maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

Revert "[LV] Induction Variable does not remain scalar under tail-folding." 

This reverts commit 617aa64c84.

while I investigate buildbot failures.
This commit is contained in:
Sjoerd Meijer 2020-05-07 09:29:56 +01:00
parent 617aa64c84
commit 20d67ffeae
25 changed files with 1366 additions and 3171 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
View File

@ -1909,9 +1909,11 @@ void InnerLoopVectorizer::widenIntOrFpInduction(PHINode *IV, TruncInst *Trunc) {
return;
}
// All IV users are scalar instructions, so only emit a scalar IV, not a
// vectorised IV.
// If we haven't yet vectorized the induction variable, splat the scalar
// induction variable, and build the necessary step vectors.
// TODO: Don't do it unless the vectorized IV is really required.
Value *ScalarIV = CreateScalarIV(Step);
CreateSplatIV(ScalarIV, Step);
buildScalarSteps(ScalarIV, Step, EntryVal, ID);
}
@ -4587,11 +4589,6 @@ void LoopVectorizationCostModel::collectLoopScalars(unsigned VF) {
if (Induction.second.getKind() == InductionDescriptor::IK_PtrInduction)
continue;
// If tail-folding is applied, the primary induction variable will be used
// to feed a vector compare.
if (Ind == Legal->getPrimaryInduction() && foldTailByMasking())
continue;
// Determine if all users of the induction variable are scalar after
// vectorization.
auto ScalarInd = llvm::all_of(Ind->users(), [&](User *U) -> bool {

6
llvm/test/Transforms/LoopVectorize/AArch64/extractvalue-no-scalarization-required.ll
View File

@ -16,6 +16,9 @@
; FORCED-LABEL: vector.body: ; preds = %vector.body, %vector.ph
; FORCED-NEXT: %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
; FORCED-NEXT: %broadcast.splatinsert = insertelement <2 x i32> undef, i32 %index, i32 0
; FORCED-NEXT: %broadcast.splat = shufflevector <2 x i32> %broadcast.splatinsert, <2 x i32> undef, <2 x i32> zeroinitializer
; FORCED-NEXT: %induction = add <2 x i32> %broadcast.splat, <i32 0, i32 1>
; FORCED-NEXT: %0 = add i32 %index, 0
; FORCED-NEXT: %1 = extractvalue { i64, i64 } %sv, 0
; FORCED-NEXT: %2 = extractvalue { i64, i64 } %sv, 0
@ -65,6 +68,9 @@ declare float @pow(float, float) readnone nounwind
; FORCED-LABEL: vector.body: ; preds = %vector.body, %vector.ph
; FORCED-NEXT: %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
; FORCED-NEXT: %broadcast.splatinsert = insertelement <2 x i32> undef, i32 %index, i32 0
; FORCED-NEXT: %broadcast.splat = shufflevector <2 x i32> %broadcast.splatinsert, <2 x i32> undef, <2 x i32> zeroinitializer
; FORCED-NEXT: %induction = add <2 x i32> %broadcast.splat, <i32 0, i32 1>
; FORCED-NEXT: %0 = add i32 %index, 0
; FORCED-NEXT: %1 = extractvalue { float, float } %sv, 0
; FORCED-NEXT: %2 = extractvalue { float, float } %sv, 0

6
llvm/test/Transforms/LoopVectorize/AArch64/pr36032.ll
View File

@ -65,9 +65,15 @@ define void @_Z1dv() local_unnamed_addr #0 {
; 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

3
llvm/test/Transforms/LoopVectorize/ARM/sphinx.ll
View File

@ -44,6 +44,9 @@ define i32 @test(float* nocapture readonly %x) {
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[VEC_PHI:%.*]] = phi <2 x double> [ [[TMP0]], [[VECTOR_PH]] ], [ [[TMP16:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <2 x i32> undef, i32 [[INDEX]], i32 0
; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <2 x i32> [[BROADCAST_SPLATINSERT]], <2 x i32> undef, <2 x i32> zeroinitializer
; CHECK-NEXT: [[INDUCTION:%.*]] = add <2 x i32> [[BROADCAST_SPLAT]], <i32 0, i32 1>
; CHECK-NEXT: [[TMP1:%.*]] = add i32 [[INDEX]], 0
; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds float, float* [[X:%.*]], i32 [[TMP1]]
; CHECK-NEXT: [[TMP3:%.*]] = getelementptr inbounds float, float* [[TMP2]], i32 0

22
llvm/test/Transforms/LoopVectorize/X86/constant-fold.ll
View File

@ -19,6 +19,9 @@ define void @f1() {
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[OFFSET_IDX:%.*]] = trunc i32 [[INDEX]] to i16
; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <2 x i16> undef, i16 [[OFFSET_IDX]], i32 0
; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <2 x i16> [[BROADCAST_SPLATINSERT]], <2 x i16> undef, <2 x i32> zeroinitializer
; CHECK-NEXT: [[INDUCTION:%.*]] = add <2 x i16> [[BROADCAST_SPLAT]], <i16 0, i16 1>
; CHECK-NEXT: [[TMP0:%.*]] = add i16 [[OFFSET_IDX]], 0
; CHECK-NEXT: [[TMP1:%.*]] = sext i16 [[TMP0]] to i64
; CHECK-NEXT: [[TMP2:%.*]] = getelementptr [2 x i16*], [2 x i16*]* @b, i16 0, i64 [[TMP1]]
@ -29,25 +32,6 @@ define void @f1() {
; CHECK-NEXT: [[TMP5:%.*]] = icmp eq i32 [[INDEX_NEXT]], 2
; CHECK-NEXT: br i1 [[TMP5]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !0
; CHECK: middle.block:
; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i32 2, 2
; CHECK-NEXT: br i1 [[CMP_N]], label [[BB3:%.*]], label [[SCALAR_PH]]
; CHECK: scalar.ph:
; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i16 [ 2, [[MIDDLE_BLOCK]] ], [ 0, [[BB1:%.*]] ]
; CHECK-NEXT: br label [[BB2:%.*]]
; CHECK: bb2:
; CHECK-NEXT: [[C_1_0:%.*]] = phi i16 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[_TMP9:%.*]], [[BB2]] ]
; CHECK-NEXT: [[_TMP1:%.*]] = zext i16 0 to i64
; CHECK-NEXT: [[_TMP2:%.*]] = getelementptr [1 x %rec8], [1 x %rec8]* @a, i16 0, i64 [[_TMP1]]
; CHECK-NEXT: [[_TMP4:%.*]] = bitcast %rec8* [[_TMP2]] to i16*
; CHECK-NEXT: [[_TMP6:%.*]] = sext i16 [[C_1_0]] to i64
; CHECK-NEXT: [[_TMP7:%.*]] = getelementptr [2 x i16*], [2 x i16*]* @b, i16 0, i64 [[_TMP6]]
; CHECK-NEXT: store i16* [[_TMP4]], i16** [[_TMP7]]
; CHECK-NEXT: [[_TMP9]] = add nsw i16 [[C_1_0]], 1
; CHECK-NEXT: [[_TMP11:%.*]] = icmp slt i16 [[_TMP9]], 2
; CHECK-NEXT: br i1 [[_TMP11]], label [[BB2]], label [[BB3]], !llvm.loop !2
; CHECK: bb3:
; CHECK-NEXT: ret void
;
bb1:
br label %bb2

3
llvm/test/Transforms/LoopVectorize/X86/imprecise-through-phis.ll
View File

@ -97,6 +97,9 @@ define double @sumIfVector(double* nocapture readonly %arr) {
; AVX: vector.body:
; AVX-NEXT: [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; AVX-NEXT: [[VEC_PHI:%.*]] = phi <4 x double> [ zeroinitializer, [[VECTOR_PH]] ], [ [[PREDPHI:%.*]], [[VECTOR_BODY]] ]
; AVX-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i32> undef, i32 [[INDEX]], i32 0
; AVX-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT]], <4 x i32> undef, <4 x i32> zeroinitializer
; AVX-NEXT: [[INDUCTION:%.*]] = add <4 x i32> [[BROADCAST_SPLAT]], <i32 0, i32 1, i32 2, i32 3>
; AVX-NEXT: [[TMP0:%.*]] = add i32 [[INDEX]], 0
; AVX-NEXT: [[TMP1:%.*]] = getelementptr double, double* [[ARR:%.*]], i32 [[TMP0]]
; AVX-NEXT: [[TMP2:%.*]] = getelementptr double, double* [[TMP1]], i32 0

