diff options
Diffstat (limited to 'llvm/test/Transforms/LoopDistribute/scev-inserted-runtime-check.ll')
| -rw-r--r-- | llvm/test/Transforms/LoopDistribute/scev-inserted-runtime-check.ll | 83 |
1 files changed, 82 insertions, 1 deletions
diff --git a/llvm/test/Transforms/LoopDistribute/scev-inserted-runtime-check.ll b/llvm/test/Transforms/LoopDistribute/scev-inserted-runtime-check.ll index 2b1fc7c7d14..8ad19cb4707 100644 --- a/llvm/test/Transforms/LoopDistribute/scev-inserted-runtime-check.ll +++ b/llvm/test/Transforms/LoopDistribute/scev-inserted-runtime-check.ll @@ -7,7 +7,6 @@ target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128" ; 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: [[A2:%.*]] = ptrtoint i32* [[A:%.*]] to i64 @@ -101,6 +100,7 @@ define void @f(i32* noalias %a, i32* noalias %b, i32* noalias %c, i32* noalias % ; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_END]], label [[FOR_BODY]] ; CHECK: for.end: ; CHECK-NEXT: ret void +; entry: br label %for.body @@ -143,3 +143,84 @@ for.body: ; preds = %for.body, %entry for.end: ; preds = %for.body ret void } + +; 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 } |
