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/scev-inserted-runtime-check.ll

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

383 lines
21 KiB
LLVM
Raw Normal View History

LoopDistribute: Add testcase where SCEV wants to insert a runtime check. Only the memory based checks were being tested. Prepare for fix in convergent handling. llvm-svn: 362854
2019-06-08 07:17:38 +08:00
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
[BasicAA] Rename deprecated -basicaa to -basic-aa Follow-up to D82607 Revert an accidental change (empty.ll) of D82683
2020-06-27 11:41:37 +08:00
; RUN: opt -basic-aa -loop-distribute -enable-loop-distribute -S -enable-mem-access-versioning=0 < %s | FileCheck %s
LoopDistribute: Add testcase where SCEV wants to insert a runtime check. Only the memory based checks were being tested. Prepare for fix in convergent handling. llvm-svn: 362854
2019-06-08 07:17:38 +08:00
target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
; PredicatedScalarEvolution decides it needs to insert a bounds check
; not based on memory access.
define void @f(i32* noalias %a, i32* noalias %b, i32* noalias %c, i32* noalias %d, i32* noalias %e, i64 %N) {
; CHECK-LABEL: @f(
; CHECK-NEXT: entry:
; CHECK-NEXT: br label [[FOR_BODY_LVER_CHECK:%.*]]
; CHECK: for.body.lver.check:
; CHECK-NEXT: [[TMP0:%.*]] = add i64 [[N:%.*]], -1
; CHECK-NEXT: [[TMP1:%.*]] = trunc i64 [[TMP0]] to i32
; CHECK-NEXT: [[MUL1:%.*]] = call { i32, i1 } @llvm.umul.with.overflow.i32(i32 2, i32 [[TMP1]])
; CHECK-NEXT: [[MUL_RESULT:%.*]] = extractvalue { i32, i1 } [[MUL1]], 0
; CHECK-NEXT: [[MUL_OVERFLOW:%.*]] = extractvalue { i32, i1 } [[MUL1]], 1
; CHECK-NEXT: [[TMP2:%.*]] = add i32 0, [[MUL_RESULT]]
; CHECK-NEXT: [[TMP3:%.*]] = sub i32 0, [[MUL_RESULT]]
; CHECK-NEXT: [[TMP4:%.*]] = icmp ugt i32 [[TMP3]], 0
; CHECK-NEXT: [[TMP5:%.*]] = icmp ult i32 [[TMP2]], 0
; CHECK-NEXT: [[TMP6:%.*]] = select i1 false, i1 [[TMP4]], i1 [[TMP5]]
; CHECK-NEXT: [[TMP7:%.*]] = icmp ugt i64 [[TMP0]], 4294967295
; CHECK-NEXT: [[TMP8:%.*]] = or i1 [[TMP6]], [[TMP7]]
; CHECK-NEXT: [[TMP9:%.*]] = or i1 [[TMP8]], [[MUL_OVERFLOW]]
Revert "[IRBuilder] Fold consistently for or/and whether constant is LHS or RHS" This reverts commit r365260 which broke the following tests: Clang :: CodeGenCXX/cfi-mfcall.cpp Clang :: CodeGenObjC/ubsan-nullability.m LLVM :: Transforms/LoopVectorize/AArch64/pr36032.ll llvm-svn: 365284
2019-07-08 06:12:01 +08:00
; CHECK-NEXT: [[TMP10:%.*]] = or i1 false, [[TMP9]]
[SCEVExpander] generateOverflowCheck(): explicitly PtrToInt the Start Currently, InsertNoopCastOfTo() would implicitly insert that cast, but now that we have SCEVPtrToIntExpr, i'm hoping we could stop InsertNoopCastOfTo() from doing that. But first all users must be fixed.
