From 20d67ffeae80ad0e26ad57b0aebf60a2905fe39a Mon Sep 17 00:00:00 2001 From: Sjoerd Meijer Date: Thu, 7 May 2020 09:29:56 +0100 Subject: [PATCH] Revert "[LV] Induction Variable does not remain scalar under tail-folding." This reverts commit 617aa64c84146468b384453375d1d34f97eb57db. while I investigate buildbot failures. --- .../Transforms/Vectorize/LoopVectorize.cpp | 11 +- .../extractvalue-no-scalarization-required.ll | 6 + .../LoopVectorize/AArch64/pr36032.ll | 6 + .../Transforms/LoopVectorize/ARM/sphinx.ll | 3 + .../LoopVectorize/X86/constant-fold.ll | 22 +- .../X86/imprecise-through-phis.ll | 3 + .../LoopVectorize/X86/load-deref-pred.ll | 686 +++--- .../LoopVectorize/X86/masked_load_store.ll | 597 ++--- .../LoopVectorize/X86/metadata-enable.ll | 486 +++-- .../Transforms/LoopVectorize/X86/optsize.ll | 168 +- .../Transforms/LoopVectorize/X86/pr35432.ll | 20 +- .../Transforms/LoopVectorize/X86/pr36524.ll | 3 + .../LoopVectorize/X86/small-size.ll | 392 +--- .../LoopVectorize/X86/strided_load_cost.ll | 3 + .../X86/vect.omp.force.small-tc.ll | 40 +- .../x86-interleaved-accesses-masked-group.ll | 1934 ++--------------- .../LoopVectorize/fcmp-vectorize.ll | 2 + .../first-order-recurrence-complex.ll | 18 +- .../float-minmax-instruction-flag.ll | 3 + .../LoopVectorize/if-pred-stores.ll | 27 +- .../Transforms/LoopVectorize/if-reduction.ll | 4 +- .../multiple-strides-vectorization.ll | 94 +- llvm/test/Transforms/LoopVectorize/pr35773.ll | 3 + .../LoopVectorize/pr44488-predication.ll | 3 + .../vector-intrinsic-call-cost.ll | 3 + 25 files changed, 1366 insertions(+), 3171 deletions(-) diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp index 965f86f76dd5..b139f8520df3 100644 --- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp +++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp @@ -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 { diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/extractvalue-no-scalarization-required.ll b/llvm/test/Transforms/LoopVectorize/AArch64/extractvalue-no-scalarization-required.ll index 80d2e282176a..a88622bfcaef 100644 --- a/llvm/test/Transforms/LoopVectorize/AArch64/extractvalue-no-scalarization-required.ll +++ b/llvm/test/Transforms/LoopVectorize/AArch64/extractvalue-no-scalarization-required.ll @@ -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, ; 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, ; FORCED-NEXT: %0 = add i32 %index, 0 ; FORCED-NEXT: %1 = extractvalue { float, float } %sv, 0 ; FORCED-NEXT: %2 = extractvalue { float, float } %sv, 0 diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/pr36032.ll b/llvm/test/Transforms/LoopVectorize/AArch64/pr36032.ll index 6b7e809046ec..c51c6c98ddf4 100644 --- a/llvm/test/Transforms/LoopVectorize/AArch64/pr36032.ll +++ b/llvm/test/Transforms/LoopVectorize/AArch64/pr36032.ll @@ -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]], ; 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]], ; CHECK-NEXT: [[TMP19:%.*]] = add i32 [[TMP18]], 0 ; CHECK-NEXT: [[TMP20:%.*]] = add i32 [[CONV]], [[TMP19]] ; CHECK-NEXT: [[TMP21:%.*]] = zext i32 [[TMP20]] to i64 diff --git a/llvm/test/Transforms/LoopVectorize/ARM/sphinx.ll b/llvm/test/Transforms/LoopVectorize/ARM/sphinx.ll index 38bcb8e6c9fb..a1cf4b318f36 100644 --- a/llvm/test/Transforms/LoopVectorize/ARM/sphinx.ll +++ b/llvm/test/Transforms/LoopVectorize/ARM/sphinx.ll @@ -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]], ; 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 diff --git a/llvm/test/Transforms/LoopVectorize/X86/constant-fold.ll b/llvm/test/Transforms/LoopVectorize/X86/constant-fold.ll index 74c07eeaa9f2..360a52c619bc 100644 --- a/llvm/test/Transforms/LoopVectorize/X86/constant-fold.ll +++ b/llvm/test/Transforms/LoopVectorize/X86/constant-fold.ll @@ -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]], ; 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 diff --git a/llvm/test/Transforms/LoopVectorize/X86/imprecise-through-phis.ll b/llvm/test/Transforms/LoopVectorize/X86/imprecise-through-phis.ll index 720a0cc4700d..f9ccbf146fca 100644 --- a/llvm/test/Transforms/LoopVectorize/X86/imprecise-through-phis.ll +++ b/llvm/test/Transforms/LoopVectorize/X86/imprecise-through-phis.ll @@ -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]], ; 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 diff --git a/llvm/test/Transforms/LoopVectorize/X86/load-deref-pred.ll b/llvm/test/Transforms/LoopVectorize/X86/load-deref-pred.ll index 3c7dae3d71fb..3accbcdd1054 100644 --- a/llvm/test/Transforms/LoopVectorize/X86/load-deref-pred.ll +++ b/llvm/test/Transforms/LoopVectorize/X86/load-deref-pred.ll @@ -165,9 +165,15 @@ define i32 @test_explicit_pred_generic(i64 %len, i1* %test_base) { ; CHECK: vector.body: ; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ] ; CHECK-NEXT: [[VEC_PHI:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP80:%.*]], [[VECTOR_BODY]] ] -; CHECK-NEXT: [[VEC_PHI1:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP81:%.*]], [[VECTOR_BODY]] ] -; CHECK-NEXT: [[VEC_PHI2:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP82:%.*]], [[VECTOR_BODY]] ] -; CHECK-NEXT: [[VEC_PHI3:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP83:%.*]], [[VECTOR_BODY]] ] +; CHECK-NEXT: [[VEC_PHI4:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP81:%.*]], [[VECTOR_BODY]] ] +; CHECK-NEXT: [[VEC_PHI5:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP82:%.*]], [[VECTOR_BODY]] ] +; CHECK-NEXT: [[VEC_PHI6:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP83:%.*]], [[VECTOR_BODY]] ] +; 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:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], +; CHECK-NEXT: [[INDUCTION1:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], +; CHECK-NEXT: [[INDUCTION2:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], +; CHECK-NEXT: [[INDUCTION3:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], ; CHECK-NEXT: [[TMP0:%.*]] = add i64 [[INDEX]], 0 ; CHECK-NEXT: [[TMP1:%.*]] = add i64 [[INDEX]], 1 ; CHECK-NEXT: [[TMP2:%.*]] = add i64 [[INDEX]], 2 @@ -241,37 +247,37 @@ define i32 @test_explicit_pred_generic(i64 %len, i1* %test_base) { ; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <4 x i32>, <4 x i32>* [[TMP69]], align 4 ; CHECK-NEXT: [[TMP70:%.*]] = getelementptr inbounds i32, i32* [[TMP64]], i32 4 ; CHECK-NEXT: [[TMP71:%.*]] = bitcast i32* [[TMP70]] to <4 x i32>* -; CHECK-NEXT: [[WIDE_LOAD4:%.*]] = load <4 x i32>, <4 x i32>* [[TMP71]], align 4 +; CHECK-NEXT: [[WIDE_LOAD7:%.*]] = load <4 x i32>, <4 x i32>* [[TMP71]], align 4 ; CHECK-NEXT: [[TMP72:%.*]] = getelementptr inbounds i32, i32* [[TMP64]], i32 8 ; CHECK-NEXT: [[TMP73:%.*]] = bitcast i32* [[TMP72]] to <4 x i32>* -; CHECK-NEXT: [[WIDE_LOAD5:%.*]] = load <4 x i32>, <4 x i32>* [[TMP73]], align 4 +; CHECK-NEXT: [[WIDE_LOAD8:%.*]] = load <4 x i32>, <4 x i32>* [[TMP73]], align 4 ; CHECK-NEXT: [[TMP74:%.*]] = getelementptr inbounds i32, i32* [[TMP64]], i32 12 ; CHECK-NEXT: [[TMP75:%.*]] = bitcast i32* [[TMP74]] to <4 x i32>* -; CHECK-NEXT: [[WIDE_LOAD6:%.*]] = load <4 x i32>, <4 x i32>* [[TMP75]], align 4 +; CHECK-NEXT: [[WIDE_LOAD9:%.*]] = load <4 x i32>, <4 x i32>* [[TMP75]], align 4 ; CHECK-NEXT: [[TMP76:%.*]] = xor <4 x i1> [[TMP39]], ; CHECK-NEXT: [[TMP77:%.*]] = xor <4 x i1> [[TMP47]], ; CHECK-NEXT: [[TMP78:%.*]] = xor <4 x i1> [[TMP55]], ; CHECK-NEXT: [[TMP79:%.*]] = xor <4 x i1> [[TMP63]], ; CHECK-NEXT: [[PREDPHI:%.*]] = select <4 x i1> [[TMP39]], <4 x i32> [[WIDE_LOAD]], <4 x i32> zeroinitializer -; CHECK-NEXT: [[PREDPHI7:%.*]] = select <4 x i1> [[TMP47]], <4 x i32> [[WIDE_LOAD4]], <4 x i32> zeroinitializer -; CHECK-NEXT: [[PREDPHI8:%.*]] = select <4 x i1> [[TMP55]], <4 x i32> [[WIDE_LOAD5]], <4 x i32> zeroinitializer -; CHECK-NEXT: [[PREDPHI9:%.*]] = select <4 x i1> [[TMP63]], <4 x i32> [[WIDE_LOAD6]], <4 x i32> zeroinitializer +; CHECK-NEXT: [[PREDPHI10:%.*]] = select <4 x i1> [[TMP47]], <4 x i32> [[WIDE_LOAD7]], <4 x i32> zeroinitializer +; CHECK-NEXT: [[PREDPHI11:%.*]] = select <4 x i1> [[TMP55]], <4 x i32> [[WIDE_LOAD8]], <4 x i32> zeroinitializer +; CHECK-NEXT: [[PREDPHI12:%.*]] = select <4 x i1> [[TMP63]], <4 x i32> [[WIDE_LOAD9]], <4 x i32> zeroinitializer ; CHECK-NEXT: [[TMP80]] = add <4 x i32> [[VEC_PHI]], [[PREDPHI]] -; CHECK-NEXT: [[TMP81]] = add <4 x i32> [[VEC_PHI1]], [[PREDPHI7]] -; CHECK-NEXT: [[TMP82]] = add <4 x i32> [[VEC_PHI2]], [[PREDPHI8]] -; CHECK-NEXT: [[TMP83]] = add <4 x i32> [[VEC_PHI3]], [[PREDPHI9]] +; CHECK-NEXT: [[TMP81]] = add <4 x i32> [[VEC_PHI4]], [[PREDPHI10]] +; CHECK-NEXT: [[TMP82]] = add <4 x i32> [[VEC_PHI5]], [[PREDPHI11]] +; CHECK-NEXT: [[TMP83]] = add <4 x i32> [[VEC_PHI6]], [[PREDPHI12]] ; CHECK-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], 16 ; CHECK-NEXT: [[TMP84:%.*]] = icmp eq i64 [[INDEX_NEXT]], 4096 ; CHECK-NEXT: br i1 [[TMP84]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !4 ; CHECK: middle.block: ; CHECK-NEXT: [[BIN_RDX:%.*]] = add <4 x i32> [[TMP81]], [[TMP80]] -; CHECK-NEXT: [[BIN_RDX10:%.*]] = add <4 x i32> [[TMP82]], [[BIN_RDX]] -; CHECK-NEXT: [[BIN_RDX11:%.*]] = add <4 x i32> [[TMP83]], [[BIN_RDX10]] -; CHECK-NEXT: [[RDX_SHUF:%.*]] = shufflevector <4 x i32> [[BIN_RDX11]], <4 x i32> undef, <4 x i32> -; CHECK-NEXT: [[BIN_RDX12:%.*]] = add <4 x i32> [[BIN_RDX11]], [[RDX_SHUF]] -; CHECK-NEXT: [[RDX_SHUF13:%.*]] = shufflevector <4 x i32> [[BIN_RDX12]], <4 x i32> undef, <4 x i32> -; CHECK-NEXT: [[BIN_RDX14:%.*]] = add <4 x i32> [[BIN_RDX12]], [[RDX_SHUF13]] -; CHECK-NEXT: [[TMP85:%.*]] = extractelement <4 x i32> [[BIN_RDX14]], i32 0 +; CHECK-NEXT: [[BIN_RDX13:%.*]] = add <4 x i32> [[TMP82]], [[BIN_RDX]] +; CHECK-NEXT: [[BIN_RDX14:%.*]] = add <4 x i32> [[TMP83]], [[BIN_RDX13]] +; CHECK-NEXT: [[RDX_SHUF:%.*]] = shufflevector <4 x i32> [[BIN_RDX14]], <4 x i32> undef, <4 x i32> +; CHECK-NEXT: [[BIN_RDX15:%.*]] = add <4 x i32> [[BIN_RDX14]], [[RDX_SHUF]] +; CHECK-NEXT: [[RDX_SHUF16:%.*]] = shufflevector <4 x i32> [[BIN_RDX15]], <4 x i32> undef, <4 x i32> +; CHECK-NEXT: [[BIN_RDX17:%.*]] = add <4 x i32> [[BIN_RDX15]], [[RDX_SHUF16]] +; CHECK-NEXT: [[TMP85:%.*]] = extractelement <4 x i32> [[BIN_RDX17]], i32 0 ; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 4096, 4096 ; CHECK-NEXT: br i1 [[CMP_N]], label [[LOOP_EXIT:%.*]], label [[SCALAR_PH]] ; CHECK: scalar.ph: @@ -340,9 +346,15 @@ define i32 @test_invariant_address(i64 %len, i1* %test_base) { ; CHECK: vector.body: ; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ] ; CHECK-NEXT: [[VEC_PHI:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP100:%.*]], [[VECTOR_BODY]] ] -; CHECK-NEXT: [[VEC_PHI1:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP101:%.*]], [[VECTOR_BODY]] ] -; CHECK-NEXT: [[VEC_PHI2:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP102:%.*]], [[VECTOR_BODY]] ] -; CHECK-NEXT: [[VEC_PHI3:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP103:%.*]], [[VECTOR_BODY]] ] +; CHECK-NEXT: [[VEC_PHI4:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP101:%.*]], [[VECTOR_BODY]] ] +; CHECK-NEXT: [[VEC_PHI5:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP102:%.*]], [[VECTOR_BODY]] ] +; CHECK-NEXT: [[VEC_PHI6:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP103:%.*]], [[VECTOR_BODY]] ] +; 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:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], +; CHECK-NEXT: [[INDUCTION1:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], +; CHECK-NEXT: [[INDUCTION2:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], +; CHECK-NEXT: [[INDUCTION3:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], ; CHECK-NEXT: [[TMP0:%.*]] = add i64 [[INDEX]], 0 ; CHECK-NEXT: [[TMP1:%.*]] = add i64 [[INDEX]], 1 ; CHECK-NEXT: [[TMP2:%.*]] = add i64 [[INDEX]], 2 @@ -444,25 +456,25 @@ define i32 @test_invariant_address(i64 %len, i1* %test_base) { ; CHECK-NEXT: [[TMP98:%.*]] = xor <4 x i1> [[TMP55]], ; CHECK-NEXT: [[TMP99:%.*]] = xor <4 x i1> [[TMP63]], ; CHECK-NEXT: [[PREDPHI:%.*]] = select <4 x i1> [[TMP39]], <4 x i32> [[TMP71]], <4 x i32> zeroinitializer -; CHECK-NEXT: [[PREDPHI4:%.*]] = select <4 x i1> [[TMP47]], <4 x i32> [[TMP79]], <4 x i32> zeroinitializer -; CHECK-NEXT: [[PREDPHI5:%.*]] = select <4 x i1> [[TMP55]], <4 x i32> [[TMP87]], <4 x i32> zeroinitializer -; CHECK-NEXT: [[PREDPHI6:%.*]] = select <4 x i1> [[TMP63]], <4 x i32> [[TMP95]], <4 x i32> zeroinitializer +; CHECK-NEXT: [[PREDPHI7:%.*]] = select <4 x i1> [[TMP47]], <4 x i32> [[TMP79]], <4 x i32> zeroinitializer +; CHECK-NEXT: [[PREDPHI8:%.*]] = select <4 x i1> [[TMP55]], <4 x i32> [[TMP87]], <4 x i32> zeroinitializer +; CHECK-NEXT: [[PREDPHI9:%.*]] = select <4 x i1> [[TMP63]], <4 x i32> [[TMP95]], <4 x i32> zeroinitializer ; CHECK-NEXT: [[TMP100]] = add <4 x i32> [[VEC_PHI]], [[PREDPHI]] -; CHECK-NEXT: [[TMP101]] = add <4 x i32> [[VEC_PHI1]], [[PREDPHI4]] -; CHECK-NEXT: [[TMP102]] = add <4 x i32> [[VEC_PHI2]], [[PREDPHI5]] -; CHECK-NEXT: [[TMP103]] = add <4 x i32> [[VEC_PHI3]], [[PREDPHI6]] +; CHECK-NEXT: [[TMP101]] = add <4 x i32> [[VEC_PHI4]], [[PREDPHI7]] +; CHECK-NEXT: [[TMP102]] = add <4 x i32> [[VEC_PHI5]], [[PREDPHI8]] +; CHECK-NEXT: [[TMP103]] = add <4 x i32> [[VEC_PHI6]], [[PREDPHI9]] ; CHECK-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], 16 ; CHECK-NEXT: [[TMP104:%.*]] = icmp eq i64 [[INDEX_NEXT]], 4096 ; CHECK-NEXT: br i1 [[TMP104]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !6 ; CHECK: middle.block: ; CHECK-NEXT: [[BIN_RDX:%.*]] = add <4 x i32> [[TMP101]], [[TMP100]] -; CHECK-NEXT: [[BIN_RDX7:%.*]] = add <4 x i32> [[TMP102]], [[BIN_RDX]] -; CHECK-NEXT: [[BIN_RDX8:%.*]] = add <4 x i32> [[TMP103]], [[BIN_RDX7]] -; CHECK-NEXT: [[RDX_SHUF:%.*]] = shufflevector <4 x i32> [[BIN_RDX8]], <4 x i32> undef, <4 x i32> -; CHECK-NEXT: [[BIN_RDX9:%.*]] = add <4 x i32> [[BIN_RDX8]], [[RDX_SHUF]] -; CHECK-NEXT: [[RDX_SHUF10:%.*]] = shufflevector <4 x i32> [[BIN_RDX9]], <4 x i32> undef, <4 x i32> -; CHECK-NEXT: [[BIN_RDX11:%.*]] = add <4 x i32> [[BIN_RDX9]], [[RDX_SHUF10]] -; CHECK-NEXT: [[TMP105:%.*]] = extractelement <4 x i32> [[BIN_RDX11]], i32 0 +; CHECK-NEXT: [[BIN_RDX10:%.*]] = add <4 x i32> [[TMP102]], [[BIN_RDX]] +; CHECK-NEXT: [[BIN_RDX11:%.*]] = add <4 x i32> [[TMP103]], [[BIN_RDX10]] +; CHECK-NEXT: [[RDX_SHUF:%.*]] = shufflevector <4 x i32> [[BIN_RDX11]], <4 x i32> undef, <4 x i32> +; CHECK-NEXT: [[BIN_RDX12:%.*]] = add <4 x i32> [[BIN_RDX11]], [[RDX_SHUF]] +; CHECK-NEXT: [[RDX_SHUF13:%.*]] = shufflevector <4 x i32> [[BIN_RDX12]], <4 x i32> undef, <4 x i32> +; CHECK-NEXT: [[BIN_RDX14:%.*]] = add <4 x i32> [[BIN_RDX12]], [[RDX_SHUF13]] +; CHECK-NEXT: [[TMP105:%.*]] = extractelement <4 x i32> [[BIN_RDX14]], i32 0 ; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 4096, 4096 ; CHECK-NEXT: br i1 [[CMP_N]], label [[LOOP_EXIT:%.*]], label [[SCALAR_PH]] ; CHECK: scalar.ph: @@ -524,11 +536,17 @@ define i32 @test_step_narrower_than_access(i64 %len, i1* %test_base) { ; CHECK: vector.ph: ; CHECK-NEXT: br label [[VECTOR_BODY:%.*]] ; CHECK: vector.body: -; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[PRED_LOAD_CONTINUE33:%.*]] ] -; CHECK-NEXT: [[VEC_PHI:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP180:%.*]], [[PRED_LOAD_CONTINUE33]] ] -; CHECK-NEXT: [[VEC_PHI1:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP181:%.*]], [[PRED_LOAD_CONTINUE33]] ] -; CHECK-NEXT: [[VEC_PHI2:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP182:%.*]], [[PRED_LOAD_CONTINUE33]] ] -; CHECK-NEXT: [[VEC_PHI3:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP183:%.*]], [[PRED_LOAD_CONTINUE33]] ] +; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[PRED_LOAD_CONTINUE36:%.*]] ] +; CHECK-NEXT: [[VEC_PHI:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP180:%.*]], [[PRED_LOAD_CONTINUE36]] ] +; CHECK-NEXT: [[VEC_PHI4:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP181:%.*]], [[PRED_LOAD_CONTINUE36]] ] +; CHECK-NEXT: [[VEC_PHI5:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP182:%.*]], [[PRED_LOAD_CONTINUE36]] ] +; CHECK-NEXT: [[VEC_PHI6:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP183:%.