686
llvm/test/Transforms/LoopVectorize/X86/load-deref-pred.ll
View File

File diff suppressed because it is too large Load Diff

597
llvm/test/Transforms/LoopVectorize/X86/masked_load_store.ll
View File

File diff suppressed because it is too large Load Diff

486
llvm/test/Transforms/LoopVectorize/X86/metadata-enable.ll
View File

File diff suppressed because it is too large Load Diff

168
llvm/test/Transforms/LoopVectorize/X86/optsize.ll
View File

@ -17,11 +17,12 @@ define i32 @foo_optsize() #0 {
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP0:%.*]] = add i32 [[INDEX]], 0
; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <64 x i32> undef, i32 [[TMP0]], i32 0
; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <64 x i32> undef, i32 [[INDEX]], i32 0
; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <64 x i32> [[BROADCAST_SPLATINSERT]], <64 x i32> undef, <64 x i32> zeroinitializer
; CHECK-NEXT: [[INDUCTION:%.*]] = add <64 x i32> [[BROADCAST_SPLAT]], <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63>
; CHECK-NEXT: [[TMP0:%.*]] = add i32 [[INDEX]], 0
; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds [32 x i8], [32 x i8]* @tab, i32 0, i32 [[TMP0]]
; CHECK-NEXT: [[TMP2:%.*]] = icmp ule <64 x i32> [[BROADCAST_SPLAT]], <i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202>
; CHECK-NEXT: [[TMP2:%.*]] = icmp ule <64 x i32> [[INDUCTION]], <i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202>
; CHECK-NEXT: [[TMP3:%.*]] = getelementptr inbounds i8, i8* [[TMP1]], i32 0
; CHECK-NEXT: [[TMP4:%.*]] = bitcast i8* [[TMP3]] to <64 x i8>*
; CHECK-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <64 x i8> @llvm.masked.load.v64i8.p0v64i8(<64 x i8>* [[TMP4]], i32 1, <64 x i1> [[TMP2]], <64 x i8> undef)
@ -51,47 +52,6 @@ define i32 @foo_optsize() #0 {
; CHECK: for.end:
; CHECK-NEXT: ret i32 0
;
; AUTOVF-LABEL: @foo_optsize(
; AUTOVF-NEXT: entry:
; AUTOVF-NEXT: br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; AUTOVF: vector.ph:
; AUTOVF-NEXT: br label [[VECTOR_BODY:%.*]]
; AUTOVF: vector.body:
; AUTOVF-NEXT: [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; AUTOVF-NEXT: [[TMP0:%.*]] = add i32 [[INDEX]], 0
; AUTOVF-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <32 x i32> undef, i32 [[TMP0]], i32 0
; AUTOVF-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <32 x i32> [[BROADCAST_SPLATINSERT]], <32 x i32> undef, <32 x i32> zeroinitializer
; AUTOVF-NEXT: [[TMP1:%.*]] = getelementptr inbounds [32 x i8], [32 x i8]* @tab, i32 0, i32 [[TMP0]]
; AUTOVF-NEXT: [[TMP2:%.*]] = icmp ule <32 x i32> [[BROADCAST_SPLAT]], <i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202>
; AUTOVF-NEXT: [[TMP3:%.*]] = getelementptr inbounds i8, i8* [[TMP1]], i32 0
; AUTOVF-NEXT: [[TMP4:%.*]] = bitcast i8* [[TMP3]] to <32 x i8>*
; AUTOVF-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <32 x i8> @llvm.masked.load.v32i8.p0v32i8(<32 x i8>* [[TMP4]], i32 1, <32 x i1> [[TMP2]], <32 x i8> undef)
; AUTOVF-NEXT: [[TMP5:%.*]] = icmp eq <32 x i8> [[WIDE_MASKED_LOAD]], zeroinitializer
; AUTOVF-NEXT: [[TMP6:%.*]] = extractelement <32 x i1> [[TMP5]], i32 0
; AUTOVF-NEXT: [[TMP7:%.*]] = select <32 x i1> [[TMP5]], <32 x i8> <i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2>, <32 x i8> <i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1>
; AUTOVF-NEXT: [[TMP8:%.*]] = bitcast i8* [[TMP3]] to <32 x i8>*
; AUTOVF-NEXT: call void @llvm.masked.store.v32i8.p0v32i8(<32 x i8> [[TMP7]], <32 x i8>* [[TMP8]], i32 1, <32 x i1> [[TMP2]])
; AUTOVF-NEXT: [[INDEX_NEXT]] = add i32 [[INDEX]], 32
; AUTOVF-NEXT: [[TMP9:%.*]] = icmp eq i32 [[INDEX_NEXT]], 224
; AUTOVF-NEXT: br i1 [[TMP9]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !0
; AUTOVF: middle.block:
; AUTOVF-NEXT: br i1 true, label [[FOR_END:%.*]], label [[SCALAR_PH]]
; AUTOVF: scalar.ph:
; AUTOVF-NEXT: [[BC_RESUME_VAL:%.*]] = phi i32 [ 224, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; AUTOVF-NEXT: br label [[FOR_BODY:%.*]]
; AUTOVF: for.body:
; AUTOVF-NEXT: [[I_08:%.*]] = phi i32 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INC:%.*]], [[FOR_BODY]] ]
; AUTOVF-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [32 x i8], [32 x i8]* @tab, i32 0, i32 [[I_08]]
; AUTOVF-NEXT: [[TMP10:%.*]] = load i8, i8* [[ARRAYIDX]], align 1
; AUTOVF-NEXT: [[CMP1:%.*]] = icmp eq i8 [[TMP10]], 0
; AUTOVF-NEXT: [[DOT:%.*]] = select i1 [[CMP1]], i8 2, i8 1
; AUTOVF-NEXT: store i8 [[DOT]], i8* [[ARRAYIDX]], align 1
; AUTOVF-NEXT: [[INC]] = add nsw i32 [[I_08]], 1
; AUTOVF-NEXT: [[EXITCOND:%.*]] = icmp eq i32 [[I_08]], 202
; AUTOVF-NEXT: br i1 [[EXITCOND]], label [[FOR_END]], label [[FOR_BODY]], !llvm.loop !2
; AUTOVF: for.end:
; AUTOVF-NEXT: ret i32 0
;
entry:
br label %for.body
@ -121,11 +81,12 @@ define i32 @foo_minsize() #1 {
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP0:%.*]] = add i32 [[INDEX]], 0
; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <64 x i32> undef, i32 [[TMP0]], i32 0
; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <64 x i32> undef, i32 [[INDEX]], i32 0
; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <64 x i32> [[BROADCAST_SPLATINSERT]], <64 x i32> undef, <64 x i32> zeroinitializer
; CHECK-NEXT: [[INDUCTION:%.*]] = add <64 x i32> [[BROADCAST_SPLAT]], <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63>
; CHECK-NEXT: [[TMP0:%.*]] = add i32 [[INDEX]], 0
; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds [32 x i8], [32 x i8]* @tab, i32 0, i32 [[TMP0]]
; CHECK-NEXT: [[TMP2:%.*]] = icmp ule <64 x i32> [[BROADCAST_SPLAT]], <i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202>
; CHECK-NEXT: [[TMP2:%.*]] = icmp ule <64 x i32> [[INDUCTION]], <i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202>
; CHECK-NEXT: [[TMP3:%.*]] = getelementptr inbounds i8, i8* [[TMP1]], i32 0
; CHECK-NEXT: [[TMP4:%.*]] = bitcast i8* [[TMP3]] to <64 x i8>*
; CHECK-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <64 x i8> @llvm.masked.load.v64i8.p0v64i8(<64 x i8>* [[TMP4]], i32 1, <64 x i1> [[TMP2]], <64 x i8> undef)
@ -155,47 +116,6 @@ define i32 @foo_minsize() #1 {
; CHECK: for.end:
; CHECK-NEXT: ret i32 0
;
; AUTOVF-LABEL: @foo_minsize(
; AUTOVF-NEXT: entry:
; AUTOVF-NEXT: br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; AUTOVF: vector.ph:
; AUTOVF-NEXT: br label [[VECTOR_BODY:%.*]]
; AUTOVF: vector.body:
; AUTOVF-NEXT: [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; AUTOVF-NEXT: [[TMP0:%.*]] = add i32 [[INDEX]], 0
; AUTOVF-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <32 x i32> undef, i32 [[TMP0]], i32 0
; AUTOVF-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <32 x i32> [[BROADCAST_SPLATINSERT]], <32 x i32> undef, <32 x i32> zeroinitializer
; AUTOVF-NEXT: [[TMP1:%.*]] = getelementptr inbounds [32 x i8], [32 x i8]* @tab, i32 0, i32 [[TMP0]]
; AUTOVF-NEXT: [[TMP2:%.*]] = icmp ule <32 x i32> [[BROADCAST_SPLAT]], <i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202, i32 202>
; AUTOVF-NEXT: [[TMP3:%.*]] = getelementptr inbounds i8, i8* [[TMP1]], i32 0
; AUTOVF-NEXT: [[TMP4:%.*]] = bitcast i8* [[TMP3]] to <32 x i8>*
; AUTOVF-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <32 x i8> @llvm.masked.load.v32i8.p0v32i8(<32 x i8>* [[TMP4]], i32 1, <32 x i1> [[TMP2]], <32 x i8> undef)
; AUTOVF-NEXT: [[TMP5:%.*]] = icmp eq <32 x i8> [[WIDE_MASKED_LOAD]], zeroinitializer
; AUTOVF-NEXT: [[TMP6:%.*]] = extractelement <32 x i1> [[TMP5]], i32 0
; AUTOVF-NEXT: [[TMP7:%.*]] = select <32 x i1> [[TMP5]], <32 x i8> <i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2>, <32 x i8> <i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1>
; AUTOVF-NEXT: [[TMP8:%.*]] = bitcast i8* [[TMP3]] to <32 x i8>*
; AUTOVF-NEXT: call void @llvm.masked.store.v32i8.p0v32i8(<32 x i8> [[TMP7]], <32 x i8>* [[TMP8]], i32 1, <32 x i1> [[TMP2]])
; AUTOVF-NEXT: [[INDEX_NEXT]] = add i32 [[INDEX]], 32
; AUTOVF-NEXT: [[TMP9:%.*]] = icmp eq i32 [[INDEX_NEXT]], 224
; AUTOVF-NEXT: br i1 [[TMP9]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !4
; AUTOVF: middle.block:
; AUTOVF-NEXT: br i1 true, label [[FOR_END:%.*]], label [[SCALAR_PH]]
; AUTOVF: scalar.ph:
; AUTOVF-NEXT: [[BC_RESUME_VAL:%.*]] = phi i32 [ 224, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; AUTOVF-NEXT: br label [[FOR_BODY:%.*]]
; AUTOVF: for.body:
; AUTOVF-NEXT: [[I_08:%.*]] = phi i32 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INC:%.*]], [[FOR_BODY]] ]
; AUTOVF-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [32 x i8], [32 x i8]* @tab, i32 0, i32 [[I_08]]
; AUTOVF-NEXT: [[TMP10:%.*]] = load i8, i8* [[ARRAYIDX]], align 1
; AUTOVF-NEXT: [[CMP1:%.*]] = icmp eq i8 [[TMP10]], 0
; AUTOVF-NEXT: [[DOT:%.*]] = select i1 [[CMP1]], i8 2, i8 1
; AUTOVF-NEXT: store i8 [[DOT]], i8* [[ARRAYIDX]], align 1
; AUTOVF-NEXT: [[INC]] = add nsw i32 [[I_08]], 1
; AUTOVF-NEXT: [[EXITCOND:%.*]] = icmp eq i32 [[I_08]], 202
; AUTOVF-NEXT: br i1 [[EXITCOND]], label [[FOR_END]], label [[FOR_BODY]], !llvm.loop !5
; AUTOVF: for.end:
; AUTOVF-NEXT: ret i32 0
;
entry:
br label %for.body
@ -220,39 +140,15 @@ attributes #1 = { minsize }
; We can't vectorize this one because we version for stride==1; even having TC
; a multiple of VF.
; CHECK-LABEL: @scev4stride1
; CHECK-NOT: vector.scevcheck
; CHECK-NOT: vector.body:
; CHECK-LABEL: for.body:
; AUTOVF-LABEL: @scev4stride1
; AUTOVF-NOT: vector.scevcheck
; AUTOVF-NOT: vector.body:
; AUTOVF-LABEL: for.body:
define void @scev4stride1(i32* noalias nocapture %a, i32* noalias nocapture readonly %b, i32 %k) #2 {
; CHECK-LABEL: @scev4stride1(
; CHECK-NEXT: for.body.preheader:
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[I_07:%.*]] = phi i32 [ [[INC:%.*]], [[FOR_BODY]] ], [ 0, [[FOR_BODY_PREHEADER:%.*]] ]
; CHECK-NEXT: [[MUL:%.*]] = mul nsw i32 [[I_07]], [[K:%.*]]
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i32 [[MUL]]
; CHECK-NEXT: [[TMP0:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
; CHECK-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i32 [[I_07]]
; CHECK-NEXT: store i32 [[TMP0]], i32* [[ARRAYIDX1]], align 4
; CHECK-NEXT: [[INC]] = add nuw nsw i32 [[I_07]], 1
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i32 [[INC]], 256
; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_END_LOOPEXIT:%.*]], label [[FOR_BODY]]
; CHECK: for.end.loopexit:
; CHECK-NEXT: ret void
;
; AUTOVF-LABEL: @scev4stride1(
; AUTOVF-NEXT: for.body.preheader:
; AUTOVF-NEXT: br label [[FOR_BODY:%.*]]
; AUTOVF: for.body:
; AUTOVF-NEXT: [[I_07:%.*]] = phi i32 [ [[INC:%.*]], [[FOR_BODY]] ], [ 0, [[FOR_BODY_PREHEADER:%.*]] ]
; AUTOVF-NEXT: [[MUL:%.*]] = mul nsw i32 [[I_07]], [[K:%.*]]
; AUTOVF-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i32 [[MUL]]
; AUTOVF-NEXT: [[TMP0:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
; AUTOVF-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i32 [[I_07]]
; AUTOVF-NEXT: store i32 [[TMP0]], i32* [[ARRAYIDX1]], align 4
; AUTOVF-NEXT: [[INC]] = add nuw nsw i32 [[I_07]], 1
; AUTOVF-NEXT: [[EXITCOND:%.*]] = icmp eq i32 [[INC]], 256
; AUTOVF-NEXT: br i1 [[EXITCOND]], label [[FOR_END_LOOPEXIT:%.*]], label [[FOR_BODY]]
; AUTOVF: for.end.loopexit:
; AUTOVF-NEXT: ret void
;
for.body.preheader:
br label %for.body
@ -278,31 +174,15 @@ attributes #2 = { optsize }
; We can't vectorize this one because we version for overflow check and tiny
; trip count leads to opt-for-size (which otherwise could fold the tail by
; masking).
; CHECK-LABEL: @main
; CHECK-NOT: vector.scevcheck
; CHECK-NOT: vector.body:
; CHECK-LABEL: for.cond:
; AUTOVF-LABEL: @main
; AUTOVF-NOT: vector.scevcheck
; AUTOVF-NOT: vector.body:
; AUTOVF-LABEL: for.cond:
define i32 @main() local_unnamed_addr {
; CHECK-LABEL: @main(
; CHECK-NEXT: while.cond:
; CHECK-NEXT: br label [[FOR_COND:%.*]]
; CHECK: for.cond:
; CHECK-NEXT: [[D_0:%.*]] = phi i32 [ 0, [[WHILE_COND:%.*]] ], [ [[ADD:%.*]], [[FOR_COND]] ]
; CHECK-NEXT: [[CONV:%.*]] = and i32 [[D_0]], 65535
; CHECK-NEXT: [[CMP:%.*]] = icmp ult i32 [[CONV]], 4
; CHECK-NEXT: [[ADD]] = add nuw nsw i32 [[CONV]], 1
; CHECK-NEXT: br i1 [[CMP]], label [[FOR_COND]], label [[WHILE_COND_LOOPEXIT:%.*]]
; CHECK: while.cond.loopexit:
; CHECK-NEXT: ret i32 0
;
; AUTOVF-LABEL: @main(
; AUTOVF-NEXT: while.cond:
; AUTOVF-NEXT: br label [[FOR_COND:%.*]]
; AUTOVF: for.cond:
; AUTOVF-NEXT: [[D_0:%.*]] = phi i32 [ 0, [[WHILE_COND:%.*]] ], [ [[ADD:%.*]], [[FOR_COND]] ]
; AUTOVF-NEXT: [[CONV:%.*]] = and i32 [[D_0]], 65535
; AUTOVF-NEXT: [[CMP:%.*]] = icmp ult i32 [[CONV]], 4
; AUTOVF-NEXT: [[ADD]] = add nuw nsw i32 [[CONV]], 1
; AUTOVF-NEXT: br i1 [[CMP]], label [[FOR_COND]], label [[WHILE_COND_LOOPEXIT:%.*]]
; AUTOVF: while.cond.loopexit:
; AUTOVF-NEXT: ret i32 0
;
while.cond:
br label %for.cond

20
llvm/test/Transforms/LoopVectorize/X86/pr35432.ll
View File

@ -40,16 +40,16 @@ define i32 @main() local_unnamed_addr #0 {
; CHECK-NEXT: [[TMP4:%.*]] = zext i8 [[TMP3]] to i32
; CHECK-NEXT: [[TMP5:%.*]] = add i32 [[TMP4]], 1
; CHECK-NEXT: [[TMP6:%.*]] = icmp ult i32 [[TMP2]], [[TMP4]]
; CHECK-NEXT: [[UMIN:%.*]] = select i1 [[TMP6]], i32 [[TMP2]], i32 [[TMP4]]
; CHECK-NEXT: [[TMP7:%.*]] = sub i32 [[TMP5]], [[UMIN]]
; CHECK-NEXT: [[UMAX:%.*]] = select i1 [[TMP6]], i32 [[TMP2]], i32 [[TMP4]]
; CHECK-NEXT: [[TMP7:%.*]] = sub i32 [[TMP5]], [[UMAX]]
; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i32 [[TMP7]], 8
; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_SCEVCHECK:%.*]]
; CHECK: vector.scevcheck:
; CHECK-NEXT: [[TMP8:%.*]] = add i8 [[CONV3]], -1
; CHECK-NEXT: [[TMP9:%.*]] = zext i8 [[TMP8]] to i32
; CHECK-NEXT: [[TMP10:%.*]] = icmp ult i32 [[TMP2]], [[TMP9]]
; CHECK-NEXT: [[UMIN1:%.*]] = select i1 [[TMP10]], i32 [[TMP2]], i32 [[TMP9]]
; CHECK-NEXT: [[TMP11:%.*]] = sub i32 [[TMP9]], [[UMIN1]]
; CHECK-NEXT: [[UMAX1:%.*]] = select i1 [[TMP10]], i32 [[TMP2]], i32 [[TMP9]]
; CHECK-NEXT: [[TMP11:%.*]] = sub i32 [[TMP9]], [[UMAX1]]
; CHECK-NEXT: [[TMP12:%.*]] = trunc i32 [[TMP11]] to i8
; CHECK-NEXT: [[MUL:%.*]] = call { i8, i1 } @llvm.umul.with.overflow.i8(i8 1, i8 [[TMP12]])
; CHECK-NEXT: [[MUL_RESULT:%.*]] = extractvalue { i8, i1 } [[MUL]], 0
@ -77,6 +77,10 @@ define i32 @main() local_unnamed_addr #0 {
; CHECK-NEXT: [[VEC_PHI2:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP27:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP23:%.*]] = trunc i32 [[INDEX]] to i8
; CHECK-NEXT: [[OFFSET_IDX:%.*]] = sub i8 [[CONV3]], [[TMP23]]
; 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: [[TMP24:%.*]] = add i8 [[OFFSET_IDX]], 0
; CHECK-NEXT: [[TMP25:%.*]] = add i8 [[OFFSET_IDX]], -4
; CHECK-NEXT: [[TMP26]] = add <4 x i32> [[VEC_PHI]], <i32 1, i32 1, i32 1, i32 1>
@ -91,10 +95,10 @@ define i32 @main() local_unnamed_addr #0 {
; CHECK: middle.block:
; CHECK-NEXT: [[BIN_RDX:%.*]] = add <4 x i32> [[TMP27]], [[TMP26]]
; 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_RDX3:%.*]] = add <4 x i32> [[BIN_RDX]], [[RDX_SHUF]]
; CHECK-NEXT: [[RDX_SHUF4:%.*]] = shufflevector <4 x i32> [[BIN_RDX3]], <4 x i32> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
; CHECK-NEXT: [[BIN_RDX5:%.*]] = add <4 x i32> [[BIN_RDX3]], [[RDX_SHUF4]]
; CHECK-NEXT: [[TMP33:%.*]] = extractelement <4 x i32> [[BIN_RDX5]], i32 0
; 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: [[TMP33:%.*]] = extractelement <4 x i32> [[BIN_RDX6]], i32 0
; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i32 [[TMP7]], [[N_VEC]]
; CHECK-NEXT: br i1 [[CMP_N]], label [[FOR_COND4_FOR_INC9_CRIT_EDGE:%.*]], label [[SCALAR_PH]]
; CHECK: scalar.ph:

