[llvm] r326158 - Fix r326154 buildbots test fail
Adam Nemet via llvm-commits
llvm-commits at lists.llvm.org
Mon Feb 26 22:42:55 PST 2018
I haven’t seen that but we typically don’t let the cost model dictate the vectorization and interleave factors because that is subtarget-specific.
> On Feb 26, 2018, at 10:37 PM, Evgeny Stupachenko <evstupac at gmail.com> wrote:
>
> Thanks. Maybe I should apply the same fix for the second test.
>
>> On Mon, Feb 26, 2018 at 9:44 PM, Adam Nemet <anemet at apple.com> wrote:
>> Hopefully fixed in r326169.
>>
>>
>>> On Feb 26, 2018, at 8:05 PM, Adam Nemet via llvm-commits <llvm-commits at lists.llvm.org> wrote:
>>>
>>> Hi Evgeny,
>>>
>>> This is still failing after your commit:
>>>
>>> http://lab.llvm.org:8080/green/job/clang-stage1-cmake-RA-incremental/46796/#showFailuresLink
>>>
>>> Adam
>>>
>>>> On Feb 26, 2018, at 5:33 PM, Evgeny Stupachenko via llvm-commits <llvm-commits at lists.llvm.org> wrote:
>>>>
>>>> Author: evstupac
>>>> Date: Mon Feb 26 17:33:11 2018
>>>> New Revision: 326158
>>>>
>>>> URL: http://llvm.org/viewvc/llvm-project?rev=326158&view=rev
>>>> Log:
>>>> Fix r326154 buildbots test fail
>>>>
>>>> Summary:
>>>>
>>>> Add specific mtriples to tests added in r326154.
>>>>
>>>> From: Evgeny Stupachenko <evstupac at gmail.com>
>>>> <evgeny.v.stupachenko at intel.com>
>>>>
>>>> Added:
>>>> llvm/trunk/test/Transforms/LoopVectorize/AArch64/pr36032.ll
>>>> - copied, changed from r326154, llvm/trunk/test/Transforms/LoopVectorize/pr36032.ll
>>>> llvm/trunk/test/Transforms/LoopVectorize/X86/pr35432.ll
>>>> - copied, changed from r326154, llvm/trunk/test/Transforms/LoopVectorize/pr35432.ll
>>>> Removed:
>>>> llvm/trunk/test/Transforms/LoopVectorize/pr35432.ll
>>>> llvm/trunk/test/Transforms/LoopVectorize/pr36032.ll
>>>>
>>>> Copied: llvm/trunk/test/Transforms/LoopVectorize/AArch64/pr36032.ll (from r326154, llvm/trunk/test/Transforms/LoopVectorize/pr36032.ll)
>>>> URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/Transforms/LoopVectorize/AArch64/pr36032.ll?p2=llvm/trunk/test/Transforms/LoopVectorize/AArch64/pr36032.ll&p1=llvm/trunk/test/Transforms/LoopVectorize/pr36032.ll&r1=326154&r2=326158&rev=326158&view=diff
>>>> ==============================================================================
>>>> --- llvm/trunk/test/Transforms/LoopVectorize/pr36032.ll (original)
>>>> +++ llvm/trunk/test/Transforms/LoopVectorize/AArch64/pr36032.ll Mon Feb 26 17:33:11 2018
>>>> @@ -1,10 +1,9 @@
>>>> ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
>>>> -; RUN: opt -loop-vectorize -S < %s | FileCheck %s
>>>> +; RUN: opt -loop-vectorize -S -mtriple=aarch64-unknown-linux-gnu < %s | FileCheck %s
>>>>
>>>> ; The test checks that there is no assert caused by issue described in PR36032
>>>>
>>>> target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
>>>> -target triple = "aarch64--"
>>>>
>>>> %struct.anon = type { i8 }
>>>>
>>>>
>>>> Copied: llvm/trunk/test/Transforms/LoopVectorize/X86/pr35432.ll (from r326154, llvm/trunk/test/Transforms/LoopVectorize/pr35432.ll)
>>>> URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/Transforms/LoopVectorize/X86/pr35432.ll?p2=llvm/trunk/test/Transforms/LoopVectorize/X86/pr35432.ll&p1=llvm/trunk/test/Transforms/LoopVectorize/pr35432.ll&r1=326154&r2=326158&rev=326158&view=diff
>>>> ==============================================================================
>>>> --- llvm/trunk/test/Transforms/LoopVectorize/pr35432.ll (original)