*]], [[PRED_LOAD_CONTINUE36]] ] +; 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:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], +; CHECK-NEXT: [[INDUCTION1:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], +; CHECK-NEXT: [[INDUCTION2:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], +; CHECK-NEXT: [[INDUCTION3:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], ; CHECK-NEXT: [[TMP0:%.*]] = add i64 [[INDEX]], 0 ; CHECK-NEXT: [[TMP1:%.*]] = add i64 [[INDEX]], 1 ; CHECK-NEXT: [[TMP2:%.*]] = add i64 [[INDEX]], 2 @@ -605,194 +623,194 @@ define i32 @test_step_narrower_than_access(i64 %len, i1* %test_base) { ; CHECK: pred.load.continue: ; CHECK-NEXT: [[TMP70:%.*]] = phi <4 x i32> [ undef, [[VECTOR_BODY]] ], [ [[TMP69]], [[PRED_LOAD_IF]] ] ; CHECK-NEXT: [[TMP71:%.*]] = extractelement <4 x i1> [[TMP39]], i32 1 -; CHECK-NEXT: br i1 [[TMP71]], label [[PRED_LOAD_IF4:%.*]], label [[PRED_LOAD_CONTINUE5:%.*]] -; CHECK: pred.load.if4: +; CHECK-NEXT: br i1 [[TMP71]], label [[PRED_LOAD_IF7:%.*]], label [[PRED_LOAD_CONTINUE8:%.*]] +; CHECK: pred.load.if7: ; CHECK-NEXT: [[TMP72:%.*]] = bitcast i32* [[BASE]] to i16* ; CHECK-NEXT: [[TMP73:%.*]] = getelementptr inbounds i16, i16* [[TMP72]], i64 [[TMP1]] ; CHECK-NEXT: [[TMP74:%.*]] = bitcast i16* [[TMP73]] to i32* ; CHECK-NEXT: [[TMP75:%.*]] = load i32, i32* [[TMP74]] ; CHECK-NEXT: [[TMP76:%.*]] = insertelement <4 x i32> [[TMP70]], i32 [[TMP75]], i32 1 -; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE5]] -; CHECK: pred.load.continue5: -; CHECK-NEXT: [[TMP77:%.*]] = phi <4 x i32> [ [[TMP70]], [[PRED_LOAD_CONTINUE]] ], [ [[TMP76]], [[PRED_LOAD_IF4]] ] +; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE8]] +; CHECK: pred.load.continue8: +; CHECK-NEXT: [[TMP77:%.*]] = phi <4 x i32> [ [[TMP70]], [[PRED_LOAD_CONTINUE]] ], [ [[TMP76]], [[PRED_LOAD_IF7]] ] ; CHECK-NEXT: [[TMP78:%.*]] = extractelement <4 x i1> [[TMP39]], i32 2 -; CHECK-NEXT: br i1 [[TMP78]], label [[PRED_LOAD_IF6:%.*]], label [[PRED_LOAD_CONTINUE7:%.*]] -; CHECK: pred.load.if6: +; CHECK-NEXT: br i1 [[TMP78]], label [[PRED_LOAD_IF9:%.*]], label [[PRED_LOAD_CONTINUE10:%.*]] +; CHECK: pred.load.if9: ; CHECK-NEXT: [[TMP79:%.*]] = bitcast i32* [[BASE]] to i16* ; CHECK-NEXT: [[TMP80:%.*]] = getelementptr inbounds i16, i16* [[TMP79]], i64 [[TMP2]] ; CHECK-NEXT: [[TMP81:%.*]] = bitcast i16* [[TMP80]] to i32* ; CHECK-NEXT: [[TMP82:%.*]] = load i32, i32* [[TMP81]] ; CHECK-NEXT: [[TMP83:%.*]] = insertelement <4 x i32> [[TMP77]], i32 [[TMP82]], i32 2 -; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE7]] -; CHECK: pred.load.continue7: -; CHECK-NEXT: [[TMP84:%.*]] = phi <4 x i32> [ [[TMP77]], [[PRED_LOAD_CONTINUE5]] ], [ [[TMP83]], [[PRED_LOAD_IF6]] ] +; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE10]] +; CHECK: pred.load.continue10: +; CHECK-NEXT: [[TMP84:%.*]] = phi <4 x i32> [ [[TMP77]], [[PRED_LOAD_CONTINUE8]] ], [ [[TMP83]], [[PRED_LOAD_IF9]] ] ; CHECK-NEXT: [[TMP85:%.*]] = extractelement <4 x i1> [[TMP39]], i32 3 -; CHECK-NEXT: br i1 [[TMP85]], label [[PRED_LOAD_IF8:%.*]], label [[PRED_LOAD_CONTINUE9:%.*]] -; CHECK: pred.load.if8: +; CHECK-NEXT: br i1 [[TMP85]], label [[PRED_LOAD_IF11:%.*]], label [[PRED_LOAD_CONTINUE12:%.*]] +; CHECK: pred.load.if11: ; CHECK-NEXT: [[TMP86:%.*]] = bitcast i32* [[BASE]] to i16* ; CHECK-NEXT: [[TMP87:%.*]] = getelementptr inbounds i16, i16* [[TMP86]], i64 [[TMP3]] ; CHECK-NEXT: [[TMP88:%.*]] = bitcast i16* [[TMP87]] to i32* ; CHECK-NEXT: [[TMP89:%.*]] = load i32, i32* [[TMP88]] ; CHECK-NEXT: [[TMP90:%.*]] = insertelement <4 x i32> [[TMP84]], i32 [[TMP89]], i32 3 -; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE9]] -; CHECK: pred.load.continue9: -; CHECK-NEXT: [[TMP91:%.*]] = phi <4 x i32> [ [[TMP84]], [[PRED_LOAD_CONTINUE7]] ], [ [[TMP90]], [[PRED_LOAD_IF8]] ] +; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE12]] +; CHECK: pred.load.continue12: +; CHECK-NEXT: [[TMP91:%.*]] = phi <4 x i32> [ [[TMP84]], [[PRED_LOAD_CONTINUE10]] ], [ [[TMP90]], [[PRED_LOAD_IF11]] ] ; CHECK-NEXT: [[TMP92:%.*]] = extractelement <4 x i1> [[TMP47]], i32 0 -; CHECK-NEXT: br i1 [[TMP92]], label [[PRED_LOAD_IF10:%.*]], label [[PRED_LOAD_CONTINUE11:%.*]] -; CHECK: pred.load.if10: +; CHECK-NEXT: br i1 [[TMP92]], label [[PRED_LOAD_IF13:%.*]], label [[PRED_LOAD_CONTINUE14:%.*]] +; CHECK: pred.load.if13: ; CHECK-NEXT: [[TMP93:%.*]] = bitcast i32* [[BASE]] to i16* ; CHECK-NEXT: [[TMP94:%.*]] = getelementptr inbounds i16, i16* [[TMP93]], i64 [[TMP4]] ; CHECK-NEXT: [[TMP95:%.*]] = bitcast i16* [[TMP94]] to i32* ; CHECK-NEXT: [[TMP96:%.*]] = load i32, i32* [[TMP95]] ; CHECK-NEXT: [[TMP97:%.*]] = insertelement <4 x i32> undef, i32 [[TMP96]], i32 0 -; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE11]] -; CHECK: pred.load.continue11: -; CHECK-NEXT: [[TMP98:%.*]] = phi <4 x i32> [ undef, [[PRED_LOAD_CONTINUE9]] ], [ [[TMP97]], [[PRED_LOAD_IF10]] ] +; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE14]] +; CHECK: pred.load.continue14: +; CHECK-NEXT: [[TMP98:%.*]] = phi <4 x i32> [ undef, [[PRED_LOAD_CONTINUE12]] ], [ [[TMP97]], [[PRED_LOAD_IF13]] ] ; CHECK-NEXT: [[TMP99:%.*]] = extractelement <4 x i1> [[TMP47]], i32 1 -; CHECK-NEXT: br i1 [[TMP99]], label [[PRED_LOAD_IF12:%.*]], label [[PRED_LOAD_CONTINUE13:%.*]] -; CHECK: pred.load.if12: +; CHECK-NEXT: br i1 [[TMP99]], label [[PRED_LOAD_IF15:%.*]], label [[PRED_LOAD_CONTINUE16:%.*]] +; CHECK: pred.load.if15: ; CHECK-NEXT: [[TMP100:%.*]] = bitcast i32* [[BASE]] to i16* ; CHECK-NEXT: [[TMP101:%.*]] = getelementptr inbounds i16, i16* [[TMP100]], i64 [[TMP5]] ; CHECK-NEXT: [[TMP102:%.*]] = bitcast i16* [[TMP101]] to i32* ; CHECK-NEXT: [[TMP103:%.*]] = load i32, i32* [[TMP102]] ; CHECK-NEXT: [[TMP104:%.*]] = insertelement <4 x i32> [[TMP98]], i32 [[TMP103]], i32 1 -; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE13]] -; CHECK: pred.load.continue13: -; CHECK-NEXT: [[TMP105:%.*]] = phi <4 x i32> [ [[TMP98]], [[PRED_LOAD_CONTINUE11]] ], [ [[TMP104]], [[PRED_LOAD_IF12]] ] +; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE16]] +; CHECK: pred.load.continue16: +; CHECK-NEXT: [[TMP105:%.*]] = phi <4 x i32> [ [[TMP98]], [[PRED_LOAD_CONTINUE14]] ], [ [[TMP104]], [[PRED_LOAD_IF15]] ] ; CHECK-NEXT: [[TMP106:%.*]] = extractelement <4 x i1> [[TMP47]], i32 2 -; CHECK-NEXT: br i1 [[TMP106]], label [[PRED_LOAD_IF14:%.*]], label [[PRED_LOAD_CONTINUE15:%.*]] -; CHECK: pred.load.if14: +; CHECK-NEXT: br i1 [[TMP106]], label [[PRED_LOAD_IF17:%.*]], label [[PRED_LOAD_CONTINUE18:%.*]] +; CHECK: pred.load.if17: ; CHECK-NEXT: [[TMP107:%.*]] = bitcast i32* [[BASE]] to i16* ; CHECK-NEXT: [[TMP108:%.*]] = getelementptr inbounds i16, i16* [[TMP107]], i64 [[TMP6]] ; CHECK-NEXT: [[TMP109:%.*]] = bitcast i16* [[TMP108]] to i32* ; CHECK-NEXT: [[TMP110:%.*]] = load i32, i32* [[TMP109]] ; CHECK-NEXT: [[TMP111:%.*]] = insertelement <4 x i32> [[TMP105]], i32 [[TMP110]], i32 2 -; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE15]] -; CHECK: pred.load.continue15: -; CHECK-NEXT: [[TMP112:%.*]] = phi <4 x i32> [ [[TMP105]], [[PRED_LOAD_CONTINUE13]] ], [ [[TMP111]], [[PRED_LOAD_IF14]] ] +; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE18]] +; CHECK: pred.load.continue18: +; CHECK-NEXT: [[TMP112:%.*]] = phi <4 x i32> [ [[TMP105]], [[PRED_LOAD_CONTINUE16]] ], [ [[TMP111]], [[PRED_LOAD_IF17]] ] ; CHECK-NEXT: [[TMP113:%.*]] = extractelement <4 x i1> [[TMP47]], i32 3 -; CHECK-NEXT: br i1 [[TMP113]], label [[PRED_LOAD_IF16:%.*]], label [[PRED_LOAD_CONTINUE17:%.*]] -; CHECK: pred.load.if16: +; CHECK-NEXT: br i1 [[TMP113]], label [[PRED_LOAD_IF19:%.*]], label [[PRED_LOAD_CONTINUE20:%.*]] +; CHECK: pred.load.if19: ; CHECK-NEXT: [[TMP114:%.*]] = bitcast i32* [[BASE]] to i16* ; CHECK-NEXT: [[TMP115:%.*]] = getelementptr inbounds i16, i16* [[TMP114]], i64 [[TMP7]] ; CHECK-NEXT: [[TMP116:%.*]] = bitcast i16* [[TMP115]] to i32* ; CHECK-NEXT: [[TMP117:%.*]] = load i32, i32* [[TMP116]] ; CHECK-NEXT: [[TMP118:%.*]] = insertelement <4 x i32> [[TMP112]], i32 [[TMP117]], i32 3 -; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE17]] -; CHECK: pred.load.continue17: -; CHECK-NEXT: [[TMP119:%.*]] = phi <4 x i32> [ [[TMP112]], [[PRED_LOAD_CONTINUE15]] ], [ [[TMP118]], [[PRED_LOAD_IF16]] ] +; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE20]] +; CHECK: pred.load.continue20: +; CHECK-NEXT: [[TMP119:%.*]] = phi <4 x i32> [ [[TMP112]], [[PRED_LOAD_CONTINUE18]] ], [ [[TMP118]], [[PRED_LOAD_IF19]] ] ; CHECK-NEXT: [[TMP120:%.*]] = extractelement <4 x i1> [[TMP55]], i32 0 -; CHECK-NEXT: br i1 [[TMP120]], label [[PRED_LOAD_IF18:%.*]], label [[PRED_LOAD_CONTINUE19:%.*]] -; CHECK: pred.load.if18: +; CHECK-NEXT: br i1 [[TMP120]], label [[PRED_LOAD_IF21:%.*]], label [[PRED_LOAD_CONTINUE22:%.*]] +; CHECK: pred.load.if21: ; CHECK-NEXT: [[TMP121:%.*]] = bitcast i32* [[BASE]] to i16* ; CHECK-NEXT: [[TMP122:%.*]] = getelementptr inbounds i16, i16* [[TMP121]], i64 [[TMP8]] ; CHECK-NEXT: [[TMP123:%.*]] = bitcast i16* [[TMP122]] to i32* ; CHECK-NEXT: [[TMP124:%.*]] = load i32, i32* [[TMP123]] ; CHECK-NEXT: [[TMP125:%.*]] = insertelement <4 x i32> undef, i32 [[TMP124]], i32 0 -; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE19]] -; CHECK: pred.load.continue19: -; CHECK-NEXT: [[TMP126:%.*]] = phi <4 x i32> [ undef, [[PRED_LOAD_CONTINUE17]] ], [ [[TMP125]], [[PRED_LOAD_IF18]] ] +; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE22]] +; CHECK: pred.load.continue22: +; CHECK-NEXT: [[TMP126:%.*]] = phi <4 x i32> [ undef, [[PRED_LOAD_CONTINUE20]] ], [ [[TMP125]], [[PRED_LOAD_IF21]] ] ; CHECK-NEXT: [[TMP127:%.*]] = extractelement <4 x i1> [[TMP55]], i32 1 -; CHECK-NEXT: br i1 [[TMP127]], label [[PRED_LOAD_IF20:%.*]], label [[PRED_LOAD_CONTINUE21:%.*]] -; CHECK: pred.load.if20: +; CHECK-NEXT: br i1 [[TMP127]], label [[PRED_LOAD_IF23:%.*]], label [[PRED_LOAD_CONTINUE24:%.*]] +; CHECK: pred.load.if23: ; CHECK-NEXT: [[TMP128:%.*]] = bitcast i32* [[BASE]] to i16* ; CHECK-NEXT: [[TMP129:%.*]] = getelementptr inbounds i16, i16* [[TMP128]], i64 [[TMP9]] ; CHECK-NEXT: [[TMP130:%.*]] = bitcast i16* [[TMP129]] to i32* ; CHECK-NEXT: [[TMP131:%.*]] = load i32, i32* [[TMP130]] ; CHECK-NEXT: [[TMP132:%.*]] = insertelement <4 x i32> [[TMP126]], i32 [[TMP131]], i32 1 -; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE21]] -; CHECK: pred.load.continue21: -; CHECK-NEXT: [[TMP133:%.*]] = phi <4 x i32> [ [[TMP126]], [[PRED_LOAD_CONTINUE19]] ], [ [[TMP132]], [[PRED_LOAD_IF20]] ] +; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE24]] +; CHECK: pred.load.continue24: +; CHECK-NEXT: [[TMP133:%.*]] = phi <4 x i32> [ [[TMP126]], [[PRED_LOAD_CONTINUE22]] ], [ [[TMP132]], [[PRED_LOAD_IF23]] ] ; CHECK-NEXT: [[TMP134:%.*]] = extractelement <4 x i1> [[TMP55]], i32 2 -; CHECK-NEXT: br i1 [[TMP134]], label [[PRED_LOAD_IF22:%.*]], label [[PRED_LOAD_CONTINUE23:%.*]] -; CHECK: pred.load.if22: +; CHECK-NEXT: br i1 [[TMP134]], label [[PRED_LOAD_IF25:%.*]], label [[PRED_LOAD_CONTINUE26:%.*]] +; CHECK: pred.load.if25: ; CHECK-NEXT: [[TMP135:%.*]] = bitcast i32* [[BASE]] to i16* ; CHECK-NEXT: [[TMP136:%.*]] = getelementptr inbounds i16, i16* [[TMP135]], i64 [[TMP10]] ; CHECK-NEXT: [[TMP137:%.*]] = bitcast i16* [[TMP136]] to i32* ; CHECK-NEXT: [[TMP138:%.*]] = load i32, i32* [[TMP137]] ; CHECK-NEXT: [[TMP139:%.*]] = insertelement <4 x i32> [[TMP133]], i32 [[TMP138]], i32 2 -; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE23]] -; CHECK: pred.load.continue23: -; CHECK-NEXT: [[TMP140:%.*]] = phi <4 x i32> [ [[TMP133]], [[PRED_LOAD_CONTINUE21]] ], [ [[TMP139]], [[PRED_LOAD_IF22]] ] +; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE26]] +; CHECK: pred.load.continue26: +; CHECK-NEXT: [[TMP140:%.*]] = phi <4 x i32> [ [[TMP133]], [[PRED_LOAD_CONTINUE24]] ], [ [[TMP139]], [[PRED_LOAD_IF25]] ] ; CHECK-NEXT: [[TMP141:%.*]] = extractelement <4 x i1> [[TMP55]], i32 3 -; CHECK-NEXT: br i1 [[TMP141]], label [[PRED_LOAD_IF24:%.*]], label [[PRED_LOAD_CONTINUE25:%.*]] -; CHECK: pred.load.if24: +; CHECK-NEXT: br i1 [[TMP141]], label [[PRED_LOAD_IF27:%.*]], label [[PRED_LOAD_CONTINUE28:%.*]] +; CHECK: pred.load.if27: ; CHECK-NEXT: [[TMP142:%.*]] = bitcast i32* [[BASE]] to i16* ; CHECK-NEXT: [[TMP143:%.*]] = getelementptr inbounds i16, i16* [[TMP142]], i64 [[TMP11]] ; CHECK-NEXT: [[TMP144:%.*]] = bitcast i16* [[TMP143]] to i32* ; CHECK-NEXT: [[TMP145:%.*]] = load i32, i32* [[TMP144]] ; CHECK-NEXT: [[TMP146:%.*]] = insertelement <4 x i32> [[TMP140]], i32 [[TMP145]], i32 3 -; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE25]] -; CHECK: pred.load.continue25: -; CHECK-NEXT: [[TMP147:%.*]] = phi <4 x i32> [ [[TMP140]], [[PRED_LOAD_CONTINUE23]] ], [ [[TMP146]], [[PRED_LOAD_IF24]] ] +; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE28]] +; CHECK: pred.load.continue28: +; CHECK-NEXT: [[TMP147:%.*]] = phi <4 x i32> [ [[TMP140]], [[PRED_LOAD_CONTINUE26]] ], [ [[TMP146]], [[PRED_LOAD_IF27]] ] ; CHECK-NEXT: [[TMP148:%.*]] = extractelement <4 x i1> [[TMP63]], i32 0 -; CHECK-NEXT: br i1 [[TMP148]], label [[PRED_LOAD_IF26:%.*]], label [[PRED_LOAD_CONTINUE27:%.*]] -; CHECK: pred.load.if26: +; CHECK-NEXT: br i1 [[TMP148]], label [[PRED_LOAD_IF29:%.*]], label [[PRED_LOAD_CONTINUE30:%.*]] +; CHECK: pred.load.if29: ; CHECK-NEXT: [[TMP149:%.*]] = bitcast i32* [[BASE]] to i16* ; CHECK-NEXT: [[TMP150:%.*]] = getelementptr inbounds i16, i16* [[TMP149]], i64 [[TMP12]] ; CHECK-NEXT: [[TMP151:%.*]] = bitcast i16* [[TMP150]] to i32* ; CHECK-NEXT: [[TMP152:%.*]] = load i32, i32* [[TMP151]] ; CHECK-NEXT: [[TMP153:%.*]] = insertelement <4 x i32> undef, i32 [[TMP152]], i32 0 -; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE27]] -; CHECK: pred.load.continue27: -; CHECK-NEXT: [[TMP154:%.*]] = phi <4 x i32> [ undef, [[PRED_LOAD_CONTINUE25]] ], [ [[TMP153]], [[PRED_LOAD_IF26]] ] +; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE30]] +; CHECK: pred.load.continue30: +; CHECK-NEXT: [[TMP154:%.*]] = phi <4 x i32> [ undef, [[PRED_LOAD_CONTINUE28]] ], [ [[TMP153]], [[PRED_LOAD_IF29]] ] ; CHECK-NEXT: [[TMP155:%.*]] = extractelement <4 x i1> [[TMP63]], i32 1 -; CHECK-NEXT: br i1 [[TMP155]], label [[PRED_LOAD_IF28:%.*]], label [[PRED_LOAD_CONTINUE29:%.*]] -; CHECK: pred.load.if28: +; CHECK-NEXT: br i1 [[TMP155]], label [[PRED_LOAD_IF31:%.*]], label [[PRED_LOAD_CONTINUE32:%.*]] +; CHECK: pred.load.if31: ; CHECK-NEXT: [[TMP156:%.*]] = bitcast i32* [[BASE]] to i16* ; CHECK-NEXT: [[TMP157:%.*]] = getelementptr inbounds i16, i16* [[TMP156]], i64 [[TMP13]] ; CHECK-NEXT: [[TMP158:%.*]] = bitcast i16* [[TMP157]] to i32* ; CHECK-NEXT: [[TMP159:%.*]] = load i32, i32* [[TMP158]] ; CHECK-NEXT: [[TMP160:%.*]] = insertelement <4 x i32> [[TMP154]], i32 [[TMP159]], i32 1 -; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE29]] -; CHECK: pred.load.continue29: -; CHECK-NEXT: [[TMP161:%.*]] = phi <4 x i32> [ [[TMP154]], [[PRED_LOAD_CONTINUE27]] ], [ [[TMP160]], [[PRED_LOAD_IF28]] ] +; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE32]] +; CHECK: pred.load.continue32: +; CHECK-NEXT: [[TMP161:%.*]] = phi <4 x i32> [ [[TMP154]], [[PRED_LOAD_CONTINUE30]] ], [ [[TMP160]], [[PRED_LOAD_IF31]] ] ; CHECK-NEXT: [[TMP162:%.*]] = extractelement <4 x i1> [[TMP63]], i32 2 -; CHECK-NEXT: br i1 [[TMP162]], label [[PRED_LOAD_IF30:%.*]], label [[PRED_LOAD_CONTINUE31:%.*]] -; CHECK: pred.load.if30: +; CHECK-NEXT: br i1 [[TMP162]], label [[PRED_LOAD_IF33:%.*]], label [[PRED_LOAD_CONTINUE34:%.*]] +; CHECK: pred.load.if33: ; CHECK-NEXT: [[TMP163:%.*]] = bitcast i32* [[BASE]] to i16* ; CHECK-NEXT: [[TMP164:%.*]] = getelementptr inbounds i16, i16* [[TMP163]], i64 [[TMP14]] ; CHECK-NEXT: [[TMP165:%.*]] = bitcast i16* [[TMP164]] to i32* ; CHECK-NEXT: [[TMP166:%.*]] = load i32, i32* [[TMP165]] ; CHECK-NEXT: [[TMP167:%.*]] = insertelement <4 x i32> [[TMP161]], i32 [[TMP166]], i32 2 -; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE31]] -; CHECK: pred.load.continue31: -; CHECK-NEXT: [[TMP168:%.*]] = phi <4 x i32> [ [[TMP161]], [[PRED_LOAD_CONTINUE29]] ], [ [[TMP167]], [[PRED_LOAD_IF30]] ] +; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE34]] +; CHECK: pred.load.continue34: +; CHECK-NEXT: [[TMP168:%.*]] = phi <4 x i32> [ [[TMP161]], [[PRED_LOAD_CONTINUE32]] ], [ [[TMP167]], [[PRED_LOAD_IF33]] ] ; CHECK-NEXT: [[TMP169:%.*]] = extractelement <4 x i1> [[TMP63]], i32 3 -; CHECK-NEXT: br i1 [[TMP169]], label [[PRED_LOAD_IF32:%.*]], label [[PRED_LOAD_CONTINUE33]] -; CHECK: pred.load.if32: +; CHECK-NEXT: br i1 [[TMP169]], label [[PRED_LOAD_IF35:%.