3
llvm/test/Transforms/LoopVectorize/X86/pr36524.ll
View File

@ -14,6 +14,9 @@ define void @foo() {
; CHECK-NEXT: [[TMP10:%.*]] = add i64 [[OFFSET_IDX]], 3
; CHECK-NEXT: [[OFFSET_IDX1:%.*]] = add i64 2, [[INDEX]]
; CHECK-NEXT: [[TMP11:%.*]] = trunc i64 [[OFFSET_IDX1]] to i32
; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i32> undef, i32 [[TMP11]], i32 0
; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT]], <4 x i32> undef, <4 x i32> zeroinitializer
; CHECK-NEXT: [[INDUCTION:%.*]] = add <4 x i32> [[BROADCAST_SPLAT]], <i32 0, i32 1, i32 2, i32 3>
; CHECK-NEXT: [[TMP12:%.*]] = add i32 [[TMP11]], 0
; CHECK-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], 4
; CHECK-NEXT: [[VEC_IND_NEXT]] = add <4 x i64> [[VEC_IND]], <i64 4, i64 4, i64 4, i64 4>

392
llvm/test/Transforms/LoopVectorize/X86/small-size.ll
View File

@ -45,10 +45,8 @@ define void @example1() optsize {
; CHECK-NEXT: br i1 true, label [[TMP10:%.*]], label [[SCALAR_PH]]
; CHECK: scalar.ph:
; CHECK-NEXT: br label [[TMP9:%.*]]
; CHECK: 9:
; CHECK-NEXT: br i1 undef, label [[TMP10]], label [[TMP9]], !llvm.loop !2
; CHECK: 10:
; CHECK-NEXT: ret void
; CHECK: br i1 undef, label [[TMP10]], label [[TMP9]], !llvm.loop !2
; CHECK: ret void
;
br label %1
@ -82,197 +80,51 @@ define void @example2(i32 %n, i32 %x) optsize {
; CHECK: vector.ph:
; CHECK-NEXT: [[N_RND_UP:%.*]] = add nuw nsw i64 [[TMP3]], 4
; CHECK-NEXT: [[N_VEC:%.*]] = and i64 [[N_RND_UP]], 8589934588
; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i64> undef, i64 [[TMP3]], i32 0
; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT]], <4 x i64> undef, <4 x i32> zeroinitializer
; CHECK-NEXT: [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <4 x i64> undef, i64 [[TMP3]], i32 0
; CHECK-NEXT: [[BROADCAST_SPLAT2:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT1]], <4 x i64> undef, <4 x i32> zeroinitializer
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[PRED_STORE_CONTINUE6:%.*]] ]
; CHECK-NEXT: [[VEC_IND:%.*]] = phi <4 x i64> [ <i64 0, i64 1, i64 2, i64 3>, [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[PRED_STORE_CONTINUE6]] ]
; CHECK-NEXT: [[TMP4:%.*]] = icmp ule <4 x i64> [[VEC_IND]], [[BROADCAST_SPLAT]]
; CHECK-NEXT: [[TMP5:%.*]] = extractelement <4 x i1> [[TMP4]], i32 0
; CHECK-NEXT: br i1 [[TMP5]], label [[PRED_STORE_IF:%.*]], label [[PRED_STORE_CONTINUE:%.*]]
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[PRED_STORE_CONTINUE8:%.*]] ]
; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i64> undef, i64 [[INDEX]], i32 0
; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT]], <4 x i64> undef, <4 x i32> zeroinitializer
; CHECK-NEXT: [[INDUCTION:%.*]] = or <4 x i64> [[BROADCAST_SPLAT]], <i64 0, i64 1, i64 2, i64 3>
; CHECK-NEXT: [[TMP5:%.*]] = or i64 [[INDEX]], 1
; CHECK-NEXT: [[TMP6:%.*]] = or i64 [[INDEX]], 2
; CHECK-NEXT: [[TMP7:%.*]] = or i64 [[INDEX]], 3
; CHECK-NEXT: [[TMP8:%.*]] = icmp ule <4 x i64> [[INDUCTION]], [[BROADCAST_SPLAT2]]
; CHECK-NEXT: [[TMP9:%.*]] = extractelement <4 x i1> [[TMP8]], i32 0
; CHECK-NEXT: br i1 [[TMP9]], label [[PRED_STORE_IF:%.*]], label [[PRED_STORE_CONTINUE:%.*]]
; CHECK: pred.store.if:
; CHECK-NEXT: [[TMP6:%.*]] = getelementptr inbounds [2048 x i32], [2048 x i32]* @b, i64 0, i64 [[INDEX]]
; CHECK-NEXT: store i32 [[X:%.*]], i32* [[TMP6]], align 16
; CHECK-NEXT: [[TMP10:%.*]] = getelementptr inbounds [2048 x i32], [2048 x i32]* @b, i64 0, i64 [[INDEX]]
; CHECK-NEXT: store i32 [[X:%.*]], i32* [[TMP10]], align 16
; CHECK-NEXT: br label [[PRED_STORE_CONTINUE]]
; CHECK: pred.store.continue:
; CHECK-NEXT: [[TMP7:%.*]] = extractelement <4 x i1> [[TMP4]], i32 1
; CHECK-NEXT: br i1 [[TMP7]], label [[PRED_STORE_IF1:%.*]], label [[PRED_STORE_CONTINUE2:%.*]]
; CHECK: pred.store.if1:
; CHECK-NEXT: [[TMP8:%.*]] = or i64 [[INDEX]], 1
; CHECK-NEXT: [[TMP9:%.*]] = getelementptr inbounds [2048 x i32], [2048 x i32]* @b, i64 0, i64 [[TMP8]]
; CHECK-NEXT: store i32 [[X]], i32* [[TMP9]], align 4
; CHECK-NEXT: br label [[PRED_STORE_CONTINUE2]]
; CHECK: pred.store.continue2:
; CHECK-NEXT: [[TMP10:%.*]] = extractelement <4 x i1> [[TMP4]], i32 2
; CHECK-NEXT: br i1 [[TMP10]], label [[PRED_STORE_IF3:%.*]], label [[PRED_STORE_CONTINUE4:%.*]]
; CHECK-NEXT: [[TMP11:%.*]] = extractelement <4 x i1> [[TMP8]], i32 1
; CHECK-NEXT: br i1 [[TMP11]], label [[PRED_STORE_IF3:%.*]], label [[PRED_STORE_CONTINUE4:%.*]]
; CHECK: pred.store.if3:
; CHECK-NEXT: [[TMP11:%.*]] = or i64 [[INDEX]], 2
; CHECK-NEXT: [[TMP12:%.*]] = getelementptr inbounds [2048 x i32], [2048 x i32]* @b, i64 0, i64 [[TMP11]]
; CHECK-NEXT: store i32 [[X]], i32* [[TMP12]], align 8
; CHECK-NEXT: [[TMP12:%.*]] = getelementptr inbounds [2048 x i32], [2048 x i32]* @b, i64 0, i64 [[TMP5]]
; CHECK-NEXT: store i32 [[X]], i32* [[TMP12]], align 4
; CHECK-NEXT: br label [[PRED_STORE_CONTINUE4]]
; CHECK: pred.store.continue4:
; CHECK-NEXT: [[TMP13:%.*]] = extractelement <4 x i1> [[TMP4]], i32 3
; CHECK-NEXT: br i1 [[TMP13]], label [[PRED_STORE_IF5:%.*]], label [[PRED_STORE_CONTINUE6]]
; CHECK-NEXT: [[TMP13:%.*]] = extractelement <4 x i1> [[TMP8]], i32 2
; CHECK-NEXT: br i1 [[TMP13]], label [[PRED_STORE_IF5:%.*]], label [[PRED_STORE_CONTINUE6:%.*]]
; CHECK: pred.store.if5:
; CHECK-NEXT: [[TMP14:%.*]] = or i64 [[INDEX]], 3
; CHECK-NEXT: [[TMP15:%.*]] = getelementptr inbounds [2048 x i32], [2048 x i32]* @b, i64 0, i64 [[TMP14]]
; CHECK-NEXT: store i32 [[X]], i32* [[TMP15]], align 4
; CHECK-NEXT: [[TMP14:%.*]] = getelementptr inbounds [2048 x i32], [2048 x i32]* @b, i64 0, i64 [[TMP6]]
; CHECK-NEXT: store i32 [[X]], i32* [[TMP14]], align 8
; CHECK-NEXT: br label [[PRED_STORE_CONTINUE6]]
; CHECK: pred.store.continue6:
; CHECK-NEXT: [[TMP15:%.*]] = extractelement <4 x i1> [[TMP8]], i32 3
; CHECK-NEXT: br i1 [[TMP15]], label [[PRED_STORE_IF7:%.*]], label [[PRED_STORE_CONTINUE8]]
; CHECK: pred.store.if7:
; CHECK-NEXT: [[TMP16:%.*]] = getelementptr inbounds [2048 x i32], [2048 x i32]* @b, i64 0, i64 [[TMP7]]
; CHECK-NEXT: store i32 [[X]], i32* [[TMP16]], align 4
; CHECK-NEXT: br label [[PRED_STORE_CONTINUE8]]
; CHECK: pred.store.continue8:
; CHECK-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], 4
; CHECK-NEXT: [[VEC_IND_NEXT]] = add <4 x i64> [[VEC_IND]], <i64 4, i64 4, i64 4, i64 4>
; CHECK-NEXT: [[TMP16:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT: br i1 [[TMP16]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !4
; CHECK-NEXT: [[TMP17:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT: br i1 [[TMP17]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !4
; CHECK: middle.block:
; CHECK-NEXT: br i1 true, label [[DOT_PREHEADER_CRIT_EDGE:%.*]], label [[SCALAR_PH]]
; CHECK: scalar.ph:
; CHECK-NEXT: br label [[DOTLR_PH5:%.*]]
; CHECK: ..preheader_crit_edge:
; CHECK-NEXT: [[PHITMP:%.*]] = sext i32 [[N]] to i64
; CHECK-NEXT: br label [[DOTPREHEADER]]
; CHECK: .preheader:
; CHECK-NEXT: [[I_0_LCSSA:%.*]] = phi i64 [ [[PHITMP]], [[DOT_PREHEADER_CRIT_EDGE]] ], [ 0, [[TMP0:%.*]] ]
; CHECK-NEXT: [[TMP17:%.*]] = icmp eq i32 [[N]], 0
; CHECK-NEXT: br i1 [[TMP17]], label [[DOT_CRIT_EDGE:%.*]], label [[DOTLR_PH_PREHEADER:%.*]]
; CHECK: .lr.ph.preheader:
; CHECK-NEXT: [[TMP18:%.*]] = add i32 [[N]], -1
; CHECK-NEXT: [[TMP19:%.*]] = zext i32 [[TMP18]] to i64
; CHECK-NEXT: br i1 false, label [[SCALAR_PH8:%.*]], label [[VECTOR_PH10:%.*]]
; CHECK: vector.ph10:
; CHECK-NEXT: [[N_RND_UP11:%.*]] = add nuw nsw i64 [[TMP19]], 4
; CHECK-NEXT: [[N_VEC13:%.*]] = and i64 [[N_RND_UP11]], 8589934588
; CHECK-NEXT: [[BROADCAST_SPLATINSERT20:%.*]] = insertelement <4 x i64> undef, i64 [[TMP19]], i32 0
; CHECK-NEXT: [[BROADCAST_SPLAT21:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT20]], <4 x i64> undef, <4 x i32> zeroinitializer
; CHECK-NEXT: br label [[VECTOR_BODY9:%.*]]
; CHECK: vector.body9:
; CHECK-NEXT: [[INDEX14:%.*]] = phi i64 [ 0, [[VECTOR_PH10]] ], [ [[INDEX_NEXT15:%.*]], [[PRED_STORE_CONTINUE46:%.*]] ]
; CHECK-NEXT: [[OFFSET_IDX:%.*]] = add i64 [[I_0_LCSSA]], [[INDEX14]]
; CHECK-NEXT: [[TMP20:%.*]] = add i64 [[OFFSET_IDX]], 1
; CHECK-NEXT: [[TMP21:%.*]] = add i64 [[OFFSET_IDX]], 2
; CHECK-NEXT: [[TMP22:%.*]] = add i64 [[OFFSET_IDX]], 3
; CHECK-NEXT: [[BROADCAST_SPLATINSERT23:%.*]] = insertelement <4 x i64> undef, i64 [[INDEX14]], i32 0
; CHECK-NEXT: [[BROADCAST_SPLAT24:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT23]], <4 x i64> undef, <4 x i32> zeroinitializer
; CHECK-NEXT: [[VEC_IV:%.*]] = or <4 x i64> [[BROADCAST_SPLAT24]], <i64 0, i64 1, i64 2, i64 3>
; CHECK-NEXT: [[TMP23:%.*]] = icmp ule <4 x i64> [[VEC_IV]], [[BROADCAST_SPLAT21]]
; CHECK-NEXT: [[TMP24:%.*]] = extractelement <4 x i1> [[TMP23]], i32 0
; CHECK-NEXT: br i1 [[TMP24]], label [[PRED_LOAD_IF:%.*]], label [[PRED_LOAD_CONTINUE:%.*]]
; CHECK: pred.load.if:
; CHECK-NEXT: [[TMP25:%.*]] = getelementptr inbounds [2048 x i32], [2048 x i32]* @b, i64 0, i64 [[OFFSET_IDX]]
; CHECK-NEXT: [[TMP26:%.*]] = load i32, i32* [[TMP25]], align 4
; CHECK-NEXT: [[TMP27:%.*]] = insertelement <4 x i32> undef, i32 [[TMP26]], i32 0
; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE]]
; CHECK: pred.load.continue:
; CHECK-NEXT: [[TMP28:%.*]] = phi <4 x i32> [ undef, [[VECTOR_BODY9]] ], [ [[TMP27]], [[PRED_LOAD_IF]] ]
; CHECK-NEXT: [[TMP29:%.*]] = extractelement <4 x i1> [[TMP23]], i32 1
; CHECK-NEXT: br i1 [[TMP29]], label [[PRED_LOAD_IF25:%.*]], label [[PRED_LOAD_CONTINUE26:%.*]]
; CHECK: pred.load.if25:
; CHECK-NEXT: [[TMP30:%.*]] = getelementptr inbounds [2048 x i32], [2048 x i32]* @b, i64 0, i64 [[TMP20]]
; CHECK-NEXT: [[TMP31:%.*]] = load i32, i32* [[TMP30]], align 4
; CHECK-NEXT: [[TMP32:%.*]] = insertelement <4 x i32> [[TMP28]], i32 [[TMP31]], i32 1
; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE26]]
; CHECK: pred.load.continue26:
; CHECK-NEXT: [[TMP33:%.*]] = phi <4 x i32> [ [[TMP28]], [[PRED_LOAD_CONTINUE]] ], [ [[TMP32]], [[PRED_LOAD_IF25]] ]
; CHECK-NEXT: [[TMP34:%.*]] = extractelement <4 x i1> [[TMP23]], i32 2
; CHECK-NEXT: br i1 [[TMP34]], label [[PRED_LOAD_IF27:%.*]], label [[PRED_LOAD_CONTINUE28:%.*]]
; CHECK: pred.load.if27:
; CHECK-NEXT: [[TMP35:%.*]] = getelementptr inbounds [2048 x i32], [2048 x i32]* @b, i64 0, i64 [[TMP21]]
; CHECK-NEXT: [[TMP36:%.*]] = load i32, i32* [[TMP35]], align 4
; CHECK-NEXT: [[TMP37:%.*]] = insertelement <4 x i32> [[TMP33]], i32 [[TMP36]], i32 2
; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE28]]
; CHECK: pred.load.continue28:
; CHECK-NEXT: [[TMP38:%.*]] = phi <4 x i32> [ [[TMP33]], [[PRED_LOAD_CONTINUE26]] ], [ [[TMP37]], [[PRED_LOAD_IF27]] ]
; CHECK-NEXT: [[TMP39:%.*]] = extractelement <4 x i1> [[TMP23]], i32 3
