maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/Transforms/LoopDistribute/basic-with-memchecks.ll

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

289 lines
8.7 KiB
LLVM
Raw Normal View History

[test] Fixup tests with -analyze in llvm/test/Transforms
2021-09-05 07:43:53 +08:00
; RUN: opt -aa-pipeline=basic-aa -passes=loop-distribute -enable-loop-distribute -verify-loop-info -verify-dom-info -S \
Revert "Temporarily Revert "Add basic loop fusion pass."" The reversion apparently deleted the test/Transforms directory. Will be re-reverting again. llvm-svn: 358552
2019-04-17 12:52:47 +08:00
; RUN: < %s | FileCheck %s
[test] Fixup tests with -analyze in llvm/test/Transforms
2021-09-05 07:43:53 +08:00
; RUN: opt -aa-pipeline=basic-aa -passes='loop-distribute,loop-vectorize' -enable-loop-distribute -force-vector-width=4 \
Revert "Temporarily Revert "Add basic loop fusion pass."" The reversion apparently deleted the test/Transforms directory. Will be re-reverting again. llvm-svn: 358552
2019-04-17 12:52:47 +08:00
; RUN: -verify-loop-info -verify-dom-info -S < %s | \
; RUN: FileCheck --check-prefix=VECTORIZE %s
[test] Fixup tests with -analyze in llvm/test/Transforms
2021-09-05 07:43:53 +08:00
; RUN: opt -aa-pipeline=basic-aa -passes='loop-distribute,print-access-info' -enable-loop-distribute \
; RUN: -verify-loop-info -verify-dom-info -disable-output < %s 2>&1 | FileCheck %s --check-prefix=ANALYSIS
LoopDistribute/LAA: Respect convergent This case is slightly tricky, because loop distribution should be allowed in some cases, and not others. As long as runtime dependency checks don't need to be introduced, this should be OK. This is further complicated by the fact that LoopDistribute partially ignores if LAA says that vectorization is safe, and then does its own runtime pointer legality checks. Note this pass still does not handle noduplicate correctly, as this should always be forbidden with it. I'm not going to bother trying to fix it, as it would require more effort and I think noduplicate should be removed. https://reviews.llvm.org/D62607 llvm-svn: 363160
2019-06-12 21:34:19 +08:00
Revert "Temporarily Revert "Add basic loop fusion pass."" The reversion apparently deleted the test/Transforms directory. Will be re-reverting again. llvm-svn: 358552
2019-04-17 12:52:47 +08:00
; The memcheck version of basic.ll. We should distribute and vectorize the
; second part of this loop with 5 memchecks (A+1 x {C, D, E} + C x {A, B})
;
; for (i = 0; i < n; i++) {
; A[i + 1] = A[i] * B[i];
; -------------------------------
; C[i] = D[i] * E[i];
; }
target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-apple-macosx10.10.0"
@B = common global i32* null, align 8
@A = common global i32* null, align 8
@C = common global i32* null, align 8
@D = common global i32* null, align 8
@E = common global i32* null, align 8
LoopDistribute/LAA: Add tests to catch regressions I broke 2 of these with a patch, but were not covered by existing tests. https://reviews.llvm.org/D63035 llvm-svn: 363158
2019-06-12 21:15:59 +08:00
; CHECK-LABEL: @f(
Revert "Temporarily Revert "Add basic loop fusion pass."" The reversion apparently deleted the test/Transforms directory. Will be re-reverting again. llvm-svn: 358552
2019-04-17 12:52:47 +08:00
define void @f() {
entry:
%a = load i32*, i32** @A, align 8
%b = load i32*, i32** @B, align 8
%c = load i32*, i32** @C, align 8
%d = load i32*, i32** @D, align 8
%e = load i32*, i32** @E, align 8
br label %for.body
; We have two compares for each array overlap check.
; Since the checks to A and A + 4 get merged, this will give us a
; total of 8 compares.
;
; CHECK: for.body.lver.check:
; CHECK: = icmp
; CHECK: = icmp
; CHECK: = icmp
; CHECK: = icmp
; CHECK: = icmp
; CHECK: = icmp
; CHECK: = icmp
; CHECK: = icmp
; CHECK-NOT: = icmp
[LoopUtils] Simplify addRuntimeCheck to return a single value. This simplifies the return value of addRuntimeCheck from a pair of instructions to a single `Value *`. The existing users of addRuntimeChecks were ignoring the first element of the pair, hence there is not reason to track FirstInst and return it. Additionally all users of addRuntimeChecks use the second returned `Instruction *` just as `Value *`, so there is no need to return an `Instruction *`. Therefore there is no need to create a redundant dummy `and X, true` instruction any longer. Effectively this change should not impact the generated code because the redundant AND will be folded by later optimizations. But it is easy to avoid creating it in the first place and it allows more accurately estimating the cost of the runtime checks.
2021-10-19 00:55:48 +08:00
; CHECK: br i1 %conflict.rdx25, label %for.body.ph.lver.orig, label %for.body.ph.ldist1
Revert "Temporarily Revert "Add basic loop fusion pass."" The reversion apparently deleted the test/Transforms directory. Will be re-reverting again. llvm-svn: 358552
2019-04-17 12:52:47 +08:00
; The non-distributed loop that the memchecks fall back on.