*]], label [[PRED_LOAD_CONTINUE36]] +; CHECK: pred.load.if35: ; CHECK-NEXT: [[TMP170:%.*]] = bitcast i32* [[BASE]] to i16* ; CHECK-NEXT: [[TMP171:%.*]] = getelementptr inbounds i16, i16* [[TMP170]], i64 [[TMP15]] ; CHECK-NEXT: [[TMP172:%.*]] = bitcast i16* [[TMP171]] to i32* ; CHECK-NEXT: [[TMP173:%.*]] = load i32, i32* [[TMP172]] ; CHECK-NEXT: [[TMP174:%.*]] = insertelement <4 x i32> [[TMP168]], i32 [[TMP173]], i32 3 -; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE33]] -; CHECK: pred.load.continue33: -; CHECK-NEXT: [[TMP175:%.*]] = phi <4 x i32> [ [[TMP168]], [[PRED_LOAD_CONTINUE31]] ], [ [[TMP174]], [[PRED_LOAD_IF32]] ] +; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE36]] +; CHECK: pred.load.continue36: +; CHECK-NEXT: [[TMP175:%.*]] = phi <4 x i32> [ [[TMP168]], [[PRED_LOAD_CONTINUE34]] ], [ [[TMP174]], [[PRED_LOAD_IF35]] ] ; CHECK-NEXT: [[TMP176:%.*]] = xor <4 x i1> [[TMP39]], ; CHECK-NEXT: [[TMP177:%.*]] = xor <4 x i1> [[TMP47]], ; CHECK-NEXT: [[TMP178:%.*]] = xor <4 x i1> [[TMP55]], ; CHECK-NEXT: [[TMP179:%.*]] = xor <4 x i1> [[TMP63]], ; CHECK-NEXT: [[PREDPHI:%.*]] = select <4 x i1> [[TMP39]], <4 x i32> [[TMP91]], <4 x i32> zeroinitializer -; CHECK-NEXT: [[PREDPHI34:%.*]] = select <4 x i1> [[TMP47]], <4 x i32> [[TMP119]], <4 x i32> zeroinitializer -; CHECK-NEXT: [[PREDPHI35:%.*]] = select <4 x i1> [[TMP55]], <4 x i32> [[TMP147]], <4 x i32> zeroinitializer -; CHECK-NEXT: [[PREDPHI36:%.*]] = select <4 x i1> [[TMP63]], <4 x i32> [[TMP175]], <4 x i32> zeroinitializer +; CHECK-NEXT: [[PREDPHI37:%.*]] = select <4 x i1> [[TMP47]], <4 x i32> [[TMP119]], <4 x i32> zeroinitializer +; CHECK-NEXT: [[PREDPHI38:%.*]] = select <4 x i1> [[TMP55]], <4 x i32> [[TMP147]], <4 x i32> zeroinitializer +; CHECK-NEXT: [[PREDPHI39:%.*]] = select <4 x i1> [[TMP63]], <4 x i32> [[TMP175]], <4 x i32> zeroinitializer ; CHECK-NEXT: [[TMP180]] = add <4 x i32> [[VEC_PHI]], [[PREDPHI]] -; CHECK-NEXT: [[TMP181]] = add <4 x i32> [[VEC_PHI1]], [[PREDPHI34]] -; CHECK-NEXT: [[TMP182]] = add <4 x i32> [[VEC_PHI2]], [[PREDPHI35]] -; CHECK-NEXT: [[TMP183]] = add <4 x i32> [[VEC_PHI3]], [[PREDPHI36]] +; CHECK-NEXT: [[TMP181]] = add <4 x i32> [[VEC_PHI4]], [[PREDPHI37]] +; CHECK-NEXT: [[TMP182]] = add <4 x i32> [[VEC_PHI5]], [[PREDPHI38]] +; CHECK-NEXT: [[TMP183]] = add <4 x i32> [[VEC_PHI6]], [[PREDPHI39]] ; CHECK-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], 16 ; CHECK-NEXT: [[TMP184:%.*]] = icmp eq i64 [[INDEX_NEXT]], 4096 ; CHECK-NEXT: br i1 [[TMP184]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !8 ; CHECK: middle.block: ; CHECK-NEXT: [[BIN_RDX:%.*]] = add <4 x i32> [[TMP181]], [[TMP180]] -; CHECK-NEXT: [[BIN_RDX37:%.*]] = add <4 x i32> [[TMP182]], [[BIN_RDX]] -; CHECK-NEXT: [[BIN_RDX38:%.*]] = add <4 x i32> [[TMP183]], [[BIN_RDX37]] -; CHECK-NEXT: [[RDX_SHUF:%.*]] = shufflevector <4 x i32> [[BIN_RDX38]], <4 x i32> undef, <4 x i32> -; CHECK-NEXT: [[BIN_RDX39:%.*]] = add <4 x i32> [[BIN_RDX38]], [[RDX_SHUF]] -; CHECK-NEXT: [[RDX_SHUF40:%.*]] = shufflevector <4 x i32> [[BIN_RDX39]], <4 x i32> undef, <4 x i32> -; CHECK-NEXT: [[BIN_RDX41:%.*]] = add <4 x i32> [[BIN_RDX39]], [[RDX_SHUF40]] -; CHECK-NEXT: [[TMP185:%.*]] = extractelement <4 x i32> [[BIN_RDX41]], i32 0 +; CHECK-NEXT: [[BIN_RDX40:%.*]] = add <4 x i32> [[TMP182]], [[BIN_RDX]] +; CHECK-NEXT: [[BIN_RDX41:%.*]] = add <4 x i32> [[TMP183]], [[BIN_RDX40]] +; CHECK-NEXT: [[RDX_SHUF:%.*]] = shufflevector <4 x i32> [[BIN_RDX41]], <4 x i32> undef, <4 x i32> +; CHECK-NEXT: [[BIN_RDX42:%.*]] = add <4 x i32> [[BIN_RDX41]], [[RDX_SHUF]] +; CHECK-NEXT: [[RDX_SHUF43:%.*]] = shufflevector <4 x i32> [[BIN_RDX42]], <4 x i32> undef, <4 x i32> +; CHECK-NEXT: [[BIN_RDX44:%.*]] = add <4 x i32> [[BIN_RDX42]], [[RDX_SHUF43]] +; CHECK-NEXT: [[TMP185:%.*]] = extractelement <4 x i32> [[BIN_RDX44]], i32 0 ; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 4096, 4096 ; CHECK-NEXT: br i1 [[CMP_N]], label [[LOOP_EXIT:%.*]], label [[SCALAR_PH]] ; CHECK: scalar.ph: @@ -867,9 +885,15 @@ define i32 @test_max_trip_count(i64 %len, i1* %test_base, i64 %n) { ; CHECK: vector.body: ; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ] ; CHECK-NEXT: [[VEC_PHI:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP81:%.*]], [[VECTOR_BODY]] ] -; CHECK-NEXT: [[VEC_PHI1:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP82:%.*]], [[VECTOR_BODY]] ] -; CHECK-NEXT: [[VEC_PHI2:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP83:%.*]], [[VECTOR_BODY]] ] -; CHECK-NEXT: [[VEC_PHI3:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP84:%.*]], [[VECTOR_BODY]] ] +; CHECK-NEXT: [[VEC_PHI4:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP82:%.*]], [[VECTOR_BODY]] ] +; CHECK-NEXT: [[VEC_PHI5:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP83:%.*]], [[VECTOR_BODY]] ] +; CHECK-NEXT: [[VEC_PHI6:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP84:%.*]], [[VECTOR_BODY]] ] +; 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:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], +; CHECK-NEXT: [[INDUCTION1:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], +; CHECK-NEXT: [[INDUCTION2:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], +; CHECK-NEXT: [[INDUCTION3:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], ; CHECK-NEXT: [[TMP1:%.*]] = add i64 [[INDEX]], 0 ; CHECK-NEXT: [[TMP2:%.*]] = add i64 [[INDEX]], 1 ; CHECK-NEXT: [[TMP3:%.*]] = add i64 [[INDEX]], 2 @@ -943,37 +967,37 @@ define i32 @test_max_trip_count(i64 %len, i1* %test_base, i64 %n) { ; CHECK-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* [[TMP70]], i32 4, <4 x i1> [[TMP40]], <4 x i32> undef) ; CHECK-NEXT: [[TMP71:%.*]] = getelementptr inbounds i32, i32* [[TMP65]], i32 4 ; CHECK-NEXT: [[TMP72:%.*]] = bitcast i32* [[TMP71]] to <4 x i32>* -; CHECK-NEXT: [[WIDE_MASKED_LOAD4:%.*]] = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* [[TMP72]], i32 4, <4 x i1> [[TMP48]], <4 x i32> undef) +; CHECK-NEXT: [[WIDE_MASKED_LOAD7:%.*]] = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* [[TMP72]], i32 4, <4 x i1> [[TMP48]], <4 x i32> undef) ; CHECK-NEXT: [[TMP73:%.*]] = getelementptr inbounds i32, i32* [[TMP65]], i32 8 ; CHECK-NEXT: [[TMP74:%.*]] = bitcast i32* [[TMP73]] to <4 x i32>* -; CHECK-NEXT: [[WIDE_MASKED_LOAD5:%.*]] = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* [[TMP74]], i32 4, <4 x i1> [[TMP56]], <4 x i32> undef) +; CHECK-NEXT: [[WIDE_MASKED_LOAD8:%.*]] = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* [[TMP74]], i32 4, <4 x i1> [[TMP56]], <4 x i32> undef) ; CHECK-NEXT: [[TMP75:%.*]] = getelementptr inbounds i32, i32* [[TMP65]], i32 12 ; CHECK-NEXT: [[TMP76:%.*]] = bitcast i32* [[TMP75]] to <4 x i32>* -; CHECK-NEXT: [[WIDE_MASKED_LOAD6:%.*]] = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* [[TMP76]], i32 4, <4 x i1> [[TMP64]], <4 x i32> undef) +; CHECK-NEXT: [[WIDE_MASKED_LOAD9:%.*]] = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* [[TMP76]], i32 4, <4 x i1> [[TMP64]], <4 x i32> undef) ; CHECK-NEXT: [[TMP77:%.*]] = xor <4 x i1> [[TMP40]], ; CHECK-NEXT: [[TMP78:%.*]] = xor <4 x i1> [[TMP48]], ; CHECK-NEXT: [[TMP79:%.*]] = xor <4 x i1> [[TMP56]], ; CHECK-NEXT: [[TMP80:%.*]] = xor <4 x i1> [[TMP64]], ; CHECK-NEXT: [[PREDPHI:%.*]] = select <4 x i1> [[TMP40]], <4 x i32> [[WIDE_MASKED_LOAD]], <4 x i32> zeroinitializer -; CHECK-NEXT: [[PREDPHI7:%.*]] = select <4 x i1> [[TMP48]], <4 x i32> [[WIDE_MASKED_LOAD4]], <4 x i32> zeroinitializer -; CHECK-NEXT: [[PREDPHI8:%.*]] = select <4 x i1> [[TMP56]], <4 x i32> [[WIDE_MASKED_LOAD5]], <4 x i32> zeroinitializer -; CHECK-NEXT: [[PREDPHI9:%.*]] = select <4 x i1> [[TMP64]], <4 x i32> [[WIDE_MASKED_LOAD6]], <4 x i32> zeroinitializer +; CHECK-NEXT: [[PREDPHI10:%.*]] = select <4 x i1> [[TMP48]], <4 x i32> [[WIDE_MASKED_LOAD7]], <4 x i32> zeroinitializer +; CHECK-NEXT: [[PREDPHI11:%.*]] = select <4 x i1> [[TMP56]], <4 x i32> [[WIDE_MASKED_LOAD8]], <4 x i32> zeroinitializer +; CHECK-NEXT: [[PREDPHI12:%.*]] = select <4 x i1> [[TMP64]], <4 x i32> [[WIDE_MASKED_LOAD9]], <4 x i32> zeroinitializer ; CHECK-NEXT: [[TMP81]] = add <4 x i32> [[VEC_PHI]], [[PREDPHI]] -; CHECK-NEXT: [[TMP82]] = add <4 x i32> [[VEC_PHI1]], [[PREDPHI7]] -; CHECK-NEXT: [[TMP83]] = add <4 x i32> [[VEC_PHI2]], [[PREDPHI8]] -; CHECK-NEXT: [[TMP84]] = add <4 x i32> [[VEC_PHI3]], [[PREDPHI9]] +; CHECK-NEXT: [[TMP82]] = add <4 x i32> [[VEC_PHI4]], [[PREDPHI10]] +; CHECK-NEXT: [[TMP83]] = add <4 x i32> [[VEC_PHI5]], [[PREDPHI11]] +; CHECK-NEXT: [[TMP84]] = add <4 x i32> [[VEC_PHI6]], [[PREDPHI12]] ; CHECK-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], 16 ; CHECK-NEXT: [[TMP85:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]] ; CHECK-NEXT: br i1 [[TMP85]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !10 ; CHECK: middle.block: ; CHECK-NEXT: [[BIN_RDX:%.*]] = add <4 x i32> [[TMP82]], [[TMP81]] -; CHECK-NEXT: [[BIN_RDX10:%.*]] = add <4 x i32> [[TMP83]], [[BIN_RDX]] -; CHECK-NEXT: [[BIN_RDX11:%.*]] = add <4 x i32> [[TMP84]], [[BIN_RDX10]] -; CHECK-NEXT: [[RDX_SHUF:%.*]] = shufflevector <4 x i32> [[BIN_RDX11]], <4 x i32> undef, <4 x i32> -; CHECK-NEXT: [[BIN_RDX12:%.*]] = add <4 x i32> [[BIN_RDX11]], [[RDX_SHUF]] -; CHECK-NEXT: [[RDX_SHUF13:%.*]] = shufflevector <4 x i32> [[BIN_RDX12]], <4 x i32> undef, <4 x i32> -; CHECK-NEXT: [[BIN_RDX14:%.*]] = add <4 x i32> [[BIN_RDX12]], [[RDX_SHUF13]] -; CHECK-NEXT: [[TMP86:%.*]] = extractelement <4 x i32> [[BIN_RDX14]], i32 0 +; CHECK-NEXT: [[BIN_RDX13:%.*]] = add <4 x i32> [[TMP83]], [[BIN_RDX]] +; CHECK-NEXT: [[BIN_RDX14:%.*]] = add <4 x i32> [[TMP84]], [[BIN_RDX13]] +; CHECK-NEXT: [[RDX_SHUF:%.*]] = shufflevector <4 x i32> [[BIN_RDX14]], <4 x i32> undef, <4 x i32> +; CHECK-NEXT: [[BIN_RDX15:%.*]] = add <4 x i32> [[BIN_RDX14]], [[RDX_SHUF]] +; CHECK-NEXT: [[RDX_SHUF16:%.*]] = shufflevector <4 x i32> [[BIN_RDX15]], <4 x i32> undef, <4 x i32> +; CHECK-NEXT: [[BIN_RDX17:%.*]] = add <4 x i32> [[BIN_RDX15]], [[RDX_SHUF16]] +; CHECK-NEXT: [[TMP86:%.*]] = extractelement <4 x i32> [[BIN_RDX17]], i32 0 ; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[TMP0]], [[N_VEC]] ; CHECK-NEXT: br i1 [[CMP_N]], label [[LOOP_EXIT:%.*]], label [[SCALAR_PH]] ; CHECK: scalar.ph: @@ -1043,10 +1067,16 @@ define i32 @test_non_zero_start(i64 %len, i1* %test_base) { ; CHECK: vector.body: ; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ] ; CHECK-NEXT: [[VEC_PHI:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP80:%.*]], [[VECTOR_BODY]] ] -; CHECK-NEXT: [[VEC_PHI1:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP81:%.*]], [[VECTOR_BODY]] ] -; CHECK-NEXT: [[VEC_PHI2:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP82:%.*]], [[VECTOR_BODY]] ] -; CHECK-NEXT: [[VEC_PHI3:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP83:%.*]], [[VECTOR_BODY]] ] +; CHECK-NEXT: [[VEC_PHI4:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP81:%.*]], [[VECTOR_BODY]] ] +; CHECK-NEXT: [[VEC_PHI5:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP82:%.*]], [[VECTOR_BODY]] ] +; CHECK-NEXT: [[VEC_PHI6:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP83:%.*]], [[VECTOR_BODY]] ] ; CHECK-NEXT: [[OFFSET_IDX:%.*]] = add i64 1024, [[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]], +; CHECK-NEXT: [[INDUCTION1:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], +; CHECK-NEXT: [[INDUCTION2:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], +; CHECK-NEXT: [[INDUCTION3:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], ; CHECK-NEXT: [[TMP0:%.*]] = add i64 [[OFFSET_IDX]], 0 ; CHECK-NEXT: [[TMP1:%.*]] = add i64 [[OFFSET_IDX]], 1 ; CHECK-NEXT: [[TMP2:%.*]] = add i64 [[OFFSET_IDX]], 2 @@ -1120,37 +1150,37 @@ define i32 @test_non_zero_start(i64 %len, i1* %test_base) { ; CHECK-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* [[TMP69]], i32 4, <4 x i1> [[TMP39]], <4 x i32> undef) ; CHECK-NEXT: [[TMP70:%.*]] = getelementptr inbounds i32, i32* [[TMP64]], i32 4 ; CHECK-NEXT: [[TMP71:%.*]] = bitcast i32* [[TMP70]] to <4 x i32>* -; CHECK-NEXT: [[WIDE_MASKED_LOAD4:%.*]] = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* [[TMP71]], i32 4, <4 x i1> [[TMP47]], <4 x i32> undef) +; CHECK-NEXT: [[WIDE_MASKED_LOAD7:%.*]] = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* [[TMP71]], i32 4, <4 x i1> [[TMP47]], <4 x i32> undef) ; CHECK-NEXT: [[TMP72:%.*]] = getelementptr inbounds i32, i32* [[TMP64]], i32 8 ; CHECK-NEXT: [[TMP73:%.*]] = bitcast i32* [[TMP72]] to <4 x i32>* -; CHECK-NEXT: [[WIDE_MASKED_LOAD5:%.*]] = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* [[TMP73]], i32 4, <4 x i1> [[TMP55]], <4 x i32> undef) +; CHECK-NEXT: [[WIDE_MASKED_LOAD8:%.*]] = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* [[TMP73]], i32 4, <4 x i1> [[TMP55]], <4 x i32> undef) ; CHECK-NEXT: [[TMP74:%.*]] = getelementptr inbounds i32, i32* [[TMP64]], i32 12 ; CHECK-NEXT: [[TMP75:%.*]] = bitcast i32* [[TMP74]] to <4 x i32>* -; CHECK-NEXT: [[WIDE_MASKED_LOAD6:%.*]] = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* [[TMP75]], i32 4, <4 x i1> [[TMP63]], <4 x i32> undef) +; CHECK-NEXT: [[WIDE_MASKED_LOAD9:%.*]] = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* [[TMP75]], i32 4, <4 x i1> [[TMP63]], <4 x i32> undef) ; CHECK-NEXT: [[TMP76:%.*]] = xor <4 x i1> [[TMP39]], ; CHECK-NEXT: [[TMP77:%.*]] = xor <4 x i1> [[TMP47]], ; CHECK-NEXT: [[TMP78:%.*]] = xor <4 x i1> [[TMP55]], ; CHECK-NEXT: [[TMP79:%.*]] = xor <4 x i1> [[TMP63]], ; CHECK-NEXT: [[PREDPHI:%.*]] = select <4 x i1> [[TMP39]], <4 x i32> [[WIDE_MASKED_LOAD]], <4 x i32> zeroinitializer -; CHECK-NEXT: [[PREDPHI7:%.*]] = select <4 x i1> [[TMP47]], <4 x i32> [[WIDE_MASKED_LOAD4]], <4 x i32> zeroinitializer -; CHECK-NEXT: [[PREDPHI8:%.*]] = select <4 x i1> [[TMP55]], <4 x i32> [[WIDE_MASKED_LOAD5]], <4 x i32> zeroinitializer -; CHECK-NEXT: [[PREDPHI9:%.*]] = select <4 x i1> [[TMP63]], <4 x i32> [[WIDE_MASKED_LOAD6]], <4 x i32> zeroinitializer +; CHECK-NEXT: [[PREDPHI10:%.*]] = select <4 x i1> [[TMP47]], <4 x i32> [[WIDE_MASKED_LOAD7]], <4 x i32> zeroinitializer +; CHECK-NEXT: [[PREDPHI11:%.*]] = select <4 x i1> [[TMP55]], <4 x i32> [[WIDE_MASKED_LOAD8]], <4 x i32> zeroinitializer +; CHECK-NEXT: [[PREDPHI12:%.*]] = select <4 x i1> [[TMP63]], <4 x i32> [[WIDE_MASKED_LOAD9]], <4 x i32> zeroinitializer ; CHECK-NEXT: [[TMP80]] = add <4 x i32> [[VEC_PHI]], [[PREDPHI]] -; CHECK-NEXT: [[TMP81]] = add <4 x i32> [[VEC_PHI1]], [[PREDPHI7]] -; CHECK-NEXT: [[TMP82]] = add <4 x i32> [[VEC_PHI2]], [[PREDPHI8]] -; CHECK-NEXT: [[TMP83]] = add <4 x i32> [[VEC_PHI3]], [[PREDPHI9]] +; CHECK-NEXT: [[TMP81]] = add <4 x i32> [[VEC_PHI4]], [[PREDPHI10]] +; CHECK-NEXT: [[TMP82]] = add <4 x i32> [[VEC_PHI5]], [[PREDPHI11]] +; CHECK-NEXT: [[TMP83]] = add <4 x i32> [[VEC_PHI6]], [[PREDPHI12]] ; CHECK-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], 16 ; CHECK-NEXT: [[TMP84:%.*]] = icmp eq i64 [[INDEX_NEXT]], 3072 ; CHECK-NEXT: br i1 [[TMP84]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !12 ; CHECK: middle.block: ; CHECK-NEXT: [[BIN_RDX:%.*]] = add <4 x i32> [[TMP81]], [[TMP80]] -; CHECK-NEXT: [[BIN_RDX10:%.*]] = add <4 x i32> [[TMP82]], [[BIN_RDX]] -; CHECK-NEXT: [[BIN_RDX11:%.*]] = add <4 x i32> [[TMP83]], [[BIN_RDX10]] -; CHECK-NEXT: [[RDX_SHUF:%.*]] = shufflevector <4 x i32> [[BIN_RDX11]], <4 x i32> undef, <4 x i32> -; CHECK-NEXT: [[BIN_RDX12:%.*]] = add <4 x i32> [[BIN_RDX11]], [[RDX_SHUF]] -; CHECK-NEXT: [[RDX_SHUF13:%.*]] = shufflevector <4 x i32> [[BIN_RDX12]], <4 x i32> undef, <4 x i32> -; CHECK-NEXT: [[BIN_RDX14:%.*]] = add <4 x i32> [[BIN_RDX12]], [[RDX_SHUF13]] -; CHECK-NEXT: [[TMP85:%.*]] = extractelement <4 x i32> [[BIN_RDX14]], i32 0 +; CHECK-NEXT: [[BIN_RDX13:%.*]] = add <4 x i32> [[TMP82]], [[BIN_RDX]] +; CHECK-NEXT: [[BIN_RDX14:%.*]] = add <4 x i32> [[TMP83]], [[BIN_RDX13]] +; CHECK-NEXT: [[RDX_SHUF:%.*]] = shufflevector <4 x i32> [[BIN_RDX14]], <4 x i32> undef, <4 x i32> +; CHECK-NEXT: [[BIN_RDX15:%.*]] = add <4 x i32> [[BIN_RDX14]], [[RDX_SHUF]] +; CHECK-NEXT: [[RDX_SHUF16:%.*]] = shufflevector <4 x i32> [[BIN_RDX15]], <4 x i32> undef, <4 x i32> +; CHECK-NEXT: [[BIN_RDX17:%.*]] = add <4 x i32> [[BIN_RDX15]], [[RDX_SHUF16]] +; CHECK-NEXT: [[TMP85:%.*]] = extractelement <4 x i32> [[BIN_RDX17]], i32 0 ; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 3072, 3072 ; CHECK-NEXT: br i1 [[CMP_N]], label [[LOOP_EXIT:%.