diff options
Diffstat (limited to 'llvm/test')
4 files changed, 41 insertions, 89 deletions
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/arbitrary-induction-step.ll b/llvm/test/Transforms/LoopVectorize/AArch64/arbitrary-induction-step.ll index 58315a73ec1..81ecd57b2a8 100644 --- a/llvm/test/Transforms/LoopVectorize/AArch64/arbitrary-induction-step.ll +++ b/llvm/test/Transforms/LoopVectorize/AArch64/arbitrary-induction-step.ll @@ -103,10 +103,10 @@ for.end: ; preds = %for.body ; CHECK-LABEL: @ptr_ind_plus2( ; CHECK: %[[V0:.*]] = load <8 x i32> -; CHECK: shufflevector <8 x i32> %[[V0]], <8 x i32> undef, <4 x i32> <i32 0, i32 2, i32 4, i32 6> -; CHECK: shufflevector <8 x i32> %[[V0]], <8 x i32> undef, <4 x i32> <i32 1, i32 3, i32 5, i32 7> ; CHECK: %[[V1:.*]] = load <8 x i32> +; CHECK: shufflevector <8 x i32> %[[V0]], <8 x i32> undef, <4 x i32> <i32 0, i32 2, i32 4, i32 6> ; CHECK: shufflevector <8 x i32> %[[V1]], <8 x i32> undef, <4 x i32> <i32 0, i32 2, i32 4, i32 6> +; CHECK: shufflevector <8 x i32> %[[V0]], <8 x i32> undef, <4 x i32> <i32 1, i32 3, i32 5, i32 7> ; CHECK: shufflevector <8 x i32> %[[V1]], <8 x i32> undef, <4 x i32> <i32 1, i32 3, i32 5, i32 7> ; CHECK: mul nsw <4 x i32> ; CHECK: mul nsw <4 x i32> diff --git a/llvm/test/Transforms/LoopVectorize/X86/scatter_crash.ll b/llvm/test/Transforms/LoopVectorize/X86/scatter_crash.ll index 4b9e996d408..5f165c52efc 100755 --- a/llvm/test/Transforms/LoopVectorize/X86/scatter_crash.ll +++ b/llvm/test/Transforms/LoopVectorize/X86/scatter_crash.ll @@ -39,102 +39,70 @@ define void @_Z3fn1v() #0 { ; CHECK-NEXT: [[IND30:%.*]] = add i64 %offset.idx, 30 ; CHECK-NEXT: [[TMP10:%.*]] = sub nsw <16 x i64> <i64 8, i64 8, i64 8, i64 8, i64 8, i64 8, i64 8, i64 8, i64 8, i64 8, i64 8, i64 8, i64 8, i64 8, i64 8, i64 8>, [[VEC_IND]] ; CHECK-NEXT: [[TMP12:%.*]] = getelementptr inbounds [10 x [10 x i32]], [10 x [10 x i32]]* @d, i64 0, i64 [[IND00]] -; CHECK-NEXT: [[TMP13:%.*]] = insertelement <16 x [10 x i32]*> undef, [10 x i32]* [[TMP12]], i32 0 ; CHECK-NEXT: [[TMP15:%.*]] = getelementptr inbounds [10 x [10 x i32]], [10 x [10 x i32]]* @d, i64 0, i64 [[IND02]] -; CHECK-NEXT: [[TMP16:%.*]] = insertelement <16 x [10 x i32]*> [[TMP13]], [10 x i32]* [[TMP15]], i32 1 ; CHECK-NEXT: [[TMP18:%.*]] = getelementptr inbounds [10 x [10 x i32]], [10 x [10 x i32]]* @d, i64 0, i64 [[IND04]] -; CHECK-NEXT: [[TMP19:%.*]] = insertelement <16 x [10 x i32]*> [[TMP16]], [10 x i32]* [[TMP18]], i32 2 ; CHECK-NEXT: [[TMP21:%.*]] = getelementptr inbounds [10 x [10 x i32]], [10 x [10 x i32]]* @d, i64 0, i64 [[IND06]] -; CHECK-NEXT: [[TMP22:%.*]] = insertelement <16 x [10 x i32]*> [[TMP19]], [10 x i32]* [[TMP21]], i32 3 ; CHECK-NEXT: [[TMP24:%.