; CHECK-NEXT: br i1 [[TMP39]], label [[PRED_LOAD_IF29:%.*]], label [[PRED_LOAD_CONTINUE30:%.*]]
; CHECK: pred.load.if29:
; CHECK-NEXT: [[TMP40:%.*]] = getelementptr inbounds [2048 x i32], [2048 x i32]* @b, i64 0, i64 [[TMP22]]
; CHECK-NEXT: [[TMP41:%.*]] = load i32, i32* [[TMP40]], align 4
; CHECK-NEXT: [[TMP42:%.*]] = insertelement <4 x i32> [[TMP38]], i32 [[TMP41]], i32 3
; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE30]]
; CHECK: pred.load.continue30:
; CHECK-NEXT: [[TMP43:%.*]] = phi <4 x i32> [ [[TMP38]], [[PRED_LOAD_CONTINUE28]] ], [ [[TMP42]], [[PRED_LOAD_IF29]] ]
; CHECK-NEXT: [[TMP44:%.*]] = extractelement <4 x i1> [[TMP23]], i32 0
; CHECK-NEXT: br i1 [[TMP44]], label [[PRED_LOAD_IF31:%.*]], label [[PRED_LOAD_CONTINUE32:%.*]]
; CHECK: pred.load.if31:
; CHECK-NEXT: [[TMP45:%.*]] = getelementptr inbounds [2048 x i32], [2048 x i32]* @c, i64 0, i64 [[OFFSET_IDX]]
; CHECK-NEXT: [[TMP46:%.*]] = load i32, i32* [[TMP45]], align 4
; CHECK-NEXT: [[TMP47:%.*]] = insertelement <4 x i32> undef, i32 [[TMP46]], i32 0
; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE32]]
; CHECK: pred.load.continue32:
; CHECK-NEXT: [[TMP48:%.*]] = phi <4 x i32> [ undef, [[PRED_LOAD_CONTINUE30]] ], [ [[TMP47]], [[PRED_LOAD_IF31]] ]
; CHECK-NEXT: [[TMP49:%.*]] = extractelement <4 x i1> [[TMP23]], i32 1
; CHECK-NEXT: br i1 [[TMP49]], label [[PRED_LOAD_IF33:%.*]], label [[PRED_LOAD_CONTINUE34:%.*]]
; CHECK: pred.load.if33:
; CHECK-NEXT: [[TMP50:%.*]] = getelementptr inbounds [2048 x i32], [2048 x i32]* @c, i64 0, i64 [[TMP20]]
; CHECK-NEXT: [[TMP51:%.*]] = load i32, i32* [[TMP50]], align 4
; CHECK-NEXT: [[TMP52:%.*]] = insertelement <4 x i32> [[TMP48]], i32 [[TMP51]], i32 1
; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE34]]
; CHECK: pred.load.continue34:
; CHECK-NEXT: [[TMP53:%.*]] = phi <4 x i32> [ [[TMP48]], [[PRED_LOAD_CONTINUE32]] ], [ [[TMP52]], [[PRED_LOAD_IF33]] ]
; CHECK-NEXT: [[TMP54:%.*]] = extractelement <4 x i1> [[TMP23]], i32 2
; CHECK-NEXT: br i1 [[TMP54]], label [[PRED_LOAD_IF35:%.*]], label [[PRED_LOAD_CONTINUE36:%.*]]
; CHECK: pred.load.if35:
; CHECK-NEXT: [[TMP55:%.*]] = getelementptr inbounds [2048 x i32], [2048 x i32]* @c, i64 0, i64 [[TMP21]]
; CHECK-NEXT: [[TMP56:%.*]] = load i32, i32* [[TMP55]], align 4
; CHECK-NEXT: [[TMP57:%.*]] = insertelement <4 x i32> [[TMP53]], i32 [[TMP56]], i32 2
; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE36]]
; CHECK: pred.load.continue36:
; CHECK-NEXT: [[TMP58:%.*]] = phi <4 x i32> [ [[TMP53]], [[PRED_LOAD_CONTINUE34]] ], [ [[TMP57]], [[PRED_LOAD_IF35]] ]
; CHECK-NEXT: [[TMP59:%.*]] = extractelement <4 x i1> [[TMP23]], i32 3
; CHECK-NEXT: br i1 [[TMP59]], label [[PRED_LOAD_IF37:%.*]], label [[PRED_LOAD_CONTINUE38:%.*]]
; CHECK: pred.load.if37:
; CHECK-NEXT: [[TMP60:%.*]] = getelementptr inbounds [2048 x i32], [2048 x i32]* @c, i64 0, i64 [[TMP22]]
; CHECK-NEXT: [[TMP61:%.*]] = load i32, i32* [[TMP60]], align 4
; CHECK-NEXT: [[TMP62:%.*]] = insertelement <4 x i32> [[TMP58]], i32 [[TMP61]], i32 3
; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE38]]
; CHECK: pred.load.continue38:
; CHECK-NEXT: [[TMP63:%.*]] = phi <4 x i32> [ [[TMP58]], [[PRED_LOAD_CONTINUE36]] ], [ [[TMP62]], [[PRED_LOAD_IF37]] ]
; CHECK-NEXT: [[TMP64:%.*]] = and <4 x i32> [[TMP63]], [[TMP43]]
; CHECK-NEXT: [[TMP65:%.*]] = extractelement <4 x i1> [[TMP23]], i32 0
; CHECK-NEXT: br i1 [[TMP65]], label [[PRED_STORE_IF39:%.*]], label [[PRED_STORE_CONTINUE40:%.*]]
; CHECK: pred.store.if39:
; CHECK-NEXT: [[TMP66:%.*]] = getelementptr inbounds [2048 x i32], [2048 x i32]* @a, i64 0, i64 [[OFFSET_IDX]]
; CHECK-NEXT: [[TMP67:%.*]] = extractelement <4 x i32> [[TMP64]], i32 0
; CHECK-NEXT: store i32 [[TMP67]], i32* [[TMP66]], align 4
; CHECK-NEXT: br label [[PRED_STORE_CONTINUE40]]
; CHECK: pred.store.continue40:
; CHECK-NEXT: [[TMP68:%.*]] = extractelement <4 x i1> [[TMP23]], i32 1
; CHECK-NEXT: br i1 [[TMP68]], label [[PRED_STORE_IF41:%.*]], label [[PRED_STORE_CONTINUE42:%.*]]
; CHECK: pred.store.if41:
; CHECK-NEXT: [[TMP69:%.*]] = getelementptr inbounds [2048 x i32], [2048 x i32]* @a, i64 0, i64 [[TMP20]]
; CHECK-NEXT: [[TMP70:%.*]] = extractelement <4 x i32> [[TMP64]], i32 1
; CHECK-NEXT: store i32 [[TMP70]], i32* [[TMP69]], align 4
; CHECK-NEXT: br label [[PRED_STORE_CONTINUE42]]
; CHECK: pred.store.continue42:
; CHECK-NEXT: [[TMP71:%.*]] = extractelement <4 x i1> [[TMP23]], i32 2
; CHECK-NEXT: br i1 [[TMP71]], label [[PRED_STORE_IF43:%.*]], label [[PRED_STORE_CONTINUE44:%.*]]
; CHECK: pred.store.if43:
; CHECK-NEXT: [[TMP72:%.*]] = getelementptr inbounds [2048 x i32], [2048 x i32]* @a, i64 0, i64 [[TMP21]]
; CHECK-NEXT: [[TMP73:%.*]] = extractelement <4 x i32> [[TMP64]], i32 2
; CHECK-NEXT: store i32 [[TMP73]], i32* [[TMP72]], align 4
; CHECK-NEXT: br label [[PRED_STORE_CONTINUE44]]
; CHECK: pred.store.continue44:
; CHECK-NEXT: [[TMP74:%.*]] = extractelement <4 x i1> [[TMP23]], i32 3
; CHECK-NEXT: br i1 [[TMP74]], label [[PRED_STORE_IF45:%.*]], label [[PRED_STORE_CONTINUE46]]
; CHECK: pred.store.if45:
; CHECK-NEXT: [[TMP75:%.*]] = getelementptr inbounds [2048 x i32], [2048 x i32]* @a, i64 0, i64 [[TMP22]]
; CHECK-NEXT: [[TMP76:%.*]] = extractelement <4 x i32> [[TMP64]], i32 3
; CHECK-NEXT: store i32 [[TMP76]], i32* [[TMP75]], align 4
; CHECK-NEXT: br label [[PRED_STORE_CONTINUE46]]
; CHECK: pred.store.continue46:
; CHECK-NEXT: [[INDEX_NEXT15]] = add i64 [[INDEX14]], 4
; CHECK-NEXT: [[TMP77:%.*]] = icmp eq i64 [[INDEX_NEXT15]], [[N_VEC13]]
; CHECK-NEXT: br i1 [[TMP77]], label [[MIDDLE_BLOCK7:%.*]], label [[VECTOR_BODY9]], !llvm.loop !5
; CHECK: middle.block7:
; CHECK-NEXT: br i1 true, label [[DOT_CRIT_EDGE_LOOPEXIT:%.*]], label [[SCALAR_PH8]]
; CHECK: scalar.ph8:
; CHECK-NEXT: br label [[DOTLR_PH:%.*]]
; CHECK: .lr.ph5:
; CHECK-NEXT: br i1 undef, label [[DOT_PREHEADER_CRIT_EDGE]], label [[DOTLR_PH5]], !llvm.loop !6
; CHECK: .lr.ph:
; CHECK-NEXT: br i1 undef, label [[DOT_CRIT_EDGE_LOOPEXIT]], label [[DOTLR_PH]], !llvm.loop !7
; CHECK: ._crit_edge.loopexit:
; CHECK-NEXT: br label [[DOT_CRIT_EDGE]]
; CHECK: ._crit_edge:
; CHECK-NEXT: ret void
;
@ -318,106 +170,18 @@ define void @example2(i32 %n, i32 %x) optsize {
; Loop has no primary induction as its integer IV has step -1 starting at
; unknown N, but can still be vectorized.
define void @example3(i32 %n, i32* noalias nocapture %p, i32* noalias nocapture %q) optsize {
; CHECK-LABEL: @example3(
; CHECK-NEXT: [[TMP1:%.*]] = icmp eq i32 [[N:%.*]], 0
; CHECK-NEXT: br i1 [[TMP1]], label [[DOT_CRIT_EDGE:%.*]], label [[DOTLR_PH_PREHEADER:%.*]]
; CHECK: .lr.ph.preheader:
; CHECK-NEXT: [[TMP2:%.*]] = add i32 [[N]], -1
; CHECK-NEXT: [[TMP3:%.*]] = zext i32 [[TMP2]] to i64
; CHECK-NEXT: br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
;CHECK-LABEL: @example3(
; CHECK: vector.ph:
; CHECK-NEXT: [[N_RND_UP:%.*]] = add nuw nsw i64 [[TMP3]], 4
; CHECK-NEXT: [[N_VEC:%.*]] = and i64 [[N_RND_UP]], 8589934588
; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i64> undef, i64 [[TMP3]], i32 0
; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT]], <4 x i64> undef, <4 x i32> zeroinitializer
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: [[BROADCAST_SPLAT2:%.*]] = shufflevector <4 x i64> {{.*}}, <4 x i64> undef, <4 x i32> zeroinitializer
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[PRED_STORE_CONTINUE25:%.*]] ]
; CHECK-NEXT: [[BROADCAST_SPLATINSERT12:%.*]] = insertelement <4 x i64> undef, i64 [[INDEX]], i32 0
; CHECK-NEXT: [[BROADCAST_SPLAT13:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT12]], <4 x i64> undef, <4 x i32> zeroinitializer
; CHECK-NEXT: [[VEC_IV:%.*]] = or <4 x i64> [[BROADCAST_SPLAT13]], <i64 0, i64 1, i64 2, i64 3>
; CHECK-NEXT: [[TMP4:%.*]] = icmp ule <4 x i64> [[VEC_IV]], [[BROADCAST_SPLAT]]
; CHECK-NEXT: [[TMP5:%.*]] = extractelement <4 x i1> [[TMP4]], i32 0
; CHECK-NEXT: br i1 [[TMP5]], label [[PRED_LOAD_IF:%.*]], label [[PRED_LOAD_CONTINUE:%.*]]
; CHECK: pred.load.if:
; CHECK-NEXT: [[NEXT_GEP8:%.*]] = getelementptr i32, i32* [[Q:%.*]], i64 [[INDEX]]
; CHECK-NEXT: [[TMP6:%.*]] = load i32, i32* [[NEXT_GEP8]], align 16
; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE]]
; CHECK: pred.load.continue:
; CHECK-NEXT: [[TMP7:%.*]] = phi i32 [ undef, [[VECTOR_BODY]] ], [ [[TMP6]], [[PRED_LOAD_IF]] ]
; CHECK-NEXT: [[TMP8:%.*]] = extractelement <4 x i1> [[TMP4]], i32 1
; CHECK-NEXT: br i1 [[TMP8]], label [[PRED_LOAD_IF14:%.*]], label [[PRED_LOAD_CONTINUE15:%.*]]
; CHECK: pred.load.if14:
; CHECK-NEXT: [[TMP9:%.*]] = or i64 [[INDEX]], 1
; CHECK-NEXT: [[NEXT_GEP9:%.*]] = getelementptr i32, i32* [[Q]], i64 [[TMP9]]
; CHECK-NEXT: [[TMP10:%.*]] = load i32, i32* [[NEXT_GEP9]], align 16
; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE15]]
; CHECK: pred.load.continue15:
; CHECK-NEXT: [[TMP11:%.*]] = phi i32 [ undef, [[PRED_LOAD_CONTINUE]] ], [ [[TMP10]], [[PRED_LOAD_IF14]] ]
; CHECK-NEXT: [[TMP12:%.*]] = extractelement <4 x i1> [[TMP4]], i32 2
; CHECK-NEXT: br i1 [[TMP12]], label [[PRED_LOAD_IF16:%.*]], label [[PRED_LOAD_CONTINUE17:%.*]]
; CHECK: pred.load.if16:
; CHECK-NEXT: [[TMP13:%.*]] = or i64 [[INDEX]], 2
; CHECK-NEXT: [[NEXT_GEP10:%.*]] = getelementptr i32, i32* [[Q]], i64 [[TMP13]]
; CHECK-NEXT: [[TMP14:%.*]] = load i32, i32* [[NEXT_GEP10]], align 16
; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE17]]
; CHECK: pred.load.continue17:
; CHECK-NEXT: [[TMP15:%.*]] = phi i32 [ undef, [[PRED_LOAD_CONTINUE15]] ], [ [[TMP14]], [[PRED_LOAD_IF16]] ]
; CHECK-NEXT: [[TMP16:%.*]] = extractelement <4 x i1> [[TMP4]], i32 3
; CHECK-NEXT: br i1 [[TMP16]], label [[PRED_LOAD_IF18:%.*]], label [[PRED_LOAD_CONTINUE19:%.*]]
; CHECK: pred.load.if18:
; CHECK-NEXT: [[TMP17:%.*]] = or i64 [[INDEX]], 3
; CHECK-NEXT: [[NEXT_GEP11:%.*]] = getelementptr i32, i32* [[Q]], i64 [[TMP17]]
; CHECK-NEXT: [[TMP18:%.*]] = load i32, i32* [[NEXT_GEP11]], align 16
; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE19]]
; CHECK: pred.load.continue19:
; CHECK-NEXT: [[TMP19:%.*]] = phi i32 [ undef, [[PRED_LOAD_CONTINUE17]] ], [ [[TMP18]], [[PRED_LOAD_IF18]] ]
; CHECK-NEXT: [[TMP20:%.*]] = extractelement <4 x i1> [[TMP4]], i32 0
; CHECK-NEXT: br i1 [[TMP20]], label [[PRED_STORE_IF:%.*]], label [[PRED_STORE_CONTINUE:%.*]]
; CHECK: pred.store.if:
; CHECK-NEXT: [[NEXT_GEP:%.*]] = getelementptr i32, i32* [[P:%.*]], i64 [[INDEX]]
; CHECK-NEXT: store i32 [[TMP7]], i32* [[NEXT_GEP]], align 16
; CHECK-NEXT: br label [[PRED_STORE_CONTINUE]]
; CHECK: pred.store.continue:
; CHECK-NEXT: [[TMP21:%.*]] = extractelement <4 x i1> [[TMP4]], i32 1