*]], label [[SCALAR_PH]] ; CHECK: scalar.ph: @@ -1268,12 +1298,18 @@ define i32 @test_non_unit_stride(i64 %len, i1* %test_base) { ; CHECK: vector.ph: ; CHECK-NEXT: br label [[VECTOR_BODY:%.*]] ; CHECK: vector.body: -; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[PRED_LOAD_CONTINUE33:%.*]] ] -; CHECK-NEXT: [[VEC_PHI:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP148:%.*]], [[PRED_LOAD_CONTINUE33]] ] -; CHECK-NEXT: [[VEC_PHI1:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP149:%.*]], [[PRED_LOAD_CONTINUE33]] ] -; CHECK-NEXT: [[VEC_PHI2:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP150:%.*]], [[PRED_LOAD_CONTINUE33]] ] -; CHECK-NEXT: [[VEC_PHI3:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP151:%.*]], [[PRED_LOAD_CONTINUE33]] ] +; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[PRED_LOAD_CONTINUE36:%.*]] ] +; CHECK-NEXT: [[VEC_PHI:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP148:%.*]], [[PRED_LOAD_CONTINUE36]] ] +; CHECK-NEXT: [[VEC_PHI4:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP149:%.*]], [[PRED_LOAD_CONTINUE36]] ] +; CHECK-NEXT: [[VEC_PHI5:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP150:%.*]], [[PRED_LOAD_CONTINUE36]] ] +; CHECK-NEXT: [[VEC_PHI6:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP151:%.*]], [[PRED_LOAD_CONTINUE36]] ] ; CHECK-NEXT: [[OFFSET_IDX:%.*]] = mul i64 [[INDEX]], 2 +; 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]], +; CHECK-NEXT: [[INDUCTION1:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], +; CHECK-NEXT: [[INDUCTION2:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], +; CHECK-NEXT: [[INDUCTION3:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], ; CHECK-NEXT: [[TMP0:%.*]] = add i64 [[OFFSET_IDX]], 0 ; CHECK-NEXT: [[TMP1:%.*]] = add i64 [[OFFSET_IDX]], 2 ; CHECK-NEXT: [[TMP2:%.*]] = add i64 [[OFFSET_IDX]], 4 @@ -1348,164 +1384,164 @@ define i32 @test_non_unit_stride(i64 %len, i1* %test_base) { ; CHECK: pred.load.continue: ; CHECK-NEXT: [[TMP68:%.*]] = phi <4 x i32> [ undef, [[VECTOR_BODY]] ], [ [[TMP67]], [[PRED_LOAD_IF]] ] ; CHECK-NEXT: [[TMP69:%.*]] = extractelement <4 x i1> [[TMP39]], i32 1 -; CHECK-NEXT: br i1 [[TMP69]], label [[PRED_LOAD_IF4:%.*]], label [[PRED_LOAD_CONTINUE5:%.*]] -; CHECK: pred.load.if4: +; CHECK-NEXT: br i1 [[TMP69]], label [[PRED_LOAD_IF7:%.*]], label [[PRED_LOAD_CONTINUE8:%.*]] +; CHECK: pred.load.if7: ; CHECK-NEXT: [[TMP70:%.*]] = getelementptr inbounds i32, i32* [[BASE]], i64 [[TMP1]] ; CHECK-NEXT: [[TMP71:%.*]] = load i32, i32* [[TMP70]] ; CHECK-NEXT: [[TMP72:%.*]] = insertelement <4 x i32> [[TMP68]], i32 [[TMP71]], i32 1 -; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE5]] -; CHECK: pred.load.continue5: -; CHECK-NEXT: [[TMP73:%.*]] = phi <4 x i32> [ [[TMP68]], [[PRED_LOAD_CONTINUE]] ], [ [[TMP72]], [[PRED_LOAD_IF4]] ] +; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE8]] +; CHECK: pred.load.continue8: +; CHECK-NEXT: [[TMP73:%.*]] = phi <4 x i32> [ [[TMP68]], [[PRED_LOAD_CONTINUE]] ], [ [[TMP72]], [[PRED_LOAD_IF7]] ] ; CHECK-NEXT: [[TMP74:%.*]] = extractelement <4 x i1> [[TMP39]], i32 2 -; CHECK-NEXT: br i1 [[TMP74]], label [[PRED_LOAD_IF6:%.*]], label [[PRED_LOAD_CONTINUE7:%.*]] -; CHECK: pred.load.if6: +; CHECK-NEXT: br i1 [[TMP74]], label [[PRED_LOAD_IF9:%.*]], label [[PRED_LOAD_CONTINUE10:%.*]] +; CHECK: pred.load.if9: ; CHECK-NEXT: [[TMP75:%.*]] = getelementptr inbounds i32, i32* [[BASE]], i64 [[TMP2]] ; CHECK-NEXT: [[TMP76:%.*]] = load i32, i32* [[TMP75]] ; CHECK-NEXT: [[TMP77:%.*]] = insertelement <4 x i32> [[TMP73]], i32 [[TMP76]], i32 2 -; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE7]] -; CHECK: pred.load.continue7: -; CHECK-NEXT: [[TMP78:%.*]] = phi <4 x i32> [ [[TMP73]], [[PRED_LOAD_CONTINUE5]] ], [ [[TMP77]], [[PRED_LOAD_IF6]] ] +; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE10]] +; CHECK: pred.load.continue10: +; CHECK-NEXT: [[TMP78:%.*]] = phi <4 x i32> [ [[TMP73]], [[PRED_LOAD_CONTINUE8]] ], [ [[TMP77]], [[PRED_LOAD_IF9]] ] ; CHECK-NEXT: [[TMP79:%.*]] = extractelement <4 x i1> [[TMP39]], i32 3 -; CHECK-NEXT: br i1 [[TMP79]], label [[PRED_LOAD_IF8:%.*]], label [[PRED_LOAD_CONTINUE9:%.*]] -; CHECK: pred.load.if8: +; CHECK-NEXT: br i1 [[TMP79]], label [[PRED_LOAD_IF11:%.*]], label [[PRED_LOAD_CONTINUE12:%.*]] +; CHECK: pred.load.if11: ; CHECK-NEXT: [[TMP80:%.*]] = getelementptr inbounds i32, i32* [[BASE]], i64 [[TMP3]] ; CHECK-NEXT: [[TMP81:%.*]] = load i32, i32* [[TMP80]] ; CHECK-NEXT: [[TMP82:%.*]] = insertelement <4 x i32> [[TMP78]], i32 [[TMP81]], i32 3 -; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE9]] -; CHECK: pred.load.continue9: -; CHECK-NEXT: [[TMP83:%.*]] = phi <4 x i32> [ [[TMP78]], [[PRED_LOAD_CONTINUE7]] ], [ [[TMP82]], [[PRED_LOAD_IF8]] ] +; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE12]] +; CHECK: pred.load.continue12: +; CHECK-NEXT: [[TMP83:%.*]] = phi <4 x i32> [ [[TMP78]], [[PRED_LOAD_CONTINUE10]] ], [ [[TMP82]], [[PRED_LOAD_IF11]] ] ; CHECK-NEXT: [[TMP84:%.*]] = extractelement <4 x i1> [[TMP47]], i32 0 -; CHECK-NEXT: br i1 [[TMP84]], label [[PRED_LOAD_IF10:%.*]], label [[PRED_LOAD_CONTINUE11:%.*]] -; CHECK: pred.load.if10: +; CHECK-NEXT: br i1 [[TMP84]], label [[PRED_LOAD_IF13:%.*]], label [[PRED_LOAD_CONTINUE14:%.*]] +; CHECK: pred.load.if13: ; CHECK-NEXT: [[TMP85:%.*]] = getelementptr inbounds i32, i32* [[BASE]], i64 [[TMP4]] ; CHECK-NEXT: [[TMP86:%.*]] = load i32, i32* [[TMP85]] ; CHECK-NEXT: [[TMP87:%.*]] = insertelement <4 x i32> undef, i32 [[TMP86]], i32 0 -; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE11]] -; CHECK: pred.load.continue11: -; CHECK-NEXT: [[TMP88:%.*]] = phi <4 x i32> [ undef, [[PRED_LOAD_CONTINUE9]] ], [ [[TMP87]], [[PRED_LOAD_IF10]] ] +; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE14]] +; CHECK: pred.load.continue14: +; CHECK-NEXT: [[TMP88:%.*]] = phi <4 x i32> [ undef, [[PRED_LOAD_CONTINUE12]] ], [ [[TMP87]], [[PRED_LOAD_IF13]] ] ; CHECK-NEXT: [[TMP89:%.*]] = extractelement <4 x i1> [[TMP47]], i32 1 -; CHECK-NEXT: br i1 [[TMP89]], label [[PRED_LOAD_IF12:%.*]], label [[PRED_LOAD_CONTINUE13:%.*]] -; CHECK: pred.load.if12: +; CHECK-NEXT: br i1 [[TMP89]], label [[PRED_LOAD_IF15:%.*]], label [[PRED_LOAD_CONTINUE16:%.*]] +; CHECK: pred.load.if15: ; CHECK-NEXT: [[TMP90:%.*]] = getelementptr inbounds i32, i32* [[BASE]], i64 [[TMP5]] ; CHECK-NEXT: [[TMP91:%.*]] = load i32, i32* [[TMP90]] ; CHECK-NEXT: [[TMP92:%.*]] = insertelement <4 x i32> [[TMP88]], i32 [[TMP91]], i32 1 -; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE13]] -; CHECK: pred.load.continue13: -; CHECK-NEXT: [[TMP93:%.*]] = phi <4 x i32> [ [[TMP88]], [[PRED_LOAD_CONTINUE11]] ], [ [[TMP92]], [[PRED_LOAD_IF12]] ] +; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE16]] +; CHECK: pred.load.continue16: +; CHECK-NEXT: [[TMP93:%.*]] = phi <4 x i32> [ [[TMP88]], [[PRED_LOAD_CONTINUE14]] ], [ [[TMP92]], [[PRED_LOAD_IF15]] ] ; CHECK-NEXT: [[TMP94:%.*]] = extractelement <4 x i1> [[TMP47]], i32 2 -; CHECK-NEXT: br i1 [[TMP94]], label [[PRED_LOAD_IF14:%.*]], label [[PRED_LOAD_CONTINUE15:%.*]] -; CHECK: pred.load.if14: +; CHECK-NEXT: br i1 [[TMP94]], label [[PRED_LOAD_IF17:%.*]], label [[PRED_LOAD_CONTINUE18:%.*]] +; CHECK: pred.load.if17: ; CHECK-NEXT: [[TMP95:%.*]] = getelementptr inbounds i32, i32* [[BASE]], i64 [[TMP6]] ; CHECK-NEXT: [[TMP96:%.*]] = load i32, i32* [[TMP95]] ; CHECK-NEXT: [[TMP97:%.*]] = insertelement <4 x i32> [[TMP93]], i32 [[TMP96]], i32 2 -; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE15]] -; CHECK: pred.load.continue15: -; CHECK-NEXT: [[TMP98:%.*]] = phi <4 x i32> [ [[TMP93]], [[PRED_LOAD_CONTINUE13]] ], [ [[TMP97]], [[PRED_LOAD_IF14]] ] +; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE18]] +; CHECK: pred.load.continue18: +; CHECK-NEXT: [[TMP98:%.*]] = phi <4 x i32> [ [[TMP93]], [[PRED_LOAD_CONTINUE16]] ], [ [[TMP97]], [[PRED_LOAD_IF17]] ] ; CHECK-NEXT: [[TMP99:%.*]] = extractelement <4 x i1> [[TMP47]], i32 3 -; CHECK-NEXT: br i1 [[TMP99]], label [[PRED_LOAD_IF16:%.*]], label [[PRED_LOAD_CONTINUE17:%.*]] -; CHECK: pred.load.if16: +; CHECK-NEXT: br i1 [[TMP99]], label [[PRED_LOAD_IF19:%.*]], label [[PRED_LOAD_CONTINUE20:%.*]] +; CHECK: pred.load.if19: ; CHECK-NEXT: [[TMP100:%.*]] = getelementptr inbounds i32, i32* [[BASE]], i64 [[TMP7]] ; CHECK-NEXT: [[TMP101:%.*]] = load i32, i32* [[TMP100]] ; CHECK-NEXT: [[TMP102:%.*]] = insertelement <4 x i32> [[TMP98]], i32 [[TMP101]], i32 3 -; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE17]] -; CHECK: pred.load.continue17: -; CHECK-NEXT: [[TMP103:%.*]] = phi <4 x i32> [ [[TMP98]], [[PRED_LOAD_CONTINUE15]] ], [ [[TMP102]], [[PRED_LOAD_IF16]] ] +; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE20]] +; CHECK: pred.load.continue20: +; CHECK-NEXT: [[TMP103:%.*]] = phi <4 x i32> [ [[TMP98]], [[PRED_LOAD_CONTINUE18]] ], [ [[TMP102]], [[PRED_LOAD_IF19]] ] ; CHECK-NEXT: [[TMP104:%.*]] = extractelement <4 x i1> [[TMP55]], i32 0 -; CHECK-NEXT: br i1 [[TMP104]], label [[PRED_LOAD_IF18:%.*]], label [[PRED_LOAD_CONTINUE19:%.*]] -; CHECK: pred.load.if18: +; CHECK-NEXT: br i1 [[TMP104]], label [[PRED_LOAD_IF21:%.*]], label [[PRED_LOAD_CONTINUE22:%.*]] +; CHECK: pred.load.if21: ; CHECK-NEXT: [[TMP105:%.*]] = getelementptr inbounds i32, i32* [[BASE]], i64 [[TMP8]] ; CHECK-NEXT: [[TMP106:%.*]] = load i32, i32* [[TMP105]] ; CHECK-NEXT: [[TMP107:%.*]] = insertelement <4 x i32> undef, i32 [[TMP106]], i32 0 -; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE19]] -; CHECK: pred.load.continue19: -; CHECK-NEXT: [[TMP108:%.*]] = phi <4 x i32> [ undef, [[PRED_LOAD_CONTINUE17]] ], [ [[TMP107]], [[PRED_LOAD_IF18]] ] +; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE22]] +; CHECK: pred.load.continue22: +; CHECK-NEXT: [[TMP108:%.*]] = phi <4 x i32> [ undef, [[PRED_LOAD_CONTINUE20]] ], [ [[TMP107]], [[PRED_LOAD_IF21]] ] ; CHECK-NEXT: [[TMP109:%.*]] = extractelement <4 x i1> [[TMP55]], i32 1 -; CHECK-NEXT: br i1 [[TMP109]], label [[PRED_LOAD_IF20:%.*]], label [[PRED_LOAD_CONTINUE21:%.*]] -; CHECK: pred.load.if20: +; CHECK-NEXT: br i1 [[TMP109]], label [[PRED_LOAD_IF23:%.*]], label [[PRED_LOAD_CONTINUE24:%.*]] +; CHECK: pred.load.if23: ; CHECK-NEXT: [[TMP110:%.*]] = getelementptr inbounds i32, i32* [[BASE]], i64 [[TMP9]] ; CHECK-NEXT: [[TMP111:%.*]] = load i32, i32* [[TMP110]] ; CHECK-NEXT: [[TMP112:%.*]] = insertelement <4 x i32> [[TMP108]], i32 [[TMP111]], i32 1 -; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE21]] -; CHECK: pred.load.continue21: -; CHECK-NEXT: [[TMP113:%.*]] = phi <4 x i32> [ [[TMP108]], [[PRED_LOAD_CONTINUE19]] ], [ [[TMP112]], [[PRED_LOAD_IF20]] ] +; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE24]] +; CHECK: pred.load.continue24: +; CHECK-NEXT: [[TMP113:%.*]] = phi <4 x i32> [ [[TMP108]], [[PRED_LOAD_CONTINUE22]] ], [ [[TMP112]], [[PRED_LOAD_IF23]] ] ; CHECK-NEXT: [[TMP114:%.*]] = extractelement <4 x i1> [[TMP55]], i32 2 -; CHECK-NEXT: br i1 [[TMP114]], label [[PRED_LOAD_IF22:%.*]], label [[PRED_LOAD_CONTINUE23:%.*]] -; CHECK: pred.load.if22: +; CHECK-NEXT: br i1 [[TMP114]], label [[PRED_LOAD_IF25:%.*]], label [[PRED_LOAD_CONTINUE26:%.*]] +; CHECK: pred.load.if25: ; CHECK-NEXT: [[TMP115:%.*]] = getelementptr inbounds i32, i32* [[BASE]], i64 [[TMP10]] ; CHECK-NEXT: [[TMP116:%.*]] = load i32, i32* [[TMP115]] ; CHECK-NEXT: [[TMP117:%.*]] = insertelement <4 x i32> [[TMP113]], i32 [[TMP116]], i32 2 -; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE23]] -; CHECK: pred.load.continue23: -; CHECK-NEXT: [[TMP118:%.*]] = phi <4 x i32> [ [[TMP113]], [[PRED_LOAD_CONTINUE21]] ], [ [[TMP117]], [[PRED_LOAD_IF22]] ] +; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE26]] +; CHECK: pred.load.continue26: +; CHECK-NEXT: [[TMP118:%.*]] = phi <4 x i32> [ [[TMP113]], [[PRED_LOAD_CONTINUE24]] ], [ [[TMP117]], [[PRED_LOAD_IF25]] ] ; CHECK-NEXT: [[TMP119:%.*]] = extractelement <4 x i1> [[TMP55]], i32 3 -; CHECK-NEXT: br i1 [[TMP119]], label [[PRED_LOAD_IF24:%.*]], label [[PRED_LOAD_CONTINUE25:%.*]] -; CHECK: pred.load.if24: +; CHECK-NEXT: br i1 [[TMP119]], label [[PRED_LOAD_IF27:%.*]], label [[PRED_LOAD_CONTINUE28:%.*]] +; CHECK: pred.load.if27: ; CHECK-NEXT: [[TMP120:%.*]] = getelementptr inbounds i32, i32* [[BASE]], i64 [[TMP11]] ; CHECK-NEXT: [[TMP121:%.*]] = load i32, i32* [[TMP120]] ; CHECK-NEXT: [[TMP122:%.*]] = insertelement <4 x i32> [[TMP118]], i32 [[TMP121]], i32 3 -; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE25]] -; CHECK: pred.load.continue25: -; CHECK-NEXT: [[TMP123:%.*]] = phi <4 x i32> [ [[TMP118]], [[PRED_LOAD_CONTINUE23]] ], [ [[TMP122]], [[PRED_LOAD_IF24]] ] +; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE28]] +; CHECK: pred.load.continue28: +; CHECK-NEXT: [[TMP123:%.*]] = phi <4 x i32> [ [[TMP118]], [[PRED_LOAD_CONTINUE26]] ], [ [[TMP122]], [[PRED_LOAD_IF27]] ] ; CHECK-NEXT: [[TMP124:%.*]] = extractelement <4 x i1> [[TMP63]], i32 0 -; CHECK-NEXT: br i1 [[TMP124]], label [[PRED_LOAD_IF26:%.*]], label [[PRED_LOAD_CONTINUE27:%.*]] -; CHECK: pred.load.if26: +; CHECK-NEXT: br i1 [[TMP124]], label [[PRED_LOAD_IF29:%.*]], label [[PRED_LOAD_CONTINUE30:%.*]] +; CHECK: pred.load.if29: ; CHECK-NEXT: [[TMP125:%.*]] = getelementptr inbounds i32, i32* [[BASE]], i64 [[TMP12]] ; CHECK-NEXT: [[TMP126:%.*]] = load i32, i32* [[TMP125]] ; CHECK-NEXT: [[TMP127:%.*]] = insertelement <4 x i32> undef, i32 [[TMP126]], i32 0 -; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE27]] -; CHECK: pred.load.continue27: -; CHECK-NEXT: [[TMP128:%.*]] = phi <4 x i32> [ undef, [[PRED_LOAD_CONTINUE25]] ], [ [[TMP127]], [[PRED_LOAD_IF26]] ] +; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE30]] +; CHECK: pred.load.continue30: +; CHECK-NEXT: [[TMP128:%.*]] = phi <4 x i32> [ undef, [[PRED_LOAD_CONTINUE28]] ], [ [[TMP127]], [[PRED_LOAD_IF29]] ] ; CHECK-NEXT: [[TMP129:%.*]] = extractelement <4 x i1> [[TMP63]], i32 1 -; CHECK-NEXT: br i1 [[TMP129]], label [[PRED_LOAD_IF28:%.*]], label [[PRED_LOAD_CONTINUE29:%.*]] -; CHECK: pred.load.if28: +; CHECK-NEXT: br i1 [[TMP129]], label [[PRED_LOAD_IF31:%.*]], label [[PRED_LOAD_CONTINUE32:%.*]] +; CHECK: pred.load.if31: ; CHECK-NEXT: [[TMP130:%.*]] = getelementptr inbounds i32, i32* [[BASE]], i64 [[TMP13]] ; CHECK-NEXT: [[TMP131:%.*]] = load i32, i32* [[TMP130]] ; CHECK-NEXT: [[TMP132:%.*]] = insertelement <4 x i32> [[TMP128]], i32 [[TMP131]], i32 1 -; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE29]] -; CHECK: pred.load.continue29: -; CHECK-NEXT: [[TMP133:%.*]] = phi <4 x i32> [ [[TMP128]], [[PRED_LOAD_CONTINUE27]] ], [ [[TMP132]], [[PRED_LOAD_IF28]] ] +; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE32]] +; CHECK: pred.load.continue32: +; CHECK-NEXT: [[TMP133:%.*]] = phi <4 x i32> [ [[TMP128]], [[PRED_LOAD_CONTINUE30]] ], [ [[TMP132]], [[PRED_LOAD_IF31]] ] ; CHECK-NEXT: [[TMP134:%.*]] = extractelement <4 x i1> [[TMP63]], i32 2 -; CHECK-NEXT: br i1 [[TMP134]], label [[PRED_LOAD_IF30:%.*]], label [[PRED_LOAD_CONTINUE31:%.*]] -; CHECK: pred.load.if30: +; CHECK-NEXT: br i1 [[TMP134]], label [[PRED_LOAD_IF33:%.*]], label [[PRED_LOAD_CONTINUE34:%.*]] +; CHECK: pred.load.if33: ; CHECK-NEXT: [[TMP135:%.*]] = getelementptr inbounds i32, i32* [[BASE]], i64 [[TMP14]] ; CHECK-NEXT: [[TMP136:%.*]] = load i32, i32* [[TMP135]] ; CHECK-NEXT: [[TMP137:%.*]] = insertelement <4 x i32> [[TMP133]], i32 [[TMP136]], i32 2 -; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE31]] -; CHECK: pred.load.continue31: -; CHECK-NEXT: [[TMP138:%.*]] = phi <4 x i32> [ [[TMP133]], [[PRED_LOAD_CONTINUE29]] ], [ [[TMP137]], [[PRED_LOAD_IF30]] ] +; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE34]] +; CHECK: pred.load.continue34: +; CHECK-NEXT: [[TMP138:%.*]] = phi <4 x i32> [ [[TMP133]], [[PRED_LOAD_CONTINUE32]] ], [ [[TMP137]], [[PRED_LOAD_IF33]] ] ; CHECK-NEXT: [[TMP139:%.*]] = extractelement <4 x i1> [[TMP63]], i32 3 -; CHECK-NEXT: br i1 [[TMP139]], label [[PRED_LOAD_IF32:%.*]], label [[PRED_LOAD_CONTINUE33]] -; CHECK: pred.load.if32: +; CHECK-NEXT: br i1 [[TMP139]], label [[PRED_LOAD_IF35:%.*]], label [[PRED_LOAD_CONTINUE36]] +; CHECK: pred.load.if35: ; CHECK-NEXT: [[TMP140:%.*]] = getelementptr inbounds i32, i32* [[BASE]], i64 [[TMP15]] ; CHECK-NEXT: [[TMP141:%.*]] = load i32, i32* [[TMP140]] ; CHECK-NEXT: [[TMP142:%.