>>>> +++ llvm/trunk/test/Transforms/LoopVectorize/X86/pr35432.ll Mon Feb 26 17:33:11 2018
>>>> @@ -1,5 +1,5 @@
>>>> ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
>>>> -; RUN: opt -loop-vectorize -S < %s | FileCheck %s
>>>> +; RUN: opt -loop-vectorize -mtriple=x86_64-unknown-linux-gnu -S < %s | FileCheck %s
>>>>
>>>> ; The test checks that there is no assert caused by issue described in PR35432
>>>>
>>>>
>>>> Removed: llvm/trunk/test/Transforms/LoopVectorize/pr35432.ll
>>>> URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/Transforms/LoopVectorize/pr35432.ll?rev=326157&view=auto
>>>> ==============================================================================
>>>> --- llvm/trunk/test/Transforms/LoopVectorize/pr35432.ll (original)
>>>> +++ llvm/trunk/test/Transforms/LoopVectorize/pr35432.ll (removed)
>>>> @@ -1,213 +0,0 @@
>>>> -; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
>>>> -; RUN: opt -loop-vectorize -S < %s | FileCheck %s
>>>> -
>>>> -; The test checks that there is no assert caused by issue described in PR35432
>>>> -
>>>> -target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
>>>> -target triple = "x86_64-unknown-linux-gnu"
>>>> -
>>>> - at a = common local_unnamed_addr global [192 x [192 x i32]] zeroinitializer, align 16
>>>> -
>>>> -; Function Attrs: nounwind uwtable
>>>> -define i32 @main() local_unnamed_addr #0 {
>>>> -; CHECK-LABEL: @main(
>>>> -; CHECK-NEXT: entry:
>>>> -; CHECK-NEXT: [[I:%.*]] = alloca i32, align 4
>>>> -; CHECK-NEXT: [[S:%.*]] = alloca i16, align 2
>>>> -; CHECK-NEXT: [[TMP0:%.*]] = bitcast i32* [[I]] to i8*
>>>> -; CHECK-NEXT: call void @llvm.lifetime.start.p0i8(i64 4, i8* nonnull [[TMP0]])
>>>> -; CHECK-NEXT: store i32 0, i32* [[I]], align 4
>>>> -; CHECK-NEXT: [[TMP1:%.*]] = bitcast i16* [[S]] to i8*
>>>> -; CHECK-NEXT: call void @llvm.lifetime.start.p0i8(i64 2, i8* nonnull [[TMP1]])
>>>> -; CHECK-NEXT: [[CALL:%.*]] = call i32 (i32*, ...) bitcast (i32 (...)* @goo to i32 (i32*, ...)*)(i32* nonnull [[I]])
>>>> -; CHECK-NEXT: [[TMP2:%.*]] = load i32, i32* [[I]], align 4
>>>> -; CHECK-NEXT: [[STOREMERGE6:%.*]] = trunc i32 [[TMP2]] to i16
>>>> -; CHECK-NEXT: store i16 [[STOREMERGE6]], i16* [[S]], align 2
>>>> -; CHECK-NEXT: [[CONV17:%.*]] = and i32 [[TMP2]], 65472
>>>> -; CHECK-NEXT: [[CMP8:%.*]] = icmp eq i32 [[CONV17]], 0
>>>> -; CHECK-NEXT: br i1 [[CMP8]], label [[FOR_BODY_LR_PH:%.*]], label [[FOR_END12:%.*]]
>>>> -; CHECK: for.body.lr.ph:
>>>> -; CHECK-NEXT: [[TMP3:%.*]] = sub i32 -1, [[TMP2]]
>>>> -; CHECK-NEXT: br label [[FOR_BODY:%.*]]
>>>> -; CHECK: for.body:
>>>> -; CHECK-NEXT: [[STOREMERGE_IN9:%.*]] = phi i32 [ [[TMP2]], [[FOR_BODY_LR_PH]] ], [ [[ADD:%.*]], [[FOR_INC9:%.*]] ]
>>>> -; CHECK-NEXT: [[CONV52:%.*]] = and i32 [[STOREMERGE_IN9]], 255
>>>> -; CHECK-NEXT: [[CMP63:%.*]] = icmp ult i32 [[TMP2]], [[CONV52]]
>>>> -; CHECK-NEXT: br i1 [[CMP63]], label [[FOR_BODY8_LR_PH:%.*]], label [[FOR_INC9]]
>>>> -; CHECK: for.body8.lr.ph:
>>>> -; CHECK-NEXT: [[CONV3:%.*]] = trunc i32 [[STOREMERGE_IN9]] to i8
>>>> -; CHECK-NEXT: [[DOTPROMOTED:%.*]] = load i32, i32* getelementptr inbounds ([192 x [192 x i32]], [192 x [192 x i32]]* @a, i64 0, i64 0, i64 0), align 16
>>>> -; CHECK-NEXT: [[TMP4:%.*]] = add i8 [[CONV3]], -1
>>>> -; CHECK-NEXT: [[TMP5:%.*]] = zext i8 [[TMP4]] to i32
>>>> -; CHECK-NEXT: [[TMP6:%.*]] = sub i32 -1, [[TMP5]]
>>>> -; CHECK-NEXT: [[TMP7:%.*]] = icmp ugt i32 [[TMP6]], [[TMP3]]
>>>> -; CHECK-NEXT: [[UMAX:%.*]] = select i1 [[TMP7]], i32 [[TMP6]], i32 [[TMP3]]