*]] = getelementptr inbounds [10 x [10 x i32]], [10 x [10 x i32]]* @d, i64 0, i64 [[IND08]] -; CHECK-NEXT: [[TMP25:%.*]] = insertelement <16 x [10 x i32]*> [[TMP22]], [10 x i32]* [[TMP24]], i32 4 ; CHECK-NEXT: [[TMP27:%.*]] = getelementptr inbounds [10 x [10 x i32]], [10 x [10 x i32]]* @d, i64 0, i64 [[IND10]] -; CHECK-NEXT: [[TMP28:%.*]] = insertelement <16 x [10 x i32]*> [[TMP25]], [10 x i32]* [[TMP27]], i32 5 ; CHECK-NEXT: [[TMP30:%.*]] = getelementptr inbounds [10 x [10 x i32]], [10 x [10 x i32]]* @d, i64 0, i64 [[IND12]] -; CHECK-NEXT: [[TMP31:%.*]] = insertelement <16 x [10 x i32]*> [[TMP28]], [10 x i32]* [[TMP30]], i32 6 ; CHECK-NEXT: [[TMP33:%.*]] = getelementptr inbounds [10 x [10 x i32]], [10 x [10 x i32]]* @d, i64 0, i64 [[IND14]] -; CHECK-NEXT: [[TMP34:%.*]] = insertelement <16 x [10 x i32]*> [[TMP31]], [10 x i32]* [[TMP33]], i32 7 ; CHECK-NEXT: [[TMP36:%.*]] = getelementptr inbounds [10 x [10 x i32]], [10 x [10 x i32]]* @d, i64 0, i64 [[IND16]] -; CHECK-NEXT: [[TMP37:%.*]] = insertelement <16 x [10 x i32]*> [[TMP34]], [10 x i32]* [[TMP36]], i32 8 ; CHECK-NEXT: [[TMP39:%.*]] = getelementptr inbounds [10 x [10 x i32]], [10 x [10 x i32]]* @d, i64 0, i64 [[IND18]] -; CHECK-NEXT: [[TMP40:%.*]] = insertelement <16 x [10 x i32]*> [[TMP37]], [10 x i32]* [[TMP39]], i32 9 ; CHECK-NEXT: [[TMP42:%.*]] = getelementptr inbounds [10 x [10 x i32]], [10 x [10 x i32]]* @d, i64 0, i64 [[IND20]] -; CHECK-NEXT: [[TMP43:%.*]] = insertelement <16 x [10 x i32]*> [[TMP40]], [10 x i32]* [[TMP42]], i32 10 ; CHECK-NEXT: [[TMP45:%.*]] = getelementptr inbounds [10 x [10 x i32]], [10 x [10 x i32]]* @d, i64 0, i64 [[IND22]] -; CHECK-NEXT: [[TMP46:%.*]] = insertelement <16 x [10 x i32]*> [[TMP43]], [10 x i32]* [[TMP45]], i32 11 ; CHECK-NEXT: [[TMP48:%.*]] = getelementptr inbounds [10 x [10 x i32]], [10 x [10 x i32]]* @d, i64 0, i64 [[IND24]] -; CHECK-NEXT: [[TMP49:%.*]] = insertelement <16 x [10 x i32]*> [[TMP46]], [10 x i32]* [[TMP48]], i32 12 ; CHECK-NEXT: [[TMP51:%.*]] = getelementptr inbounds [10 x [10 x i32]], [10 x [10 x i32]]* @d, i64 0, i64 [[IND26]] -; CHECK-NEXT: [[TMP52:%.*]] = insertelement <16 x [10 x i32]*> [[TMP49]], [10 x i32]* [[TMP51]], i32 13 ; CHECK-NEXT: [[TMP54:%.*]] = getelementptr inbounds [10 x [10 x i32]], [10 x [10 x i32]]* @d, i64 0, i64 [[IND28]] -; CHECK-NEXT: [[TMP55:%.*]] = insertelement <16 x [10 x i32]*> [[TMP52]], [10 x i32]* [[TMP54]], i32 14 ; CHECK-NEXT: [[TMP57:%.*]] = getelementptr inbounds [10 x [10 x i32]], [10 x [10 x i32]]* @d, i64 0, i64 [[IND30]] -; CHECK-NEXT: [[TMP58:%.*]] = insertelement <16 x [10 x i32]*> [[TMP55]], [10 x i32]* [[TMP57]], i32 15 ; CHECK-NEXT: [[TMP59:%.