*]] = insertelement <4 x i32> [[TMP138]], i32 [[TMP141]], i32 3 -; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE33]] -; CHECK: pred.load.continue33: -; CHECK-NEXT: [[TMP143:%.*]] = phi <4 x i32> [ [[TMP138]], [[PRED_LOAD_CONTINUE31]] ], [ [[TMP142]], [[PRED_LOAD_IF32]] ] +; CHECK-NEXT: br label [[PRED_LOAD_CONTINUE36]] +; CHECK: pred.load.continue36: +; CHECK-NEXT: [[TMP143:%.*]] = phi <4 x i32> [ [[TMP138]], [[PRED_LOAD_CONTINUE34]] ], [ [[TMP142]], [[PRED_LOAD_IF35]] ] ; CHECK-NEXT: [[TMP144:%.*]] = xor <4 x i1> [[TMP39]], ; CHECK-NEXT: [[TMP145:%.*]] = xor <4 x i1> [[TMP47]], ; CHECK-NEXT: [[TMP146:%.*]] = xor <4 x i1> [[TMP55]], ; CHECK-NEXT: [[TMP147:%.*]] = xor <4 x i1> [[TMP63]], ; CHECK-NEXT: [[PREDPHI:%.*]] = select <4 x i1> [[TMP39]], <4 x i32> [[TMP83]], <4 x i32> zeroinitializer -; CHECK-NEXT: [[PREDPHI34:%.*]] = select <4 x i1> [[TMP47]], <4 x i32> [[TMP103]], <4 x i32> zeroinitializer -; CHECK-NEXT: [[PREDPHI35:%.*]] = select <4 x i1> [[TMP55]], <4 x i32> [[TMP123]], <4 x i32> zeroinitializer -; CHECK-NEXT: [[PREDPHI36:%.*]] = select <4 x i1> [[TMP63]], <4 x i32> [[TMP143]], <4 x i32> zeroinitializer +; CHECK-NEXT: [[PREDPHI37:%.*]] = select <4 x i1> [[TMP47]], <4 x i32> [[TMP103]], <4 x i32> zeroinitializer +; CHECK-NEXT: [[PREDPHI38:%.*]] = select <4 x i1> [[TMP55]], <4 x i32> [[TMP123]], <4 x i32> zeroinitializer +; CHECK-NEXT: [[PREDPHI39:%.*]] = select <4 x i1> [[TMP63]], <4 x i32> [[TMP143]], <4 x i32> zeroinitializer ; CHECK-NEXT: [[TMP148]] = add <4 x i32> [[VEC_PHI]], [[PREDPHI]] -; CHECK-NEXT: [[TMP149]] = add <4 x i32> [[VEC_PHI1]], [[PREDPHI34]] -; CHECK-NEXT: [[TMP150]] = add <4 x i32> [[VEC_PHI2]], [[PREDPHI35]] -; CHECK-NEXT: [[TMP151]] = add <4 x i32> [[VEC_PHI3]], [[PREDPHI36]] +; CHECK-NEXT: [[TMP149]] = add <4 x i32> [[VEC_PHI4]], [[PREDPHI37]] +; CHECK-NEXT: [[TMP150]] = add <4 x i32> [[VEC_PHI5]], [[PREDPHI38]] +; CHECK-NEXT: [[TMP151]] = add <4 x i32> [[VEC_PHI6]], [[PREDPHI39]] ; CHECK-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], 16 ; CHECK-NEXT: [[TMP152:%.*]] = icmp eq i64 [[INDEX_NEXT]], 2048 ; CHECK-NEXT: br i1 [[TMP152]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !14 ; CHECK: middle.block: ; CHECK-NEXT: [[BIN_RDX:%.*]] = add <4 x i32> [[TMP149]], [[TMP148]] -; CHECK-NEXT: [[BIN_RDX37:%.*]] = add <4 x i32> [[TMP150]], [[BIN_RDX]] -; CHECK-NEXT: [[BIN_RDX38:%.*]] = add <4 x i32> [[TMP151]], [[BIN_RDX37]] -; CHECK-NEXT: [[RDX_SHUF:%.*]] = shufflevector <4 x i32> [[BIN_RDX38]], <4 x i32> undef, <4 x i32> -; CHECK-NEXT: [[BIN_RDX39:%.*]] = add <4 x i32> [[BIN_RDX38]], [[RDX_SHUF]] -; CHECK-NEXT: [[RDX_SHUF40:%.*]] = shufflevector <4 x i32> [[BIN_RDX39]], <4 x i32> undef, <4 x i32> -; CHECK-NEXT: [[BIN_RDX41:%.*]] = add <4 x i32> [[BIN_RDX39]], [[RDX_SHUF40]] -; CHECK-NEXT: [[TMP153:%.*]] = extractelement <4 x i32> [[BIN_RDX41]], i32 0 +; CHECK-NEXT: [[BIN_RDX40:%.*]] = add <4 x i32> [[TMP150]], [[BIN_RDX]] +; CHECK-NEXT: [[BIN_RDX41:%.*]] = add <4 x i32> [[TMP151]], [[BIN_RDX40]] +; CHECK-NEXT: [[RDX_SHUF:%.*]] = shufflevector <4 x i32> [[BIN_RDX41]], <4 x i32> undef, <4 x i32> +; CHECK-NEXT: [[BIN_RDX42:%.*]] = add <4 x i32> [[BIN_RDX41]], [[RDX_SHUF]] +; CHECK-NEXT: [[RDX_SHUF43:%.*]] = shufflevector <4 x i32> [[BIN_RDX42]], <4 x i32> undef, <4 x i32> +; CHECK-NEXT: [[BIN_RDX44:%.*]] = add <4 x i32> [[BIN_RDX42]], [[RDX_SHUF43]] +; CHECK-NEXT: [[TMP153:%.*]] = extractelement <4 x i32> [[BIN_RDX44]], i32 0 ; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 2048, 2048 ; CHECK-NEXT: br i1 [[CMP_N]], label [[LOOP_EXIT:%.*]], label [[SCALAR_PH]] ; CHECK: scalar.ph: @@ -1570,9 +1606,15 @@ define i32 @neg_off_by_many(i64 %len, i1* %test_base) { ; CHECK: vector.body: ; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ] ; CHECK-NEXT: [[VEC_PHI:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP80:%.*]], [[VECTOR_BODY]] ] -; CHECK-NEXT: [[VEC_PHI1:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP81:%.*]], [[VECTOR_BODY]] ] -; CHECK-NEXT: [[VEC_PHI2:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP82:%.*]], [[VECTOR_BODY]] ] -; CHECK-NEXT: [[VEC_PHI3:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP83:%.*]], [[VECTOR_BODY]] ] +; CHECK-NEXT: [[VEC_PHI4:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP81:%.*]], [[VECTOR_BODY]] ] +; CHECK-NEXT: [[VEC_PHI5:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP82:%.*]], [[VECTOR_BODY]] ] +; CHECK-NEXT: [[VEC_PHI6:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP83:%.*]], [[VECTOR_BODY]] ] +; 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:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], +; CHECK-NEXT: [[INDUCTION1:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], +; CHECK-NEXT: [[INDUCTION2:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], +; CHECK-NEXT: [[INDUCTION3:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], ; CHECK-NEXT: [[TMP0:%.*]] = add i64 [[INDEX]], 0 ; CHECK-NEXT: [[TMP1:%.*]] = add i64 [[INDEX]], 1 ; CHECK-NEXT: [[TMP2:%.*]] = add i64 [[INDEX]], 2 @@ -1646,37 +1688,37 @@ define i32 @neg_off_by_many(i64 %len, i1* %test_base) { ; CHECK-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* [[TMP69]], i32 4, <4 x i1> [[TMP39]], <4 x i32> undef) ; CHECK-NEXT: [[TMP70:%.*]] = getelementptr inbounds i32, i32* [[TMP64]], i32 4 ; CHECK-NEXT: [[TMP71:%.*]] = bitcast i32* [[TMP70]] to <4 x i32>* -; CHECK-NEXT: [[WIDE_MASKED_LOAD4:%.*]] = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* [[TMP71]], i32 4, <4 x i1> [[TMP47]], <4 x i32> undef) +; CHECK-NEXT: [[WIDE_MASKED_LOAD7:%.*]] = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* [[TMP71]], i32 4, <4 x i1> [[TMP47]], <4 x i32> undef) ; CHECK-NEXT: [[TMP72:%.*]] = getelementptr inbounds i32, i32* [[TMP64]], i32 8 ; CHECK-NEXT: [[TMP73:%.*]] = bitcast i32* [[TMP72]] to <4 x i32>* -; CHECK-NEXT: [[WIDE_MASKED_LOAD5:%.*]] = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* [[TMP73]], i32 4, <4 x i1> [[TMP55]], <4 x i32> undef) +; CHECK-NEXT: [[WIDE_MASKED_LOAD8:%.*]] = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* [[TMP73]], i32 4, <4 x i1> [[TMP55]], <4 x i32> undef) ; CHECK-NEXT: [[TMP74:%.*]] = getelementptr inbounds i32, i32* [[TMP64]], i32 12 ; CHECK-NEXT: [[TMP75:%.*]] = bitcast i32* [[TMP74]] to <4 x i32>* -; CHECK-NEXT: [[WIDE_MASKED_LOAD6:%.*]] = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* [[TMP75]], i32 4, <4 x i1> [[TMP63]], <4 x i32> undef) +; CHECK-NEXT: [[WIDE_MASKED_LOAD9:%.*]] = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* [[TMP75]], i32 4, <4 x i1> [[TMP63]], <4 x i32> undef) ; CHECK-NEXT: [[TMP76:%.*]] = xor <4 x i1> [[TMP39]], ; CHECK-NEXT: [[TMP77:%.*]] = xor <4 x i1> [[TMP47]], ; CHECK-NEXT: [[TMP78:%.*]] = xor <4 x i1> [[TMP55]], ; CHECK-NEXT: [[TMP79:%.*]] = xor <4 x i1> [[TMP63]], ; CHECK-NEXT: [[PREDPHI:%.*]] = select <4 x i1> [[TMP39]], <4 x i32> [[WIDE_MASKED_LOAD]], <4 x i32> zeroinitializer -; CHECK-NEXT: [[PREDPHI7:%.*]] = select <4 x i1> [[TMP47]], <4 x i32> [[WIDE_MASKED_LOAD4]], <4 x i32> zeroinitializer -; CHECK-NEXT: [[PREDPHI8:%.*]] = select <4 x i1> [[TMP55]], <4 x i32> [[WIDE_MASKED_LOAD5]], <4 x i32> zeroinitializer -; CHECK-NEXT: [[PREDPHI9:%.*]] = select <4 x i1> [[TMP63]], <4 x i32> [[WIDE_MASKED_LOAD6]], <4 x i32> zeroinitializer +; CHECK-NEXT: [[PREDPHI10:%.*]] = select <4 x i1> [[TMP47]], <4 x i32> [[WIDE_MASKED_LOAD7]], <4 x i32> zeroinitializer +; CHECK-NEXT: [[PREDPHI11:%.*]] = select <4 x i1> [[TMP55]], <4 x i32> [[WIDE_MASKED_LOAD8]], <4 x i32> zeroinitializer +; CHECK-NEXT: [[PREDPHI12:%.*]] = select <4 x i1> [[TMP63]], <4 x i32> [[WIDE_MASKED_LOAD9]], <4 x i32> zeroinitializer ; CHECK-NEXT: [[TMP80]] = add <4 x i32> [[VEC_PHI]], [[PREDPHI]] -; CHECK-NEXT: [[TMP81]] = add <4 x i32> [[VEC_PHI1]], [[PREDPHI7]] -; CHECK-NEXT: [[TMP82]] = add <4 x i32> [[VEC_PHI2]], [[PREDPHI8]] -; CHECK-NEXT: [[TMP83]] = add <4 x i32> [[VEC_PHI3]], [[PREDPHI9]] +; CHECK-NEXT: [[TMP81]] = add <4 x i32> [[VEC_PHI4]], [[PREDPHI10]] +; CHECK-NEXT: [[TMP82]] = add <4 x i32> [[VEC_PHI5]], [[PREDPHI11]] +; CHECK-NEXT: [[TMP83]] = add <4 x i32> [[VEC_PHI6]], [[PREDPHI12]] ; CHECK-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], 16 ; CHECK-NEXT: [[TMP84:%.*]] = icmp eq i64 [[INDEX_NEXT]], 4096 ; CHECK-NEXT: br i1 [[TMP84]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !16 ; CHECK: middle.block: ; CHECK-NEXT: [[BIN_RDX:%.*]] = add <4 x i32> [[TMP81]], [[TMP80]] -; CHECK-NEXT: [[BIN_RDX10:%.*]] = add <4 x i32> [[TMP82]], [[BIN_RDX]] -; CHECK-NEXT: [[BIN_RDX11:%.*]] = add <4 x i32> [[TMP83]], [[BIN_RDX10]] -; CHECK-NEXT: [[RDX_SHUF:%.*]] = shufflevector <4 x i32> [[BIN_RDX11]], <4 x i32> undef, <4 x i32> -; CHECK-NEXT: [[BIN_RDX12:%.*]] = add <4 x i32> [[BIN_RDX11]], [[RDX_SHUF]] -; CHECK-NEXT: [[RDX_SHUF13:%.*]] = shufflevector <4 x i32> [[BIN_RDX12]], <4 x i32> undef, <4 x i32> -; CHECK-NEXT: [[BIN_RDX14:%.*]] = add <4 x i32> [[BIN_RDX12]], [[RDX_SHUF13]] -; CHECK-NEXT: [[TMP85:%.*]] = extractelement <4 x i32> [[BIN_RDX14]], i32 0 +; CHECK-NEXT: [[BIN_RDX13:%.*]] = add <4 x i32> [[TMP82]], [[BIN_RDX]] +; CHECK-NEXT: [[BIN_RDX14:%.*]] = add <4 x i32> [[TMP83]], [[BIN_RDX13]] +; CHECK-NEXT: [[RDX_SHUF:%.*]] = shufflevector <4 x i32> [[BIN_RDX14]], <4 x i32> undef, <4 x i32> +; CHECK-NEXT: [[BIN_RDX15:%.*]] = add <4 x i32> [[BIN_RDX14]], [[RDX_SHUF]] +; CHECK-NEXT: [[RDX_SHUF16:%.*]] = shufflevector <4 x i32> [[BIN_RDX15]], <4 x i32> undef, <4 x i32> +; CHECK-NEXT: [[BIN_RDX17:%.*]] = add <4 x i32> [[BIN_RDX15]], [[RDX_SHUF16]] +; CHECK-NEXT: [[TMP85:%.*]] = extractelement <4 x i32> [[BIN_RDX17]], i32 0 ; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 4096, 4096 ; CHECK-NEXT: br i1 [[CMP_N]], label [[LOOP_EXIT:%.*]], label [[SCALAR_PH]] ; CHECK: scalar.ph: @@ -1741,9 +1783,15 @@ define i32 @neg_off_by_one_iteration(i64 %len, i1* %test_base) { ; CHECK: vector.body: ; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ] ; CHECK-NEXT: [[VEC_PHI:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP80:%.*]], [[VECTOR_BODY]] ] -; CHECK-NEXT: [[VEC_PHI1:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP81:%.*]], [[VECTOR_BODY]] ] -; CHECK-NEXT: [[VEC_PHI2:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP82:%.*]], [[VECTOR_BODY]] ] -; CHECK-NEXT: [[VEC_PHI3:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP83:%.*]], [[VECTOR_BODY]] ] +; CHECK-NEXT: [[VEC_PHI4:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP81:%.*]], [[VECTOR_BODY]] ] +; CHECK-NEXT: [[VEC_PHI5:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP82:%.*]], [[VECTOR_BODY]] ] +; CHECK-NEXT: [[VEC_PHI6:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP83:%.*]], [[VECTOR_BODY]] ] +; 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:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], +; CHECK-NEXT: [[INDUCTION1:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], +; CHECK-NEXT: [[INDUCTION2:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], +; CHECK-NEXT: [[INDUCTION3:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], ; CHECK-NEXT: [[TMP0:%.*]] = add i64 [[INDEX]], 0 ; CHECK-NEXT: [[TMP1:%.*]] = add i64 [[INDEX]], 1 ; CHECK-NEXT: [[TMP2:%.*]] = add i64 [[INDEX]], 2 @@ -1817,37 +1865,37 @@ define i32 @neg_off_by_one_iteration(i64 %len, i1* %test_base) { ; CHECK-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* [[TMP69]], i32 4, <4 x i1> [[TMP39]], <4 x i32> undef) ; CHECK-NEXT: [[TMP70:%.*]] = getelementptr inbounds i32, i32* [[TMP64]], i32 4 ; CHECK-NEXT: [[TMP71:%.*]] = bitcast i32* [[TMP70]] to <4 x i32>* -; CHECK-NEXT: [[WIDE_MASKED_LOAD4:%.*]] = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* [[TMP71]], i32 4, <4 x i1> [[TMP47]], <4 x i32> undef) +; CHECK-NEXT: [[WIDE_MASKED_LOAD7:%.*]] = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* [[TMP71]], i32 4, <4 x i1> [[TMP47]], <4 x i32> undef) ; CHECK-NEXT: [[TMP72:%.*]] = getelementptr inbounds i32, i32* [[TMP64]], i32 8 ; CHECK-NEXT: [[TMP73:%.*]] = bitcast i32* [[TMP72]] to <4 x i32>* -; CHECK-NEXT: [[WIDE_MASKED_LOAD5:%.*]] = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* [[TMP73]], i32 4, <4 x i1> [[TMP55]], <4 x i32> undef) +; CHECK-NEXT: [[WIDE_MASKED_LOAD8:%.*]] = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* [[TMP73]], i32 4, <4 x i1> [[TMP55]], <4 x i32> undef) ; CHECK-NEXT: [[TMP74:%.*]] = getelementptr inbounds i32, i32* [[TMP64]], i32 12 ; CHECK-NEXT: [[TMP75:%.*]] = bitcast i32* [[TMP74]] to <4 x i32>* -; CHECK-NEXT: [[WIDE_MASKED_LOAD6:%.*]] = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* [[TMP75]], i32 4, <4 x i1> [[TMP63]], <4 x i32> undef) +; CHECK-NEXT: [[WIDE_MASKED_LOAD9:%.*]] = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* [[TMP75]], i32 4, <4 x i1> [[TMP63]], <4 x i32> undef) ; CHECK-NEXT: [[TMP76:%.*]] = xor <4 x i1> [[TMP39]], ; CHECK-NEXT: [[TMP77:%.*]] = xor <4 x i1> [[TMP47]], ; CHECK-NEXT: [[TMP78:%.*]] = xor <4 x i1> [[TMP55]], ; CHECK-NEXT: [[TMP79:%.*]] = xor <4 x i1> [[TMP63]], ; CHECK-NEXT: [[PREDPHI:%.*]] = select <4 x i1> [[TMP39]], <4 x i32> [[WIDE_MASKED_LOAD]], <4 x i32> zeroinitializer -; CHECK-NEXT: [[PREDPHI7:%.*]] = select <4 x i1> [[TMP47]], <4 x i32> [[WIDE_MASKED_LOAD4]], <4 x i32> zeroinitializer -; CHECK-NEXT: [[PREDPHI8:%.*]] = select <4 x i1> [[TMP55]], <4 x i32> [[WIDE_MASKED_LOAD5]], <4 x i32> zeroinitializer -; CHECK-NEXT: [[PREDPHI9:%.*]] = select <4 x i1> [[TMP63]], <4 x i32> [[WIDE_MASKED_LOAD6]], <4 x i32> zeroinitializer +; CHECK-NEXT: [[PREDPHI10:%.*]] = select <4 x i1> [[TMP47]], <4 x i32> [[WIDE_MASKED_LOAD7]], <4 x i32> zeroinitializer +; CHECK-NEXT: [[PREDPHI11:%.*]] = select <4 x i1> [[TMP55]], <4 x i32> [[WIDE_MASKED_LOAD8]], <4 x i32> zeroinitializer +; CHECK-NEXT: [[PREDPHI12:%.*]] = select <4 x i1> [[TMP63]], <4 x i32> [[WIDE_MASKED_LOAD9]], <4 x i32> zeroinitializer ; CHECK-NEXT: [[TMP80]] = add <4 x i32> [[VEC_PHI]], [[PREDPHI]] -; CHECK-NEXT: [[TMP81]] = add <4 x i32> [[VEC_PHI1]], [[PREDPHI7]] -; CHECK-NEXT: [[TMP82]] = add <4 x i32> [[VEC_PHI2]], [[PREDPHI8]] -; CHECK-NEXT: [[TMP83]] = add <4 x i32> [[VEC_PHI3]], [[PREDPHI9]] +; CHECK-NEXT: [[TMP81]] = add <4 x i32> [[VEC_PHI4]], [[PREDPHI10]] +; CHECK-NEXT: [[TMP82]] = add <4 x i32> [[VEC_PHI5]], [[PREDPHI11]] +; CHECK-NEXT: [[TMP83]] = add <4 x i32> [[VEC_PHI6]], [[PREDPHI12]] ; CHECK-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], 16 ; CHECK-NEXT: [[TMP84:%.*]] = icmp eq i64 [[INDEX_NEXT]], 4096 ; CHECK-NEXT: br i1 [[TMP84]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !18 ; CHECK: middle.block: ; CHECK-NEXT: [[BIN_RDX:%.*]] = add <4 x i32> [[TMP81]], [[TMP80]] -; CHECK-NEXT: [[BIN_RDX10:%.*]] = add <4 x i32> [[TMP82]], [[BIN_RDX]] -; CHECK-NEXT: [[BIN_RDX11:%.*]] = add <4 x i32> [[TMP83]], [[BIN_RDX10]] -; CHECK-NEXT: [[RDX_SHUF:%.*]] = shufflevector <4 x i32> [[BIN_RDX11]], <4 x i32> undef, <4 x i32> -; CHECK-NEXT: [[BIN_RDX12:%.*]] = add <4 x i32> [[BIN_RDX11]], [[RDX_SHUF]] -; CHECK-NEXT: [[RDX_SHUF13:%.*]] = shufflevector <4 x i32> [[BIN_RDX12]], <4 x i32> undef, <4 x i32> -; CHECK-NEXT: [[BIN_RDX14:%.*]] = add <4 x i32> [[BIN_RDX12]], [[RDX_SHUF13]] -; CHECK-NEXT: [[TMP85:%.*]] = extractelement <4 x i32> [[BIN_RDX14]], i32 0 +; CHECK-NEXT: [[BIN_RDX13:%.*]] = add <4 x i32> [[TMP82]], [[BIN_RDX]] +; CHECK-NEXT: [[BIN_RDX14:%.*]] = add <4 x i32> [[TMP83]], [[BIN_RDX13]] +; CHECK-NEXT: [[RDX_SHUF:%.*]] = shufflevector <4 x i32> [[BIN_RDX14]], <4 x i32> undef, <4 x i32> +; CHECK-NEXT: [[BIN_RDX15:%.*]] = add <4 x i32> [[BIN_RDX14]], [[RDX_SHUF]] +; CHECK-NEXT: [[RDX_SHUF16:%.*]] = shufflevector <4 x i32> [[BIN_RDX15]], <4 x i32> undef, <4 x i32> +; CHECK-NEXT: [[BIN_RDX17:%.*]] = add <4 x i32> [[BIN_RDX15]], [[RDX_SHUF16]] +; CHECK-NEXT: [[TMP85:%.*]] = extractelement <4 x i32> [[BIN_RDX17]], i32 0 ; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 4096, 4096 ; CHECK-NEXT: br i1 [[CMP_N]], label [[LOOP_EXIT:%.*]], label [[SCALAR_PH]] ; CHECK: scalar.ph: @@ -1912,9 +1960,15 @@ define i32 @neg_off_by_one_byte(i64 %len, i1* %test_base) { ; CHECK: vector.body: ; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ] ; CHECK-NEXT: [[VEC_PHI:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP80:%.*]], [[VECTOR_BODY]] ] -; CHECK-NEXT: [[VEC_PHI1:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP81:%.*]], [[VECTOR_BODY]] ] -; CHECK-NEXT: [[VEC_PHI2:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP82:%.