; CHECK-NEXT: br i1 [[TMP21]], label [[PRED_STORE_IF20:%.*]], label [[PRED_STORE_CONTINUE21:%.*]]
; CHECK: pred.store.if20:
; CHECK-NEXT: [[TMP22:%.*]] = or i64 [[INDEX]], 1
; CHECK-NEXT: [[NEXT_GEP5:%.*]] = getelementptr i32, i32* [[P]], i64 [[TMP22]]
; CHECK-NEXT: store i32 [[TMP11]], i32* [[NEXT_GEP5]], align 16
; CHECK-NEXT: br label [[PRED_STORE_CONTINUE21]]
; CHECK: pred.store.continue21:
; CHECK-NEXT: [[TMP23:%.*]] = extractelement <4 x i1> [[TMP4]], i32 2
; CHECK-NEXT: br i1 [[TMP23]], label [[PRED_STORE_IF22:%.*]], label [[PRED_STORE_CONTINUE23:%.*]]
; CHECK: pred.store.if22:
; CHECK-NEXT: [[TMP24:%.*]] = or i64 [[INDEX]], 2
; CHECK-NEXT: [[NEXT_GEP6:%.*]] = getelementptr i32, i32* [[P]], i64 [[TMP24]]
; CHECK-NEXT: store i32 [[TMP15]], i32* [[NEXT_GEP6]], align 16
; CHECK-NEXT: br label [[PRED_STORE_CONTINUE23]]
; CHECK: pred.store.continue23:
; CHECK-NEXT: [[TMP25:%.*]] = extractelement <4 x i1> [[TMP4]], i32 3
; CHECK-NEXT: br i1 [[TMP25]], label [[PRED_STORE_IF24:%.*]], label [[PRED_STORE_CONTINUE25]]
; CHECK: pred.store.if24:
; CHECK-NEXT: [[TMP26:%.*]] = or i64 [[INDEX]], 3
; CHECK-NEXT: [[NEXT_GEP7:%.*]] = getelementptr i32, i32* [[P]], i64 [[TMP26]]
; CHECK-NEXT: store i32 [[TMP19]], i32* [[NEXT_GEP7]], align 16
; CHECK-NEXT: br label [[PRED_STORE_CONTINUE25]]
; CHECK: pred.store.continue25:
; CHECK-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], 4
; CHECK-NEXT: [[TMP27:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT: br i1 [[TMP27]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !8
; CHECK: middle.block:
; CHECK-NEXT: br i1 true, label [[DOT_CRIT_EDGE_LOOPEXIT:%.*]], label [[SCALAR_PH]]
; CHECK: scalar.ph:
; CHECK-NEXT: br label [[DOTLR_PH:%.*]]
; CHECK: .lr.ph:
; CHECK-NEXT: br i1 undef, label [[DOT_CRIT_EDGE_LOOPEXIT]], label [[DOTLR_PH]], !llvm.loop !9
; CHECK: ._crit_edge.loopexit:
; CHECK-NEXT: br label [[DOT_CRIT_EDGE]]
; CHECK: ._crit_edge:
; CHECK-NEXT: ret void
;
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0,
; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i64> undef, i64 [[INDEX]], i32 0
; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT]], <4 x i64> undef, <4 x i32> zeroinitializer
; CHECK-NEXT: [[VPIV:%.*]] = or <4 x i64> [[BROADCAST_SPLAT]], <i64 0, i64 1, i64 2, i64 3>
; CHECK: {{.*}} = icmp ule <4 x i64> [[VPIV]], [[BROADCAST_SPLAT2]]
;CHECK-NOT: <4 x i32>
;CHECK: ret void
define void @example3(i32 %n, i32* noalias nocapture %p, i32* noalias nocapture %q) optsize {
%1 = icmp eq i32 %n, 0
br i1 %1, label %._crit_edge, label %.lr.ph
@ -438,25 +202,10 @@ define void @example3(i32 %n, i32* noalias nocapture %p, i32* noalias nocapture
}
; We can't vectorize this one because we need a runtime ptr check.
;CHECK-LABEL: @example23(
;CHECK-NOT: <4 x i32>
;CHECK: ret void
define void @example23(i16* nocapture %src, i32* nocapture %dst) optsize {
; CHECK-LABEL: @example23(
; CHECK-NEXT: br label [[TMP1:%.*]]
; CHECK: 1:
; CHECK-NEXT: [[DOT04:%.*]] = phi i16* [ [[SRC:%.*]], [[TMP0:%.*]] ], [ [[TMP2:%.*]], [[TMP1]] ]
; CHECK-NEXT: [[DOT013:%.*]] = phi i32* [ [[DST:%.*]], [[TMP0]] ], [ [[TMP6:%.*]], [[TMP1]] ]
; CHECK-NEXT: [[I_02:%.*]] = phi i32 [ 0, [[TMP0]] ], [ [[TMP7:%.*]], [[TMP1]] ]
; CHECK-NEXT: [[TMP2]] = getelementptr inbounds i16, i16* [[DOT04]], i64 1
; CHECK-NEXT: [[TMP3:%.*]] = load i16, i16* [[DOT04]], align 2
; CHECK-NEXT: [[TMP4:%.*]] = zext i16 [[TMP3]] to i32
; CHECK-NEXT: [[TMP5:%.*]] = shl nuw nsw i32 [[TMP4]], 7
; CHECK-NEXT: [[TMP6]] = getelementptr inbounds i32, i32* [[DOT013]], i64 1
; CHECK-NEXT: store i32 [[TMP5]], i32* [[DOT013]], align 4
; CHECK-NEXT: [[TMP7]] = add nuw nsw i32 [[I_02]], 1
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i32 [[TMP7]], 256
; CHECK-NEXT: br i1 [[EXITCOND]], label [[TMP8:%.*]], label [[TMP1]]
; CHECK: 8:
; CHECK-NEXT: ret void
;
br label %1
; <label>:1 ; preds = %1, %0
@ -501,10 +250,8 @@ define void @example23b(i16* noalias nocapture %src, i32* noalias nocapture %dst
; CHECK-NEXT: br i1 true, label [[TMP7:%.*]], label [[SCALAR_PH]]
; CHECK: scalar.ph:
; CHECK-NEXT: br label [[TMP6:%.*]]
; CHECK: 6:
; CHECK-NEXT: br i1 undef, label [[TMP7]], label [[TMP6]], !llvm.loop !11
; CHECK: 7:
; CHECK-NEXT: ret void
; CHECK: br i1 undef, label [[TMP7]], label [[TMP6]], !llvm.loop !11
; CHECK: ret void
;
br label %1
@ -535,7 +282,9 @@ define void @example23c(i16* noalias nocapture %src, i32* noalias nocapture %dst
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[PRED_STORE_CONTINUE22:%.*]] ]
; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i64> undef, i64 [[INDEX]], i32 0
; CHECK-NEXT: [[TMP1:%.*]] = icmp ult <4 x i64> [[BROADCAST_SPLATINSERT]], <i64 257, i64 257, i64 257, i64 257>
; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT]], <4 x i64> undef, <4 x i32> zeroinitializer
; CHECK-NEXT: [[INDUCTION:%.*]] = or <4 x i64> [[BROADCAST_SPLAT]], <i64 0, i64 1, i64 2, i64 3>
; CHECK-NEXT: [[TMP1:%.*]] = icmp ult <4 x i64> [[INDUCTION]], <i64 257, i64 257, i64 257, i64 257>
; CHECK-NEXT: [[TMP2:%.*]] = extractelement <4 x i1> [[TMP1]], i32 0
; CHECK-NEXT: br i1 [[TMP2]], label [[PRED_LOAD_IF:%.*]], label [[PRED_LOAD_CONTINUE:%.*]]
; CHECK: pred.load.if:
@ -544,7 +293,7 @@ define void @example23c(i16* noalias nocapture %src, i32* noalias nocapture %dst
; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE]]
; CHECK: pred.load.continue:
; CHECK-NEXT: [[TMP4:%.*]] = phi i16 [ undef, [[VECTOR_BODY]] ], [ [[TMP3]], [[PRED_LOAD_IF]] ]
; CHECK-NEXT: [[TMP5:%.*]] = extractelement <4 x i1> [[TMP1]], i32 0
; CHECK-NEXT: [[TMP5:%.*]] = extractelement <4 x i1> [[TMP1]], i32 1
; CHECK-NEXT: br i1 [[TMP5]], label [[PRED_LOAD_IF11:%.*]], label [[PRED_LOAD_CONTINUE12:%.*]]
; CHECK: pred.load.if11:
; CHECK-NEXT: [[TMP6:%.*]] = or i64 [[INDEX]], 1
@ -553,7 +302,7 @@ define void @example23c(i16* noalias nocapture %src, i32* noalias nocapture %dst
; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE12]]
; CHECK: pred.load.continue12:
; CHECK-NEXT: [[TMP8:%.*]] = phi i16 [ undef, [[PRED_LOAD_CONTINUE]] ], [ [[TMP7]], [[PRED_LOAD_IF11]] ]
; CHECK-NEXT: [[TMP9:%.*]] = extractelement <4 x i1> [[TMP1]], i32 0
; CHECK-NEXT: [[TMP9:%.*]] = extractelement <4 x i1> [[TMP1]], i32 2
; CHECK-NEXT: br i1 [[TMP9]], label [[PRED_LOAD_IF13:%.*]], label [[PRED_LOAD_CONTINUE14:%.*]]
; CHECK: pred.load.if13:
; CHECK-NEXT: [[TMP10:%.*]] = or i64 [[INDEX]], 2
@ -562,7 +311,7 @@ define void @example23c(i16* noalias nocapture %src, i32* noalias nocapture %dst
; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE14]]
; CHECK: pred.load.continue14:
; CHECK-NEXT: [[TMP12:%.*]] = phi i16 [ undef, [[PRED_LOAD_CONTINUE12]] ], [ [[TMP11]], [[PRED_LOAD_IF13]] ]
; CHECK-NEXT: [[TMP13:%.*]] = extractelement <4 x i1> [[TMP1]], i32 0
; CHECK-NEXT: [[TMP13:%.*]] = extractelement <4 x i1> [[TMP1]], i32 3
; CHECK-NEXT: br i1 [[TMP13]], label [[PRED_LOAD_IF15:%.*]], label [[PRED_LOAD_CONTINUE16:%.*]]
; CHECK: pred.load.if15:
; CHECK-NEXT: [[TMP14:%.*]] = or i64 [[INDEX]], 3
@ -580,7 +329,7 @@ define void @example23c(i16* noalias nocapture %src, i32* noalias nocapture %dst
; CHECK-NEXT: store i32 [[TMP19]], i32* [[NEXT_GEP7]], align 4
; CHECK-NEXT: br label [[PRED_STORE_CONTINUE]]
; CHECK: pred.store.continue:
; CHECK-NEXT: [[TMP20:%.*]] = extractelement <4 x i1> [[TMP1]], i32 0
; CHECK-NEXT: [[TMP20:%.*]] = extractelement <4 x i1> [[TMP1]], i32 1
; CHECK-NEXT: br i1 [[TMP20]], label [[PRED_STORE_IF17:%.*]], label [[PRED_STORE_CONTINUE18:%.*]]
; CHECK: pred.store.if17:
; CHECK-NEXT: [[TMP21:%.*]] = zext i16 [[TMP8]] to i32
@ -590,7 +339,7 @@ define void @example23c(i16* noalias nocapture %src, i32* noalias nocapture %dst
; CHECK-NEXT: store i32 [[TMP22]], i32* [[NEXT_GEP8]], align 4
; CHECK-NEXT: br label [[PRED_STORE_CONTINUE18]]
; CHECK: pred.store.continue18:
; CHECK-NEXT: [[TMP24:%.*]] = extractelement <4 x i1> [[TMP1]], i32 0
; CHECK-NEXT: [[TMP24:%.*]] = extractelement <4 x i1> [[TMP1]], i32 2
; CHECK-NEXT: br i1 [[TMP24]], label [[PRED_STORE_IF19:%.*]], label [[PRED_STORE_CONTINUE20:%.*]]
; CHECK: pred.store.if19:
; CHECK-NEXT: [[TMP25:%.*]] = zext i16 [[TMP12]] to i32
@ -600,7 +349,7 @@ define void @example23c(i16* noalias nocapture %src, i32* noalias nocapture %dst
; CHECK-NEXT: store i32 [[TMP26]], i32* [[NEXT_GEP9]], align 4
; CHECK-NEXT: br label [[PRED_STORE_CONTINUE20]]
; CHECK: pred.store.continue20:
; CHECK-NEXT: [[TMP28:%.*]] = extractelement <4 x i1> [[TMP1]], i32 0
; CHECK-NEXT: [[TMP28:%.*]] = extractelement <4 x i1> [[TMP1]], i32 3
; CHECK-NEXT: br i1 [[TMP28]], label [[PRED_STORE_IF21:%.*]], label [[PRED_STORE_CONTINUE22]]
; CHECK: pred.store.if21:
; CHECK-NEXT: [[TMP29:%.*]] = zext i16 [[TMP16]] to i32
@ -617,10 +366,8 @@ define void @example23c(i16* noalias nocapture %src, i32* noalias nocapture %dst
; CHECK-NEXT: br i1 true, label [[TMP34:%.*]], label [[SCALAR_PH]]
; CHECK: scalar.ph:
; CHECK-NEXT: br label [[TMP33:%.*]]
; CHECK: 33:
; CHECK-NEXT: br i1 undef, label [[TMP34]], label [[TMP33]], !llvm.loop !13
; CHECK: 34:
; CHECK-NEXT: ret void
; CHECK: br i1 undef, label [[TMP34]], label [[TMP33]], !llvm.loop !13
; CHECK: ret void
;
br label %1
@ -645,24 +392,9 @@ define void @example23c(i16* noalias nocapture %src, i32* noalias nocapture %dst
; We CAN'T vectorize this example because it would entail a tail and an
; induction is used outside the loop.
define i64 @example23d(i16* noalias nocapture %src, i32* noalias nocapture %dst) optsize {
; CHECK-LABEL: @example23d(
; CHECK-NEXT: br label [[TMP1:%.*]]
; CHECK: 1:
; CHECK-NEXT: [[DOT04:%.*]] = phi i16* [ [[SRC:%.*]], [[TMP0:%.*]] ], [ [[TMP2:%.*]], [[TMP1]] ]
; CHECK-NEXT: [[DOT013:%.*]] = phi i32* [ [[DST:%.*]], [[TMP0]] ], [ [[TMP6:%.*]], [[TMP1]] ]
; CHECK-NEXT: [[I_02:%.*]] = phi i64 [ 0, [[TMP0]] ], [ [[TMP7:%.*]], [[TMP1]] ]
; CHECK-NEXT: [[TMP2]] = getelementptr inbounds i16, i16* [[DOT04]], i64 1
; CHECK-NEXT: [[TMP3:%.*]] = load i16, i16* [[DOT04]], align 2
; CHECK-NEXT: [[TMP4:%.*]] = zext i16 [[TMP3]] to i32
; CHECK-NEXT: [[TMP5:%.*]] = shl nuw nsw i32 [[TMP4]], 7
; CHECK-NEXT: [[TMP6]] = getelementptr inbounds i32, i32* [[DOT013]], i64 1
; CHECK-NEXT: store i32 [[TMP5]], i32* [[DOT013]], align 4
; CHECK-NEXT: [[TMP7]] = add nuw nsw i64 [[I_02]], 1
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i64 [[TMP7]], 257
; CHECK-NEXT: br i1 [[EXITCOND]], label [[TMP8:%.*]], label [[TMP1]]
; CHECK: 8:
; CHECK-NEXT: ret i64 [[TMP7]]
;
;CHECK-LABEL: @example23d(
; CHECK-NOT: <4 x
; CHECK: ret i64
br label %1
; <label>:1 ; preds = %1, %0