; CHECK: for.body.ph.lver.orig:
; CHECK: br label %for.body.lver.orig
; CHECK: for.body.lver.orig:
[LoopVersioning] Form dedicated exits for versioned loop to preserve simplify form The exit blocks of the versioned and non-versioned loops are not dedicated and thus the two loops are not in simplify form. Insert dummy exit blocks after loop versioning with `formDedicatedExits()` to preserve the simplify form for subsequence passes. Reviewed By: aeubanks Differential Revision: https://reviews.llvm.org/D89569
2020-10-24 21:39:42 +08:00
; CHECK: br i1 %exitcond.lver.orig, label %for.end.loopexit, label %for.body.lver.orig
Revert "Temporarily Revert "Add basic loop fusion pass."" The reversion apparently deleted the test/Transforms directory. Will be re-reverting again. llvm-svn: 358552
2019-04-17 12:52:47 +08:00
; Verify the two distributed loops.
; CHECK: for.body.ph.ldist1:
; CHECK: br label %for.body.ldist1
; CHECK: for.body.ldist1:
; CHECK: %mulA.ldist1 = mul i32 %loadB.ldist1, %loadA.ldist1
; CHECK: br i1 %exitcond.ldist1, label %for.body.ph, label %for.body.ldist1
; CHECK: for.body.ph:
; CHECK: br label %for.body
; CHECK: for.body:
; CHECK: %mulC = mul i32 %loadD, %loadE
; CHECK: for.end:
; VECTORIZE: mul <4 x i32>
for.body: ; preds = %for.body, %entry
%ind = phi i64 [ 0, %entry ], [ %add, %for.body ]
%arrayidxA = getelementptr inbounds i32, i32* %a, i64 %ind
%loadA = load i32, i32* %arrayidxA, align 4
%arrayidxB = getelementptr inbounds i32, i32* %b, i64 %ind
%loadB = load i32, i32* %arrayidxB, align 4
%mulA = mul i32 %loadB, %loadA
%add = add nuw nsw i64 %ind, 1
%arrayidxA_plus_4 = getelementptr inbounds i32, i32* %a, i64 %add
store i32 %mulA, i32* %arrayidxA_plus_4, align 4
%arrayidxD = getelementptr inbounds i32, i32* %d, i64 %ind
%loadD = load i32, i32* %arrayidxD, align 4
%arrayidxE = getelementptr inbounds i32, i32* %e, i64 %ind
%loadE = load i32, i32* %arrayidxE, align 4
%mulC = mul i32 %loadD, %loadE
%arrayidxC = getelementptr inbounds i32, i32* %c, i64 %ind
store i32 %mulC, i32* %arrayidxC, align 4
%exitcond = icmp eq i64 %add, 20
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body
ret void
}
LoopDistribute/LAA: Add tests to catch regressions I broke 2 of these with a patch, but were not covered by existing tests. https://reviews.llvm.org/D63035 llvm-svn: 363158
2019-06-12 21:15:59 +08:00
; Make sure there's no "Multiple reports generated" assert with a
; volatile load, and no distribution
; TODO: Distribution of volatile may be possible under some
; circumstance, but the current implementation does not touch them.
; CHECK-LABEL: @f_volatile_load(
; CHECK: br label %for.body{{$}}
; CHECK-NOT: load
; CHECK: {{^}}for.body:
; CHECK: load i32
; CHECK: load i32
; CHECK: load volatile i32
; CHECK: load i32
; CHECK: br i1 %exitcond, label %for.end, label %for.body{{$}}
; CHECK-NOT: load
; VECTORIZE-NOT: load <4 x i32>
; VECTORIZE-NOT: mul <4 x i32>
define void @f_volatile_load() {
entry:
%a = load i32*, i32** @A, align 8
%b = load i32*, i32** @B, align 8
%c = load i32*, i32** @C, align 8
%d = load i32*, i32** @D, align 8
%e = load i32*, i32** @E, align 8
br label %for.body
for.body:
%ind = phi i64 [ 0, %entry ], [ %add, %for.body ]
%arrayidxA = getelementptr inbounds i32, i32* %a, i64 %ind
%loadA = load i32, i32* %arrayidxA, align 4
%arrayidxB = getelementptr inbounds i32, i32* %b, i64 %ind
%loadB = load i32, i32* %arrayidxB, align 4
%mulA = mul i32 %loadB, %loadA
%add = add nuw nsw i64 %ind, 1
%arrayidxA_plus_4 = getelementptr inbounds i32, i32* %a, i64 %add
store i32 %mulA, i32* %arrayidxA_plus_4, align 4
%arrayidxD = getelementptr inbounds i32, i32* %d, i64 %ind
%loadD = load volatile i32, i32* %arrayidxD, align 4
%arrayidxE = getelementptr inbounds i32, i32* %e, i64 %ind
%loadE = load i32, i32* %arrayidxE, align 4
%mulC = mul i32 %loadD, %loadE
%arrayidxC = getelementptr inbounds i32, i32* %c, i64 %ind
store i32 %mulC, i32* %arrayidxC, align 4
%exitcond = icmp eq i64 %add, 20
br i1 %exitcond, label %for.end, label %for.body
for.end:
ret void
}
LoopDistribute/LAA: Respect convergent This case is slightly tricky, because loop distribution should be allowed in some cases, and not others. As long as runtime dependency checks don't need to be introduced, this should be OK. This is further complicated by the fact that LoopDistribute partially ignores if LAA says that vectorization is safe, and then does its own runtime pointer legality checks. Note this pass still does not handle noduplicate correctly, as this should always be forbidden with it. I'm not going to bother trying to fix it, as it would require more effort and I think noduplicate should be removed. https://reviews.llvm.org/D62607 llvm-svn: 363160
2019-06-12 21:34:19 +08:00
declare i32 @llvm.convergent(i32) #0
; This is the same as f, and would require the same bounds
; check. However, it is not OK to introduce new control dependencies
; on the convergent call.