*]] = add nsw <16 x i64> [[TMP10]], [[VEC_IND3]] -; CHECK-NEXT: [[TMP60:%.*]] = extractelement <16 x [10 x i32]*> [[TMP58]], i32 0 ; CHECK-NEXT: [[TMP61:%.*]] = extractelement <16 x i64> [[TMP59]], i32 0 -; CHECK-NEXT: [[TMP62:%.*]] = getelementptr inbounds [10 x i32], [10 x i32]* [[TMP60]], i64 [[TMP61]], i64 0 -; CHECK-NEXT: [[TMP63:%.*]] = insertelement <16 x i32*> undef, i32* [[TMP62]], i32 0 -; CHECK-NEXT: [[TMP64:%.*]] = extractelement <16 x [10 x i32]*> [[TMP58]], i32 1 +; CHECK-NEXT: [[TMP62:%.*]] = getelementptr inbounds [10 x i32], [10 x i32]* [[TMP12]], i64 [[TMP61]], i64 0 ; CHECK-NEXT: [[TMP65:%.*]] = extractelement <16 x i64> [[TMP59]], i32 1 -; CHECK-NEXT: [[TMP66:%.*]] = getelementptr inbounds [10 x i32], [10 x i32]* [[TMP64]], i64 [[TMP65]], i64 0 -; CHECK-NEXT: [[TMP67:%.*]] = insertelement <16 x i32*> [[TMP63]], i32* [[TMP66]], i32 1 -; CHECK-NEXT: [[TMP68:%.*]] = extractelement <16 x [10 x i32]*> [[TMP58]], i32 2 +; CHECK-NEXT: [[TMP66:%.*]] = getelementptr inbounds [10 x i32], [10 x i32]* [[TMP15]], i64 [[TMP65]], i64 0 ; CHECK-NEXT: [[TMP69:%.*]] = extractelement <16 x i64> [[TMP59]], i32 2 -; CHECK-NEXT: [[TMP70:%.*]] = getelementptr inbounds [10 x i32], [10 x i32]* [[TMP68]], i64 [[TMP69]], i64 0 -; CHECK-NEXT: [[TMP71:%.*]] = insertelement <16 x i32*> [[TMP67]], i32* [[TMP70]], i32 2 -; CHECK-NEXT: [[TMP72:%.*]] = extractelement <16 x [10 x i32]*> [[TMP58]], i32 3 +; CHECK-NEXT: [[TMP70:%.*]] = getelementptr inbounds [10 x i32], [10 x i32]* [[TMP18]], i64 [[TMP69]], i64 0 ; CHECK-NEXT: [[TMP73:%.*]] = extractelement <16 x i64> [[TMP59]], i32 3 -; CHECK-NEXT: [[TMP74:%.*]] = getelementptr inbounds [10 x i32], [10 x i32]* [[TMP72]], i64 [[TMP73]], i64 0 -; CHECK-NEXT: [[TMP75:%.*]] = insertelement <16 x i32*> [[TMP71]], i32* [[TMP74]], i32 3 -; CHECK-NEXT: [[TMP76:%.*]] = extractelement <16 x [10 x i32]*> [[TMP58]], i32 4 +; CHECK-NEXT: [[TMP74:%.*]] = getelementptr inbounds [10 x i32], [10 x i32]* [[TMP21]], i64 [[TMP73]], i64 0 ; CHECK-NEXT: [[TMP77:%.*]] = extractelement <16 x i64> [[TMP59]], i32 4 -; CHECK-NEXT: [[TMP78:%.*]] = getelementptr inbounds [10 x i32], [10 x i32]* [[TMP76]], i64 [[TMP77]], i64 0 -; CHECK-NEXT: [[TMP79:%.*]] = insertelement <16 x i32*> [[TMP75]], i32* [[TMP78]], i32 4 -; CHECK-NEXT: [[TMP80:%.*]] = extractelement <16 x [10 x i32]*> [[TMP58]], i32 5 +; CHECK-NEXT: [[TMP78:%.*]] = getelementptr inbounds [10 x i32], [10 x i32]* [[TMP24]], i64 [[TMP77]], i64 0 ; CHECK-NEXT: [[TMP81:%.*]] = extractelement <16 x i64> [[TMP59]], i32 5 -; CHECK-NEXT: [[TMP82:%.*]] = getelementptr inbounds [10 x i32], [10 x i32]* [[TMP80]], i64 [[TMP81]], i64 0 -; CHECK-NEXT: [[TMP83:%.