEvolution &SE) {
|
|
|
|
|
auto *L2 = *LI.begin();
|
|
|
|
|
auto *L1 = *std::next(LI.begin());
|
|
|
|
|
auto *L0 = *std::next(LI.begin(), 2);
|
|
|
|
|
|
|
|
|
|
auto GetAddRec = [&SE](const Loop *L, std::initializer_list<const SCEV *> Ops) {
|
|
|
|
|
SmallVector<const SCEV *, 4> OpsCopy(Ops);
|
|
|
|
|
return SE.getAddRecExpr(OpsCopy, L, SCEV::FlagAnyWrap);
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
auto GetAdd = [&SE](std::initializer_list<const SCEV *> Ops) {
|
|
|
|
|
SmallVector<const SCEV *, 4> OpsCopy(Ops);
|
|
|
|
|
return SE.getAddExpr(OpsCopy, SCEV::FlagAnyWrap);
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
// We first populate the AddRecs vector with a few "interesting" SCEV
|
|
|
|
|
// expressions, and then we go through the list and assert that each
|
|
|
|
|
// expression in it has an invertible normalization.
|
|
|
|
|
|
|
|
|
|
std::vector<const SCEV *> Exprs;
|
|
|
|
|
{
|
|
|
|
|
const SCEV *V0 = SE.getSCEV(&*F.arg_begin());
|
|
|
|
|
const SCEV *V1 = SE.getSCEV(&*std::next(F.arg_begin(), 1));
|
|
|
|
|
const SCEV *V2 = SE.getSCEV(&*std::next(F.arg_begin(), 2));
|
|
|
|
|
const SCEV *V3 = SE.getSCEV(&*std::next(F.arg_begin(), 3));
|
|
|
|
|
|
|
|
|
|
Exprs.push_back(GetAddRec(L0, {V0})); // 0
|
|
|
|
|
Exprs.push_back(GetAddRec(L0, {V0, V1})); // 1
|
|
|
|
|
Exprs.push_back(GetAddRec(L0, {V0, V1, V2})); // 2
|
|
|
|
|
Exprs.push_back(GetAddRec(L0, {V0, V1, V2, V3})); // 3
|
|
|
|
|
|
|
|
|
|
Exprs.push_back(
|
|
|
|
|
GetAddRec(L1, {Exprs[1], Exprs[2], Exprs[3], Exprs[0]})); // 4
|
|
|
|
|
Exprs.push_back(
|
|
|
|
|
GetAddRec(L1, {Exprs[1], Exprs[2], Exprs[0], Exprs[3]})); // 5
|
|
|
|
|
Exprs.push_back(
|
|
|
|
|
GetAddRec(L1, {Exprs[1], Exprs[3], Exprs[3], Exprs[1]})); // 6
|
|
|
|
|
|
|
|
|
|
Exprs.push_back(GetAdd({Exprs[6], Exprs[3], V2})); // 7
|
|
|
|
|
|
|
|
|
|
Exprs.push_back(
|
|
|
|
|
GetAddRec(L2, {Exprs[4], Exprs[3], Exprs[3], Exprs[5]})); // 8
|
|
|
|
|
|
|
|
|
|
Exprs.push_back(
|
|
|
|
|
GetAddRec(L2, {Exprs[4], Exprs[6], Exprs[7], Exprs[3], V0})); // 9
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
std::vector<PostIncLoopSet> LoopSets;
|
|
|
|
|
for (int i = 0; i < 8; i++) {
|
|
|
|
|
LoopSets.emplace_back();
|
|
|
|
|
if (i & 1)
|
|
|
|
|
LoopSets.back().insert(L0);
|
|
|
|
|
if (i & 2)
|
|
|
|
|
LoopSets.back().insert(L1);
|
|
|
|
|
if (i & 4)
|
|
|
|
|
LoopSets.back().insert(L2);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
for (const auto &LoopSet : LoopSets)
|
|
|
|
|
for (auto *S : Exprs) {
|
|
|
|
|
{
|
|
|
|
|
auto *N = llvm::normalizeForPostIncUse(S, LoopSet, SE);
|
|
|
|
|
auto *D = llvm::denormalizeForPostIncUse(N, LoopSet, SE);
|
|
|
|
|
|
|
|
|
|
// Normalization and then denormalizing better give us back the same
|
|
|
|
|
// value.