2021-04-19 21:48:02 +08:00
; CHECK-NEXT: [[TMP11:%.*]] = ptrtoint i32* [[A:%.*]] to i64
; CHECK-NEXT: [[MUL2:%.*]] = call { i64, i1 } @llvm.umul.with.overflow.i64(i64 8, i64 [[TMP0]])
; CHECK-NEXT: [[MUL_RESULT3:%.*]] = extractvalue { i64, i1 } [[MUL2]], 0
; CHECK-NEXT: [[MUL_OVERFLOW4:%.*]] = extractvalue { i64, i1 } [[MUL2]], 1
; CHECK-NEXT: [[TMP12:%.*]] = add i64 [[TMP11]], [[MUL_RESULT3]]
; CHECK-NEXT: [[TMP13:%.*]] = sub i64 [[TMP11]], [[MUL_RESULT3]]
; CHECK-NEXT: [[TMP14:%.*]] = icmp ugt i64 [[TMP13]], [[TMP11]]
; CHECK-NEXT: [[TMP15:%.*]] = icmp ult i64 [[TMP12]], [[TMP11]]
; CHECK-NEXT: [[TMP16:%.*]] = select i1 false, i1 [[TMP14]], i1 [[TMP15]]
; CHECK-NEXT: [[TMP17:%.*]] = or i1 [[TMP16]], [[MUL_OVERFLOW4]]
; CHECK-NEXT: [[TMP18:%.*]] = or i1 [[TMP10]], [[TMP17]]
; CHECK-NEXT: br i1 [[TMP18]], label [[FOR_BODY_PH_LVER_ORIG:%.*]], label [[FOR_BODY_PH_LDIST1:%.*]]
LoopDistribute: Add testcase where SCEV wants to insert a runtime check. Only the memory based checks were being tested. Prepare for fix in convergent handling. llvm-svn: 362854
2019-06-08 07:17:38 +08:00
; CHECK: for.body.ph.lver.orig:
; CHECK-NEXT: br label [[FOR_BODY_LVER_ORIG:%.*]]
; CHECK: for.body.lver.orig:
; CHECK-NEXT: [[IND_LVER_ORIG:%.*]] = phi i64 [ 0, [[FOR_BODY_PH_LVER_ORIG]] ], [ [[ADD_LVER_ORIG:%.*]], [[FOR_BODY_LVER_ORIG]] ]
; CHECK-NEXT: [[IND1_LVER_ORIG:%.*]] = phi i32 [ 0, [[FOR_BODY_PH_LVER_ORIG]] ], [ [[INC1_LVER_ORIG:%.*]], [[FOR_BODY_LVER_ORIG]] ]
; CHECK-NEXT: [[MUL_LVER_ORIG:%.*]] = mul i32 [[IND1_LVER_ORIG]], 2
; CHECK-NEXT: [[MUL_EXT_LVER_ORIG:%.*]] = zext i32 [[MUL_LVER_ORIG]] to i64
; CHECK-NEXT: [[ARRAYIDXA_LVER_ORIG:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[MUL_EXT_LVER_ORIG]]
; CHECK-NEXT: [[LOADA_LVER_ORIG:%.*]] = load i32, i32* [[ARRAYIDXA_LVER_ORIG]], align 4
; CHECK-NEXT: [[ARRAYIDXB_LVER_ORIG:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i64 [[MUL_EXT_LVER_ORIG]]
; CHECK-NEXT: [[LOADB_LVER_ORIG:%.*]] = load i32, i32* [[ARRAYIDXB_LVER_ORIG]], align 4
; CHECK-NEXT: [[MULA_LVER_ORIG:%.*]] = mul i32 [[LOADB_LVER_ORIG]], [[LOADA_LVER_ORIG]]
; CHECK-NEXT: [[ADD_LVER_ORIG]] = add nuw nsw i64 [[IND_LVER_ORIG]], 1
; CHECK-NEXT: [[INC1_LVER_ORIG]] = add i32 [[IND1_LVER_ORIG]], 1
; CHECK-NEXT: [[ARRAYIDXA_PLUS_4_LVER_ORIG:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[ADD_LVER_ORIG]]
; CHECK-NEXT: store i32 [[MULA_LVER_ORIG]], i32* [[ARRAYIDXA_PLUS_4_LVER_ORIG]], align 4
; CHECK-NEXT: [[ARRAYIDXD_LVER_ORIG:%.*]] = getelementptr inbounds i32, i32* [[D:%.*]], i64 [[MUL_EXT_LVER_ORIG]]
; CHECK-NEXT: [[LOADD_LVER_ORIG:%.*]] = load i32, i32* [[ARRAYIDXD_LVER_ORIG]], align 4
; CHECK-NEXT: [[ARRAYIDXE_LVER_ORIG:%.*]] = getelementptr inbounds i32, i32* [[E:%.*]], i64 [[MUL_EXT_LVER_ORIG]]
; CHECK-NEXT: [[LOADE_LVER_ORIG:%.*]] = load i32, i32* [[ARRAYIDXE_LVER_ORIG]], align 4
; CHECK-NEXT: [[MULC_LVER_ORIG:%.*]] = mul i32 [[LOADD_LVER_ORIG]], [[LOADE_LVER_ORIG]]
; CHECK-NEXT: [[ARRAYIDXC_LVER_ORIG:%.*]] = getelementptr inbounds i32, i32* [[C:%.*]], i64 [[MUL_EXT_LVER_ORIG]]
; CHECK-NEXT: store i32 [[MULC_LVER_ORIG]], i32* [[ARRAYIDXC_LVER_ORIG]], align 4
; CHECK-NEXT: [[EXITCOND_LVER_ORIG:%.*]] = icmp eq i64 [[ADD_LVER_ORIG]], [[N]]
[NFC][SCEVExpander][LoopDistribute] Regenerate scev-inserted-runtime-check.ll check lines
2021-04-19 21:44:13 +08:00
; CHECK-NEXT: br i1 [[EXITCOND_LVER_ORIG]], label [[FOR_END_LOOPEXIT:%.*]], label [[FOR_BODY_LVER_ORIG]]
LoopDistribute: Add testcase where SCEV wants to insert a runtime check. Only the memory based checks were being tested. Prepare for fix in convergent handling. llvm-svn: 362854