*]] = insertelement <16 x i32*> [[TMP79]], i32* [[TMP82]], i32 5 -; CHECK-NEXT: [[TMP84:%.*]] = extractelement <16 x [10 x i32]*> [[TMP58]], i32 6 +; CHECK-NEXT: [[TMP82:%.*]] = getelementptr inbounds [10 x i32], [10 x i32]* [[TMP27]], i64 [[TMP81]], i64 0 ; CHECK-NEXT: [[TMP85:%.*]] = extractelement <16 x i64> [[TMP59]], i32 6 -; CHECK-NEXT: [[TMP86:%.*]] = getelementptr inbounds [10 x i32], [10 x i32]* [[TMP84]], i64 [[TMP85]], i64 0 -; CHECK-NEXT: [[TMP87:%.*]] = insertelement <16 x i32*> [[TMP83]], i32* [[TMP86]], i32 6 -; CHECK-NEXT: [[TMP88:%.*]] = extractelement <16 x [10 x i32]*> [[TMP58]], i32 7 +; CHECK-NEXT: [[TMP86:%.*]] = getelementptr inbounds [10 x i32], [10 x i32]* [[TMP30]], i64 [[TMP85]], i64 0 ; CHECK-NEXT: [[TMP89:%.*]] = extractelement <16 x i64> [[TMP59]], i32 7 -; CHECK-NEXT: [[TMP90:%.*]] = getelementptr inbounds [10 x i32], [10 x i32]* [[TMP88]], i64 [[TMP89]], i64 0 -; CHECK-NEXT: [[TMP91:%.*]] = insertelement <16 x i32*> [[TMP87]], i32* [[TMP90]], i32 7 -; CHECK-NEXT: [[TMP92:%.*]] = extractelement <16 x [10 x i32]*> [[TMP58]], i32 8 +; CHECK-NEXT: [[TMP90:%.*]] = getelementptr inbounds [10 x i32], [10 x i32]* [[TMP33]], i64 [[TMP89]], i64 0 ; CHECK-NEXT: [[TMP93:%.*]] = extractelement <16 x i64> [[TMP59]], i32 8 -; CHECK-NEXT: [[TMP94:%.*]] = getelementptr inbounds [10 x i32], [10 x i32]* [[TMP92]], i64 [[TMP93]], i64 0 -; CHECK-NEXT: [[TMP95:%.*]] = insertelement <16 x i32*> [[TMP91]], i32* [[TMP94]], i32 8 -; CHECK-NEXT: [[TMP96:%.*]] = extractelement <16 x [10 x i32]*> [[TMP58]], i32 9 +; CHECK-NEXT: [[TMP94:%.*]] = getelementptr inbounds [10 x i32], [10 x i32]* [[TMP36]], i64 [[TMP93]], i64 0 ; CHECK-NEXT: [[TMP97:%.*]] = extractelement <16 x i64> [[TMP59]], i32 9 -; CHECK-NEXT: [[TMP98:%.*]] = getelementptr inbounds [10 x i32], [10 x i32]* [[TMP96]], i64 [[TMP97]], i64 0 -; CHECK-NEXT: [[TMP99:%.*]] = insertelement <16 x i32*> [[TMP95]], i32* [[TMP98]], i32 9 -; CHECK-NEXT: [[TMP100:%.*]] = extractelement <16 x [10 x i32]*> [[TMP58]], i32 10 +; CHECK-NEXT: [[TMP98:%.*]] = getelementptr inbounds [10 x i32], [10 x i32]* [[TMP39]], i64 [[TMP97]], i64 0 ; CHECK-NEXT: [[TMP101:%.*]] = extractelement <16 x i64> [[TMP59]], i32 10 -; CHECK-NEXT: [[TMP102:%.*]] = getelementptr inbounds [10 x i32], [10 x i32]* [[TMP100]], i64 [[TMP101]], i64 0 -; CHECK-NEXT: [[TMP103:%.*]] = insertelement <16 x i32*> [[TMP99]], i32* [[TMP102]], i32 10 -; CHECK-NEXT: [[TMP104:%.*]] = extractelement <16 x [10 x i32]*> [[TMP58]], i32 11 +; CHECK-NEXT: [[TMP102:%.*]] = getelementptr inbounds [10 x i32], [10 x i32]* [[TMP42]], i64 [[TMP101]], i64 0 ; CHECK-NEXT: [[TMP105:%.