; CHECK-LABEL: @f_with_convergent(
; CHECK: call i32 @llvm.convergent
; CHECK-NOT: call i32 @llvm.convergent
; ANALYSIS: for.body:
; ANALYSIS: Report: cannot add control dependency to convergent operation
define void @f_with_convergent() #1 {
entry:
%a = load i32*, i32** @A, align 8
%b = load i32*, i32** @B, align 8
%c = load i32*, i32** @C, align 8
%d = load i32*, i32** @D, align 8
%e = load i32*, i32** @E, align 8
br label %for.body
for.body: ; preds = %for.body, %entry
%ind = phi i64 [ 0, %entry ], [ %add, %for.body ]
%arrayidxA = getelementptr inbounds i32, i32* %a, i64 %ind
%loadA = load i32, i32* %arrayidxA, align 4
%arrayidxB = getelementptr inbounds i32, i32* %b, i64 %ind
%loadB = load i32, i32* %arrayidxB, align 4
%mulA = mul i32 %loadB, %loadA
%add = add nuw nsw i64 %ind, 1
%arrayidxA_plus_4 = getelementptr inbounds i32, i32* %a, i64 %add
store i32 %mulA, i32* %arrayidxA_plus_4, align 4
%arrayidxD = getelementptr inbounds i32, i32* %d, i64 %ind
%loadD = load i32, i32* %arrayidxD, align 4
%arrayidxE = getelementptr inbounds i32, i32* %e, i64 %ind
%loadE = load i32, i32* %arrayidxE, align 4
%convergentD = call i32 @llvm.convergent(i32 %loadD)
%mulC = mul i32 %convergentD, %loadE
%arrayidxC = getelementptr inbounds i32, i32* %c, i64 %ind
store i32 %mulC, i32* %arrayidxC, align 4
%exitcond = icmp eq i64 %add, 20
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body
ret void
}
; Make sure an explicit request for distribution is ignored if it
; requires possibly illegal checks.
; CHECK-LABEL: @f_with_convergent_forced_distribute(
; CHECK: call i32 @llvm.convergent
; CHECK-NOT: call i32 @llvm.convergent
define void @f_with_convergent_forced_distribute() #1 {
entry:
%a = load i32*, i32** @A, align 8
%b = load i32*, i32** @B, align 8
%c = load i32*, i32** @C, align 8
%d = load i32*, i32** @D, align 8
%e = load i32*, i32** @E, align 8
br label %for.body
for.body: ; preds = %for.body, %entry
%ind = phi i64 [ 0, %entry ], [ %add, %for.body ]
%arrayidxA = getelementptr inbounds i32, i32* %a, i64 %ind
%loadA = load i32, i32* %arrayidxA, align 4
%arrayidxB = getelementptr inbounds i32, i32* %b, i64 %ind
%loadB = load i32, i32* %arrayidxB, align 4
%mulA = mul i32 %loadB, %loadA
%add = add nuw nsw i64 %ind, 1
%arrayidxA_plus_4 = getelementptr inbounds i32, i32* %a, i64 %add
store i32 %mulA, i32* %arrayidxA_plus_4, align 4
%arrayidxD = getelementptr inbounds i32, i32* %d, i64 %ind
%loadD = load i32, i32* %arrayidxD, align 4
%arrayidxE = getelementptr inbounds i32, i32* %e, i64 %ind
%loadE = load i32, i32* %arrayidxE, align 4
%convergentD = call i32 @llvm.convergent(i32 %loadD)
%mulC = mul i32 %convergentD, %loadE
%arrayidxC = getelementptr inbounds i32, i32* %c, i64 %ind
store i32 %mulC, i32* %arrayidxC, align 4
%exitcond = icmp eq i64 %add, 20
br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !0
for.end: ; preds = %for.body
ret void
}
attributes #0 = { nounwind readnone convergent }
attributes #1 = { nounwind convergent }
!0 = distinct !{!0, !1}
!1 = !{!"llvm.loop.distribute.enable", i1 true}