>>>> -; CHECK-NEXT: [[TMP8:%.*]] = add i32 [[UMAX]], 2
>>>> -; CHECK-NEXT: [[TMP9:%.*]] = add i32 [[TMP8]], [[TMP5]]
>>>> -; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i32 [[TMP9]], 8
>>>> -; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_SCEVCHECK:%.*]]
>>>> -; CHECK: vector.scevcheck:
>>>> -; CHECK-NEXT: [[TMP10:%.*]] = add i8 [[CONV3]], -1
>>>> -; CHECK-NEXT: [[TMP11:%.*]] = zext i8 [[TMP10]] to i32
>>>> -; CHECK-NEXT: [[TMP12:%.*]] = sub i32 -1, [[TMP11]]
>>>> -; CHECK-NEXT: [[TMP13:%.*]] = icmp ugt i32 [[TMP12]], [[TMP3]]
>>>> -; CHECK-NEXT: [[UMAX1:%.*]] = select i1 [[TMP13]], i32 [[TMP12]], i32 [[TMP3]]
>>>> -; CHECK-NEXT: [[TMP14:%.*]] = add i32 [[UMAX1]], 1
>>>> -; CHECK-NEXT: [[TMP15:%.*]] = add i32 [[TMP14]], [[TMP11]]
>>>> -; CHECK-NEXT: [[TMP16:%.*]] = trunc i32 [[TMP15]] to i8
>>>> -; CHECK-NEXT: [[MUL:%.*]] = call { i8, i1 } @llvm.umul.with.overflow.i8(i8 1, i8 [[TMP16]])
>>>> -; CHECK-NEXT: [[MUL_RESULT:%.*]] = extractvalue { i8, i1 } [[MUL]], 0
>>>> -; CHECK-NEXT: [[MUL_OVERFLOW:%.*]] = extractvalue { i8, i1 } [[MUL]], 1
>>>> -; CHECK-NEXT: [[TMP17:%.*]] = add i8 [[TMP10]], [[MUL_RESULT]]
>>>> -; CHECK-NEXT: [[TMP18:%.*]] = sub i8 [[TMP10]], [[MUL_RESULT]]
>>>> -; CHECK-NEXT: [[TMP19:%.*]] = icmp ugt i8 [[TMP18]], [[TMP10]]
>>>> -; CHECK-NEXT: [[TMP20:%.*]] = icmp ult i8 [[TMP17]], [[TMP10]]
>>>> -; CHECK-NEXT: [[TMP21:%.*]] = select i1 true, i1 [[TMP19]], i1 [[TMP20]]
>>>> -; CHECK-NEXT: [[TMP22:%.*]] = icmp ugt i32 [[TMP15]], 255
>>>> -; CHECK-NEXT: [[TMP23:%.*]] = or i1 [[TMP21]], [[TMP22]]
>>>> -; CHECK-NEXT: [[TMP24:%.*]] = or i1 [[TMP23]], [[MUL_OVERFLOW]]
>>>> -; CHECK-NEXT: [[TMP25:%.*]] = or i1 false, [[TMP24]]
>>>> -; CHECK-NEXT: br i1 [[TMP25]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
>>>> -; CHECK: vector.ph:
>>>> -; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i32 [[TMP9]], 8
>>>> -; CHECK-NEXT: [[N_VEC:%.*]] = sub i32 [[TMP9]], [[N_MOD_VF]]
>>>> -; CHECK-NEXT: [[CAST_CRD:%.*]] = trunc i32 [[N_VEC]] to i8
>>>> -; CHECK-NEXT: [[IND_END:%.*]] = sub i8 [[CONV3]], [[CAST_CRD]]
>>>> -; CHECK-NEXT: [[TMP26:%.*]] = insertelement <4 x i32> zeroinitializer, i32 [[DOTPROMOTED]], i32 0
>>>> -; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
>>>> -; CHECK: vector.body:
>>>> -; CHECK-NEXT: [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
>>>> -; CHECK-NEXT: [[VEC_PHI:%.*]] = phi <4 x i32> [ [[TMP26]], [[VECTOR_PH]] ], [ [[TMP30:%.*]], [[VECTOR_BODY]] ]
>>>> -; CHECK-NEXT: [[VEC_PHI2:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP31:%.*]], [[VECTOR_BODY]] ]
>>>> -; CHECK-NEXT: [[TMP27:%.*]] = trunc i32 [[INDEX]] to i8
>>>> -; CHECK-NEXT: [[OFFSET_IDX:%.*]] = sub i8 [[CONV3]], [[TMP27]]
>>>> -; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i8> undef, i8 [[OFFSET_IDX]], i32 0
>>>> -; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i8> [[BROADCAST_SPLATINSERT]], <4 x i8> undef, <4 x i32> zeroinitializer
>>>> -; CHECK-NEXT: [[INDUCTION:%.*]] = add <4 x i8> [[BROADCAST_SPLAT]], <i8 0, i8 -1, i8 -2, i8 -3>
>>>> -; CHECK-NEXT: [[INDUCTION3:%.*]] = add <4 x i8> [[BROADCAST_SPLAT]], <i8 -4, i8 -5, i8 -6, i8 -7>
>>>> -; CHECK-NEXT: [[TMP28:%.*]] = add i8 [[OFFSET_IDX]], 0
>>>> -; CHECK-NEXT: [[TMP29:%.*]] = add i8 [[OFFSET_IDX]], -4
>>>> -; CHECK-NEXT: [[TMP30]] = add <4 x i32> [[VEC_PHI]], <i32 1, i32 1, i32 1, i32 1>
>>>> -; CHECK-NEXT: [[TMP31]] = add <4 x i32> [[VEC_PHI2]], <i32 1, i32 1, i32 1, i32 1>
>>>> -; CHECK-NEXT: [[TMP32:%.*]] = add i8 [[TMP28]], -1