3
llvm/test/Transforms/LoopVectorize/X86/strided_load_cost.ll
View File

@ -19,6 +19,9 @@ define i32 @matrix_row_col([100 x i32]* nocapture readonly %data, i32 %i, i32 %j
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[VEC_PHI:%.*]] = phi <8 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP37:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <8 x i64> undef, i64 [[INDEX]], i32 0
; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <8 x i64> [[BROADCAST_SPLATINSERT]], <8 x i64> undef, <8 x i32> zeroinitializer
; CHECK-NEXT: [[INDUCTION:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], <i64 0, i64 1, i64 2, i64 3, i64 4, i64 5, i64 6, i64 7>
; CHECK-NEXT: [[TMP0:%.*]] = add i64 [[INDEX]], 0
; CHECK-NEXT: [[TMP1:%.*]] = add i64 [[INDEX]], 1
; CHECK-NEXT: [[TMP2:%.*]] = add i64 [[INDEX]], 2

40
llvm/test/Transforms/LoopVectorize/X86/vect.omp.force.small-tc.ll
View File

@ -24,18 +24,21 @@ define void @vectorized(float* noalias nocapture %A, float* noalias nocapture re
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <8 x i64> undef, i64 [[INDEX]], i32 0
; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <8 x i64> [[BROADCAST_SPLATINSERT]], <8 x i64> undef, <8 x i32> zeroinitializer
; CHECK-NEXT: [[INDUCTION:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], <i64 0, i64 1, i64 2, i64 3, i64 4, i64 5, i64 6, i64 7>
; CHECK-NEXT: [[TMP0:%.*]] = add i64 [[INDEX]], 0
; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds float, float* [[B:%.*]], i64 [[TMP0]]
; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds float, float* [[TMP1]], i32 0
; CHECK-NEXT: [[TMP3:%.*]] = bitcast float* [[TMP2]] to <8 x float>*
; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <8 x float>, <8 x float>* [[TMP3]], align 4, !llvm.access.group !0
; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <8 x float>, <8 x float>* [[TMP3]], align 4
; CHECK-NEXT: [[TMP4:%.*]] = getelementptr inbounds float, float* [[A:%.*]], i64 [[TMP0]]
; CHECK-NEXT: [[TMP5:%.*]] = getelementptr inbounds float, float* [[TMP4]], i32 0
; CHECK-NEXT: [[TMP6:%.*]] = bitcast float* [[TMP5]] to <8 x float>*
; CHECK-NEXT: [[WIDE_LOAD1:%.*]] = load <8 x float>, <8 x float>* [[TMP6]], align 4, !llvm.access.group !0
; CHECK-NEXT: [[WIDE_LOAD1:%.*]] = load <8 x float>, <8 x float>* [[TMP6]], align 4
; CHECK-NEXT: [[TMP7:%.*]] = fadd fast <8 x float> [[WIDE_LOAD]], [[WIDE_LOAD1]]
; CHECK-NEXT: [[TMP8:%.*]] = bitcast float* [[TMP5]] to <8 x float>*
; CHECK-NEXT: store <8 x float> [[TMP7]], <8 x float>* [[TMP8]], align 4, !llvm.access.group !0
; CHECK-NEXT: store <8 x float> [[TMP7]], <8 x float>* [[TMP8]], align 4
; CHECK-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], 8
; CHECK-NEXT: [[TMP9:%.*]] = icmp eq i64 [[INDEX_NEXT]], 16
; CHECK-NEXT: br i1 [[TMP9]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !1
@ -94,11 +97,12 @@ define void @vectorized1(float* noalias nocapture %A, float* noalias nocapture r
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP0:%.*]] = add i64 [[INDEX]], 0
; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <8 x i64> undef, i64 [[TMP0]], i32 0
; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <8 x i64> undef, i64 [[INDEX]], i32 0
; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <8 x i64> [[BROADCAST_SPLATINSERT]], <8 x i64> undef, <8 x i32> zeroinitializer
; CHECK-NEXT: [[INDUCTION:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], <i64 0, i64 1, i64 2, i64 3, i64 4, i64 5, i64 6, i64 7>
; CHECK-NEXT: [[TMP0:%.*]] = add i64 [[INDEX]], 0
; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds float, float* [[B:%.*]], i64 [[TMP0]]
; CHECK-NEXT: [[TMP2:%.*]] = icmp ule <8 x i64> [[BROADCAST_SPLAT]], <i64 19, i64 19, i64 19, i64 19, i64 19, i64 19, i64 19, i64 19>
; CHECK-NEXT: [[TMP2:%.*]] = icmp ule <8 x i64> [[INDUCTION]], <i64 19, i64 19, i64 19, i64 19, i64 19, i64 19, i64 19, i64 19>
; CHECK-NEXT: [[TMP3:%.*]] = getelementptr inbounds float, float* [[TMP1]], i32 0
; CHECK-NEXT: [[TMP4:%.*]] = bitcast float* [[TMP3]] to <8 x float>*
; CHECK-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <8 x float> @llvm.masked.load.v8f32.p0v8f32(<8 x float>* [[TMP4]], i32 4, <8 x i1> [[TMP2]], <8 x float> undef), !llvm.access.group !6
@ -108,26 +112,13 @@ define void @vectorized1(float* noalias nocapture %A, float* noalias nocapture r
; CHECK-NEXT: [[WIDE_MASKED_LOAD1:%.*]] = call <8 x float> @llvm.masked.load.v8f32.p0v8f32(<8 x float>* [[TMP7]], i32 4, <8 x i1> [[TMP2]], <8 x float> undef), !llvm.access.group !6
; CHECK-NEXT: [[TMP8:%.*]] = fadd fast <8 x float> [[WIDE_MASKED_LOAD]], [[WIDE_MASKED_LOAD1]]
; CHECK-NEXT: [[TMP9:%.*]] = bitcast float* [[TMP6]] to <8 x float>*
; CHECK-NEXT: call void @llvm.masked.store.v8f32.p0v8f32(<8 x float> [[TMP8]], <8 x float>* [[TMP9]], i32 4, <8 x i1> [[TMP2]]), !llvm.access.group !6
; CHECK-NEXT: call void @llvm.masked.store.v8f32.p0v8f32(<8 x float> [[TMP8]], <8 x float>* [[TMP9]], i32 4, <8 x i1> [[TMP2]])
; CHECK-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], 8
; CHECK-NEXT: [[TMP10:%.*]] = icmp eq i64 [[INDEX_NEXT]], 24
; CHECK-NEXT: br i1 [[TMP10]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !7
; CHECK: middle.block:
; CHECK-NEXT: br i1 true, label [[FOR_END:%.*]], label [[SCALAR_PH]]
; CHECK: scalar.ph:
; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ 24, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds float, float* [[B]], i64 [[INDVARS_IV]]
; CHECK-NEXT: [[TMP11:%.*]] = load float, float* [[ARRAYIDX]], align 4, !llvm.access.group !6
; CHECK-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds float, float* [[A]], i64 [[INDVARS_IV]]
; CHECK-NEXT: [[TMP12:%.*]] = load float, float* [[ARRAYIDX2]], align 4, !llvm.access.group !6
; CHECK-NEXT: [[ADD:%.*]] = fadd fast float [[TMP11]], [[TMP12]]
; CHECK-NEXT: store float [[ADD]], float* [[ARRAYIDX2]], align 4, !llvm.access.group !6
; CHECK-NEXT: [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], 20
; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_END]], label [[FOR_BODY]], !llvm.loop !9
; CHECK: for.end:
; CHECK-NEXT: ret void
;
@ -165,18 +156,21 @@ define void @vectorized2(float* noalias nocapture %A, float* noalias nocapture r
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <8 x i64> undef, i64 [[INDEX]], i32 0
; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <8 x i64> [[BROADCAST_SPLATINSERT]], <8 x i64> undef, <8 x i32> zeroinitializer
; CHECK-NEXT: [[INDUCTION:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], <i64 0, i64 1, i64 2, i64 3, i64 4, i64 5, i64 6, i64 7>
; CHECK-NEXT: [[TMP0:%.*]] = add i64 [[INDEX]], 0
; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds float, float* [[B:%.*]], i64 [[TMP0]]
; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds float, float* [[TMP1]], i32 0
; CHECK-NEXT: [[TMP3:%.*]] = bitcast float* [[TMP2]] to <8 x float>*
; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <8 x float>, <8 x float>* [[TMP3]], align 4, !llvm.access.group !6
; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <8 x float>, <8 x float>* [[TMP3]], align 4
; CHECK-NEXT: [[TMP4:%.*]] = getelementptr inbounds float, float* [[A:%.*]], i64 [[TMP0]]
; CHECK-NEXT: [[TMP5:%.*]] = getelementptr inbounds float, float* [[TMP4]], i32 0
; CHECK-NEXT: [[TMP6:%.*]] = bitcast float* [[TMP5]] to <8 x float>*
; CHECK-NEXT: [[WIDE_LOAD1:%.*]] = load <8 x float>, <8 x float>* [[TMP6]], align 4, !llvm.access.group !6
; CHECK-NEXT: [[WIDE_LOAD1:%.*]] = load <8 x float>, <8 x float>* [[TMP6]], align 4
; CHECK-NEXT: [[TMP7:%.*]] = fadd fast <8 x float> [[WIDE_LOAD]], [[WIDE_LOAD1]]
; CHECK-NEXT: [[TMP8:%.*]] = bitcast float* [[TMP5]] to <8 x float>*
; CHECK-NEXT: store <8 x float> [[TMP7]], <8 x float>* [[TMP8]], align 4, !llvm.access.group !6
; CHECK-NEXT: store <8 x float> [[TMP7]], <8 x float>* [[TMP8]], align 4
; CHECK-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], 8
; CHECK-NEXT: [[TMP9:%.*]] = icmp eq i64 [[INDEX_NEXT]], 16
; CHECK-NEXT: br i1 [[TMP9]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !10