*]] = extractelement <16 x i64> [[TMP59]], i32 11 -; CHECK-NEXT: [[TMP106:%.*]] = getelementptr inbounds [10 x i32], [10 x i32]* [[TMP104]], i64 [[TMP105]], i64 0 -; CHECK-NEXT: [[TMP107:%.*]] = insertelement <16 x i32*> [[TMP103]], i32* [[TMP106]], i32 11 -; CHECK-NEXT: [[TMP108:%.*]] = extractelement <16 x [10 x i32]*> [[TMP58]], i32 12 +; CHECK-NEXT: [[TMP106:%.*]] = getelementptr inbounds [10 x i32], [10 x i32]* [[TMP45]], i64 [[TMP105]], i64 0 ; CHECK-NEXT: [[TMP109:%.*]] = extractelement <16 x i64> [[TMP59]], i32 12 -; CHECK-NEXT: [[TMP110:%.*]] = getelementptr inbounds [10 x i32], [10 x i32]* [[TMP108]], i64 [[TMP109]], i64 0 -; CHECK-NEXT: [[TMP111:%.*]] = insertelement <16 x i32*> [[TMP107]], i32* [[TMP110]], i32 12 -; CHECK-NEXT: [[TMP112:%.*]] = extractelement <16 x [10 x i32]*> [[TMP58]], i32 13 +; CHECK-NEXT: [[TMP110:%.*]] = getelementptr inbounds [10 x i32], [10 x i32]* [[TMP48]], i64 [[TMP109]], i64 0 ; CHECK-NEXT: [[TMP113:%.*]] = extractelement <16 x i64> [[TMP59]], i32 13 -; CHECK-NEXT: [[TMP114:%.*]] = getelementptr inbounds [10 x i32], [10 x i32]* [[TMP112]], i64 [[TMP113]], i64 0 -; CHECK-NEXT: [[TMP115:%.*]] = insertelement <16 x i32*> [[TMP111]], i32* [[TMP114]], i32 13 -; CHECK-NEXT: [[TMP116:%.*]] = extractelement <16 x [10 x i32]*> [[TMP58]], i32 14 +; CHECK-NEXT: [[TMP114:%.*]] = getelementptr inbounds [10 x i32], [10 x i32]* [[TMP51]], i64 [[TMP113]], i64 0 ; CHECK-NEXT: [[TMP117:%.*]] = extractelement <16 x i64> [[TMP59]], i32 14 -; CHECK-NEXT: [[TMP118:%.*]] = getelementptr inbounds [10 x i32], [10 x i32]* [[TMP116]], i64 [[TMP117]], i64 0 -; CHECK-NEXT: [[TMP119:%.*]] = insertelement <16 x i32*> [[TMP115]], i32* [[TMP118]], i32 14 -; CHECK-NEXT: [[TMP120:%.*]] = extractelement <16 x [10 x i32]*> [[TMP58]], i32 15 +; CHECK-NEXT: [[TMP118:%.*]] = getelementptr inbounds [10 x i32], [10 x i32]* [[TMP54]], i64 [[TMP117]], i64 0 ; CHECK-NEXT: [[TMP121:%.*]] = extractelement <16 x i64> [[TMP59]], i32 15 -; CHECK-NEXT: [[TMP122:%.*]] = getelementptr inbounds [10 x i32], [10 x i32]* [[TMP120]], i64 [[TMP121]], i64 0 -; CHECK-NEXT: [[TMP123:%.*]] = insertelement <16 x i32*> [[TMP119]], i32* [[TMP122]], i32 15 +; CHECK-NEXT: [[TMP122:%.*]] = getelementptr inbounds [10 x i32], [10 x i32]* [[TMP57]], i64 [[TMP121]], i64 0 +; CHECK-NEXT: [[TMP13:%.*]] = insertelement <16 x [10 x i32]*> undef, [10 x i32]* [[TMP12]], i32 0 +; CHECK-NEXT: [[TMP16:%.*]] = insertelement <16 x [10 x i32]*> [[TMP13]], [10 x i32]* [[TMP15]], i32 1 +; CHECK-NEXT: [[TMP19:%.*]] = insertelement <16 x [10 x i32]*> [[TMP16]], [10 x i32]* [[TMP18]], i32 2 +; CHECK-NEXT: [[TMP22:%.