>>>> -; CHECK-NEXT: [[TMP33:%.*]] = add i8 [[TMP29]], -1
>>>> -; CHECK-NEXT: [[TMP34:%.*]] = zext i8 [[TMP32]] to i32
>>>> -; CHECK-NEXT: [[TMP35:%.*]] = zext i8 [[TMP33]] to i32
>>>> -; CHECK-NEXT: [[INDEX_NEXT]] = add i32 [[INDEX]], 8
>>>> -; CHECK-NEXT: [[TMP36:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
>>>> -; CHECK-NEXT: br i1 [[TMP36]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !0
>>>> -; CHECK: middle.block:
>>>> -; CHECK-NEXT: [[BIN_RDX:%.*]] = add <4 x i32> [[TMP31]], [[TMP30]]
>>>> -; CHECK-NEXT: [[RDX_SHUF:%.*]] = shufflevector <4 x i32> [[BIN_RDX]], <4 x i32> undef, <4 x i32> <i32 2, i32 3, i32 undef, i32 undef>
>>>> -; CHECK-NEXT: [[BIN_RDX4:%.*]] = add <4 x i32> [[BIN_RDX]], [[RDX_SHUF]]
>>>> -; CHECK-NEXT: [[RDX_SHUF5:%.*]] = shufflevector <4 x i32> [[BIN_RDX4]], <4 x i32> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
>>>> -; CHECK-NEXT: [[BIN_RDX6:%.*]] = add <4 x i32> [[BIN_RDX4]], [[RDX_SHUF5]]
>>>> -; CHECK-NEXT: [[TMP37:%.*]] = extractelement <4 x i32> [[BIN_RDX6]], i32 0
>>>> -; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i32 [[TMP9]], [[N_VEC]]
>>>> -; CHECK-NEXT: br i1 [[CMP_N]], label [[FOR_COND4_FOR_INC9_CRIT_EDGE:%.*]], label [[SCALAR_PH]]
>>>> -; CHECK: scalar.ph:
>>>> -; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i8 [ [[IND_END]], [[MIDDLE_BLOCK]] ], [ [[CONV3]], [[FOR_BODY8_LR_PH]] ], [ [[CONV3]], [[VECTOR_SCEVCHECK]] ]
>>>> -; CHECK-NEXT: [[BC_MERGE_RDX:%.*]] = phi i32 [ [[DOTPROMOTED]], [[FOR_BODY8_LR_PH]] ], [ [[DOTPROMOTED]], [[VECTOR_SCEVCHECK]] ], [ [[TMP37]], [[MIDDLE_BLOCK]] ]
>>>> -; CHECK-NEXT: br label [[FOR_BODY8:%.*]]
>>>> -; CHECK: for.body8:
>>>> -; CHECK-NEXT: [[INC5:%.*]] = phi i32 [ [[BC_MERGE_RDX]], [[SCALAR_PH]] ], [ [[INC:%.*]], [[FOR_BODY8]] ]
>>>> -; CHECK-NEXT: [[C_04:%.*]] = phi i8 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[DEC:%.*]], [[FOR_BODY8]] ]
>>>> -; CHECK-NEXT: [[INC]] = add i32 [[INC5]], 1
>>>> -; CHECK-NEXT: [[DEC]] = add i8 [[C_04]], -1
>>>> -; CHECK-NEXT: [[CONV5:%.*]] = zext i8 [[DEC]] to i32
>>>> -; CHECK-NEXT: [[CMP6:%.*]] = icmp ult i32 [[TMP2]], [[CONV5]]
>>>> -; CHECK-NEXT: br i1 [[CMP6]], label [[FOR_BODY8]], label [[FOR_COND4_FOR_INC9_CRIT_EDGE]], !llvm.loop !2
>>>> -; CHECK: for.cond4.for.inc9_crit_edge:
>>>> -; CHECK-NEXT: [[INC_LCSSA:%.*]] = phi i32 [ [[INC]], [[FOR_BODY8]] ], [ [[TMP37]], [[MIDDLE_BLOCK]] ]
>>>> -; CHECK-NEXT: store i32 [[INC_LCSSA]], i32* getelementptr inbounds ([192 x [192 x i32]], [192 x [192 x i32]]* @a, i64 0, i64 0, i64 0), align 16
>>>> -; CHECK-NEXT: br label [[FOR_INC9]]
>>>> -; CHECK: for.inc9:
>>>> -; CHECK-NEXT: [[CONV10:%.*]] = and i32 [[STOREMERGE_IN9]], 65535
>>>> -; CHECK-NEXT: [[ADD]] = add nuw nsw i32 [[CONV10]], 1
>>>> -; CHECK-NEXT: [[CONV1:%.*]] = and i32 [[ADD]], 65472
>>>> -; CHECK-NEXT: [[CMP:%.*]] = icmp eq i32 [[CONV1]], 0
>>>> -; CHECK-NEXT: br i1 [[CMP]], label [[FOR_BODY]], label [[FOR_COND_FOR_END12_CRIT_EDGE:%.*]]
>>>> -; CHECK: for.cond.for.end12_crit_edge:
>>>> -; CHECK-NEXT: [[ADD_LCSSA:%.*]] = phi i32 [ [[ADD]], [[FOR_INC9]] ]
>>>> -; CHECK-NEXT: [[STOREMERGE:%.*]] = trunc i32 [[ADD_LCSSA]] to i16
>>>> -; CHECK-NEXT: store i16 [[STOREMERGE]], i16* [[S]], align 2
>>>> -; CHECK-NEXT: br label [[FOR_END12]]
>>>> -; CHECK: for.end12:
>>>> -; CHECK-NEXT: [[CALL13:%.*]] = call i32 (i16*, ...) bitcast (i32 (...)* @foo to i32 (i16*, ...)*)(i16* nonnull [[S]])
>>>> -; CHECK-NEXT: call void @llvm.lifetime.end.p0i8(i64 2, i8* nonnull [[TMP1]])