1934
llvm/test/Transforms/LoopVectorize/X86/x86-interleaved-accesses-masked-group.ll
View File

File diff suppressed because it is too large Load Diff

2
llvm/test/Transforms/LoopVectorize/fcmp-vectorize.ll
View File

@ -6,6 +6,8 @@ define void @test1() {
; CHECK-LABEL: test1(
; CHECK-LABEL: vector.body:
; CHECK-NEXT: %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
; CHECK-NEXT: %broadcast.splatinsert = insertelement <4 x i32> undef, i32 %index, i32 0
; CHECK: %induction = add <4 x i32> %broadcast.splat, <i32 0, i32 1, i32 2, i32 3>
; CHECK: %index.next = add i32 %index, 4
entry:

18
llvm/test/Transforms/LoopVectorize/first-order-recurrence-complex.ll
View File

@ -8,8 +8,8 @@
define void @can_sink_after_store(i32 %x, i32* %ptr, i64 %tc) local_unnamed_addr #0 {
; CHECK-LABEL: vector.ph:
; CHECK: %broadcast.splatinsert = insertelement <4 x i32> undef, i32 %x, i32 0
; CHECK-NEXT: %broadcast.splat = shufflevector <4 x i32> %broadcast.splatinsert, <4 x i32> undef, <4 x i32> zeroinitializer
; CHECK: %broadcast.splatinsert1 = insertelement <4 x i32> undef, i32 %x, i32 0
; CHECK-NEXT: %broadcast.splat2 = shufflevector <4 x i32> %broadcast.splatinsert1, <4 x i32> undef, <4 x i32> zeroinitializer
; CHECK-NEXT: %vector.recur.init = insertelement <4 x i32> undef, i32 %.pre, i32 3
; CHECK-NEXT: br label %vector.body
@ -17,13 +17,16 @@ define void @can_sink_after_store(i32 %x, i32* %ptr, i64 %tc) local_unnamed_addr
; CHECK-NEXT: %index = phi i64 [ 0, %vector.ph ], [ %index.next, %vector.body ]
; CHECK-NEXT: %vector.recur = phi <4 x i32> [ %vector.recur.init, %vector.ph ], [ %wide.load, %vector.body ]
; CHECK-NEXT: %offset.idx = add i64 1, %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: %0 = add i64 %offset.idx, 0
; CHECK-NEXT: %1 = getelementptr inbounds [257 x i32], [257 x i32]* @p, i64 0, i64 %0
; CHECK-NEXT: %2 = getelementptr inbounds i32, i32* %1, i32 0
; CHECK-NEXT: %3 = bitcast i32* %2 to <4 x i32>*
; CHECK-NEXT: %wide.load = load <4 x i32>, <4 x i32>* %3, align 4
; CHECK-NEXT: %4 = shufflevector <4 x i32> %vector.recur, <4 x i32> %wide.load, <4 x i32> <i32 3, i32 4, i32 5, i32 6>
; CHECK-NEXT: %5 = add <4 x i32> %4, %broadcast.splat
; CHECK-NEXT: %5 = add <4 x i32> %4, %broadcast.splat2
; CHECK-NEXT: %6 = add <4 x i32> %5, %wide.load
; CHECK-NEXT: %7 = getelementptr inbounds [257 x i32], [257 x i32]* @q, i64 0, i64 %0
; CHECK-NEXT: %8 = getelementptr inbounds i32, i32* %7, i32 0
@ -62,8 +65,8 @@ exit:
; and not introduce traps on additional paths.
define void @sink_sdiv(i32 %x, i32* %ptr, i64 %tc) local_unnamed_addr #0 {
; CHECK-LABEL: vector.ph:
; CHECK: %broadcast.splatinsert = insertelement <4 x i32> undef, i32 %x, i32 0
; CHECK-NEXT: %broadcast.splat = shufflevector <4 x i32> %broadcast.splatinsert, <4 x i32> undef, <4 x i32> zeroinitializer
; CHECK: %broadcast.splatinsert1 = insertelement <4 x i32> undef, i32 %x, i32 0
; CHECK-NEXT: %broadcast.splat2 = shufflevector <4 x i32> %broadcast.splatinsert1, <4 x i32> undef, <4 x i32> zeroinitializer
; CHECK-NEXT: %vector.recur.init = insertelement <4 x i32> undef, i32 %.pre, i32 3
; CHECK-NEXT: br label %vector.body
@ -71,13 +74,16 @@ define void @sink_sdiv(i32 %x, i32* %ptr, i64 %tc) local_unnamed_addr #0 {
; CHECK-NEXT: %index = phi i64 [ 0, %vector.ph ], [ %index.next, %vector.body ]
; CHECK-NEXT: %vector.recur = phi <4 x i32> [ %vector.recur.init, %vector.ph ], [ %wide.load, %vector.body ]
; CHECK-NEXT: %offset.idx = add i64 1, %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: %0 = add i64 %offset.idx, 0
; CHECK-NEXT: %1 = getelementptr inbounds [257 x i32], [257 x i32]* @p, i64 0, i64 %0
; CHECK-NEXT: %2 = getelementptr inbounds i32, i32* %1, i32 0
; CHECK-NEXT: %3 = bitcast i32* %2 to <4 x i32>*
; CHECK-NEXT: %wide.load = load <4 x i32>, <4 x i32>* %3, align 4
; CHECK-NEXT: %4 = shufflevector <4 x i32> %vector.recur, <4 x i32> %wide.load, <4 x i32> <i32 3, i32 4, i32 5, i32 6>
; CHECK-NEXT: %5 = sdiv <4 x i32> %4, %broadcast.splat
; CHECK-NEXT: %5 = sdiv <4 x i32> %4, %broadcast.splat2
; CHECK-NEXT: %6 = add <4 x i32> %5, %wide.load
; CHECK-NEXT: %7 = getelementptr inbounds [257 x i32], [257 x i32]* @q, i64 0, i64 %0
; CHECK-NEXT: %8 = getelementptr inbounds i32, i32* %7, i32 0

3
llvm/test/Transforms/LoopVectorize/float-minmax-instruction-flag.ll
View File

@ -57,6 +57,9 @@ define float @minloopattr(float* nocapture readonly %arg) #0 {
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[VEC_PHI:%.*]] = phi <4 x float> [ [[MINMAX_IDENT_SPLAT]], [[VECTOR_PH]] ], [ [[TMP6:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[OFFSET_IDX:%.*]] = add i64 1, [[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: [[TMP0:%.*]] = add i64 [[OFFSET_IDX]], 0
; CHECK-NEXT: [[TMP1:%.*]] = getelementptr float, float* [[ARG]], i64 [[TMP0]]
; CHECK-NEXT: [[TMP2:%.*]] = getelementptr float, float* [[TMP1]], i32 0

27
llvm/test/Transforms/LoopVectorize/if-pred-stores.ll
View File

@ -113,6 +113,9 @@ define i32 @test(i32* nocapture %f) #0 {
; VEC-NEXT: br label [[VECTOR_BODY:%.*]]
; VEC: vector.body:
; VEC-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INDEX_NEXT:%.*]], [[PRED_STORE_CONTINUE2:%.*]] ]
; VEC-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <2 x i64> undef, i64 [[INDEX]], i32 0
; VEC-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <2 x i64> [[BROADCAST_SPLATINSERT]], <2 x i64> undef, <2 x i32> zeroinitializer
; VEC-NEXT: [[INDUCTION:%.*]] = add <2 x i64> [[BROADCAST_SPLAT]], <i64 0, i64 1>
; VEC-NEXT: [[TMP0:%.*]] = add i64 [[INDEX]], 0
; VEC-NEXT: [[TMP1:%.*]] = getelementptr inbounds i32, i32* [[F:%.*]], i64 [[TMP0]]
; VEC-NEXT: [[TMP2:%.*]] = getelementptr inbounds i32, i32* [[TMP1]], i32 0
@ -455,19 +458,25 @@ define void @minimal_bit_widths(i1 %c) {
;
; VEC-LABEL: @minimal_bit_widths(
; VEC-NEXT: entry:
; VEC-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <2 x i1> undef, i1 [[C:%.*]], i32 0
; VEC-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <2 x i1> [[BROADCAST_SPLATINSERT]], <2 x i1> undef, <2 x i32> zeroinitializer
; VEC-NEXT: [[BROADCAST_SPLATINSERT5:%.*]] = insertelement <2 x i1> undef, i1 [[C:%.*]], i32 0
; VEC-NEXT: [[BROADCAST_SPLAT6:%.*]] = shufflevector <2 x i1> [[BROADCAST_SPLATINSERT5]], <2 x i1> undef, <2 x i32> zeroinitializer
; VEC-NEXT: br label [[VECTOR_BODY:%.*]]
; VEC: vector.body:
; VEC-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INDEX_NEXT:%.*]], [[PRED_STORE_CONTINUE3:%.*]] ]
; VEC-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INDEX_NEXT:%.*]], [[PRED_STORE_CONTINUE8:%.*]] ]
; VEC-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <2 x i64> undef, i64 [[INDEX]], i32 0
; VEC-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <2 x i64> [[BROADCAST_SPLATINSERT]], <2 x i64> undef, <2 x i32> zeroinitializer
; VEC-NEXT: [[INDUCTION:%.*]] = add <2 x i64> [[BROADCAST_SPLAT]], <i64 0, i64 1>
; VEC-NEXT: [[TMP0:%.*]] = add i64 [[INDEX]], 0
; VEC-NEXT: [[OFFSET_IDX:%.*]] = sub i64 undef, [[INDEX]]
; VEC-NEXT: [[BROADCAST_SPLATINSERT2:%.*]] = insertelement <2 x i64> undef, i64 [[OFFSET_IDX]], i32 0
; VEC-NEXT: [[BROADCAST_SPLAT3:%.*]] = shufflevector <2 x i64> [[BROADCAST_SPLATINSERT2]], <2 x i64> undef, <2 x i32> zeroinitializer
; VEC-NEXT: [[INDUCTION4:%.*]] = add <2 x i64> [[BROADCAST_SPLAT3]], <i64 0, i64 -1>
; VEC-NEXT: [[TMP1:%.*]] = add i64 [[OFFSET_IDX]], 0
; VEC-NEXT: [[TMP2:%.*]] = getelementptr i8, i8* undef, i64 [[TMP0]]
; VEC-NEXT: [[TMP3:%.*]] = getelementptr i8, i8* [[TMP2]], i32 0
; VEC-NEXT: [[TMP4:%.*]] = bitcast i8* [[TMP3]] to <2 x i8>*
; VEC-NEXT: [[WIDE_LOAD:%.*]] = load <2 x i8>, <2 x i8>* [[TMP4]], align 1
; VEC-NEXT: [[TMP5:%.*]] = extractelement <2 x i1> [[BROADCAST_SPLAT]], i32 0
; VEC-NEXT: [[TMP5:%.*]] = extractelement <2 x i1> [[BROADCAST_SPLAT6]], i32 0
; VEC-NEXT: br i1 [[TMP5]], label [[PRED_STORE_IF:%.*]], label [[PRED_STORE_CONTINUE:%.*]]
; VEC: pred.store.if:
; VEC-NEXT: [[TMP6:%.*]] = extractelement <2 x i8> [[WIDE_LOAD]], i32 0
@ -476,17 +485,17 @@ define void @minimal_bit_widths(i1 %c) {
; VEC-NEXT: store i8 [[TMP8]], i8* [[TMP2]], align 1
; VEC-NEXT: br label [[PRED_STORE_CONTINUE]]
; VEC: pred.store.continue:
; VEC-NEXT: [[TMP9:%.*]] = extractelement <2 x i1> [[BROADCAST_SPLAT]], i32 1
; VEC-NEXT: br i1 [[TMP9]], label [[PRED_STORE_IF2:%.*]], label [[PRED_STORE_CONTINUE3]]
; VEC: pred.store.if2:
; VEC-NEXT: [[TMP9:%.*]] = extractelement <2 x i1> [[BROADCAST_SPLAT6]], i32 1
; VEC-NEXT: br i1 [[TMP9]], label [[PRED_STORE_IF7:%.*]], label [[PRED_STORE_CONTINUE8]]
; VEC: pred.store.if7:
; VEC-NEXT: [[TMP10:%.*]] = extractelement <2 x i8> [[WIDE_LOAD]], i32 1
; VEC-NEXT: [[TMP11:%.*]] = zext i8 [[TMP10]] to i32
; VEC-NEXT: [[TMP12:%.*]] = trunc i32 [[TMP11]] to i8
; VEC-NEXT: [[TMP13:%.*]] = add i64 [[INDEX]], 1
; VEC-NEXT: [[TMP14:%.*]] = getelementptr i8, i8* undef, i64 [[TMP13]]
; VEC-NEXT: store i8 [[TMP12]], i8* [[TMP14]], align 1
; VEC-NEXT: br label [[PRED_STORE_CONTINUE3]]
; VEC: pred.store.continue3:
; VEC-NEXT: br label [[PRED_STORE_CONTINUE8]]
; VEC: pred.store.continue8:
; VEC-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], 2
; VEC-NEXT: [[TMP15:%.*]] = icmp eq i64 [[INDEX_NEXT]], undef
; VEC-NEXT: br i1 [[TMP15]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !4