*]] = insertelement <16 x [10 x i32]*> [[TMP19]], [10 x i32]* [[TMP21]], i32 3 +; CHECK-NEXT: [[TMP25:%.*]] = insertelement <16 x [10 x i32]*> [[TMP22]], [10 x i32]* [[TMP24]], i32 4 +; CHECK-NEXT: [[TMP28:%.*]] = insertelement <16 x [10 x i32]*> [[TMP25]], [10 x i32]* [[TMP27]], i32 5 +; CHECK-NEXT: [[TMP31:%.*]] = insertelement <16 x [10 x i32]*> [[TMP28]], [10 x i32]* [[TMP30]], i32 6 +; CHECK-NEXT: [[TMP34:%.*]] = insertelement <16 x [10 x i32]*> [[TMP31]], [10 x i32]* [[TMP33]], i32 7 +; CHECK-NEXT: [[TMP37:%.*]] = insertelement <16 x [10 x i32]*> [[TMP34]], [10 x i32]* [[TMP36]], i32 8 +; CHECK-NEXT: [[TMP40:%.*]] = insertelement <16 x [10 x i32]*> [[TMP37]], [10 x i32]* [[TMP39]], i32 9 +; CHECK-NEXT: [[TMP43:%.*]] = insertelement <16 x [10 x i32]*> [[TMP40]], [10 x i32]* [[TMP42]], i32 10 +; CHECK-NEXT: [[TMP46:%.*]] = insertelement <16 x [10 x i32]*> [[TMP43]], [10 x i32]* [[TMP45]], i32 11 +; CHECK-NEXT: [[TMP49:%.*]] = insertelement <16 x [10 x i32]*> [[TMP46]], [10 x i32]* [[TMP48]], i32 12 +; CHECK-NEXT: [[TMP52:%.*]] = insertelement <16 x [10 x i32]*> [[TMP49]], [10 x i32]* [[TMP51]], i32 13 +; CHECK-NEXT: [[TMP55:%.*]] = insertelement <16 x [10 x i32]*> [[TMP52]], [10 x i32]* [[TMP54]], i32 14 +; CHECK-NEXT: [[TMP58:%.*]] = insertelement <16 x [10 x i32]*> [[TMP55]], [10 x i32]* [[TMP57]], i32 15 ; CHECK-NEXT: [[VECTORGEP:%.*]] = getelementptr inbounds [10 x i32], <16 x [10 x i32]*> [[TMP58]], <16 x i64> [[TMP59]], i64 0 ; CHECK-NEXT: call void @llvm.masked.scatter.v16i32(<16 x i32> <i32 8, i32 8, i32 8, i32 8, i32 8, i32 8, i32 8, i32 8, i32 8, i32 8, i32 8, i32 8, i32 8, i32 8, i32 8, i32 8>, <16 x i32*> [[VECTORGEP]], i32 16, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>) ; CHECK: [[STEP_ADD:%.*]] = add <16 x i64> [[VEC_IND]], <i64 32, i64 32, i64 32, i64 32, i64 32, i64 32, i64 32, i64 32, i64 32, i64 32, i64 32, i64 32, i64 32, i64 32, i64 32, i64 32> diff --git a/llvm/test/Transforms/LoopVectorize/if-pred-non-void.ll b/llvm/test/Transforms/LoopVectorize/if-pred-non-void.ll index 881eb51f9bc..8e1f292650c 100644 --- a/llvm/test/Transforms/LoopVectorize/if-pred-non-void.ll +++ b/llvm/test/Transforms/LoopVectorize/if-pred-non-void.ll @@ -115,15 +115,6 @@ if.end: ; preds = %if.then, %for.body br i1 %exitcond, label %for.cond.cleanup, label %for.body } -; Future-use test for predication under smarter scalar-scalar: this test will -; fail when the vectorizer starts feeding scalarized values directly to their -; scalar users, i.e. w/o generating redundant insertelement/extractelement -; instructions. This case is already supported by the predication code (which -; should generate a phi for the scalar predicated value rather