>>>> -; CHECK-NEXT: call void @llvm.lifetime.end.p0i8(i64 4, i8* nonnull [[TMP0]])
>>>> -; CHECK-NEXT: ret i32 0
>>>> -;
>>>> -entry:
>>>> - %i = alloca i32, align 4
>>>> - %s = alloca i16, align 2
>>>> - %0 = bitcast i32* %i to i8*
>>>> - call void @llvm.lifetime.start.p0i8(i64 4, i8* nonnull %0) #3
>>>> - store i32 0, i32* %i, align 4
>>>> - %1 = bitcast i16* %s to i8*
>>>> - call void @llvm.lifetime.start.p0i8(i64 2, i8* nonnull %1) #3
>>>> - %call = call i32 (i32*, ...) bitcast (i32 (...)* @goo to i32 (i32*, ...)*)(i32* nonnull %i) #3
>>>> - %2 = load i32, i32* %i, align 4
>>>> - %storemerge6 = trunc i32 %2 to i16
>>>> - store i16 %storemerge6, i16* %s, align 2
>>>> - %conv17 = and i32 %2, 65472
>>>> - %cmp8 = icmp eq i32 %conv17, 0
>>>> - br i1 %cmp8, label %for.body.lr.ph, label %for.end12
>>>> -
>>>> -for.body.lr.ph: ; preds = %entry
>>>> - br label %for.body
>>>> -
>>>> -for.body: ; preds = %for.body.lr.ph, %for.inc9
>>>> - %storemerge.in9 = phi i32 [ %2, %for.body.lr.ph ], [ %add, %for.inc9 ]
>>>> - %conv52 = and i32 %storemerge.in9, 255
>>>> - %cmp63 = icmp ult i32 %2, %conv52
>>>> - br i1 %cmp63, label %for.body8.lr.ph, label %for.inc9
>>>> -
>>>> -for.body8.lr.ph: ; preds = %for.body
>>>> - %conv3 = trunc i32 %storemerge.in9 to i8
>>>> - %.promoted = load i32, i32* getelementptr inbounds ([192 x [192 x i32]], [192 x [192 x i32]]* @a, i64 0, i64 0, i64 0), align 16
>>>> - br label %for.body8
>>>> -
>>>> -for.body8: ; preds = %for.body8.lr.ph, %for.body8
>>>> - %inc5 = phi i32 [ %.promoted, %for.body8.lr.ph ], [ %inc, %for.body8 ]
>>>> - %c.04 = phi i8 [ %conv3, %for.body8.lr.ph ], [ %dec, %for.body8 ]
>>>> - %inc = add i32 %inc5, 1
>>>> - %dec = add i8 %c.04, -1
>>>> - %conv5 = zext i8 %dec to i32
>>>> - %cmp6 = icmp ult i32 %2, %conv5
>>>> - br i1 %cmp6, label %for.body8, label %for.cond4.for.inc9_crit_edge
>>>> -
>>>> -for.cond4.for.inc9_crit_edge: ; preds = %for.body8
>>>> - %inc.lcssa = phi i32 [ %inc, %for.body8 ]
>>>> - store i32 %inc.lcssa, i32* getelementptr inbounds ([192 x [192 x i32]], [192 x [192 x i32]]* @a, i64 0, i64 0, i64 0), align 16
>>>> - br label %for.inc9
>>>> -
>>>> -for.inc9: ; preds = %for.cond4.for.inc9_crit_edge, %for.body
>>>> - %conv10 = and i32 %storemerge.in9, 65535
>>>> - %add = add nuw nsw i32 %conv10, 1
>>>> - %conv1 = and i32 %add, 65472
>>>> - %cmp = icmp eq i32 %conv1, 0
>>>> - br i1 %cmp, label %for.body, label %for.cond.for.end12_crit_edge
>>>> -
>>>> -for.cond.for.end12_crit_edge: ; preds = %for.inc9
>>>> - %add.lcssa = phi i32 [ %add, %for.inc9 ]
>>>> - %storemerge = trunc i32 %add.lcssa to i16
>>>> - store i16 %storemerge, i16* %s, align 2
>>>> - br label %for.end12
>>>> -
>>>> -for.end12: ; preds = %for.cond.for.end12_crit_edge, %entry
>>>> - %call13 = call i32 (i16*, ...) bitcast (i32 (...)* @foo to i32 (i16*, ...)*)(i16* nonnull %s) #3
>>>> - call void @llvm.lifetime.end.p0i8(i64 2, i8* nonnull %1) #3
>>>> - call void @llvm.lifetime.end.p0i8(i64 4, i8* nonnull %0) #3
>>>> - ret i32 0
>>>> -}
>>>> -
>>>> -; Function Attrs: argmemonly nounwind
>>>> -declare void @llvm.lifetime.start.p0i8(i64, i8* nocapture) #1
>>>> -
>>>> -declare i32 @goo(...) local_unnamed_addr #2
>>>> -
>>>> -declare i32 @foo(...) local_unnamed_addr #2
>>>> -
>>>> -; Function Attrs: argmemonly nounwind
>>>> -declare void @llvm.lifetime.end.p0i8(i64, i8* nocapture) #1
>>>>
>>>> Removed: llvm/trunk/test/Transforms/LoopVectorize/pr36032.ll