2019-06-08 07:17:38 +08:00
; CHECK: for.body.ph.ldist1:
; CHECK-NEXT: br label [[FOR_BODY_LDIST1:%.*]]
; CHECK: for.body.ldist1:
; CHECK-NEXT: [[IND_LDIST1:%.*]] = phi i64 [ 0, [[FOR_BODY_PH_LDIST1]] ], [ [[ADD_LDIST1:%.*]], [[FOR_BODY_LDIST1]] ]
; CHECK-NEXT: [[IND1_LDIST1:%.*]] = phi i32 [ 0, [[FOR_BODY_PH_LDIST1]] ], [ [[INC1_LDIST1:%.*]], [[FOR_BODY_LDIST1]] ]
; CHECK-NEXT: [[MUL_LDIST1:%.*]] = mul i32 [[IND1_LDIST1]], 2
; CHECK-NEXT: [[MUL_EXT_LDIST1:%.*]] = zext i32 [[MUL_LDIST1]] to i64
; CHECK-NEXT: [[ARRAYIDXA_LDIST1:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[MUL_EXT_LDIST1]]
[NFC][SCEVExpander][LoopDistribute] Regenerate scev-inserted-runtime-check.ll check lines
2021-04-19 21:44:13 +08:00
; CHECK-NEXT: [[LOADA_LDIST1:%.*]] = load i32, i32* [[ARRAYIDXA_LDIST1]], align 4, !alias.scope !0
LoopDistribute: Add testcase where SCEV wants to insert a runtime check. Only the memory based checks were being tested. Prepare for fix in convergent handling. llvm-svn: 362854
2019-06-08 07:17:38 +08:00
; CHECK-NEXT: [[ARRAYIDXB_LDIST1:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[MUL_EXT_LDIST1]]
Revert "[IRBuilder] Fold consistently for or/and whether constant is LHS or RHS" This reverts commit r365260 which broke the following tests: Clang :: CodeGenCXX/cfi-mfcall.cpp Clang :: CodeGenObjC/ubsan-nullability.m LLVM :: Transforms/LoopVectorize/AArch64/pr36032.ll llvm-svn: 365284
2019-07-08 06:12:01 +08:00
; CHECK-NEXT: [[LOADB_LDIST1:%.*]] = load i32, i32* [[ARRAYIDXB_LDIST1]], align 4
LoopDistribute: Add testcase where SCEV wants to insert a runtime check. Only the memory based checks were being tested. Prepare for fix in convergent handling. llvm-svn: 362854
2019-06-08 07:17:38 +08:00
; CHECK-NEXT: [[MULA_LDIST1:%.*]] = mul i32 [[LOADB_LDIST1]], [[LOADA_LDIST1]]
; CHECK-NEXT: [[ADD_LDIST1]] = add nuw nsw i64 [[IND_LDIST1]], 1
; CHECK-NEXT: [[INC1_LDIST1]] = add i32 [[IND1_LDIST1]], 1
; CHECK-NEXT: [[ARRAYIDXA_PLUS_4_LDIST1:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[ADD_LDIST1]]
[NFC][SCEVExpander][LoopDistribute] Regenerate scev-inserted-runtime-check.ll check lines
2021-04-19 21:44:13 +08:00
; CHECK-NEXT: store i32 [[MULA_LDIST1]], i32* [[ARRAYIDXA_PLUS_4_LDIST1]], align 4, !alias.scope !3
LoopDistribute: Add testcase where SCEV wants to insert a runtime check. Only the memory based checks were being tested. Prepare for fix in convergent handling. llvm-svn: 362854
2019-06-08 07:17:38 +08:00
; CHECK-NEXT: [[EXITCOND_LDIST1:%.*]] = icmp eq i64 [[ADD_LDIST1]], [[N]]
; CHECK-NEXT: br i1 [[EXITCOND_LDIST1]], label [[FOR_BODY_PH:%.*]], label [[FOR_BODY_LDIST1]]
; CHECK: for.body.ph:
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[IND:%.*]] = phi i64 [ 0, [[FOR_BODY_PH]] ], [ [[ADD:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT: [[IND1:%.*]] = phi i32 [ 0, [[FOR_BODY_PH]] ], [ [[INC1:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT: [[MUL:%.*]] = mul i32 [[IND1]], 2
; CHECK-NEXT: [[MUL_EXT:%.*]] = zext i32 [[MUL]] to i64
; CHECK-NEXT: [[ADD]] = add nuw nsw i64 [[IND]], 1
; CHECK-NEXT: [[INC1]] = add i32 [[IND1]], 1
; CHECK-NEXT: [[ARRAYIDXD:%.*]] = getelementptr inbounds i32, i32* [[D]], i64 [[MUL_EXT]]
Revert "[IRBuilder] Fold consistently for or/and whether constant is LHS or RHS" This reverts commit r365260 which broke the following tests: Clang :: CodeGenCXX/cfi-mfcall.cpp Clang :: CodeGenObjC/ubsan-nullability.m LLVM :: Transforms/LoopVectorize/AArch64/pr36032.ll llvm-svn: 365284
2019-07-08 06:12:01 +08:00
; CHECK-NEXT: [[LOADD:%.*]] = load i32, i32* [[ARRAYIDXD]], align 4