than for the -; insertelement), but cannot be tested yet. -; If you got this test to fail, kindly fix the test by using the alternative -; FFU sequence. This will make the test check how we handle this case from -; now on. define void @test_scalar2scalar(i32* nocapture %asd, i32* nocapture %bsd) { entry: br label %for.body @@ -136,18 +127,9 @@ for.cond.cleanup: ; preds = %if.end ; CHECK: br i1 %{{.*}}, label %[[THEN:[a-zA-Z0-9.]+]], label %[[FI:[a-zA-Z0-9.]+]] ; CHECK: [[THEN]]: ; CHECK: %[[PD:[a-zA-Z0-9]+]] = sdiv i32 %{{.*}}, %{{.*}} -; CHECK: %[[PDV:[a-zA-Z0-9]+]] = insertelement <2 x i32> undef, i32 %[[PD]], i32 0 ; CHECK: br label %[[FI]] ; CHECK: [[FI]]: -; CHECK: %[[PH:[a-zA-Z0-9]+]] = phi <2 x i32> [ undef, %vector.body ], [ %[[PDV]], %[[THEN]] ] -; FFU-LABEL: test_scalar2scalar -; FFU: vector.body: -; FFU: br i1 %{{.*}}, label %[[THEN:[a-zA-Z0-9.]+]], label %[[FI:[a-zA-Z0-9.]+]] -; FFU: [[THEN]]: -; FFU: %[[PD:[a-zA-Z0-9]+]] = sdiv i32 %{{.*}}, %{{.*}} -; FFU: br label %[[FI]] -; FFU: [[FI]]: -; FFU: %{{.*}} = phi i32 [ undef, %vector.body ], [ %[[PD]], %[[THEN]] ] +; CHECK: %{{.*}} = phi i32 [ undef, %vector.body ], [ %[[PD]], %[[THEN]] ] for.body: ; preds = %if.end, %entry %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %if.end ] diff --git a/llvm/test/Transforms/LoopVectorize/if-pred-stores.ll b/llvm/test/Transforms/LoopVectorize/if-pred-stores.ll index 037f3476658..91aa2d3f44f 100644 --- a/llvm/test/Transforms/LoopVectorize/if-pred-stores.ll +++ b/llvm/test/Transforms/LoopVectorize/if-pred-stores.ll @@ -11,6 +11,10 @@ entry: br label %for.body ; VEC-LABEL: test +; VEC: %[[v0:.+]] = add i64 %index, 0 +; VEC: %[[v1:.+]] = add i64 %index, 1 +; VEC: %[[v2:.+]] = getelementptr inbounds i32, i32* %f, i64 %[[v0]] +; VEC: %[[v4:.+]] = getelementptr inbounds i32, i32* %f, i64 %[[v1]] ; VEC: %[[v8:.+]] = icmp sgt <2 x i32> %{{.*}}, <i32 100, i32 100> ; VEC: %[[v9:.+]] = add nsw <2 x i32> %{{.*}}, <i32 20, i32 20> ; VEC: %[[v10:.+]] = and <2 x i1> %[[v8]], <i1 true, i1 true> @@ -20,8 +24,7 @@ entry: ; ; VEC: [[cond]]: ; VEC: %[[v13:.+]] = extractelement <2 x i32> %[[v9]], i32 0 -; VEC: %[[v14:.+]] = extractelement <2 x i32*> %{{.*}}, i32 0 -; VEC: store i32 %[[v13]], i32* %[[v14]], align 4 +; VEC: store i32 %[[v13]], i32* %[[v2]], align 4 ; VEC: br label %[[else:.+]] ; ; VEC: [[else]]: @@ -31,8 +34,7 @@ entry: ; ; VEC: [[cond2]]: ; VEC: %[[v17:.+]] = extractelement <2 x i32> %[[v9]], i32 1 -; VEC: %[[v18:.+]] = extractelement <2 x i32*> %{{.+}} i32 1 -; VEC: store i32 %[[v17]], i32* %[[v18]], align 4 +; VEC: store i32 %[[v17]], i32* %[[v4]], align 4 ; VEC: br label %[[else2:.+]] ; ; VEC: [[else2]]: |
