From 73f60e398890941521d55868705c0b539ed80f94 Mon Sep 17 00:00:00 2001 From: Roman Lebedev Date: Mon, 19 Apr 2021 16:48:02 +0300 Subject: [PATCH] [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. --- .../Transforms/Utils/ScalarEvolutionExpander.cpp | 5 ++- .../wrapping-pointer-versioning.ll | 2 ++ .../LoopDistribute/scev-inserted-runtime-check.ll | 36 +++++++++++----------- 3 files changed, 24 insertions(+), 19 deletions(-) diff --git a/llvm/lib/Transforms/Utils/ScalarEvolutionExpander.cpp b/llvm/lib/Transforms/Utils/ScalarEvolutionExpander.cpp index 2c9b4cb..4d70b91 100644 --- a/llvm/lib/Transforms/Utils/ScalarEvolutionExpander.cpp +++ b/llvm/lib/Transforms/Utils/ScalarEvolutionExpander.cpp @@ -2495,7 +2495,10 @@ Value *SCEVExpander::generateOverflowCheck(const SCEVAddRecExpr *AR, Value *StepValue = expandCodeForImpl(Step, Ty, Loc, false); Value *NegStepValue = expandCodeForImpl(SE.getNegativeSCEV(Step), Ty, Loc, false); - Value *StartValue = expandCodeForImpl(Start, ARExpandTy, Loc, false); + Value *StartValue = expandCodeForImpl( + isa(ARExpandTy) ? Start + : SE.getPtrToIntExpr(Start, ARExpandTy), + ARExpandTy, Loc, false); ConstantInt *Zero = ConstantInt::get(Loc->getContext(), APInt::getNullValue(DstBits)); diff --git a/llvm/test/Analysis/LoopAccessAnalysis/wrapping-pointer-versioning.ll b/llvm/test/Analysis/LoopAccessAnalysis/wrapping-pointer-versioning.ll index 80ada52..7a0d068 100644 --- a/llvm/test/Analysis/LoopAccessAnalysis/wrapping-pointer-versioning.ll +++ b/llvm/test/Analysis/LoopAccessAnalysis/wrapping-pointer-versioning.ll @@ -55,6 +55,8 @@ target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128" ; LV-NEXT: [[Or0:%[^ ]*]] = or i1 false, [[PredCheck0]] +; LV-NEXT: [[A0:%[^ ]*]] = ptrtoint i16* %a to i64 + ; LV-NEXT: [[OFMul1:%[^ ]*]] = call { i64, i1 } @llvm.umul.with.overflow.i64(i64 4, i64 [[BE]]) ; LV-NEXT: [[OFMulResult1:%[^ ]*]] = extractvalue { i64, i1 } [[OFMul1]], 0 ; LV-NEXT: [[OFMulOverflow1:%[^ ]*]] = extractvalue { i64, i1 } [[OFMul1]], 1 diff --git a/llvm/test/Transforms/LoopDistribute/scev-inserted-runtime-check.ll b/llvm/test/Transforms/LoopDistribute/scev-inserted-runtime-check.ll index 238d53f..c9a6bf8 100644 --- a/llvm/test/Transforms/LoopDistribute/scev-inserted-runtime-check.ll +++ b/llvm/test/Transforms/LoopDistribute/scev-inserted-runtime-check.ll @@ -9,7 +9,6 @@ target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128" 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: [[A2:%.*]] = ptrtoint i32* [[A:%.*]] to i64 ; CHECK-NEXT: br label [[FOR_BODY_LVER_CHECK:%.*]] ; CHECK: for.body.lver.check: ; CHECK-NEXT: [[TMP0:%.*]] = add i64 [[N:%.*]], -1 @@ -26,17 +25,18 @@ define void @f(i32* noalias %a, i32* noalias %b, i32* noalias %c, i32* noalias % ; CHECK-NEXT: [[TMP8:%.*]] = or i1 [[TMP6]], [[TMP7]] ; CHECK-NEXT: [[TMP9:%.*]] = or i1 [[TMP8]], [[MUL_OVERFLOW]] ; CHECK-NEXT: [[TMP10:%.*]] = or i1 false, [[TMP9]] -; CHECK-NEXT: [[MUL3:%.*]] = call { i64, i1 } @llvm.umul.with.overflow.i64(i64 8, i64 [[TMP0]]) -; CHECK-NEXT: [[MUL_RESULT4:%.*]] = extractvalue { i64, i1 } [[MUL3]], 0 -; CHECK-NEXT: [[MUL_OVERFLOW5:%.*]] = extractvalue { i64, i1 } [[MUL3]], 1 -; CHECK-NEXT: [[TMP11:%.*]] = add i64 [[A2]], [[MUL_RESULT4]] -; CHECK-NEXT: [[TMP12:%.*]] = sub i64 [[A2]], [[MUL_RESULT4]] -; CHECK-NEXT: [[TMP13:%.*]] = icmp ugt i64 [[TMP12]], [[A2]] -; CHECK-NEXT: [[TMP14:%.*]] = icmp ult i64 [[TMP11]], [[A2]] -; CHECK-NEXT: [[TMP15:%.*]] = select i1 false, i1 [[TMP13]], i1 [[TMP14]] -; CHECK-NEXT: [[TMP16:%.*]] = or i1 [[TMP15]], [[MUL_OVERFLOW5]] -; CHECK-NEXT: [[TMP17:%.*]] = or i1 [[TMP10]], [[TMP16]] -; CHECK-NEXT: br i1 [[TMP17]], label [[FOR_BODY_PH_LVER_ORIG:%.*]], label [[FOR_BODY_PH_LDIST1:%.*]] +; 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:%.*]] ; CHECK: for.body.ph.lver.orig: ; CHECK-NEXT: br label [[FOR_BODY_LVER_ORIG:%.*]] ; CHECK: for.body.lver.orig: @@ -97,10 +97,10 @@ define void @f(i32* noalias %a, i32* noalias %b, i32* noalias %c, i32* noalias % ; 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_LOOPEXIT6:%.*]], label [[FOR_BODY]] +; 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.loopexit6: +; CHECK: for.end.loopexit5: ; CHECK-NEXT: br label [[FOR_END]] ; CHECK: for.end: ; CHECK-NEXT: ret void @@ -177,10 +177,10 @@ define void @f_with_offset(i32* noalias %b, i32* noalias %c, i32* noalias %d, i3 ; 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: [[TMP11:%.*]] = add i64 ptrtoint (i32* getelementptr inbounds ([8192 x i32], [8192 x i32]* @global_a, i64 0, i64 42) to i64), [[MUL_RESULT3]] -; CHECK-NEXT: [[TMP12:%.*]] = sub i64 ptrtoint (i32* getelementptr inbounds ([8192 x i32], [8192 x i32]* @global_a, i64 0, i64 42) to i64), [[MUL_RESULT3]] -; CHECK-NEXT: [[TMP13:%.*]] = icmp ugt i64 [[TMP12]], ptrtoint (i32* getelementptr inbounds ([8192 x i32], [8192 x i32]* @global_a, i64 0, i64 42) to i64) -; CHECK-NEXT: [[TMP14:%.*]] = icmp ult i64 [[TMP11]], ptrtoint (i32* getelementptr inbounds ([8192 x i32], [8192 x i32]* @global_a, i64 0, i64 42) to i64) +; 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) ; 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]] -- 2.7.4