LoopDistribute: Add testcase where SCEV wants to insert a runtime check. Only the memory based checks were being tested. Prepare for fix in convergent handling. llvm-svn: 362854
2019-06-08 07:17:38 +08:00
; CHECK-NEXT: [[ARRAYIDXE:%.*]] = getelementptr inbounds i32, i32* [[E]], i64 [[MUL_EXT]]
Revert "[IRBuilder] Fold consistently for or/and whether constant is LHS or RHS" This reverts commit r365260 which broke the following tests: Clang :: CodeGenCXX/cfi-mfcall.cpp Clang :: CodeGenObjC/ubsan-nullability.m LLVM :: Transforms/LoopVectorize/AArch64/pr36032.ll llvm-svn: 365284
2019-07-08 06:12:01 +08:00
; CHECK-NEXT: [[LOADE:%.*]] = load i32, i32* [[ARRAYIDXE]], align 4
LoopDistribute: Add testcase where SCEV wants to insert a runtime check. Only the memory based checks were being tested. Prepare for fix in convergent handling. llvm-svn: 362854
2019-06-08 07:17:38 +08:00
; CHECK-NEXT: [[MULC:%.*]] = mul i32 [[LOADD]], [[LOADE]]
; CHECK-NEXT: [[ARRAYIDXC:%.*]] = getelementptr inbounds i32, i32* [[C]], i64 [[MUL_EXT]]
Revert "[IRBuilder] Fold consistently for or/and whether constant is LHS or RHS" This reverts commit r365260 which broke the following tests: Clang :: CodeGenCXX/cfi-mfcall.cpp Clang :: CodeGenObjC/ubsan-nullability.m LLVM :: Transforms/LoopVectorize/AArch64/pr36032.ll llvm-svn: 365284
2019-07-08 06:12:01 +08:00
; CHECK-NEXT: store i32 [[MULC]], i32* [[ARRAYIDXC]], align 4
LoopDistribute: Add testcase where SCEV wants to insert a runtime check. Only the memory based checks were being tested. Prepare for fix in convergent handling. llvm-svn: 362854
2019-06-08 07:17:38 +08:00
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i64 [[ADD]], [[N]]
[SCEVExpander] generateOverflowCheck(): explicitly PtrToInt the Start Currently, InsertNoopCastOfTo() would implicitly insert that cast, but now that we have SCEVPtrToIntExpr, i'm hoping we could stop InsertNoopCastOfTo() from doing that. But first all users must be fixed.
2021-04-19 21:48:02 +08:00
; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_END_LOOPEXIT5:%.*]], label [[FOR_BODY]]
[NFC][SCEVExpander][LoopDistribute] Regenerate scev-inserted-runtime-check.ll check lines
2021-04-19 21:44:13 +08:00
; CHECK: for.end.loopexit:
; CHECK-NEXT: br label [[FOR_END:%.*]]
[SCEVExpander] generateOverflowCheck(): explicitly PtrToInt the Start Currently, InsertNoopCastOfTo() would implicitly insert that cast, but now that we have SCEVPtrToIntExpr, i'm hoping we could stop InsertNoopCastOfTo() from doing that. But first all users must be fixed.
2021-04-19 21:48:02 +08:00
; CHECK: for.end.loopexit5:
[NFC][SCEVExpander][LoopDistribute] Regenerate scev-inserted-runtime-check.ll check lines
2021-04-19 21:44:13 +08:00
; CHECK-NEXT: br label [[FOR_END]]
LoopDistribute: Add testcase where SCEV wants to insert a runtime check. Only the memory based checks were being tested. Prepare for fix in convergent handling. llvm-svn: 362854
2019-06-08 07:17:38 +08:00
; CHECK: for.end:
; CHECK-NEXT: 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
;
LoopDistribute: Add testcase where SCEV wants to insert a runtime check. Only the memory based checks were being tested. Prepare for fix in convergent handling. llvm-svn: 362854
2019-06-08 07:17:38 +08:00
entry:
br label %for.body
for.body: ; preds = %for.body, %entry
%ind = phi i64 [ 0, %entry ], [ %add, %for.body ]
%ind1 = phi i32 [ 0, %entry ], [ %inc1, %for.body ]
%mul = mul i32 %ind1, 2
%mul_ext = zext i32 %mul to i64
[NFC][SCEVExpander][LoopDistribute] Add test for SCEVPtrToIntExpr in SCEVExpander::generateOverflowCheck() We shouldn't end up with ptrtoint-of-getelementptr there.