4
llvm/test/Transforms/LoopVectorize/if-reduction.ll
View File

@ -100,7 +100,7 @@ for.end: ; preds = %for.body, %entry
; }
; CHECK-LABEL: @fcmp_val_fadd_select1(
; CHECK: %[[V1:.*]] = fcmp fast ogt <4 x float> %[[V0:.*]], %broadcast.splat
; CHECK: %[[V1:.*]] = fcmp fast ogt <4 x float> %[[V0:.*]], %broadcast.splat2
; CHECK: %[[V3:.*]] = fadd fast <4 x float> %[[V0]], %[[V2:.*]]
; CHECK: select <4 x i1> %[[V1]], <4 x float> %[[V3]], <4 x float> %[[V2]]
define float @fcmp_val_fadd_select1(float* noalias %x, float %y, i32 %N) nounwind readonly {
@ -143,7 +143,7 @@ for.end: ; preds = %for.body, %entry
; }
; CHECK-LABEL: @fcmp_val_fadd_select2(
; CHECK: %[[V1:.*]] = fcmp fast ogt <4 x double> %[[V0:.*]], %broadcast.splat
; CHECK: %[[V1:.*]] = fcmp fast ogt <4 x double> %[[V0:.*]], %broadcast.splat2
; CHECK: %[[V3:.*]] = fadd fast <4 x double> %[[V0]], %[[V2:.*]]
; CHECK: select <4 x i1> %[[V1]], <4 x double> %[[V3]], <4 x double> %[[V2]]
define double @fcmp_val_fadd_select2(double* noalias %x, double %y, i32 %N) nounwind readonly {

94
llvm/test/Transforms/LoopVectorize/multiple-strides-vectorization.ll
View File

@ -1,4 +1,3 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -loop-vectorize -force-vector-width=4 -S < %s | FileCheck %s
; This is the test case from PR26314.
@ -23,95 +22,16 @@
; }
; }
; CHECK-LABEL: Test
; CHECK: <4 x i64>
; CHECK: <4 x i32>, <4 x i32>
; CHECK: !{!"llvm.loop.isvectorized", i32 1}
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
%struct.s = type { [32 x i32], [32 x i32], [32 x [32 x i32]] }
define void @Test(%struct.s* nocapture %obj, i64 %z) #0 {
; CHECK-LABEL: @Test(
; CHECK-NEXT: [[OBJ4:%.*]] = bitcast %struct.s* [[OBJ:%.*]] to i8*
; CHECK-NEXT: [[SCEVGEP5:%.*]] = getelementptr [[STRUCT_S:%.*]], %struct.s* [[OBJ]], i64 0, i32 0, i64 [[Z:%.*]]
; CHECK-NEXT: [[SCEVGEP56:%.*]] = bitcast i32* [[SCEVGEP5]] to i8*
; CHECK-NEXT: br label [[DOTOUTER_PREHEADER:%.*]]
; CHECK: .outer.preheader:
; CHECK-NEXT: [[I:%.*]] = phi i64 [ 0, [[TMP0:%.*]] ], [ [[I_NEXT:%.*]], [[DOTOUTER:%.*]] ]
; CHECK-NEXT: [[SCEVGEP:%.*]] = getelementptr [[STRUCT_S]], %struct.s* [[OBJ]], i64 0, i32 2, i64 [[I]], i64 0
; CHECK-NEXT: [[SCEVGEP1:%.*]] = bitcast i32* [[SCEVGEP]] to i8*
; CHECK-NEXT: [[SCEVGEP2:%.*]] = getelementptr [[STRUCT_S]], %struct.s* [[OBJ]], i64 0, i32 2, i64 [[I]], i64 [[Z]]
; CHECK-NEXT: [[SCEVGEP23:%.*]] = bitcast i32* [[SCEVGEP2]] to i8*
; CHECK-NEXT: [[SCEVGEP7:%.*]] = getelementptr [[STRUCT_S]], %struct.s* [[OBJ]], i64 0, i32 1, i64 [[I]]
; CHECK-NEXT: [[SCEVGEP78:%.*]] = bitcast i32* [[SCEVGEP7]] to i8*
; CHECK-NEXT: [[UGLYGEP:%.*]] = getelementptr i8, i8* [[SCEVGEP78]], i64 1
; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.s* [[OBJ]], i64 0, i32 1, i64 [[I]]
; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[Z]], 4
; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_MEMCHECK:%.*]]
; CHECK: vector.memcheck:
; CHECK-NEXT: [[BOUND0:%.*]] = icmp ult i8* [[SCEVGEP1]], [[SCEVGEP56]]
; CHECK-NEXT: [[BOUND1:%.*]] = icmp ult i8* [[OBJ4]], [[SCEVGEP23]]
; CHECK-NEXT: [[FOUND_CONFLICT:%.*]] = and i1 [[BOUND0]], [[BOUND1]]
; CHECK-NEXT: [[BC:%.*]] = bitcast i32* [[TMP1]] to i8*
; CHECK-NEXT: [[BOUND09:%.*]] = icmp ult i8* [[SCEVGEP1]], [[UGLYGEP]]
; CHECK-NEXT: [[BOUND110:%.*]] = icmp ult i8* [[BC]], [[SCEVGEP23]]
; CHECK-NEXT: [[FOUND_CONFLICT11:%.*]] = and i1 [[BOUND09]], [[BOUND110]]
; CHECK-NEXT: [[CONFLICT_RDX:%.*]] = or i1 [[FOUND_CONFLICT]], [[FOUND_CONFLICT11]]
; CHECK-NEXT: [[MEMCHECK_CONFLICT:%.*]] = and i1 [[CONFLICT_RDX]], true
; CHECK-NEXT: br i1 [[MEMCHECK_CONFLICT]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[Z]], 4
; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 [[Z]], [[N_MOD_VF]]
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP2:%.*]] = add i64 [[INDEX]], 0
; CHECK-NEXT: [[TMP3:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.s* [[OBJ]], i64 0, i32 0, i64 [[TMP2]]
; CHECK-NEXT: [[TMP4:%.*]] = getelementptr inbounds i32, i32* [[TMP3]], i32 0
; CHECK-NEXT: [[TMP5:%.*]] = bitcast i32* [[TMP4]] to <4 x i32>*
; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <4 x i32>, <4 x i32>* [[TMP5]], align 4, !alias.scope !0
; CHECK-NEXT: [[TMP6:%.*]] = load i32, i32* [[TMP1]], !alias.scope !3
; CHECK-NEXT: [[TMP7:%.*]] = load i32, i32* [[TMP1]], !alias.scope !3
; CHECK-NEXT: [[TMP8:%.*]] = load i32, i32* [[TMP1]], !alias.scope !3
; CHECK-NEXT: [[TMP9:%.*]] = load i32, i32* [[TMP1]], !alias.scope !3
; CHECK-NEXT: [[TMP10:%.*]] = insertelement <4 x i32> undef, i32 [[TMP6]], i32 0
; CHECK-NEXT: [[TMP11:%.*]] = insertelement <4 x i32> [[TMP10]], i32 [[TMP7]], i32 1
; CHECK-NEXT: [[TMP12:%.*]] = insertelement <4 x i32> [[TMP11]], i32 [[TMP8]], i32 2
; CHECK-NEXT: [[TMP13:%.*]] = insertelement <4 x i32> [[TMP12]], i32 [[TMP9]], i32 3
; CHECK-NEXT: [[TMP14:%.*]] = add nsw <4 x i32> [[TMP13]], [[WIDE_LOAD]]
; CHECK-NEXT: [[TMP15:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.s* [[OBJ]], i64 0, i32 2, i64 [[I]], i64 [[TMP2]]
; CHECK-NEXT: [[TMP16:%.*]] = getelementptr inbounds i32, i32* [[TMP15]], i32 0
; CHECK-NEXT: [[TMP17:%.*]] = bitcast i32* [[TMP16]] to <4 x i32>*
; CHECK-NEXT: [[WIDE_LOAD12:%.*]] = load <4 x i32>, <4 x i32>* [[TMP17]], align 4, !alias.scope !5, !noalias !7
; CHECK-NEXT: [[TMP18:%.*]] = add nsw <4 x i32> [[TMP14]], [[WIDE_LOAD12]]
; CHECK-NEXT: [[TMP19:%.*]] = bitcast i32* [[TMP16]] to <4 x i32>*
; CHECK-NEXT: store <4 x i32> [[TMP18]], <4 x i32>* [[TMP19]], align 4, !alias.scope !5, !noalias !7
; CHECK-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], 4
; CHECK-NEXT: [[TMP20:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT: br i1 [[TMP20]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !8
; CHECK: middle.block:
; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[Z]], [[N_VEC]]
; CHECK-NEXT: br i1 [[CMP_N]], label [[DOTOUTER]], label [[SCALAR_PH]]
; CHECK: scalar.ph:
; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[DOTOUTER_PREHEADER]] ], [ 0, [[VECTOR_MEMCHECK]] ]
; CHECK-NEXT: br label [[DOTINNER:%.*]]
; CHECK: .exit:
; CHECK-NEXT: ret void
; CHECK: .outer:
; CHECK-NEXT: [[I_NEXT]] = add nuw nsw i64 [[I]], 1
; CHECK-NEXT: [[EXITCOND_OUTER:%.*]] = icmp eq i64 [[I_NEXT]], 32
; CHECK-NEXT: br i1 [[EXITCOND_OUTER]], label [[DOTEXIT:%.*]], label [[DOTOUTER_PREHEADER]]
; CHECK: .inner:
; CHECK-NEXT: [[J:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[J_NEXT:%.*]], [[DOTINNER]] ]
; CHECK-NEXT: [[TMP21:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.s* [[OBJ]], i64 0, i32 0, i64 [[J]]
; CHECK-NEXT: [[TMP22:%.*]] = load i32, i32* [[TMP21]]
; CHECK-NEXT: [[TMP23:%.*]] = load i32, i32* [[TMP1]]
; CHECK-NEXT: [[TMP24:%.*]] = add nsw i32 [[TMP23]], [[TMP22]]
; CHECK-NEXT: [[TMP25:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.s* [[OBJ]], i64 0, i32 2, i64 [[I]], i64 [[J]]
; CHECK-NEXT: [[TMP26:%.*]] = load i32, i32* [[TMP25]]
; CHECK-NEXT: [[TMP27:%.*]] = add nsw i32 [[TMP24]], [[TMP26]]
; CHECK-NEXT: store i32 [[TMP27]], i32* [[TMP25]]
; CHECK-NEXT: [[J_NEXT]] = add nuw nsw i64 [[J]], 1
; CHECK-NEXT: [[EXITCOND_INNER:%.*]] = icmp eq i64 [[J_NEXT]], [[Z]]
; CHECK-NEXT: br i1 [[EXITCOND_INNER]], label [[DOTOUTER]], label [[DOTINNER]], !llvm.loop !10
;
br label %.outer.preheader
@ -122,7 +42,7 @@ define void @Test(%struct.s* nocapture %obj, i64 %z) #0 {
.exit:
ret void
.outer:
%i.next = add nuw nsw i64 %i, 1
%exitcond.outer = icmp eq i64 %i.next, 32
@ -137,7 +57,7 @@ define void @Test(%struct.s* nocapture %obj, i64 %z) #0 {
%6 = getelementptr inbounds %struct.s, %struct.s* %obj, i64 0, i32 2, i64 %i, i64 %j
%7 = load i32, i32* %6
%8 = add nsw i32 %5, %7
store i32 %8, i32* %6
store i32 %8, i32* %6
%j.next = add nuw nsw i64 %j, 1
%exitcond.inner = icmp eq i64 %j.next, %z
br i1 %exitcond.inner, label %.outer, label %.inner

3
llvm/test/Transforms/LoopVectorize/pr35773.ll
View File

@ -31,6 +31,9 @@ for.body:
; CHECK-NEXT: [[I32_IV:%.*]] = phi <4 x i32> [ <i32 0, i32 9, i32 18, i32 27>, [[VECTOR_PH]] ], [ [[I32_IV_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[IV_FROM_TRUNC:%.*]] = phi <4 x i8> [ <i8 0, i8 9, i8 18, i8 27>, [[VECTOR_PH]] ], [ [[IV_FROM_TRUNC_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i32> undef, i32 [[MAIN_IV]], i32 0
; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT]], <4 x i32> undef, <4 x i32> zeroinitializer
; CHECK-NEXT: [[INDUCTION:%.*]] = add <4 x i32> [[BROADCAST_SPLAT]], <i32 0, i32 1, i32 2, i32 3>
; CHECK-NEXT: [[TMP7:%.*]] = add i32 [[MAIN_IV]], 0
; CHECK-NEXT: [[I8_IV_NEXT]] = add <4 x i8> [[I8_IV]], [[IV_FROM_TRUNC]]

3
llvm/test/Transforms/LoopVectorize/pr44488-predication.ll
View File

@ -13,6 +13,9 @@ define i16 @test_true_and_false_branch_equal() {
; CHECK-NEXT: [[INDEX:%.*]] = phi i32 [ 0, %vector.ph ], [ [[INDEX_NEXT:%.*]], [[PRED_SREM_CONTINUE2:%.*]] ]
; CHECK-NEXT: [[TMP0:%.*]] = trunc i32 [[INDEX]] to i16
; CHECK-NEXT: [[OFFSET_IDX:%.*]] = add i16 99, [[TMP0]]
; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <2 x i16> undef, i16 [[OFFSET_IDX]], i32 0
; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <2 x i16> [[BROADCAST_SPLATINSERT]], <2 x i16> undef, <2 x i32> zeroinitializer
; CHECK-NEXT: [[INDUCTION:%.*]] = add <2 x i16> [[BROADCAST_SPLAT]], <i16 0, i16 1>
; CHECK-NEXT: [[TMP1:%.*]] = add i16 [[OFFSET_IDX]], 0
; CHECK-NEXT: [[TMP2:%.*]] = load i16, i16* @v_38, align 1
; CHECK-NEXT: [[TMP3:%.*]] = load i16, i16* @v_38, align 1

3
llvm/test/Transforms/LoopVectorize/vector-intrinsic-call-cost.ll
View File

@ -3,6 +3,9 @@
; CHECK-LABEL: @test_fshl
; CHECK-LABEL: vector.body:
; CHECK-NEXT: %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
; CHECK-NEXT: %broadcast.splatinsert = insertelement <4 x i32> undef, i32 %index, i32 0
; CHECK-NEXT: %broadcast.splat = shufflevector <4 x i32> %broadcast.splatinsert, <4 x i32> undef, <4 x i32> zeroinitializer
; CHECK-NEXT: %induction = add <4 x i32> %broadcast.splat, <i32 0, i32 1, i32 2, i32 3>
; CHECK-NEXT: %0 = add i32 %index, 0
; CHECK-NEXT: %1 = call <4 x i16> @llvm.fshl.v4i16(<4 x i16> undef, <4 x i16> undef, <4 x i16> <i16 15, i16 15, i16 15, i16 15>)
; CHECK-NEXT: %index.next = add i32 %index, 4