>>>> URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/Transforms/LoopVectorize/pr36032.ll?rev=326157&view=auto
>>>> ==============================================================================
>>>> --- llvm/trunk/test/Transforms/LoopVectorize/pr36032.ll (original)
>>>> +++ llvm/trunk/test/Transforms/LoopVectorize/pr36032.ll (removed)
>>>> @@ -1,154 +0,0 @@
>>>> -; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
>>>> -; RUN: opt -loop-vectorize -S < %s | FileCheck %s
>>>> -
>>>> -; The test checks that there is no assert caused by issue described in PR36032
>>>> -
>>>> -target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
>>>> -target triple = "aarch64--"
>>>> -
>>>> -%struct.anon = type { i8 }
>>>> -
>>>> - at c = local_unnamed_addr global [6 x i8] zeroinitializer, align 1
>>>> - at b = internal global %struct.anon zeroinitializer, align 1
>>>> -
>>>> -; Function Attrs: noreturn nounwind
>>>> -define void @_Z1dv() local_unnamed_addr #0 {
>>>> -; CHECK-LABEL: @_Z1dv(
>>>> -; CHECK-NEXT: entry:
>>>> -; CHECK-NEXT: [[CALL:%.*]] = tail call i8* @"_ZN3$_01aEv"(%struct.anon* nonnull @b)
>>>> -; CHECK-NEXT: [[SCEVGEP1:%.*]] = getelementptr i8, i8* [[CALL]], i64 4
>>>> -; CHECK-NEXT: br label [[FOR_COND:%.*]]
>>>> -; CHECK: for.cond:
>>>> -; CHECK-NEXT: [[F_0:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[ADD5:%.*]], [[FOR_COND_CLEANUP:%.*]] ]
>>>> -; CHECK-NEXT: [[G_0:%.*]] = phi i32 [ undef, [[ENTRY]] ], [ [[G_1_LCSSA:%.*]], [[FOR_COND_CLEANUP]] ]
>>>> -; CHECK-NEXT: [[CMP12:%.*]] = icmp ult i32 [[G_0]], 4
>>>> -; CHECK-NEXT: [[CONV:%.*]] = and i32 [[F_0]], 65535
>>>> -; CHECK-NEXT: br i1 [[CMP12]], label [[FOR_BODY_LR_PH:%.*]], label [[FOR_COND_CLEANUP]]
>>>> -; CHECK: for.body.lr.ph:
>>>> -; CHECK-NEXT: [[TMP0:%.*]] = zext i32 [[G_0]] to i64
>>>> -; CHECK-NEXT: [[TMP1:%.*]] = sub i64 4, [[TMP0]]
>>>> -; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[TMP1]], 4
>>>> -; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_SCEVCHECK:%.*]]
>>>> -; CHECK: vector.scevcheck:
>>>> -; CHECK-NEXT: [[TMP2:%.*]] = sub i64 3, [[TMP0]]
>>>> -; CHECK-NEXT: [[TMP3:%.*]] = add i32 [[G_0]], [[CONV]]
>>>> -; CHECK-NEXT: [[TMP4:%.*]] = trunc i64 [[TMP2]] to i32
>>>> -; CHECK-NEXT: [[MUL:%.*]] = call { i32, i1 } @llvm.umul.with.overflow.i32(i32 1, i32 [[TMP4]])
>>>> -; CHECK-NEXT: [[MUL_RESULT:%.*]] = extractvalue { i32, i1 } [[MUL]], 0
>>>> -; CHECK-NEXT: [[MUL_OVERFLOW:%.*]] = extractvalue { i32, i1 } [[MUL]], 1
>>>> -; CHECK-NEXT: [[TMP5:%.*]] = add i32 [[TMP3]], [[MUL_RESULT]]
>>>> -; CHECK-NEXT: [[TMP6:%.*]] = sub i32 [[TMP3]], [[MUL_RESULT]]
>>>> -; CHECK-NEXT: [[TMP7:%.*]] = icmp ugt i32 [[TMP6]], [[TMP3]]
>>>> -; CHECK-NEXT: [[TMP8:%.*]] = icmp ult i32 [[TMP5]], [[TMP3]]
>>>> -; CHECK-NEXT: [[TMP9:%.*]] = select i1 false, i1 [[TMP7]], i1 [[TMP8]]
>>>> -; CHECK-NEXT: [[TMP10:%.*]] = icmp ugt i64 [[TMP2]], 4294967295
>>>> -; CHECK-NEXT: [[TMP11:%.*]] = or i1 [[TMP9]], [[TMP10]]
>>>> -; CHECK-NEXT: [[TMP12:%.*]] = or i1 [[TMP11]], [[MUL_OVERFLOW]]
>>>> -; CHECK-NEXT: [[TMP13:%.*]] = or i1 false, [[TMP12]]
>>>> -; CHECK-NEXT: br i1 [[TMP13]], label [[SCALAR_PH]], label [[VECTOR_MEMCHECK:%.*]]
>>>> -; CHECK: vector.memcheck:
>>>> -; CHECK-NEXT: [[SCEVGEP:%.*]] = getelementptr i8, i8* [[CALL]], i64 [[TMP0]]
>>>> -; CHECK-NEXT: [[TMP14:%.*]] = add i32 [[G_0]], [[CONV]]
>>>> -; CHECK-NEXT: [[TMP15:%.*]] = zext i32 [[TMP14]] to i64
>>>> -; CHECK-NEXT: [[SCEVGEP2:%.*]] = getelementptr [6 x i8], [6 x i8]* @c, i64 0, i64 [[TMP15]]