2021-04-19 21:46:08 +08:00
%arrayidxA = getelementptr inbounds i32, i32* %a, i64 %mul_ext
%loadA = load i32, i32* %arrayidxA, align 4
%arrayidxB = getelementptr inbounds i32, i32* %b, i64 %mul_ext
%loadB = load i32, i32* %arrayidxB, align 4
%mulA = mul i32 %loadB, %loadA
%add = add nuw nsw i64 %ind, 1
%inc1 = add i32 %ind1, 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 %mul_ext
%loadD = load i32, i32* %arrayidxD, align 4
%arrayidxE = getelementptr inbounds i32, i32* %e, i64 %mul_ext
%loadE = load i32, i32* %arrayidxE, align 4
%mulC = mul i32 %loadD, %loadE
%arrayidxC = getelementptr inbounds i32, i32* %c, i64 %mul_ext
store i32 %mulC, i32* %arrayidxC, align 4
%exitcond = icmp eq i64 %add, %N
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body
ret void
}
declare void @use64(i64)
@global_a = common local_unnamed_addr global [8192 x i32] zeroinitializer, align 16
define void @f_with_offset(i32* noalias %b, i32* noalias %c, i32* noalias %d, i32* noalias %e, i64 %N) {
; CHECK-LABEL: @f_with_offset(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[A_BASE:%.*]] = getelementptr [8192 x i32], [8192 x i32]* @global_a, i32 0, i32 0
; CHECK-NEXT: [[A_INTPTR:%.*]] = ptrtoint i32* [[A_BASE]] to i64
; CHECK-NEXT: call void @use64(i64 [[A_INTPTR]])
; CHECK-NEXT: [[A:%.*]] = getelementptr i32, i32* [[A_BASE]], i32 42
; CHECK-NEXT: br label [[FOR_BODY_LVER_CHECK:%.*]]
; CHECK: for.body.lver.check:
; CHECK-NEXT: [[TMP0:%.*]] = add i64 [[N:%.*]], -1
; CHECK-NEXT: [[TMP1:%.*]] = trunc i64 [[TMP0]] to i32
; CHECK-NEXT: [[MUL1:%.*]] = call { i32, i1 } @llvm.umul.with.overflow.i32(i32 2, i32 [[TMP1]])
; CHECK-NEXT: [[MUL_RESULT:%.*]] = extractvalue { i32, i1 } [[MUL1]], 0
; CHECK-NEXT: [[MUL_OVERFLOW:%.*]] = extractvalue { i32, i1 } [[MUL1]], 1
; CHECK-NEXT: [[TMP2:%.*]] = add i32 0, [[MUL_RESULT]]
; CHECK-NEXT: [[TMP3:%.*]] = sub i32 0, [[MUL_RESULT]]
; CHECK-NEXT: [[TMP4:%.*]] = icmp ugt i32 [[TMP3]], 0
; CHECK-NEXT: [[TMP5:%.*]] = icmp ult i32 [[TMP2]], 0
; CHECK-NEXT: [[TMP6:%.*]] = select i1 false, i1 [[TMP4]], i1 [[TMP5]]
; CHECK-NEXT: [[TMP7:%.*]] = icmp ugt i64 [[TMP0]], 4294967295
; CHECK-NEXT: [[TMP8:%.*]] = or i1 [[TMP6]], [[TMP7]]
; CHECK-NEXT: [[TMP9:%.*]] = or i1 [[TMP8]], [[MUL_OVERFLOW]]
; CHECK-NEXT: [[TMP10:%.*]] = or i1 false, [[TMP9]]
; CHECK-NEXT: [[MUL2:%.*]] = call { i64, i1 } @llvm.umul.with.overflow.i64(i64 8, i64 [[TMP0]])
; CHECK-NEXT: [[MUL_RESULT3:%.*]] = extractvalue { i64, i1 } [[MUL2]], 0
; CHECK-NEXT: [[MUL_OVERFLOW4:%.*]] = extractvalue { i64, i1 } [[MUL2]], 1
[SCEVExpander] generateOverflowCheck(): explicitly PtrToInt the Start Currently, InsertNoopCastOfTo() would implicitly insert that cast, but now that we have SCEVPtrToIntExpr, i'm hoping we could stop InsertNoopCastOfTo() from doing that. But first all users must be fixed.
2021-04-19 21:48:02 +08:00
; CHECK-NEXT: [[TMP11:%.*]] = add i64 add (i64 ptrtoint ([8192 x i32]* @global_a to i64), i64 168), [[MUL_RESULT3]]
; CHECK-NEXT: [[TMP12:%.*]] = sub i64 add (i64 ptrtoint ([8192 x i32]* @global_a to i64), i64 168), [[MUL_RESULT3]]
; CHECK-NEXT: [[TMP13:%.*]] = icmp ugt i64 [[TMP12]], add (i64 ptrtoint ([8192 x i32]* @global_a to i64), i64 168)
; CHECK-NEXT: [[TMP14:%.*]] = icmp ult i64 [[TMP11]], add (i64 ptrtoint ([8192 x i32]* @global_a to i64), i64 168)
[NFC][SCEVExpander][LoopDistribute] Add test for SCEVPtrToIntExpr in SCEVExpander::generateOverflowCheck() We shouldn't end up with ptrtoint-of-getelementptr there.