|
|
|
|
|
EXPECT_EQ(S, D) << "S = " << *S << " D = " << *D << " N = " << *N;
|
|
|
|
|
}
|
|
|
|
|
{
|
|
|
|
|
auto *D = llvm::denormalizeForPostIncUse(S, LoopSet, SE);
|
|
|
|
|
auto *N = llvm::normalizeForPostIncUse(D, LoopSet, SE);
|
|
|
|
|
|
|
|
|
|
// Denormalization and then normalizing better give us back the same
|
|
|
|
|
// value.
|
|
|
|
|
EXPECT_EQ(S, N) << "S = " << *S << " N = " << *N;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
});
|
2017-04-14 23:50:04 +08:00
|
|
|
}
|
|
|
|
|
|
2017-04-18 04:40:05 +08:00
|
|
|
// Expect the call of getZeroExtendExpr will not cost exponential time.
|
|
|
|
|
TEST_F(ScalarEvolutionsTest, SCEVZeroExtendExpr) {
|
|
|
|
|
LLVMContext C;
|
|
|
|
|
SMDiagnostic Err;
|
|
|
|
|
|
|
|
|
|
// Generate a function like below:
|
|
|
|
|
// define void @foo() {
|
|
|
|
|
// entry:
|
|
|
|
|
// br label %for.cond
|
|
|
|
|
//
|
|
|
|
|
// for.cond:
|
|
|
|
|
// %0 = phi i64 [ 100, %entry ], [ %dec, %for.inc ]
|
|
|
|
|
// %cmp = icmp sgt i64 %0, 90
|
|
|
|
|
// br i1 %cmp, label %for.inc, label %for.cond1
|
|
|
|
|
//
|
|
|
|
|
// for.inc:
|
|
|
|
|
// %dec = add nsw i64 %0, -1
|
|
|
|
|
// br label %for.cond
|
|
|
|
|
//
|
|
|
|
|
// for.cond1:
|
|
|
|
|
// %1 = phi i64 [ 100, %for.cond ], [ %dec5, %for.inc2 ]
|
|
|
|
|
// %cmp3 = icmp sgt i64 %1, 90
|
|
|
|
|
// br i1 %cmp3, label %for.inc2, label %for.cond4
|
|
|
|
|
//
|
|
|
|
|
// for.inc2:
|
|
|
|
|
// %dec5 = add nsw i64 %1, -1
|
|
|
|
|
// br label %for.cond1
|
|
|
|
|
//
|
|
|
|
|
// ......
|
|
|
|
|
//
|
|
|
|
|
// for.cond89:
|
|
|
|
|
// %19 = phi i64 [ 100, %for.cond84 ], [ %dec94, %for.inc92 ]
|
|
|
|
|
// %cmp93 = icmp sgt i64 %19, 90
|
|
|
|
|
// br i1 %cmp93, label %for.inc92, label %for.end
|
|
|
|
|
//
|
|
|
|
|
// for.inc92:
|
|
|
|
|
// %dec94 = add nsw i64 %19, -1
|
|
|
|
|
// br label %for.cond89
|
|
|
|
|
//
|
|
|
|
|
// for.end:
|
|
|
|
|
// %gep = getelementptr i8, i8* null, i64 %dec
|
|
|
|
|
// %gep6 = getelementptr i8, i8* %gep, i64 %dec5
|
|
|
|
|
// ......