*]], [[VECTOR_BODY]] ] -; CHECK-NEXT: [[VEC_PHI3:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP83:%.*]], [[VECTOR_BODY]] ] +; CHECK-NEXT: [[VEC_PHI4:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP81:%.*]], [[VECTOR_BODY]] ] +; CHECK-NEXT: [[VEC_PHI5:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP82:%.*]], [[VECTOR_BODY]] ] +; CHECK-NEXT: [[VEC_PHI6:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP83:%.*]], [[VECTOR_BODY]] ] +; 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:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], +; CHECK-NEXT: [[INDUCTION1:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], +; CHECK-NEXT: [[INDUCTION2:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], +; CHECK-NEXT: [[INDUCTION3:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], ; CHECK-NEXT: [[TMP0:%.*]] = add i64 [[INDEX]], 0 ; CHECK-NEXT: [[TMP1:%.*]] = add i64 [[INDEX]], 1 ; CHECK-NEXT: [[TMP2:%.*]] = add i64 [[INDEX]], 2 @@ -1988,37 +2042,37 @@ define i32 @neg_off_by_one_byte(i64 %len, i1* %test_base) { ; CHECK-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* [[TMP69]], i32 4, <4 x i1> [[TMP39]], <4 x i32> undef) ; CHECK-NEXT: [[TMP70:%.*]] = getelementptr inbounds i32, i32* [[TMP64]], i32 4 ; CHECK-NEXT: [[TMP71:%.*]] = bitcast i32* [[TMP70]] to <4 x i32>* -; CHECK-NEXT: [[WIDE_MASKED_LOAD4:%.*]] = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* [[TMP71]], i32 4, <4 x i1> [[TMP47]], <4 x i32> undef) +; CHECK-NEXT: [[WIDE_MASKED_LOAD7:%.*]] = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* [[TMP71]], i32 4, <4 x i1> [[TMP47]], <4 x i32> undef) ; CHECK-NEXT: [[TMP72:%.*]] = getelementptr inbounds i32, i32* [[TMP64]], i32 8 ; CHECK-NEXT: [[TMP73:%.*]] = bitcast i32* [[TMP72]] to <4 x i32>* -; CHECK-NEXT: [[WIDE_MASKED_LOAD5:%.*]] = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* [[TMP73]], i32 4, <4 x i1> [[TMP55]], <4 x i32> undef) +; CHECK-NEXT: [[WIDE_MASKED_LOAD8:%.*]] = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* [[TMP73]], i32 4, <4 x i1> [[TMP55]], <4 x i32> undef) ; CHECK-NEXT: [[TMP74:%.*]] = getelementptr inbounds i32, i32* [[TMP64]], i32 12 ; CHECK-NEXT: [[TMP75:%.*]] = bitcast i32* [[TMP74]] to <4 x i32>* -; CHECK-NEXT: [[WIDE_MASKED_LOAD6:%.*]] = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* [[TMP75]], i32 4, <4 x i1> [[TMP63]], <4 x i32> undef) +; CHECK-NEXT: [[WIDE_MASKED_LOAD9:%.*]] = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* [[TMP75]], i32 4, <4 x i1> [[TMP63]], <4 x i32> undef) ; CHECK-NEXT: [[TMP76:%.*]] = xor <4 x i1> [[TMP39]], ; CHECK-NEXT: [[TMP77:%.*]] = xor <4 x i1> [[TMP47]], ; CHECK-NEXT: [[TMP78:%.*]] = xor <4 x i1> [[TMP55]], ; CHECK-NEXT: [[TMP79:%.*]] = xor <4 x i1> [[TMP63]], ; CHECK-NEXT: [[PREDPHI:%.*]] = select <4 x i1> [[TMP39]], <4 x i32> [[WIDE_MASKED_LOAD]], <4 x i32> zeroinitializer -; CHECK-NEXT: [[PREDPHI7:%.*]] = select <4 x i1> [[TMP47]], <4 x i32> [[WIDE_MASKED_LOAD4]], <4 x i32> zeroinitializer -; CHECK-NEXT: [[PREDPHI8:%.*]] = select <4 x i1> [[TMP55]], <4 x i32> [[WIDE_MASKED_LOAD5]], <4 x i32> zeroinitializer -; CHECK-NEXT: [[PREDPHI9:%.*]] = select <4 x i1> [[TMP63]], <4 x i32> [[WIDE_MASKED_LOAD6]], <4 x i32> zeroinitializer +; CHECK-NEXT: [[PREDPHI10:%.*]] = select <4 x i1> [[TMP47]], <4 x i32> [[WIDE_MASKED_LOAD7]], <4 x i32> zeroinitializer +; CHECK-NEXT: [[PREDPHI11:%.*]] = select <4 x i1> [[TMP55]], <4 x i32> [[WIDE_MASKED_LOAD8]], <4 x i32> zeroinitializer +; CHECK-NEXT: [[PREDPHI12:%.*]] = select <4 x i1> [[TMP63]], <4 x i32> [[WIDE_MASKED_LOAD9]], <4 x i32> zeroinitializer ; CHECK-NEXT: [[TMP80]] = add <4 x i32> [[VEC_PHI]], [[PREDPHI]] -; CHECK-NEXT: [[TMP81]] = add <4 x i32> [[VEC_PHI1]], [[PREDPHI7]] -; CHECK-NEXT: [[TMP82]] = add <4 x i32> [[VEC_PHI2]], [[PREDPHI8]] -; CHECK-NEXT: [[TMP83]] = add <4 x i32> [[VEC_PHI3]], [[PREDPHI9]] +; CHECK-NEXT: [[TMP81]] = add <4 x i32> [[VEC_PHI4]], [[PREDPHI10]] +; CHECK-NEXT: [[TMP82]] = add <4 x i32> [[VEC_PHI5]], [[PREDPHI11]] +; CHECK-NEXT: [[TMP83]] = add <4 x i32> [[VEC_PHI6]], [[PREDPHI12]] ; CHECK-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], 16 ; CHECK-NEXT: [[TMP84:%.*]] = icmp eq i64 [[INDEX_NEXT]], 4096 ; CHECK-NEXT: br i1 [[TMP84]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !20 ; CHECK: middle.block: ; CHECK-NEXT: [[BIN_RDX:%.*]] = add <4 x i32> [[TMP81]], [[TMP80]] -; CHECK-NEXT: [[BIN_RDX10:%.*]] = add <4 x i32> [[TMP82]], [[BIN_RDX]] -; CHECK-NEXT: [[BIN_RDX11:%.*]] = add <4 x i32> [[TMP83]], [[BIN_RDX10]] -; CHECK-NEXT: [[RDX_SHUF:%.*]] = shufflevector <4 x i32> [[BIN_RDX11]], <4 x i32> undef, <4 x i32> -; CHECK-NEXT: [[BIN_RDX12:%.*]] = add <4 x i32> [[BIN_RDX11]], [[RDX_SHUF]] -; CHECK-NEXT: [[RDX_SHUF13:%.*]] = shufflevector <4 x i32> [[BIN_RDX12]], <4 x i32> undef, <4 x i32> -; CHECK-NEXT: [[BIN_RDX14:%.*]] = add <4 x i32> [[BIN_RDX12]], [[RDX_SHUF13]] -; CHECK-NEXT: [[TMP85:%.*]] = extractelement <4 x i32> [[BIN_RDX14]], i32 0 +; CHECK-NEXT: [[BIN_RDX13:%.*]] = add <4 x i32> [[TMP82]], [[BIN_RDX]] +; CHECK-NEXT: [[BIN_RDX14:%.*]] = add <4 x i32> [[TMP83]], [[BIN_RDX13]] +; CHECK-NEXT: [[RDX_SHUF:%.*]] = shufflevector <4 x i32> [[BIN_RDX14]], <4 x i32> undef, <4 x i32> +; CHECK-NEXT: [[BIN_RDX15:%.*]] = add <4 x i32> [[BIN_RDX14]], [[RDX_SHUF]] +; CHECK-NEXT: [[RDX_SHUF16:%.*]] = shufflevector <4 x i32> [[BIN_RDX15]], <4 x i32> undef, <4 x i32> +; CHECK-NEXT: [[BIN_RDX17:%.*]] = add <4 x i32> [[BIN_RDX15]], [[RDX_SHUF16]] +; CHECK-NEXT: [[TMP85:%.*]] = extractelement <4 x i32> [[BIN_RDX17]], i32 0 ; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 4096, 4096 ; CHECK-NEXT: br i1 [[CMP_N]], label [[LOOP_EXIT:%.*]], label [[SCALAR_PH]] ; CHECK: scalar.ph: diff --git a/llvm/test/Transforms/LoopVectorize/X86/masked_load_store.ll b/llvm/test/Transforms/LoopVectorize/X86/masked_load_store.ll index 8a4d46c0fa6b..4c0424f6044f 100644 --- a/llvm/test/Transforms/LoopVectorize/X86/masked_load_store.ll +++ b/llvm/test/Transforms/LoopVectorize/X86/masked_load_store.ll @@ -44,6 +44,9 @@ define void @foo1(i32* nocapture %A, i32* nocapture readonly %B, i32* nocapture ; AVX1-NEXT: br label [[VECTOR_BODY:%.*]] ; AVX1: vector.body: ; AVX1-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ] +; AVX1-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <8 x i64> undef, i64 [[INDEX]], i32 0 +; AVX1-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <8 x i64> [[BROADCAST_SPLATINSERT]], <8 x i64> undef, <8 x i32> zeroinitializer +; AVX1-NEXT: [[INDUCTION:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], ; AVX1-NEXT: [[TMP0:%.*]] = add i64 [[INDEX]], 0 ; AVX1-NEXT: [[TMP1:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER]], i64 [[TMP0]] ; AVX1-NEXT: [[TMP2:%.*]] = getelementptr inbounds i32, i32* [[TMP1]], i32 0 @@ -114,6 +117,12 @@ define void @foo1(i32* nocapture %A, i32* nocapture readonly %B, i32* nocapture ; AVX2-NEXT: br label [[VECTOR_BODY:%.*]] ; AVX2: vector.body: ; AVX2-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ] +; AVX2-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <8 x i64> undef, i64 [[INDEX]], i32 0 +; AVX2-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <8 x i64> [[BROADCAST_SPLATINSERT]], <8 x i64> undef, <8 x i32> zeroinitializer +; AVX2-NEXT: [[INDUCTION:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], +; AVX2-NEXT: [[INDUCTION12:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], +; AVX2-NEXT: [[INDUCTION13:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], +; AVX2-NEXT: [[INDUCTION14:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], ; AVX2-NEXT: [[TMP0:%.*]] = add i64 [[INDEX]], 0 ; AVX2-NEXT: [[TMP1:%.*]] = add i64 [[INDEX]], 8 ; AVX2-NEXT: [[TMP2:%.*]] = add i64 [[INDEX]], 16 @@ -127,17 +136,17 @@ define void @foo1(i32* nocapture %A, i32* nocapture readonly %B, i32* nocapture ; AVX2-NEXT: [[WIDE_LOAD:%.*]] = load <8 x i32>, <8 x i32>* [[TMP9]], align 4, !alias.scope !0 ; AVX2-NEXT: [[TMP10:%.*]] = getelementptr inbounds i32, i32* [[TMP4]], i32 8 ; AVX2-NEXT: [[TMP11:%.*]] = bitcast i32* [[TMP10]] to <8 x i32>* -; AVX2-NEXT: [[WIDE_LOAD12:%.*]] = load <8 x i32>, <8 x i32>* [[TMP11]], align 4, !alias.scope !0 +; AVX2-NEXT: [[WIDE_LOAD15:%.*]] = load <8 x i32>, <8 x i32>* [[TMP11]], align 4, !alias.scope !0 ; AVX2-NEXT: [[TMP12:%.*]] = getelementptr inbounds i32, i32* [[TMP4]], i32 16 ; AVX2-NEXT: [[TMP13:%.*]] = bitcast i32* [[TMP12]] to <8 x i32>* -; AVX2-NEXT: [[WIDE_LOAD13:%.*]] = load <8 x i32>, <8 x i32>* [[TMP13]], align 4, !alias.scope !0 +; AVX2-NEXT: [[WIDE_LOAD16:%.*]] = load <8 x i32>, <8 x i32>* [[TMP13]], align 4, !alias.scope !0 ; AVX2-NEXT: [[TMP14:%.*]] = getelementptr inbounds i32, i32* [[TMP4]], i32 24 ; AVX2-NEXT: [[TMP15:%.*]] = bitcast i32* [[TMP14]] to <8 x i32>* -; AVX2-NEXT: [[WIDE_LOAD14:%.*]] = load <8 x i32>, <8 x i32>* [[TMP15]], align 4, !alias.scope !0 +; AVX2-NEXT: [[WIDE_LOAD17:%.*]] = load <8 x i32>, <8 x i32>* [[TMP15]], align 4, !alias.scope !0 ; AVX2-NEXT: [[TMP16:%.*]] = icmp slt <8 x i32> [[WIDE_LOAD]], -; AVX2-NEXT: [[TMP17:%.*]] = icmp slt <8 x i32> [[WIDE_LOAD12]], -; AVX2-NEXT: [[TMP18:%.*]] = icmp slt <8 x i32> [[WIDE_LOAD13]], -; AVX2-NEXT: [[TMP19:%.*]] = icmp slt <8 x i32> [[WIDE_LOAD14]], +; AVX2-NEXT: [[TMP17:%.*]] = icmp slt <8 x i32> [[WIDE_LOAD15]], +; AVX2-NEXT: [[TMP18:%.*]] = icmp slt <8 x i32> [[WIDE_LOAD16]], +; AVX2-NEXT: [[TMP19:%.*]] = icmp slt <8 x i32> [[WIDE_LOAD17]], ; AVX2-NEXT: [[TMP20:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[TMP0]] ; AVX2-NEXT: [[TMP21:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[TMP1]] ; AVX2-NEXT: [[TMP22:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[TMP2]] @@ -147,17 +156,17 @@ define void @foo1(i32* nocapture %A, i32* nocapture readonly %B, i32* nocapture ; AVX2-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <8 x i32> @llvm.masked.load.v8i32.p0v8i32(<8 x i32>* [[TMP25]], i32 4, <8 x i1> [[TMP16]], <8 x i32> undef), !alias.scope !3 ; AVX2-NEXT: [[TMP26:%.*]] = getelementptr inbounds i32, i32* [[TMP20]], i32 8 ; AVX2-NEXT: [[TMP27:%.*]] = bitcast i32* [[TMP26]] to <8 x i32>* -; AVX2-NEXT: [[WIDE_MASKED_LOAD15:%.*]] = call <8 x i32> @llvm.masked.load.v8i32.p0v8i32(<8 x i32>* [[TMP27]], i32 4, <8 x i1> [[TMP17]], <8 x i32> undef), !alias.scope !3 +; AVX2-NEXT: [[WIDE_MASKED_LOAD18:%.*]] = call <8 x i32> @llvm.masked.load.v8i32.p0v8i32(<8 x i32>* [[TMP27]], i32 4, <8 x i1> [[TMP17]], <8 x i32> undef), !alias.scope !3 ; AVX2-NEXT: [[TMP28:%.*]] = getelementptr inbounds i32, i32* [[TMP20]], i32 16 ; AVX2-NEXT: [[TMP29:%.*]] = bitcast i32* [[TMP28]] to <8 x i32>* -; AVX2-NEXT: [[WIDE_MASKED_LOAD16:%.*]] = call <8 x i32> @llvm.masked.load.v8i32.p0v8i32(<8 x i32>* [[TMP29]], i32 4, <8 x i1> [[TMP18]], <8 x i32> undef), !alias.scope !3 +; AVX2-NEXT: [[WIDE_MASKED_LOAD19:%.*]] = call <8 x i32> @llvm.masked.load.v8i32.p0v8i32(<8 x i32>* [[TMP29]], i32 4, <8 x i1> [[TMP18]], <8 x i32> undef), !alias.scope !3 ; AVX2-NEXT: [[TMP30:%.*]] = getelementptr inbounds i32, i32* [[TMP20]], i32 24 ; AVX2-NEXT: [[TMP31:%.*]] = bitcast i32* [[TMP30]] to <8 x i32>* -; AVX2-NEXT: [[WIDE_MASKED_LOAD17:%.*]] = call <8 x i32> @llvm.masked.load.v8i32.p0v8i32(<8 x i32>* [[TMP31]], i32 4, <8 x i1> [[TMP19]], <8 x i32> undef), !alias.scope !3 +; AVX2-NEXT: [[WIDE_MASKED_LOAD20:%.*]] = call <8 x i32> @llvm.masked.load.v8i32.p0v8i32(<8 x i32>* [[TMP31]], i32 4, <8 x i1> [[TMP19]], <8 x i32> undef), !alias.scope !3 ; AVX2-NEXT: [[TMP32:%.*]] = add nsw <8 x i32> [[WIDE_MASKED_LOAD]], [[WIDE_LOAD]] -; AVX2-NEXT: [[TMP33:%.*]] = add nsw <8 x i32> [[WIDE_MASKED_LOAD15]], [[WIDE_LOAD12]] -; AVX2-NEXT: [[TMP34:%.*]] = add nsw <8 x i32> [[WIDE_MASKED_LOAD16]], [[WIDE_LOAD13]] -; AVX2-NEXT: [[TMP35:%.*]] = add nsw <8 x i32> [[WIDE_MASKED_LOAD17]], [[WIDE_LOAD14]] +; AVX2-NEXT: [[TMP33:%.*]] = add nsw <8 x i32> [[WIDE_MASKED_LOAD18]], [[WIDE_LOAD15]] +; AVX2-NEXT: [[TMP34:%.*]] = add nsw <8 x i32> [[WIDE_MASKED_LOAD19]], [[WIDE_LOAD16]] +; AVX2-NEXT: [[TMP35:%.*]] = add nsw <8 x i32> [[WIDE_MASKED_LOAD20]], [[WIDE_LOAD17]] ; AVX2-NEXT: [[TMP36:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP0]] ; AVX2-NEXT: [[TMP37:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP1]] ; AVX2-NEXT: [[TMP38:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP2]] @@ -229,6 +238,12 @@ define void @foo1(i32* nocapture %A, i32* nocapture readonly %B, i32* nocapture ; AVX512-NEXT: br label [[VECTOR_BODY:%.*]] ; AVX512: vector.body: ; AVX512-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ] +; AVX512-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <16 x i64> undef, i64 [[INDEX]], i32 0 +; AVX512-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <16 x i64> [[BROADCAST_SPLATINSERT]], <16 x i64> undef, <16 x i32> zeroinitializer +; AVX512-NEXT: [[INDUCTION:%.*]] = add <16 x i64> [[BROADCAST_SPLAT]], +; AVX512-NEXT: [[INDUCTION12:%.*]] = add <16 x i64> [[BROADCAST_SPLAT]], +; AVX512-NEXT: [[INDUCTION13:%.*]] = add <16 x i64> [[BROADCAST_SPLAT]], +; AVX512-NEXT: [[INDUCTION14:%.*]] = add <16 x i64> [[BROADCAST_SPLAT]], ; AVX512-NEXT: [[TMP0:%.*]] = add i64 [[INDEX]], 0 ; AVX512-NEXT: [[TMP1:%.*]] = add i64 [[INDEX]], 16 ; AVX512-NEXT: [[TMP2:%.*]] = add i64 [[INDEX]], 32 @@ -242,17 +257,17 @@ define void @foo1(i32* nocapture %A, i32* nocapture readonly %B, i32* nocapture ; AVX512-NEXT: [[WIDE_LOAD:%.*]] = load <16 x i32>, <16 x i32>* [[TMP9]], align 4, !alias.scope !0 ; AVX512-NEXT: [[TMP10:%.*]] = getelementptr inbounds i32, i32* [[TMP4]], i32 16 ; AVX512-NEXT: [[TMP11:%.*]] = bitcast i32* [[TMP10]] to <16 x i32>* -; AVX512-NEXT: [[WIDE_LOAD12:%.*]] = load <16 x i32>, <16 x i32>* [[TMP11]], align 4, !alias.scope !0 +; AVX512-NEXT: [[WIDE_LOAD15:%.*]] = load <16 x i32>, <16 x i32>* [[TMP11]], align 4, !alias.scope !0 ; AVX512-NEXT: [[TMP12:%.*]] = getelementptr inbounds i32, i32* [[TMP4]], i32 32 ; AVX512-NEXT: [[TMP13:%.*]] = bitcast i32* [[TMP12]] to <16 x i32>* -; AVX512-NEXT: [[WIDE_LOAD13:%.*]] = load <16 x i32>, <16 x i32>* [[TMP13]], align 4, !alias.scope !0 +; AVX512-NEXT: [[WIDE_LOAD16:%.*]] = load <16 x i32>, <16 x i32>* [[TMP13]], align 4, !alias.scope !0 ; AVX512-NEXT: [[TMP14:%.*]] = getelementptr inbounds i32, i32* [[TMP4]], i32 48 ; AVX512-NEXT: [[TMP15:%.*]] = bitcast i32* [[TMP14]] to <16 x i32>* -; AVX512-NEXT: [[WIDE_LOAD14:%.*]] = load <16 x i32>, <16 x i32>* [[TMP15]], align 4, !alias.scope !0 +; AVX512-NEXT: [[WIDE_LOAD17:%.*]] = load <16 x i32>, <16 x i32>* [[TMP15]], align 4, !alias.scope !0 ; AVX512-NEXT: [[TMP16:%.*]] = icmp slt <16 x i32> [[WIDE_LOAD]], -; AVX512-NEXT: [[TMP17:%.*]] = icmp slt <16 x i32> [[WIDE_LOAD12]], -; AVX512-NEXT: [[TMP18:%.*]] = icmp slt <16 x i32> [[WIDE_LOAD13]], -; AVX512-NEXT: [[TMP19:%.*]] = icmp slt <16 x i32> [[WIDE_LOAD14]], +; AVX512-NEXT: [[TMP17:%.*]] = icmp slt <16 x i32> [[WIDE_LOAD15]], +; AVX512-NEXT: [[TMP18:%.*]] = icmp slt <16 x i32> [[WIDE_LOAD16]], +; AVX512-NEXT: [[TMP19:%.*]] = icmp slt <16 x i32> [[WIDE_LOAD17]], ; AVX512-NEXT: [[TMP20:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[TMP0]] ; AVX512-NEXT: [[TMP21:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[TMP1]] ; AVX512-NEXT: [[TMP22:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[TMP2]] @@ -262,17 +277,17 @@ define void @foo1(i32* nocapture %A, i32* nocapture readonly %B, i32* nocapture ; AVX512-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <16 x i32> @llvm.masked.load.v16i32.p0v16i32(<16 x i32>* [[TMP25]], i32 4, <16 x i1> [[TMP16]], <16 x i32> undef), !alias.scope !3 ; AVX512-NEXT: [[TMP26:%.*]] = getelementptr inbounds i32, i32* [[TMP20]], i32 16 ; AVX512-NEXT: [[TMP27:%.*]] = bitcast i32* [[TMP26]] to <16 x i32>* -; AVX512-NEXT: [[WIDE_MASKED_LOAD15:%.*]] = call <16 x i32> @llvm.masked.load.v16i32.p0v16i32(<16 x i32>* [[TMP27]], i32 4, <16 x i1> [[TMP17]], <16 x i32> undef), !alias.scope !3 +; AVX512-NEXT: [[WIDE_MASKED_LOAD18:%.*]] = call <16 x i32> @llvm.masked.load.v16i32.p0v16i32(<16 x i32>* [[TMP27]], i32 4, <16 x i1> [[TMP17]], <16 x i32> undef), !alias.scope !3 ; AVX512-NEXT: [[TMP28:%.*]] = getelementptr inbounds i32, i32* [[TMP20]], i32 32 ; AVX512-NEXT: [[TMP29:%.*]] = bitcast i32* [[TMP28]] to <16 x i32>* -; AVX512-NEXT: [[WIDE_MASKED_LOAD16:%.