2021-04-19 21:46:08 +08:00
; CHECK-NEXT: [[TMP15:%.*]] = select i1 false, i1 [[TMP13]], i1 [[TMP14]]
; CHECK-NEXT: [[TMP16:%.*]] = or i1 [[TMP15]], [[MUL_OVERFLOW4]]
; CHECK-NEXT: [[TMP17:%.*]] = or i1 [[TMP10]], [[TMP16]]
; CHECK-NEXT: br i1 [[TMP17]], label [[FOR_BODY_PH_LVER_ORIG:%.*]], label [[FOR_BODY_PH_LDIST1:%.*]]
; CHECK: for.body.ph.lver.orig:
; CHECK-NEXT: br label [[FOR_BODY_LVER_ORIG:%.*]]
; CHECK: for.body.lver.orig:
; CHECK-NEXT: [[IND_LVER_ORIG:%.*]] = phi i64 [ 0, [[FOR_BODY_PH_LVER_ORIG]] ], [ [[ADD_LVER_ORIG:%.*]], [[FOR_BODY_LVER_ORIG]] ]
; CHECK-NEXT: [[IND1_LVER_ORIG:%.*]] = phi i32 [ 0, [[FOR_BODY_PH_LVER_ORIG]] ], [ [[INC1_LVER_ORIG:%.*]], [[FOR_BODY_LVER_ORIG]] ]
; CHECK-NEXT: [[MUL_LVER_ORIG:%.*]] = mul i32 [[IND1_LVER_ORIG]], 2
; CHECK-NEXT: [[MUL_EXT_LVER_ORIG:%.*]] = zext i32 [[MUL_LVER_ORIG]] to i64
; CHECK-NEXT: [[ARRAYIDXA_LVER_ORIG:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[MUL_EXT_LVER_ORIG]]
; CHECK-NEXT: [[LOADA_LVER_ORIG:%.*]] = load i32, i32* [[ARRAYIDXA_LVER_ORIG]], align 4
; CHECK-NEXT: [[ARRAYIDXB_LVER_ORIG:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i64 [[MUL_EXT_LVER_ORIG]]
; CHECK-NEXT: [[LOADB_LVER_ORIG:%.*]] = load i32, i32* [[ARRAYIDXB_LVER_ORIG]], align 4
; CHECK-NEXT: [[MULA_LVER_ORIG:%.*]] = mul i32 [[LOADB_LVER_ORIG]], [[LOADA_LVER_ORIG]]
; CHECK-NEXT: [[ADD_LVER_ORIG]] = add nuw nsw i64 [[IND_LVER_ORIG]], 1
; CHECK-NEXT: [[INC1_LVER_ORIG]] = add i32 [[IND1_LVER_ORIG]], 1
; CHECK-NEXT: [[ARRAYIDXA_PLUS_4_LVER_ORIG:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[ADD_LVER_ORIG]]
; CHECK-NEXT: store i32 [[MULA_LVER_ORIG]], i32* [[ARRAYIDXA_PLUS_4_LVER_ORIG]], align 4
; CHECK-NEXT: [[ARRAYIDXD_LVER_ORIG:%.*]] = getelementptr inbounds i32, i32* [[D:%.*]], i64 [[MUL_EXT_LVER_ORIG]]
; CHECK-NEXT: [[LOADD_LVER_ORIG:%.*]] = load i32, i32* [[ARRAYIDXD_LVER_ORIG]], align 4
; CHECK-NEXT: [[ARRAYIDXE_LVER_ORIG:%.*]] = getelementptr inbounds i32, i32* [[E:%.*]], i64 [[MUL_EXT_LVER_ORIG]]
; CHECK-NEXT: [[LOADE_LVER_ORIG:%.*]] = load i32, i32* [[ARRAYIDXE_LVER_ORIG]], align 4
; CHECK-NEXT: [[MULC_LVER_ORIG:%.*]] = mul i32 [[LOADD_LVER_ORIG]], [[LOADE_LVER_ORIG]]
; CHECK-NEXT: [[ARRAYIDXC_LVER_ORIG:%.*]] = getelementptr inbounds i32, i32* [[C:%.*]], i64 [[MUL_EXT_LVER_ORIG]]
; CHECK-NEXT: store i32 [[MULC_LVER_ORIG]], i32* [[ARRAYIDXC_LVER_ORIG]], align 4
; CHECK-NEXT: [[EXITCOND_LVER_ORIG:%.*]] = icmp eq i64 [[ADD_LVER_ORIG]], [[N]]
; CHECK-NEXT: br i1 [[EXITCOND_LVER_ORIG]], label [[FOR_END_LOOPEXIT:%.*]], label [[FOR_BODY_LVER_ORIG]]
; CHECK: for.body.ph.ldist1:
; CHECK-NEXT: br label [[FOR_BODY_LDIST1:%.*]]
; CHECK: for.body.ldist1:
; CHECK-NEXT: [[IND_LDIST1:%.*]] = phi i64 [ 0, [[FOR_BODY_PH_LDIST1]] ], [ [[ADD_LDIST1:%.*]], [[FOR_BODY_LDIST1]] ]
; CHECK-NEXT: [[IND1_LDIST1:%.*]] = phi i32 [ 0, [[FOR_BODY_PH_LDIST1]] ], [ [[INC1_LDIST1:%.*]], [[FOR_BODY_LDIST1]] ]
; CHECK-NEXT: [[MUL_LDIST1:%.*]] = mul i32 [[IND1_LDIST1]], 2
; CHECK-NEXT: [[MUL_EXT_LDIST1:%.*]] = zext i32 [[MUL_LDIST1]] to i64
; CHECK-NEXT: [[ARRAYIDXA_LDIST1:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[MUL_EXT_LDIST1]]
; CHECK-NEXT: [[LOADA_LDIST1:%.*]] = load i32, i32* [[ARRAYIDXA_LDIST1]], align 4, !alias.scope !5
; CHECK-NEXT: [[ARRAYIDXB_LDIST1:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[MUL_EXT_LDIST1]]
; CHECK-NEXT: [[LOADB_LDIST1:%.*]] = load i32, i32* [[ARRAYIDXB_LDIST1]], align 4