|
|
|
|
|
// %gep95 = getelementptr i8, i8* %gep91, i64 %dec94
|
|
|
|
|
// ret void
|
|
|
|
|
// }
|
|
|
|
|
FunctionType *FTy = FunctionType::get(Type::getVoidTy(Context), {}, false);
|
|
|
|
|
Function *F = cast<Function>(M.getOrInsertFunction("foo", FTy));
|
|
|
|
|
|
|
|
|
|
BasicBlock *EntryBB = BasicBlock::Create(Context, "entry", F);
|
|
|
|
|
BasicBlock *CondBB = BasicBlock::Create(Context, "for.cond", F);
|
|
|
|
|
BasicBlock *EndBB = BasicBlock::Create(Context, "for.end", F);
|
|
|
|
|
BranchInst::Create(CondBB, EntryBB);
|
|
|
|
|
BasicBlock *PrevBB = EntryBB;
|
|
|
|
|
|
|
|
|
|
Type *I64Ty = Type::getInt64Ty(Context);
|
|
|
|
|
Type *I8Ty = Type::getInt8Ty(Context);
|
|
|
|
|
Type *I8PtrTy = Type::getInt8PtrTy(Context);
|
|
|
|
|
Value *Accum = Constant::getNullValue(I8PtrTy);
|
|
|
|
|
int Iters = 20;
|
|
|
|
|
for (int i = 0; i < Iters; i++) {
|
|
|
|
|
BasicBlock *IncBB = BasicBlock::Create(Context, "for.inc", F, EndBB);
|
|
|
|
|
auto *PN = PHINode::Create(I64Ty, 2, "", CondBB);
|
|
|
|
|
PN->addIncoming(ConstantInt::get(Context, APInt(64, 100)), PrevBB);
|
|
|
|
|
auto *Cmp = CmpInst::Create(Instruction::ICmp, CmpInst::ICMP_SGT, PN,
|
|
|
|
|
ConstantInt::get(Context, APInt(64, 90)), "cmp",
|
|
|
|
|
CondBB);
|
|
|
|
|
BasicBlock *NextBB;
|
|
|
|
|
if (i != Iters - 1)
|
|
|
|
|
NextBB = BasicBlock::Create(Context, "for.cond", F, EndBB);
|
|
|
|
|
else
|
|
|
|
|
NextBB = EndBB;
|
|
|
|
|
BranchInst::Create(IncBB, NextBB, Cmp, CondBB);
|
|
|
|
|
auto *Dec = BinaryOperator::CreateNSWAdd(
|
|
|
|
|
PN, ConstantInt::get(Context, APInt(64, -1)), "dec", IncBB);
|
|
|
|
|
PN->addIncoming(Dec, IncBB);
|
|
|
|
|
BranchInst::Create(CondBB, IncBB);
|
|
|
|
|
|
|
|
|
|
Accum = GetElementPtrInst::Create(I8Ty, Accum, Dec, "gep", EndBB);
|
|
|
|
|
|
|
|
|
|
PrevBB = CondBB;
|
|
|
|
|
CondBB = NextBB;
|
|
|
|
|
}
|
|
|
|
|
ReturnInst::Create(Context, nullptr, EndBB);
|
|
|
|
|
ScalarEvolution SE = buildSE(*F);
|
|
|
|
|
const SCEV *S = SE.getSCEV(Accum);
|
|
|
|
|
Type *I128Ty = Type::getInt128Ty(Context);
|
|
|
|
|
SE.getZeroExtendExpr(S, I128Ty);
|
|
|
|
|
}
|
2017-05-27 11:22:55 +08:00
|
|
|
|
|
|
|
|
// Make sure that SCEV doesn't introduce illegal ptrtoint/inttoptr instructions
|
|
|
|
|
TEST_F(ScalarEvolutionsTest, SCEVZeroExtendExprNonIntegral) {
|
|
|
|
|
/*
|
|
|
|
|
* Create the following code:
|
|
|
|
|
* func(i64 addrspace(10)* %arg)
|
|
|
|
|
* top:
|
|
|
|
|
* br label %L.ph
|
|
|
|
|
* L.ph:
|
|
|
|
|
* br label %L
|
|
|
|
|
* L:
|
|
|
|
|
* %phi = phi i64 [i64 0, %L.ph], [ %add, %L2 ]
|
|
|
|
|
* %add = add i64 %phi2, 1
|
|
|
|
|
* br i1 undef, label %post, label %L2
|
|
|
|
|
* post:
|
|
|
|
|
* %gepbase = getelementptr i64 addrspace(10)* %arg, i64 1
|
|
|
|
|
* #= %gep = getelementptr i64 addrspace(10)* %gepbase, i64 %add =#
|
|
|
|
|
* ret void
|
|
|
|
|
*
|
|
|
|
|
* We will create the appropriate SCEV expression for %gep and expand it,
|
|
|
|
|
* then check that no inttoptr/ptrtoint instructions got inserted.