>>>> -; CHECK-NEXT: [[TMP16:%.*]] = sub i64 [[TMP15]], [[TMP0]]
>>>> -; CHECK-NEXT: [[SCEVGEP3:%.*]] = getelementptr i8, i8* getelementptr inbounds ([6 x i8], [6 x i8]* @c, i64 0, i64 4), i64 [[TMP16]]
>>>> -; CHECK-NEXT: [[BOUND0:%.*]] = icmp ult i8* [[SCEVGEP]], [[SCEVGEP3]]
>>>> -; CHECK-NEXT: [[BOUND1:%.*]] = icmp ult i8* [[SCEVGEP2]], [[SCEVGEP1]]
>>>> -; CHECK-NEXT: [[FOUND_CONFLICT:%.*]] = and i1 [[BOUND0]], [[BOUND1]]
>>>> -; CHECK-NEXT: [[MEMCHECK_CONFLICT:%.*]] = and i1 [[FOUND_CONFLICT]], true
>>>> -; CHECK-NEXT: br i1 [[MEMCHECK_CONFLICT]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
>>>> -; CHECK: vector.ph:
>>>> -; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[TMP1]], 4
>>>> -; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 [[TMP1]], [[N_MOD_VF]]
>>>> -; CHECK-NEXT: [[IND_END:%.*]] = add i64 [[TMP0]], [[N_VEC]]
>>>> -; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
>>>> -; CHECK: vector.body:
>>>> -; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
>>>> -; CHECK-NEXT: [[OFFSET_IDX:%.*]] = add i64 [[TMP0]], [[INDEX]]
>>>> -; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i64> undef, i64 [[OFFSET_IDX]], i32 0
>>>> -; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT]], <4 x i64> undef, <4 x i32> zeroinitializer
>>>> -; CHECK-NEXT: [[INDUCTION:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 0, i64 1, i64 2, i64 3>
>>>> -; CHECK-NEXT: [[TMP17:%.*]] = add i64 [[OFFSET_IDX]], 0
>>>> -; CHECK-NEXT: [[OFFSET_IDX4:%.*]] = add i64 [[TMP0]], [[INDEX]]
>>>> -; CHECK-NEXT: [[TMP18:%.*]] = trunc i64 [[OFFSET_IDX4]] to i32
>>>> -; CHECK-NEXT: [[BROADCAST_SPLATINSERT5:%.*]] = insertelement <4 x i32> undef, i32 [[TMP18]], i32 0
>>>> -; CHECK-NEXT: [[BROADCAST_SPLAT6:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT5]], <4 x i32> undef, <4 x i32> zeroinitializer
>>>> -; CHECK-NEXT: [[INDUCTION7:%.*]] = add <4 x i32> [[BROADCAST_SPLAT6]], <i32 0, i32 1, i32 2, i32 3>
>>>> -; CHECK-NEXT: [[TMP19:%.*]] = add i32 [[TMP18]], 0
>>>> -; CHECK-NEXT: [[TMP20:%.*]] = add i32 [[CONV]], [[TMP19]]
>>>> -; CHECK-NEXT: [[TMP21:%.*]] = zext i32 [[TMP20]] to i64
>>>> -; CHECK-NEXT: [[TMP22:%.*]] = getelementptr inbounds [6 x i8], [6 x i8]* @c, i64 0, i64 [[TMP21]]
>>>> -; CHECK-NEXT: [[TMP23:%.*]] = getelementptr i8, i8* [[TMP22]], i32 0
>>>> -; CHECK-NEXT: [[TMP24:%.*]] = bitcast i8* [[TMP23]] to <4 x i8>*
>>>> -; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <4 x i8>, <4 x i8>* [[TMP24]], align 1, !alias.scope !0
>>>> -; CHECK-NEXT: [[TMP25:%.*]] = getelementptr inbounds i8, i8* [[CALL]], i64 [[TMP17]]
>>>> -; CHECK-NEXT: [[TMP26:%.*]] = getelementptr i8, i8* [[TMP25]], i32 0
>>>> -; CHECK-NEXT: [[TMP27:%.*]] = bitcast i8* [[TMP26]] to <4 x i8>*
>>>> -; CHECK-NEXT: store <4 x i8> [[WIDE_LOAD]], <4 x i8>* [[TMP27]], align 1, !alias.scope !3, !noalias !0
>>>> -; CHECK-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], 4
>>>> -; CHECK-NEXT: [[TMP28:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
>>>> -; CHECK-NEXT: br i1 [[TMP28]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !5
>>>> -; CHECK: middle.block:
>>>> -; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[TMP1]], [[N_VEC]]
>>>> -; CHECK-NEXT: br i1 [[CMP_N]], label [[FOR_COND_CLEANUP_LOOPEXIT:%.*]], label [[SCALAR_PH]]
>>>> -; CHECK: scalar.ph:
>>>> -; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[IND_END]], [[MIDDLE_BLOCK]] ], [ [[TMP0]], [[FOR_BODY_LR_PH]] ], [ [[TMP0]], [[VECTOR_SCEVCHECK]] ], [ [[TMP0]], [[VECTOR_MEMCHECK]] ]