; CHECK-NEXT: [[MULA_LDIST1:%.*]] = mul i32 [[LOADB_LDIST1]], [[LOADA_LDIST1]]
; CHECK-NEXT: [[ADD_LDIST1]] = add nuw nsw i64 [[IND_LDIST1]], 1
; CHECK-NEXT: [[INC1_LDIST1]] = add i32 [[IND1_LDIST1]], 1
; CHECK-NEXT: [[ARRAYIDXA_PLUS_4_LDIST1:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[ADD_LDIST1]]
; CHECK-NEXT: store i32 [[MULA_LDIST1]], i32* [[ARRAYIDXA_PLUS_4_LDIST1]], align 4, !alias.scope !8
; CHECK-NEXT: [[EXITCOND_LDIST1:%.*]] = icmp eq i64 [[ADD_LDIST1]], [[N]]
; CHECK-NEXT: br i1 [[EXITCOND_LDIST1]], label [[FOR_BODY_PH:%.*]], label [[FOR_BODY_LDIST1]]
; CHECK: for.body.ph:
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[IND:%.*]] = phi i64 [ 0, [[FOR_BODY_PH]] ], [ [[ADD:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT: [[IND1:%.*]] = phi i32 [ 0, [[FOR_BODY_PH]] ], [ [[INC1:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT: [[MUL:%.*]] = mul i32 [[IND1]], 2
; CHECK-NEXT: [[MUL_EXT:%.*]] = zext i32 [[MUL]] to i64
; CHECK-NEXT: [[ADD]] = add nuw nsw i64 [[IND]], 1
; CHECK-NEXT: [[INC1]] = add i32 [[IND1]], 1
; CHECK-NEXT: [[ARRAYIDXD:%.*]] = getelementptr inbounds i32, i32* [[D]], i64 [[MUL_EXT]]
; CHECK-NEXT: [[LOADD:%.*]] = load i32, i32* [[ARRAYIDXD]], align 4
; CHECK-NEXT: [[ARRAYIDXE:%.*]] = getelementptr inbounds i32, i32* [[E]], i64 [[MUL_EXT]]
; CHECK-NEXT: [[LOADE:%.*]] = load i32, i32* [[ARRAYIDXE]], align 4
; CHECK-NEXT: [[MULC:%.*]] = mul i32 [[LOADD]], [[LOADE]]
; CHECK-NEXT: [[ARRAYIDXC:%.*]] = getelementptr inbounds i32, i32* [[C]], i64 [[MUL_EXT]]
; CHECK-NEXT: store i32 [[MULC]], i32* [[ARRAYIDXC]], align 4
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i64 [[ADD]], [[N]]
; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_END_LOOPEXIT5:%.*]], label [[FOR_BODY]]
; CHECK: for.end.loopexit:
; CHECK-NEXT: br label [[FOR_END:%.*]]
; CHECK: for.end.loopexit5:
; CHECK-NEXT: br label [[FOR_END]]
; CHECK: for.end:
; CHECK-NEXT: ret void
;
entry:
%a_base = getelementptr [8192 x i32], [8192 x i32]* @global_a, i32 0, i32 0
%a_intptr = ptrtoint i32* %a_base to i64
call void @use64(i64 %a_intptr)
%a = getelementptr i32, i32* %a_base, i32 42
br label %for.body
for.body: ; preds = %for.body, %entry
%ind = phi i64 [ 0, %entry ], [ %add, %for.body ]
%ind1 = phi i32 [ 0, %entry ], [ %inc1, %for.body ]
%mul = mul i32 %ind1, 2
%mul_ext = zext i32 %mul to i64
LoopDistribute: Add testcase where SCEV wants to insert a runtime check. Only the memory based checks were being tested. Prepare for fix in convergent handling. llvm-svn: 362854
2019-06-08 07:17:38 +08:00
%arrayidxA = getelementptr inbounds i32, i32* %a, i64 %mul_ext
%loadA = load i32, i32* %arrayidxA, align 4
%arrayidxB = getelementptr inbounds i32, i32* %b, i64 %mul_ext
%loadB = load i32, i32* %arrayidxB, align 4
%mulA = mul i32 %loadB, %loadA
%add = add nuw nsw i64 %ind, 1
%inc1 = add i32 %ind1, 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 %mul_ext
%loadD = load i32, i32* %arrayidxD, align 4
%arrayidxE = getelementptr inbounds i32, i32* %e, i64 %mul_ext
%loadE = load i32, i32* %arrayidxE, align 4
%mulC = mul i32 %loadD, %loadE
%arrayidxC = getelementptr inbounds i32, i32* %c, i64 %mul_ext
store i32 %mulC, i32* %arrayidxC, align 4
%exitcond = icmp eq i64 %add, %N
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body
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
; Can't add control dependency with convergent in loop body.