|
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
// Create a module with non-integral pointers in it's datalayout
|
|
|
|
|
Module NIM("nonintegral", Context);
|
|
|
|
|
std::string DataLayout = M.getDataLayoutStr();
|
|
|
|
|
if (!DataLayout.empty())
|
|
|
|
|
DataLayout += "-";
|
|
|
|
|
DataLayout += "ni:10";
|
|
|
|
|
NIM.setDataLayout(DataLayout);
|
|
|
|
|
|
|
|
|
|
Type *T_int1 = Type::getInt1Ty(Context);
|
|
|
|
|
Type *T_int64 = Type::getInt64Ty(Context);
|
|
|
|
|
Type *T_pint64 = T_int64->getPointerTo(10);
|
|
|
|
|
|
|
|
|
|
FunctionType *FTy =
|
|
|
|
|
FunctionType::get(Type::getVoidTy(Context), {T_pint64}, false);
|
|
|
|
|
Function *F = cast<Function>(NIM.getOrInsertFunction("foo", FTy));
|
|
|
|
|
|
|
|
|
|
Argument *Arg = &*F->arg_begin();
|
|
|
|
|
|
|
|
|
|
BasicBlock *Top = BasicBlock::Create(Context, "top", F);
|
|
|
|
|
BasicBlock *LPh = BasicBlock::Create(Context, "L.ph", F);
|
|
|
|
|
BasicBlock *L = BasicBlock::Create(Context, "L", F);
|
|
|
|
|
BasicBlock *Post = BasicBlock::Create(Context, "post", F);
|
|
|
|
|
|
|
|
|
|
IRBuilder<> Builder(Top);
|
|
|
|
|
Builder.CreateBr(LPh);
|
|
|
|
|
|
|
|
|
|
Builder.SetInsertPoint(LPh);
|
|
|
|
|
Builder.CreateBr(L);
|
|
|
|
|
|
|
|
|
|
Builder.SetInsertPoint(L);
|
|
|
|
|
PHINode *Phi = Builder.CreatePHI(T_int64, 2);
|
|
|
|
|
Value *Add = Builder.CreateAdd(Phi, ConstantInt::get(T_int64, 1), "add");
|
|
|
|
|
Builder.CreateCondBr(UndefValue::get(T_int1), L, Post);
|
|
|
|
|
Phi->addIncoming(ConstantInt::get(T_int64, 0), LPh);
|
|
|
|
|
Phi->addIncoming(Add, L);
|
|
|
|
|
|
|
|
|
|
Builder.SetInsertPoint(Post);
|
|
|
|
|
Value *GepBase = Builder.CreateGEP(Arg, {ConstantInt::get(T_int64, 1)});
|
|
|
|
|
Instruction *Ret = Builder.CreateRetVoid();
|
|
|
|
|
|
|
|
|
|
ScalarEvolution SE = buildSE(*F);
|
|
|
|
|
auto *AddRec =
|
|
|
|
|
SE.getAddRecExpr(SE.getUnknown(GepBase), SE.getConstant(T_int64, 1),
|
|
|
|
|
LI->getLoopFor(L), SCEV::FlagNUW);
|
|
|
|
|
|
|
|
|
|
SCEVExpander Exp(SE, NIM.getDataLayout(), "expander");
|
|
|
|
|
Exp.disableCanonicalMode();
|
|
|
|
|
Exp.expandCodeFor(AddRec, T_pint64, Ret);
|
|
|
|
|
|
|
|
|
|
// Make sure none of the instructions inserted were inttoptr/ptrtoint.
|
|
|
|
|
// The verifier will check this.
|
|
|
|
|
EXPECT_FALSE(verifyFunction(*F, &errs()));
|
|
|
|
|
}
|
|
|
|
|
|
2010-08-03 07:49:30 +08:00
|
|
|
} // end anonymous namespace
|
|
|
|
|
} // end namespace llvm
|