>>>> -; CHECK-NEXT: br label [[FOR_BODY:%.*]]
>>>> -; CHECK: for.cond.cleanup.loopexit:
>>>> -; CHECK-NEXT: br label [[FOR_COND_CLEANUP]]
>>>> -; CHECK: for.cond.cleanup:
>>>> -; CHECK-NEXT: [[G_1_LCSSA]] = phi i32 [ [[G_0]], [[FOR_COND]] ], [ 4, [[FOR_COND_CLEANUP_LOOPEXIT]] ]
>>>> -; CHECK-NEXT: [[ADD5]] = add nuw nsw i32 [[CONV]], 4
>>>> -; CHECK-NEXT: br label [[FOR_COND]]
>>>> -; CHECK: for.body:
>>>> -; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ]
>>>> -; CHECK-NEXT: [[TMP29:%.*]] = trunc i64 [[INDVARS_IV]] to i32
>>>> -; CHECK-NEXT: [[ADD:%.*]] = add i32 [[CONV]], [[TMP29]]
>>>> -; CHECK-NEXT: [[IDXPROM:%.*]] = zext i32 [[ADD]] to i64
>>>> -; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [6 x i8], [6 x i8]* @c, i64 0, i64 [[IDXPROM]]
>>>> -; CHECK-NEXT: [[TMP30:%.*]] = load i8, i8* [[ARRAYIDX]], align 1
>>>> -; CHECK-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds i8, i8* [[CALL]], i64 [[INDVARS_IV]]
>>>> -; CHECK-NEXT: store i8 [[TMP30]], i8* [[ARRAYIDX3]], align 1
>>>> -; CHECK-NEXT: [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
>>>> -; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], 4
>>>> -; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP_LOOPEXIT]], label [[FOR_BODY]], !llvm.loop !7
>>>> -;
>>>> -entry:
>>>> - %call = tail call i8* @"_ZN3$_01aEv"(%struct.anon* nonnull @b) #2
>>>> - br label %for.cond
>>>> -
>>>> -for.cond: ; preds = %for.cond.cleanup, %entry
>>>> - %f.0 = phi i32 [ 0, %entry ], [ %add5, %for.cond.cleanup ]
>>>> - %g.0 = phi i32 [ undef, %entry ], [ %g.1.lcssa, %for.cond.cleanup ]
>>>> - %cmp12 = icmp ult i32 %g.0, 4
>>>> - %conv = and i32 %f.0, 65535
>>>> - br i1 %cmp12, label %for.body.lr.ph, label %for.cond.cleanup
>>>> -
>>>> -for.body.lr.ph: ; preds = %for.cond
>>>> - %0 = zext i32 %g.0 to i64
>>>> - br label %for.body
>>>> -
>>>> -for.cond.cleanup.loopexit: ; preds = %for.body
>>>> - br label %for.cond.cleanup
>>>> -
>>>> -for.cond.cleanup: ; preds = %for.cond.cleanup.loopexit, %for.cond
>>>> - %g.1.lcssa = phi i32 [ %g.0, %for.cond ], [ 4, %for.cond.cleanup.loopexit ]
>>>> - %add5 = add nuw nsw i32 %conv, 4
>>>> - br label %for.cond
>>>> -
>>>> -for.body: ; preds = %for.body, %for.body.lr.ph
>>>> - %indvars.iv = phi i64 [ %0, %for.body.lr.ph ], [ %indvars.iv.next, %for.body ]
>>>> - %1 = trunc i64 %indvars.iv to i32
>>>> - %add = add i32 %conv, %1
>>>> - %idxprom = zext i32 %add to i64
>>>> - %arrayidx = getelementptr inbounds [6 x i8], [6 x i8]* @c, i64 0, i64 %idxprom
>>>> - %2 = load i8, i8* %arrayidx, align 1
>>>> - %arrayidx3 = getelementptr inbounds i8, i8* %call, i64 %indvars.iv
>>>> - store i8 %2, i8* %arrayidx3, align 1
>>>> - %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
>>>> - %exitcond = icmp eq i64 %indvars.iv.next, 4
>>>> - br i1 %exitcond, label %for.cond.cleanup.loopexit, label %for.body
>>>> -}
>>>> -
>>>> -declare i8* @"_ZN3$_01aEv"(%struct.anon*) local_unnamed_addr #1
>>>>
>>>>
>>>> _______________________________________________
>>>> llvm-commits mailing list
>>>> llvm-commits at lists.llvm.org
>>>> http://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-commits
>>>
>>> _______________________________________________
>>> llvm-commits mailing list
>>> llvm-commits at lists.llvm.org
>>> http://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-commits
>>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20180226/e4d35e97/attachment-0001.html>
More information about the llvm-commits
mailing list