define void @f_with_convergent(i32* noalias %a, i32* noalias %b, i32* noalias %c, i32* noalias %d, i32* noalias %e, i64 %N) #1 {
; CHECK-LABEL: @f_with_convergent(
; CHECK-NEXT: entry:
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[IND:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[ADD:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT: [[IND1:%.*]] = phi i32 [ 0, [[ENTRY]] ], [ [[INC1:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT: [[MUL:%.*]] = mul i32 [[IND1]], 2
; CHECK-NEXT: [[MUL_EXT:%.*]] = zext i32 [[MUL]] to i64
; CHECK-NEXT: [[ARRAYIDXA:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i64 [[MUL_EXT]]
; CHECK-NEXT: [[LOADA:%.*]] = load i32, i32* [[ARRAYIDXA]], align 4
; CHECK-NEXT: [[ARRAYIDXB:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i64 [[MUL_EXT]]
; CHECK-NEXT: [[LOADB:%.*]] = load i32, i32* [[ARRAYIDXB]], align 4
; CHECK-NEXT: [[MULA:%.*]] = mul i32 [[LOADB]], [[LOADA]]
; CHECK-NEXT: [[ADD]] = add nuw nsw i64 [[IND]], 1
; CHECK-NEXT: [[INC1]] = add i32 [[IND1]], 1
; CHECK-NEXT: [[ARRAYIDXA_PLUS_4:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[ADD]]
; CHECK-NEXT: store i32 [[MULA]], i32* [[ARRAYIDXA_PLUS_4]], align 4
; CHECK-NEXT: [[ARRAYIDXD:%.*]] = getelementptr inbounds i32, i32* [[D:%.*]], i64 [[MUL_EXT]]
; CHECK-NEXT: [[LOADD:%.*]] = load i32, i32* [[ARRAYIDXD]], align 4
; CHECK-NEXT: [[ARRAYIDXE:%.*]] = getelementptr inbounds i32, i32* [[E:%.*]], i64 [[MUL_EXT]]
; CHECK-NEXT: [[LOADE:%.*]] = load i32, i32* [[ARRAYIDXE]], align 4
; CHECK-NEXT: [[CONVERGENTD:%.*]] = call i32 @llvm.convergent(i32 [[LOADD]])
; CHECK-NEXT: [[MULC:%.*]] = mul i32 [[CONVERGENTD]], [[LOADE]]
; CHECK-NEXT: [[ARRAYIDXC:%.*]] = getelementptr inbounds i32, i32* [[C:%.*]], i64 [[MUL_EXT]]
; CHECK-NEXT: store i32 [[MULC]], i32* [[ARRAYIDXC]], align 4
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i64 [[ADD]], [[N:%.*]]
; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_END:%.*]], label [[FOR_BODY]]
; CHECK: for.end:
; CHECK-NEXT: ret void
;
entry:
br label %for.body
for.body: ; preds = %for.body, %entry
%ind = phi i64 [ 0, %entry ], [ %add, %for.body ]
%ind1 = phi i32 [ 0, %entry ], [ %inc1, %for.body ]
%mul = mul i32 %ind1, 2
%mul_ext = zext i32 %mul to i64
%arrayidxA = getelementptr inbounds i32, i32* %a, i64 %mul_ext
%loadA = load i32, i32* %arrayidxA, align 4
%arrayidxB = getelementptr inbounds i32, i32* %b, i64 %mul_ext
%loadB = load i32, i32* %arrayidxB, align 4
%mulA = mul i32 %loadB, %loadA
%add = add nuw nsw i64 %ind, 1
%inc1 = add i32 %ind1, 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 %mul_ext
%loadD = load i32, i32* %arrayidxD, align 4
%arrayidxE = getelementptr inbounds i32, i32* %e, i64 %mul_ext
%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 %mul_ext
store i32 %mulC, i32* %arrayidxC, align 4
%exitcond = icmp eq i64 %add, %N
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body
ret void
}
declare i32 @llvm.convergent(i32) #0
attributes #0 = { nounwind readnone convergent }
attributes #1 = { nounwind convergent }