*]] = call <16 x i32> @llvm.masked.load.v16i32.p0v16i32(<16 x i32>* [[TMP29]], i32 4, <16 x i1> [[TMP18]], <16 x i32> undef), !alias.scope !3 +; AVX512-NEXT: [[WIDE_MASKED_LOAD19:%.*]] = call <16 x i32> @llvm.masked.load.v16i32.p0v16i32(<16 x i32>* [[TMP29]], i32 4, <16 x i1> [[TMP18]], <16 x i32> undef), !alias.scope !3 ; AVX512-NEXT: [[TMP30:%.*]] = getelementptr inbounds i32, i32* [[TMP20]], i32 48 ; AVX512-NEXT: [[TMP31:%.*]] = bitcast i32* [[TMP30]] to <16 x i32>* -; AVX512-NEXT: [[WIDE_MASKED_LOAD17:%.*]] = call <16 x i32> @llvm.masked.load.v16i32.p0v16i32(<16 x i32>* [[TMP31]], i32 4, <16 x i1> [[TMP19]], <16 x i32> undef), !alias.scope !3 +; AVX512-NEXT: [[WIDE_MASKED_LOAD20:%.*]] = call <16 x i32> @llvm.masked.load.v16i32.p0v16i32(<16 x i32>* [[TMP31]], i32 4, <16 x i1> [[TMP19]], <16 x i32> undef), !alias.scope !3 ; AVX512-NEXT: [[TMP32:%.*]] = add nsw <16 x i32> [[WIDE_MASKED_LOAD]], [[WIDE_LOAD]] -; AVX512-NEXT: [[TMP33:%.*]] = add nsw <16 x i32> [[WIDE_MASKED_LOAD15]], [[WIDE_LOAD12]] -; AVX512-NEXT: [[TMP34:%.*]] = add nsw <16 x i32> [[WIDE_MASKED_LOAD16]], [[WIDE_LOAD13]] -; AVX512-NEXT: [[TMP35:%.*]] = add nsw <16 x i32> [[WIDE_MASKED_LOAD17]], [[WIDE_LOAD14]] +; AVX512-NEXT: [[TMP33:%.*]] = add nsw <16 x i32> [[WIDE_MASKED_LOAD18]], [[WIDE_LOAD15]] +; AVX512-NEXT: [[TMP34:%.*]] = add nsw <16 x i32> [[WIDE_MASKED_LOAD19]], [[WIDE_LOAD16]] +; AVX512-NEXT: [[TMP35:%.*]] = add nsw <16 x i32> [[WIDE_MASKED_LOAD20]], [[WIDE_LOAD17]] ; AVX512-NEXT: [[TMP36:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP0]] ; AVX512-NEXT: [[TMP37:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP1]] ; AVX512-NEXT: [[TMP38:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP2]] @@ -374,6 +389,9 @@ define void @foo1_addrspace1(i32 addrspace(1)* nocapture %A, i32 addrspace(1)* n ; AVX1-NEXT: br label [[VECTOR_BODY:%.*]] ; AVX1: vector.body: ; AVX1-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ] +; AVX1-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <8 x i64> undef, i64 [[INDEX]], i32 0 +; AVX1-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <8 x i64> [[BROADCAST_SPLATINSERT]], <8 x i64> undef, <8 x i32> zeroinitializer +; AVX1-NEXT: [[INDUCTION:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], ; AVX1-NEXT: [[TMP0:%.*]] = add i64 [[INDEX]], 0 ; AVX1-NEXT: [[TMP1:%.*]] = getelementptr inbounds i32, i32 addrspace(1)* [[TRIGGER]], i64 [[TMP0]] ; AVX1-NEXT: [[TMP2:%.*]] = getelementptr inbounds i32, i32 addrspace(1)* [[TMP1]], i32 0 @@ -444,6 +462,12 @@ define void @foo1_addrspace1(i32 addrspace(1)* nocapture %A, i32 addrspace(1)* n ; AVX2-NEXT: br label [[VECTOR_BODY:%.*]] ; AVX2: vector.body: ; AVX2-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ] +; AVX2-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <8 x i64> undef, i64 [[INDEX]], i32 0 +; AVX2-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <8 x i64> [[BROADCAST_SPLATINSERT]], <8 x i64> undef, <8 x i32> zeroinitializer +; AVX2-NEXT: [[INDUCTION:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], +; AVX2-NEXT: [[INDUCTION12:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], +; AVX2-NEXT: [[INDUCTION13:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], +; AVX2-NEXT: [[INDUCTION14:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], ; AVX2-NEXT: [[TMP0:%.*]] = add i64 [[INDEX]], 0 ; AVX2-NEXT: [[TMP1:%.*]] = add i64 [[INDEX]], 8 ; AVX2-NEXT: [[TMP2:%.*]] = add i64 [[INDEX]], 16 @@ -457,17 +481,17 @@ define void @foo1_addrspace1(i32 addrspace(1)* nocapture %A, i32 addrspace(1)* n ; AVX2-NEXT: [[WIDE_LOAD:%.*]] = load <8 x i32>, <8 x i32> addrspace(1)* [[TMP9]], align 4, !alias.scope !11 ; AVX2-NEXT: [[TMP10:%.*]] = getelementptr inbounds i32, i32 addrspace(1)* [[TMP4]], i32 8 ; AVX2-NEXT: [[TMP11:%.*]] = bitcast i32 addrspace(1)* [[TMP10]] to <8 x i32> addrspace(1)* -; AVX2-NEXT: [[WIDE_LOAD12:%.*]] = load <8 x i32>, <8 x i32> addrspace(1)* [[TMP11]], align 4, !alias.scope !11 +; AVX2-NEXT: [[WIDE_LOAD15:%.*]] = load <8 x i32>, <8 x i32> addrspace(1)* [[TMP11]], align 4, !alias.scope !11 ; AVX2-NEXT: [[TMP12:%.*]] = getelementptr inbounds i32, i32 addrspace(1)* [[TMP4]], i32 16 ; AVX2-NEXT: [[TMP13:%.*]] = bitcast i32 addrspace(1)* [[TMP12]] to <8 x i32> addrspace(1)* -; AVX2-NEXT: [[WIDE_LOAD13:%.*]] = load <8 x i32>, <8 x i32> addrspace(1)* [[TMP13]], align 4, !alias.scope !11 +; AVX2-NEXT: [[WIDE_LOAD16:%.*]] = load <8 x i32>, <8 x i32> addrspace(1)* [[TMP13]], align 4, !alias.scope !11 ; AVX2-NEXT: [[TMP14:%.*]] = getelementptr inbounds i32, i32 addrspace(1)* [[TMP4]], i32 24 ; AVX2-NEXT: [[TMP15:%.*]] = bitcast i32 addrspace(1)* [[TMP14]] to <8 x i32> addrspace(1)* -; AVX2-NEXT: [[WIDE_LOAD14:%.*]] = load <8 x i32>, <8 x i32> addrspace(1)* [[TMP15]], align 4, !alias.scope !11 +; AVX2-NEXT: [[WIDE_LOAD17:%.*]] = load <8 x i32>, <8 x i32> addrspace(1)* [[TMP15]], align 4, !alias.scope !11 ; AVX2-NEXT: [[TMP16:%.*]] = icmp slt <8 x i32> [[WIDE_LOAD]], -; AVX2-NEXT: [[TMP17:%.*]] = icmp slt <8 x i32> [[WIDE_LOAD12]], -; AVX2-NEXT: [[TMP18:%.*]] = icmp slt <8 x i32> [[WIDE_LOAD13]], -; AVX2-NEXT: [[TMP19:%.*]] = icmp slt <8 x i32> [[WIDE_LOAD14]], +; AVX2-NEXT: [[TMP17:%.*]] = icmp slt <8 x i32> [[WIDE_LOAD15]], +; AVX2-NEXT: [[TMP18:%.*]] = icmp slt <8 x i32> [[WIDE_LOAD16]], +; AVX2-NEXT: [[TMP19:%.*]] = icmp slt <8 x i32> [[WIDE_LOAD17]], ; AVX2-NEXT: [[TMP20:%.*]] = getelementptr inbounds i32, i32 addrspace(1)* [[B]], i64 [[TMP0]] ; AVX2-NEXT: [[TMP21:%.*]] = getelementptr inbounds i32, i32 addrspace(1)* [[B]], i64 [[TMP1]] ; AVX2-NEXT: [[TMP22:%.*]] = getelementptr inbounds i32, i32 addrspace(1)* [[B]], i64 [[TMP2]] @@ -477,17 +501,17 @@ define void @foo1_addrspace1(i32 addrspace(1)* nocapture %A, i32 addrspace(1)* n ; AVX2-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <8 x i32> @llvm.masked.load.v8i32.p1v8i32(<8 x i32> addrspace(1)* [[TMP25]], i32 4, <8 x i1> [[TMP16]], <8 x i32> undef), !alias.scope !14 ; AVX2-NEXT: [[TMP26:%.*]] = getelementptr inbounds i32, i32 addrspace(1)* [[TMP20]], i32 8 ; AVX2-NEXT: [[TMP27:%.*]] = bitcast i32 addrspace(1)* [[TMP26]] to <8 x i32> addrspace(1)* -; AVX2-NEXT: [[WIDE_MASKED_LOAD15:%.*]] = call <8 x i32> @llvm.masked.load.v8i32.p1v8i32(<8 x i32> addrspace(1)* [[TMP27]], i32 4, <8 x i1> [[TMP17]], <8 x i32> undef), !alias.scope !14 +; AVX2-NEXT: [[WIDE_MASKED_LOAD18:%.*]] = call <8 x i32> @llvm.masked.load.v8i32.p1v8i32(<8 x i32> addrspace(1)* [[TMP27]], i32 4, <8 x i1> [[TMP17]], <8 x i32> undef), !alias.scope !14 ; AVX2-NEXT: [[TMP28:%.*]] = getelementptr inbounds i32, i32 addrspace(1)* [[TMP20]], i32 16 ; AVX2-NEXT: [[TMP29:%.*]] = bitcast i32 addrspace(1)* [[TMP28]] to <8 x i32> addrspace(1)* -; AVX2-NEXT: [[WIDE_MASKED_LOAD16:%.*]] = call <8 x i32> @llvm.masked.load.v8i32.p1v8i32(<8 x i32> addrspace(1)* [[TMP29]], i32 4, <8 x i1> [[TMP18]], <8 x i32> undef), !alias.scope !14 +; AVX2-NEXT: [[WIDE_MASKED_LOAD19:%.*]] = call <8 x i32> @llvm.masked.load.v8i32.p1v8i32(<8 x i32> addrspace(1)* [[TMP29]], i32 4, <8 x i1> [[TMP18]], <8 x i32> undef), !alias.scope !14 ; AVX2-NEXT: [[TMP30:%.*]] = getelementptr inbounds i32, i32 addrspace(1)* [[TMP20]], i32 24 ; AVX2-NEXT: [[TMP31:%.*]] = bitcast i32 addrspace(1)* [[TMP30]] to <8 x i32> addrspace(1)* -; AVX2-NEXT: [[WIDE_MASKED_LOAD17:%.*]] = call <8 x i32> @llvm.masked.load.v8i32.p1v8i32(<8 x i32> addrspace(1)* [[TMP31]], i32 4, <8 x i1> [[TMP19]], <8 x i32> undef), !alias.scope !14 +; AVX2-NEXT: [[WIDE_MASKED_LOAD20:%.*]] = call <8 x i32> @llvm.masked.load.v8i32.p1v8i32(<8 x i32> addrspace(1)* [[TMP31]], i32 4, <8 x i1> [[TMP19]], <8 x i32> undef), !alias.scope !14 ; AVX2-NEXT: [[TMP32:%.*]] = add nsw <8 x i32> [[WIDE_MASKED_LOAD]], [[WIDE_LOAD]] -; AVX2-NEXT: [[TMP33:%.*]] = add nsw <8 x i32> [[WIDE_MASKED_LOAD15]], [[WIDE_LOAD12]] -; AVX2-NEXT: [[TMP34:%.*]] = add nsw <8 x i32> [[WIDE_MASKED_LOAD16]], [[WIDE_LOAD13]] -; AVX2-NEXT: [[TMP35:%.*]] = add nsw <8 x i32> [[WIDE_MASKED_LOAD17]], [[WIDE_LOAD14]] +; AVX2-NEXT: [[TMP33:%.*]] = add nsw <8 x i32> [[WIDE_MASKED_LOAD18]], [[WIDE_LOAD15]] +; AVX2-NEXT: [[TMP34:%.*]] = add nsw <8 x i32> [[WIDE_MASKED_LOAD19]], [[WIDE_LOAD16]] +; AVX2-NEXT: [[TMP35:%.*]] = add nsw <8 x i32> [[WIDE_MASKED_LOAD20]], [[WIDE_LOAD17]] ; AVX2-NEXT: [[TMP36:%.*]] = getelementptr inbounds i32, i32 addrspace(1)* [[A]], i64 [[TMP0]] ; AVX2-NEXT: [[TMP37:%.*]] = getelementptr inbounds i32, i32 addrspace(1)* [[A]], i64 [[TMP1]] ; AVX2-NEXT: [[TMP38:%.*]] = getelementptr inbounds i32, i32 addrspace(1)* [[A]], i64 [[TMP2]] @@ -559,6 +583,12 @@ define void @foo1_addrspace1(i32 addrspace(1)* nocapture %A, i32 addrspace(1)* n ; AVX512-NEXT: br label [[VECTOR_BODY:%.*]] ; AVX512: vector.body: ; AVX512-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ] +; AVX512-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <16 x i64> undef, i64 [[INDEX]], i32 0 +; AVX512-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <16 x i64> [[BROADCAST_SPLATINSERT]], <16 x i64> undef, <16 x i32> zeroinitializer +; AVX512-NEXT: [[INDUCTION:%.*]] = add <16 x i64> [[BROADCAST_SPLAT]], +; AVX512-NEXT: [[INDUCTION12:%.*]] = add <16 x i64> [[BROADCAST_SPLAT]], +; AVX512-NEXT: [[INDUCTION13:%.*]] = add <16 x i64> [[BROADCAST_SPLAT]], +; AVX512-NEXT: [[INDUCTION14:%.*]] = add <16 x i64> [[BROADCAST_SPLAT]], ; AVX512-NEXT: [[TMP0:%.*]] = add i64 [[INDEX]], 0 ; AVX512-NEXT: [[TMP1:%.*]] = add i64 [[INDEX]], 16 ; AVX512-NEXT: [[TMP2:%.*]] = add i64 [[INDEX]], 32 @@ -572,17 +602,17 @@ define void @foo1_addrspace1(i32 addrspace(1)* nocapture %A, i32 addrspace(1)* n ; AVX512-NEXT: [[WIDE_LOAD:%.*]] = load <16 x i32>, <16 x i32> addrspace(1)* [[TMP9]], align 4, !alias.scope !11 ; AVX512-NEXT: [[TMP10:%.*]] = getelementptr inbounds i32, i32 addrspace(1)* [[TMP4]], i32 16 ; AVX512-NEXT: [[TMP11:%.*]] = bitcast i32 addrspace(1)* [[TMP10]] to <16 x i32> addrspace(1)* -; AVX512-NEXT: [[WIDE_LOAD12:%.*]] = load <16 x i32>, <16 x i32> addrspace(1)* [[TMP11]], align 4, !alias.scope !11 +; AVX512-NEXT: [[WIDE_LOAD15:%.*]] = load <16 x i32>, <16 x i32> addrspace(1)* [[TMP11]], align 4, !alias.scope !11 ; AVX512-NEXT: [[TMP12:%.*]] = getelementptr inbounds i32, i32 addrspace(1)* [[TMP4]], i32 32 ; AVX512-NEXT: [[TMP13:%.*]] = bitcast i32 addrspace(1)* [[TMP12]] to <16 x i32> addrspace(1)* -; AVX512-NEXT: [[WIDE_LOAD13:%.*]] = load <16 x i32>, <16 x i32> addrspace(1)* [[TMP13]], align 4, !alias.scope !11 +; AVX512-NEXT: [[WIDE_LOAD16:%.*]] = load <16 x i32>, <16 x i32> addrspace(1)* [[TMP13]], align 4, !alias.scope !11 ; AVX512-NEXT: [[TMP14:%.*]] = getelementptr inbounds i32, i32 addrspace(1)* [[TMP4]], i32 48 ; AVX512-NEXT: [[TMP15:%.*]] = bitcast i32 addrspace(1)* [[TMP14]] to <16 x i32> addrspace(1)* -; AVX512-NEXT: [[WIDE_LOAD14:%.*]] = load <16 x i32>, <16 x i32> addrspace(1)* [[TMP15]], align 4, !alias.scope !11 +; AVX512-NEXT: [[WIDE_LOAD17:%.*]] = load <16 x i32>, <16 x i32> addrspace(1)* [[TMP15]], align 4, !alias.scope !11 ; AVX512-NEXT: [[TMP16:%.*]] = icmp slt <16 x i32> [[WIDE_LOAD]], -; AVX512-NEXT: [[TMP17:%.*]] = icmp slt <16 x i32> [[WIDE_LOAD12]], -; AVX512-NEXT: [[TMP18:%.*]] = icmp slt <16 x i32> [[WIDE_LOAD13]], -; AVX512-NEXT: [[TMP19:%.*]] = icmp slt <16 x i32> [[WIDE_LOAD14]], +; AVX512-NEXT: [[TMP17:%.*]] = icmp slt <16 x i32> [[WIDE_LOAD15]], +; AVX512-NEXT: [[TMP18:%.*]] = icmp slt <16 x i32> [[WIDE_LOAD16]], +; AVX512-NEXT: [[TMP19:%.*]] = icmp slt <16 x i32> [[WIDE_LOAD17]], ; AVX512-NEXT: [[TMP20:%.*]] = getelementptr inbounds i32, i32 addrspace(1)* [[B]], i64 [[TMP0]] ; AVX512-NEXT: [[TMP21:%.*]] = getelementptr inbounds i32, i32 addrspace(1)* [[B]], i64 [[TMP1]] ; AVX512-NEXT: [[TMP22:%.*]] = getelementptr inbounds i32, i32 addrspace(1)* [[B]], i64 [[TMP2]] @@ -592,17 +622,17 @@ define void @foo1_addrspace1(i32 addrspace(1)* nocapture %A, i32 addrspace(1)* n ; AVX512-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <16 x i32> @llvm.masked.load.v16i32.p1v16i32(<16 x i32> addrspace(1)* [[TMP25]], i32 4, <16 x i1> [[TMP16]], <16 x i32> undef), !alias.scope !14 ; AVX512-NEXT: [[TMP26:%.*]] = getelementptr inbounds i32, i32 addrspace(1)* [[TMP20]], i32 16 ; AVX512-NEXT: [[TMP27:%.*]] = bitcast i32 addrspace(1)* [[TMP26]] to <16 x i32> addrspace(1)* -; AVX512-NEXT: [[WIDE_MASKED_LOAD15:%.*]] = call <16 x i32> @llvm.masked.load.v16i32.p1v16i32(<16 x i32> addrspace(1)* [[TMP27]], i32 4, <16 x i1> [[TMP17]], <16 x i32> undef), !alias.scope !14 +; AVX512-NEXT: [[WIDE_MASKED_LOAD18:%.*]] = call <16 x i32> @llvm.masked.load.v16i32.p1v16i32(<16 x i32> addrspace(1)* [[TMP27]], i32 4, <16 x i1> [[TMP17]], <16 x i32> undef), !alias.scope !14 ; AVX512-NEXT: [[TMP28:%.*]] = getelementptr inbounds i32, i32 addrspace(1)* [[TMP20]], i32 32 ; AVX512-NEXT: [[TMP29:%.*]] = bitcast i32 addrspace(1)* [[TMP28]] to <16 x i32> addrspace(1)* -; AVX512-NEXT: [[WIDE_MASKED_LOAD16:%.*]] = call <16 x i32> @llvm.masked.load.v16i32.p1v16i32(<16 x i32> addrspace(1)* [[TMP29]], i32 4, <16 x i1> [[TMP18]], <16 x i32> undef), !alias.scope !14 +; AVX512-NEXT: [[WIDE_MASKED_LOAD19:%.*]] = call <16 x i32> @llvm.masked.load.v16i32.p1v16i32(<16 x i32> addrspace(1)* [[TMP29]], i32 4, <16 x i1> [[TMP18]], <16 x i32> undef), !alias.scope !14 ; AVX512-NEXT: [[TMP30:%.*]] = getelementptr inbounds i32, i32 addrspace(1)* [[TMP20]], i32 48 ; AVX512-NEXT: [[TMP31:%.*]] = bitcast i32 addrspace(1)* [[TMP30]] to <16 x i32> addrspace(1)* -; AVX512-NEXT: [[WIDE_MASKED_LOAD17:%.*]] = call <16 x i32> @llvm.masked.load.v16i32.p1v16i32(<16 x i32> addrspace(1)* [[TMP31]], i32 4, <16 x i1> [[TMP19]], <16 x i32> undef), !alias.scope !14 +; AVX512-NEXT: [[WIDE_MASKED_LOAD20:%.*]] = call <16 x i32> @llvm.masked.load.v16i32.p1v16i32(<16 x i32> addrspace(1)* [[TMP31]], i32 4, <16 x i1> [[TMP19]], <16 x i32> undef), !alias.scope !14 ; AVX512-NEXT: [[TMP32:%.*]] = add nsw <16 x i32> [[WIDE_MASKED_LOAD]], [[WIDE_LOAD]] -; AVX512-NEXT: [[TMP33:%.*]] = add nsw <16 x i32> [[WIDE_MASKED_LOAD15]], [[WIDE_LOAD12]] -; AVX512-NEXT: [[TMP34:%.*]] = add nsw <16 x i32> [[WIDE_MASKED_LOAD16]], [[WIDE_LOAD13]] -; AVX512-NEXT: [[TMP35:%.*]] = add nsw <16 x i32> [[WIDE_MASKED_LOAD17]], [[WIDE_LOAD14]] +; AVX512-NEXT: [[TMP33:%.*]] = add nsw <16 x i32> [[WIDE_MASKED_LOAD18]], [[WIDE_LOAD15]] +; AVX512-NEXT: [[TMP34:%.*]] = add nsw <16 x i32> [[WIDE_MASKED_LOAD19]], [[WIDE_LOAD16]] +; AVX512-NEXT: [[TMP35:%.*]] = add nsw <16 x i32> [[WIDE_MASKED_LOAD20]], [[WIDE_LOAD17]] ; AVX512-NEXT: [[TMP36:%.*]] = getelementptr inbounds i32, i32 addrspace(1)* [[A]], i64 [[TMP0]] ; AVX512-NEXT: [[TMP37:%.*]] = getelementptr inbounds i32, i32 addrspace(1)* [[A]], i64 [[TMP1]] ; AVX512-NEXT: [[TMP38:%.*]] = getelementptr inbounds i32, i32 addrspace(1)* [[A]], i64 [[TMP2]] @@ -713,6 +743,9 @@ define void @foo2(float* nocapture %A, float* nocapture readonly %B, i32* nocapt ; AVX1-NEXT: br label [[VECTOR_BODY:%.*]] ; AVX1: vector.body: ; AVX1-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ] +; AVX1-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <8 x i64> undef, i64 [[INDEX]], i32 0 +; AVX1-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <8 x i64> [[BROADCAST_SPLATINSERT]], <8 x i64> undef, <8 x i32> zeroinitializer +; AVX1-NEXT: [[INDUCTION:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], ; AVX1-NEXT: [[TMP0:%.*]] = add i64 [[INDEX]], 0 ; AVX1-NEXT: [[TMP1:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER]], i64 [[TMP0]] ; AVX1-NEXT: [[TMP2:%.*]] = getelementptr inbounds i32, i32* [[TMP1]], i32 0 @@ -785,6 +818,12 @@ define void @foo2(float* nocapture %A, float* nocapture readonly %B, i32* nocapt ; AVX2-NEXT: br label [[VECTOR_BODY:%.*]] ; AVX2: vector.body: ; AVX2-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ] +; AVX2-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <8 x i64> undef, i64 [[INDEX]], i32 0 +; AVX2-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <8 x i64> [[BROADCAST_SPLATINSERT]], <8 x i64> undef, <8 x i32> zeroinitializer +; AVX2-NEXT: [[INDUCTION:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], +; AVX2-NEXT: [[INDUCTION12:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], +; AVX2-NEXT: [[INDUCTION13:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], +; AVX2-NEXT: [[INDUCTION14:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], ; AVX2-NEXT: [[TMP0:%.*]] = add i64 [[INDEX]], 0 ; AVX2-NEXT: [[TMP1:%.*]] = add i64 [[INDEX]], 8 ; AVX2-NEXT: [[TMP2:%.*]] = add i64 [[INDEX]], 16 @@ -798,17 +837,17 @@ define void @foo2(float* nocapture %A, float* nocapture readonly %B, i32* nocapt ; AVX2-NEXT: [[WIDE_LOAD:%.*]] = load <8 x i32>, <8 x i32>* [[TMP9]], align 4, !alias.scope !21 ; AVX2-NEXT: [[TMP10:%.*]] = getelementptr inbounds i32, i32* [[TMP4]], i32 8 ; AVX2-NEXT: [[TMP11:%.*]] = bitcast i32* [[TMP10]] to <8 x i32>* -; AVX2-NEXT: [[WIDE_LOAD12:%.*]] = load <8 x i32>, <8 x i32>* [[TMP11]], align 4, !alias.scope !21 +; AVX2-NEXT: [[WIDE_LOAD15:%.*]] = load <8 x i32>, <8 x i32>* [[TMP11]], align 4, !alias.scope !21 ; AVX2-NEXT: [[TMP12:%.*]] = getelementptr inbounds i32, i32* [[TMP4]], i32 16 ; AVX2-NEXT: [[TMP13:%.*]] = bitcast i32* [[TMP12]] to <8 x i32>* -; AVX2-NEXT: [[WIDE_LOAD13:%.*]] = load <8 x i32>, <8 x i32>* [[TMP13]], align 4, !alias.scope !21 +; AVX2-NEXT: [[WIDE_LOAD16:%.*]] = load <8 x i32>, <8 x i32>* [[TMP13]], align 4, !alias.scope !21 ; AVX2-NEXT: [[TMP14:%.*]] = getelementptr inbounds i32, i32* [[TMP4]], i32 24 ; AVX2-NEXT: [[TMP15:%.*]] = bitcast i32* [[TMP14]] to <8 x i32>* -; AVX2-NEXT: [[WIDE_LOAD14:%.*]] = load <8 x i32>, <8 x i32>* [[TMP15]], align 4, !alias.scope !21 +; AVX2-NEXT: [[WIDE_LOAD17:%.*]] = load <8 x i32>, <8 x i32>* [[TMP15]], align 4, !alias.scope !21 ; AVX2-NEXT: [[TMP16:%.*]] = icmp slt <8 x i32> [[WIDE_LOAD]], -; AVX2-NEXT: [[TMP17:%.*]] = icmp slt <8 x i32> [[WIDE_LOAD12]], -; AVX2-NEXT: [[TMP18:%.*]] = icmp slt <8 x i32> [[WIDE_LOAD13]], -; AVX2-NEXT: [[TMP19:%.*]] = icmp slt <8 x i32> [[WIDE_LOAD14]], +; AVX2-NEXT: [[TMP17:%.*]] = icmp slt <8 x i32> [[WIDE_LOAD15]], +; AVX2-NEXT: [[TMP18:%.*]] = icmp slt <8 x i32> [[WIDE_LOAD16]], +; AVX2-NEXT: [[TMP19:%.*]] = icmp slt <8 x i32> [[WIDE_LOAD17]], ; AVX2-NEXT: [[TMP20:%.*]] = getelementptr inbounds float, float* [[B]], i64 [[TMP0]] ; AVX2-NEXT: [[TMP21:%.*]] = getelementptr inbounds float, float* [[B]], i64 [[TMP1]] ; AVX2-NEXT: [[TMP22:%.*]] = getelementptr inbounds float, float* [[B]], i64 [[TMP2]] @@ -818,21 +857,21 @@ define void @foo2(float* nocapture %A, float* nocapture readonly %B, i32* nocapt ; AVX2-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <8 x float> @llvm.masked.load.v8f32.p0v8f32(<8 x float>* [[TMP25]], i32 4, <8 x i1> [[TMP16]], <8 x float> undef), !alias.scope !24 ; AVX2-NEXT: [[TMP26:%.*]] = getelementptr inbounds float, float* [[TMP20]], i32 8 ; AVX2-NEXT: [[TMP27:%.*]] = bitcast float* [[TMP26]] to <8 x float>* -; AVX2-NEXT: [[WIDE_MASKED_LOAD15:%.*]] = call <8 x float> @llvm.masked.load.v8f32.p0v8f32(<8 x float>* [[TMP27]], i32 4, <8 x i1> [[TMP17]], <8 x float> undef), !alias.scope !24 +; AVX2-NEXT: [[WIDE_MASKED_LOAD18:%.*]] = call <8 x float> @llvm.masked.load.v8f32.p0v8f32(<8 x float>* [[TMP27]], i32 4, <8 x i1> [[TMP17]], <8 x float> undef), !alias.scope !24 ; AVX2-NEXT: [[TMP28:%.*]] = getelementptr inbounds float, float* [[TMP20]], i32 16 ; AVX2-NEXT: [[TMP29:%.*]] = bitcast float* [[TMP28]] to <8 x float>* -; AVX2-NEXT: [[WIDE_MASKED_LOAD16:%.*]] = call <8 x float> @llvm.masked.load.v8f32.p0v8f32(<8 x float>* [[TMP29]], i32 4, <8 x i1> [[TMP18]], <8 x float> undef), !alias.scope !24 +; AVX2-NEXT: [[WIDE_MASKED_LOAD19:%.*]] = call <8 x float> @llvm.masked.load.v8f32.p0v8f32(<8 x float>* [[TMP29]], i32 4, <8 x i1> [[TMP18]], <8 x float> undef), !alias.scope !24 ; AVX2-NEXT: [[TMP30:%.*]] = getelementptr inbounds float, float* [[TMP20]], i32 24 ; AVX2-NEXT: [[TMP31:%.*]] = bitcast float* [[TMP30]] to <8 x float>* -; AVX2-NEXT: [[WIDE_MASKED_LOAD17:%.*]] = call <8 x float> @llvm.masked.load.v8f32.p0v8f32(<8 x float>* [[TMP31]], i32 4, <8 x i1> [[TMP19]], <8 x float> undef), !alias.scope !24 +; AVX2-NEXT: [[WIDE_MASKED_LOAD20:%.*]] = call <8 x float> @llvm.masked.load.v8f32.p0v8f32(<8 x float>* [[TMP31]], i32 4, <8 x i1> [[TMP19]], <8 x float> undef), !alias.scope !24 ; AVX2-NEXT: [[TMP32:%.*]] = sitofp <8 x i32> [[WIDE_LOAD]] to <8 x float> -; AVX2-NEXT: [[TMP33:%.*]] = sitofp <8 x i32> [[WIDE_LOAD12]] to <8 x float> -; AVX2-NEXT: [[TMP34:%.*]] = sitofp <8 x i32> [[WIDE_LOAD13]] to <8 x float> -; AVX2-NEXT: [[TMP35:%.*]] = sitofp <8 x i32> [[WIDE_LOAD14]] to <8 x float> +; AVX2-NEXT: [[TMP33:%.*]] = sitofp <8 x i32> [[WIDE_LOAD15]] to <8 x float> +; AVX2-NEXT: [[TMP34:%.*]] = sitofp <8 x i32> [[WIDE_LOAD16]] to <8 x float> +; AVX2-NEXT: [[TMP35:%.*]] = sitofp <8 x i32> [[WIDE_LOAD17]] to <8 x float> ; AVX2-NEXT: [[TMP36:%.*]] = fadd <8 x float> [[WIDE_MASKED_LOAD]], [[TMP32]] -; AVX2-NEXT: [[TMP37:%.*]] = fadd <8 x float> [[WIDE_MASKED_LOAD15]], [[TMP33]] -; AVX2-NEXT: [[TMP38:%.*]] = fadd <8 x float> [[WIDE_MASKED_LOAD16]], [[TMP34]] -; AVX2-NEXT: [[TMP39:%.*]] = fadd <8 x float> [[WIDE_MASKED_LOAD17]], [[TMP35]] +; AVX2-NEXT: [[TMP37:%.*]] = fadd <8 x float> [[WIDE_MASKED_LOAD18]], [[TMP33]] +; AVX2-NEXT: [[TMP38:%.*]] = fadd <8 x float> [[WIDE_MASKED_LOAD19]], [[TMP34]] +; AVX2-NEXT: [[TMP39:%.*]] = fadd <8 x float> [[WIDE_MASKED_LOAD20]], [[TMP35]] ; AVX2-NEXT: [[TMP40:%.*]] = getelementptr inbounds float, float* [[A]], i64 [[TMP0]] ; AVX2-NEXT: [[TMP41:%.*]] = getelementptr inbounds float, float* [[A]], i64 [[TMP1]] ; AVX2-NEXT: [[TMP42:%.*]] = getelementptr inbounds float, float* [[A]], i64 [[TMP2]] @@ -905,6 +944,12 @@ define void @foo2(float* nocapture %A, float* nocapture readonly %B, i32* nocapt ; AVX512-NEXT: br label [[VECTOR_BODY:%.*]] ; AVX512: vector.body: ; AVX512-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ] +; AVX512-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <16 x i64> undef, i64 [[INDEX]], i32 0 +; AVX512-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <16 x i64> [[BROADCAST_SPLATINSERT]], <16 x i64> undef, <16 x i32> zeroinitializer +; AVX512-NEXT: [[INDUCTION:%.*]] = add <16 x i64> [[BROADCAST_SPLAT]], +; AVX512-NEXT: [[INDUCTION12:%.*]] = add <16 x i64> [[BROADCAST_SPLAT]], +; AVX512-NEXT: [[INDUCTION13:%.*]] = add <16 x i64> [[BROADCAST_SPLAT]], +; AVX512-NEXT: [[INDUCTION14:%.*]] = add <16 x i64> [[BROADCAST_SPLAT]], ; AVX512-NEXT: [[TMP0:%.*]] = add i64 [[INDEX]], 0 ; AVX512-NEXT: [[TMP1:%.*]] = add i64 [[INDEX]], 16 ; AVX512-NEXT: [[TMP2:%.*]] = add i64 [[INDEX]], 32 @@ -918,17 +963,17 @@ define void @foo2(float* nocapture %A, float* nocapture readonly %B, i32* nocapt ; AVX512-NEXT: [[WIDE_LOAD:%.*]] = load <16 x i32>, <16 x i32>* [[TMP9]], align 4, !alias.scope !21 ; AVX512-NEXT: [[TMP10:%.*]] = getelementptr inbounds i32, i32* [[TMP4]], i32 16 ; AVX512-NEXT: [[TMP11:%.*]] = bitcast i32* [[TMP10]] to <16 x i32>* -; AVX512-NEXT: [[WIDE_LOAD12:%.*]] = load <16 x i32>, <16 x i32>* [[TMP11]], align 4, !alias.scope !21 +; AVX512-NEXT: [[WIDE_LOAD15:%.*]] = load <16 x i32>, <16 x i32>* [[TMP11]], align 4, !alias.scope !21 ; AVX512-NEXT: [[TMP12:%.*]] = getelementptr inbounds i32, i32* [[TMP4]], i32 32 ; AVX512-NEXT: [[TMP13:%.*]] = bitcast i32* [[TMP12]] to <16 x i32>* -; AVX512-NEXT: [[WIDE_LOAD13:%.*]] = load <16 x i32>, <16 x i32>* [[TMP13]], align 4, !alias.scope !21 +; AVX512-NEXT: [[WIDE_LOAD16:%.*]] = load <16 x i32>, <16 x i32>* [[TMP13]], align 4, !alias.scope !21 ; AVX512-NEXT: [[TMP14:%.*]] = getelementptr inbounds i32, i32* [[TMP4]], i32 48 ; AVX512-NEXT: [[TMP15:%.*]] = bitcast i32* [[TMP14]] to <16 x i32>* -; AVX512-NEXT: [[WIDE_LOAD14:%.*]] = load <16 x i32>, <16 x i32>* [[TMP15]], align 4, !alias.scope !21 +; AVX512-NEXT: [[WIDE_LOAD17:%.*]] = load <16 x i32>, <16 x i32>* [[TMP15]], align 4, !alias.scope !21 ; AVX512-NEXT: [[TMP16:%.*]] = icmp slt <16 x i32> [[WIDE_LOAD]], -; AVX512-NEXT: [[TMP17:%.*]] = icmp slt <16 x i32> [[WIDE_LOAD12]], -; AVX512-NEXT: [[TMP18:%.*]] = icmp slt <16 x i32> [[WIDE_LOAD13]], -; AVX512-NEXT: [[TMP19:%.*]] = icmp slt <16 x i32> [[WIDE_LOAD14]], +; AVX512-NEXT: [[TMP17:%.*]] = icmp slt <16 x i32> [[WIDE_LOAD15]], +; AVX512-NEXT: [[TMP18:%.*]] = icmp slt <16 x i32> [[WIDE_LOAD16]], +; AVX512-NEXT: [[TMP19:%.*]] = icmp slt <16 x i32> [[WIDE_LOAD17]], ; AVX512-NEXT: [[TMP20:%.*]] = getelementptr inbounds float, float* [[B]], i64 [[TMP0]] ; AVX512-NEXT: [[TMP21:%.*]] = getelementptr inbounds float, float* [[B]], i64 [[TMP1]] ; AVX512-NEXT: [[TMP22:%.*]] = getelementptr inbounds float, float* [[B]], i64 [[TMP2]] @@ -938,21 +983,21 @@ define void @foo2(float* nocapture %A, float* nocapture readonly %B, i32* nocapt ; AVX512-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <16 x float> @llvm.masked.load.v16f32.p0v16f32(<16 x float>* [[TMP25]], i32 4, <16 x i1> [[TMP16]], <16 x float> undef), !alias.scope !24 ; AVX512-NEXT: [[TMP26:%.*]] = getelementptr inbounds float, float* [[TMP20]], i32 16 ; AVX512-NEXT: [[TMP27:%.*]] = bitcast float* [[TMP26]] to <16 x float>* -; AVX512-NEXT: [[WIDE_MASKED_LOAD15:%.*]] = call <16 x float> @llvm.masked.load.v16f32.p0v16f32(<16 x float>* [[TMP27]], i32 4, <16 x i1> [[TMP17]], <16 x float> undef), !alias.scope !24 +; AVX512-NEXT: [[WIDE_MASKED_LOAD18:%.*]] = call <16 x float> @llvm.masked.load.v16f32.p0v16f32(<16 x float>* [[TMP27]], i32 4, <16 x i1> [[TMP17]], <16 x float> undef), !alias.scope !24 ; AVX512-NEXT: [[TMP28:%.*]] = getelementptr inbounds float, float* [[TMP20]], i32 32 ; AVX512-NEXT: [[TMP29:%.*]] = bitcast float* [[TMP28]] to <16 x float>* -; AVX512-NEXT: [[WIDE_MASKED_LOAD16:%.*]] = call <16 x float> @llvm.masked.load.v16f32.p0v16f32(<16 x float>* [[TMP29]], i32 4, <16 x i1> [[TMP18]], <16 x float> undef), !alias.scope !24 +; AVX512-NEXT: [[WIDE_MASKED_LOAD19:%.*]] = call <16 x float> @llvm.masked.load.v16f32.p0v16f32(<16 x float>* [[TMP29]], i32 4, <16 x i1> [[TMP18]], <16 x float> undef), !alias.scope !24 ; AVX512-NEXT: [[TMP30:%.*]] = getelementptr inbounds float, float* [[TMP20]], i32 48 ; AVX512-NEXT: [[TMP31:%.*]] = bitcast float* [[TMP30]] to <16 x float>* -; AVX512-NEXT: [[WIDE_MASKED_LOAD17:%.*]] = call <16 x float> @llvm.masked.load.v16f32.p0v16f32(<16 x float>* [[TMP31]], i32 4, <16 x i1> [[TMP19]], <16 x float> undef), !alias.scope !24 +; AVX512-NEXT: [[WIDE_MASKED_LOAD20:%.*]] = call <16 x float> @llvm.masked.load.v16f32.p0v16f32(<16 x float>* [[TMP31]], i32 4, <16 x i1> [[TMP19]], <16 x float> undef), !alias.scope !24 ; AVX512-NEXT: [[TMP32:%.*]] = sitofp <16 x i32> [[WIDE_LOAD]] to <16 x float> -; AVX512-NEXT: [[TMP33:%.*]] = sitofp <16 x i32> [[WIDE_LOAD12]] to <16 x float> -; AVX512-NEXT: [[TMP34:%.*]] = sitofp <16 x i32> [[WIDE_LOAD13]] to <16 x float> -; AVX512-NEXT: [[TMP35:%.*]] = sitofp <16 x i32> [[WIDE_LOAD14]] to <16 x float> +; AVX512-NEXT: [[TMP33:%.*]] = sitofp <16 x i32> [[WIDE_LOAD15]] to <16 x float> +; AVX512-NEXT: [[TMP34:%.*]] = sitofp <16 x i32> [[WIDE_LOAD16]] to <16 x float> +; AVX512-NEXT: [[TMP35:%.*]] = sitofp <16 x i32> [[WIDE_LOAD17]] to <16 x float> ; AVX512-NEXT: [[TMP36:%.*]] = fadd <16 x float> [[WIDE_MASKED_LOAD]], [[TMP32]] -; AVX512-NEXT: [[TMP37:%.*]] = fadd <16 x float> [[WIDE_MASKED_LOAD15]], [[TMP33]] -; AVX512-NEXT: [[TMP38:%.*]] = fadd <16 x float> [[WIDE_MASKED_LOAD16]], [[TMP34]] -; AVX512-NEXT: [[TMP39:%.*]] = fadd <16 x float> [[WIDE_MASKED_LOAD17]], [[TMP35]] +; AVX512-NEXT: [[TMP37:%.*]] = fadd <16 x float> [[WIDE_MASKED_LOAD18]], [[TMP33]] +; AVX512-NEXT: [[TMP38:%.*]] = fadd <16 x float> [[WIDE_MASKED_LOAD19]], [[TMP34]] +; AVX512-NEXT: [[TMP39:%.*]] = fadd <16 x float> [[WIDE_MASKED_LOAD20]], [[TMP35]] ; AVX512-NEXT: [[TMP40:%.*]] = getelementptr inbounds float, float* [[A]], i64 [[TMP0]] ; AVX512-NEXT: [[TMP41:%.*]] = getelementptr inbounds float, float* [[A]], i64 [[TMP1]] ; AVX512-NEXT: [[TMP42:%.*]] = getelementptr inbounds float, float* [[A]], i64 [[TMP2]] @@ -1065,6 +1110,12 @@ define void @foo3(double* nocapture %A, double* nocapture readonly %B, i32* noca ; AVX-NEXT: br label [[VECTOR_BODY:%.*]] ; AVX: vector.body: ; AVX-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ] +; AVX-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i64> undef, i64 [[INDEX]], i32 0 +; AVX-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT]], <4 x i64> undef, <4 x i32> zeroinitializer +; AVX-NEXT: [[INDUCTION:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], +; AVX-NEXT: [[INDUCTION12:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], +; AVX-NEXT: [[INDUCTION13:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], +; AVX-NEXT: [[INDUCTION14:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], ; AVX-NEXT: [[TMP0:%.*]] = add i64 [[INDEX]], 0 ; AVX-NEXT: [[TMP1:%.*]] = add i64 [[INDEX]], 4 ; AVX-NEXT: [[TMP2:%.*]] = add i64 [[INDEX]], 8 @@ -1078,17 +1129,17 @@ define void @foo3(double* nocapture %A, double* nocapture readonly %B, i32* noca ; AVX-NEXT: [[WIDE_LOAD:%.*]] = load <4 x i32>, <4 x i32>* [[TMP9]], align 4, !alias.scope !31 ; AVX-NEXT: [[TMP10:%.*]] = getelementptr inbounds i32, i32* [[TMP4]], i32 4 ; AVX-NEXT: [[TMP11:%.*]] = bitcast i32* [[TMP10]] to <4 x i32>* -; AVX-NEXT: [[WIDE_LOAD12:%.*]] = load <4 x i32>, <4 x i32>* [[TMP11]], align 4, !alias.scope !31 +; AVX-NEXT: [[WIDE_LOAD15:%.*]] = load <4 x i32>, <4 x i32>* [[TMP11]], align 4, !alias.scope !31 ; AVX-NEXT: [[TMP12:%.*]] = getelementptr inbounds i32, i32* [[TMP4]], i32 8 ; AVX-NEXT: [[TMP13:%.*]] = bitcast i32* [[TMP12]] to <4 x i32>* -; AVX-NEXT: [[WIDE_LOAD13:%.*]] = load <4 x i32>, <4 x i32>* [[TMP13]], align 4, !alias.scope !31 +; AVX-NEXT: [[WIDE_LOAD16:%.*]] = load <4 x i32>, <4 x i32>* [[TMP13]], align 4, !alias.scope !31 ; AVX-NEXT: [[TMP14:%.*]] = getelementptr inbounds i32, i32* [[TMP4]], i32 12 ; AVX-NEXT: [[TMP15:%.*]] = bitcast i32* [[TMP14]] to <4 x i32>* -; AVX-NEXT: [[WIDE_LOAD14:%.*]] = load <4 x i32>, <4 x i32>* [[TMP15]], align 4, !alias.scope !31 +; AVX-NEXT: [[WIDE_LOAD17:%.*]] = load <4 x i32>, <4 x i32>* [[TMP15]], align 4, !alias.scope !31 ; AVX-NEXT: [[TMP16:%.*]] = icmp slt <4 x i32> [[WIDE_LOAD]], -; AVX-NEXT: [[TMP17:%.*]] = icmp slt <4 x i32> [[WIDE_LOAD12]], -; AVX-NEXT: [[TMP18:%.*]] = icmp slt <4 x i32> [[WIDE_LOAD13]], -; AVX-NEXT: [[TMP19:%.*]] = icmp slt <4 x i32> [[WIDE_LOAD14]], +; AVX-NEXT: [[TMP17:%.*]] = icmp slt <4 x i32> [[WIDE_LOAD15]], +; AVX-NEXT: [[TMP18:%.*]] = icmp slt <4 x i32> [[WIDE_LOAD16]], +; AVX-NEXT: [[TMP19:%.*]] = icmp slt <4 x i32> [[WIDE_LOAD17]], ; AVX-NEXT: [[TMP20:%.*]] = getelementptr inbounds double, double* [[B]], i64 [[TMP0]] ; AVX-NEXT: [[TMP21:%.*]] = getelementptr inbounds double, double* [[B]], i64 [[TMP1]] ; AVX-NEXT: [[TMP22:%.*]] = getelementptr inbounds double, double* [[B]], i64 [[TMP2]] @@ -1098,21 +1149,21 @@ define void @foo3(double* nocapture %A, double* nocapture readonly %B, i32* noca ; AVX-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <4 x double> @llvm.masked.load.v4f64.p0v4f64(<4 x double>* [[TMP25]], i32 8, <4 x i1> [[TMP16]], <4 x double> undef), !alias.scope !34 ; AVX-NEXT: [[TMP26:%.*]] = getelementptr inbounds double, double* [[TMP20]], i32 4 ; AVX-NEXT: [[TMP27:%.*]] = bitcast double* [[TMP26]] to <4 x double>* -; AVX-NEXT: [[WIDE_MASKED_LOAD15:%.*]] = call <4 x double> @llvm.masked.load.v4f64.p0v4f64(<4 x double>* [[TMP27]], i32 8, <4 x i1> [[TMP17]], <4 x double> undef), !alias.scope !34 +; AVX-NEXT: [[WIDE_MASKED_LOAD18:%.*]] = call <4 x double> @llvm.masked.load.v4f64.p0v4f64(<4 x double>* [[TMP27]], i32 8, <4 x i1> [[TMP17]], <4 x double> undef), !alias.scope !34 ; AVX-NEXT: [[TMP28:%.*]] = getelementptr inbounds double, double* [[TMP20]], i32 8 ; AVX-NEXT: [[TMP29:%.*]] = bitcast double* [[TMP28]] to <4 x double>* -; AVX-NEXT: [[WIDE_MASKED_LOAD16:%.*]] = call <4 x double> @llvm.masked.load.v4f64.p0v4f64(<4 x double>* [[TMP29]], i32 8, <4 x i1> [[TMP18]], <4 x double> undef), !alias.scope !34 +; AVX-NEXT: [[WIDE_MASKED_LOAD19:%.*]] = call <4 x double> @llvm.masked.load.v4f64.p0v4f64(<4 x double>* [[TMP29]], i32 8, <4 x i1> [[TMP18]], <4 x double> undef), !alias.scope !34 ; AVX-NEXT: [[TMP30:%.*]] = getelementptr inbounds double, double* [[TMP20]], i32 12 ; AVX-NEXT: [[TMP31:%.*]] = bitcast double* [[TMP30]] to <4 x double>* -; AVX-NEXT: [[WIDE_MASKED_LOAD17:%.*]] = call <4 x double> @llvm.masked.load.v4f64.p0v4f64(<4 x double>* [[TMP31]], i32 8, <4 x i1> [[TMP19]], <4 x double> undef), !alias.scope !34 +; AVX-NEXT: [[WIDE_MASKED_LOAD20:%.*]] = call <4 x double> @llvm.masked.load.v4f64.p0v4f64(<4 x double>* [[TMP31]], i32 8, <4 x i1> [[TMP19]], <4 x double> undef), !alias.scope !34 ; AVX-NEXT: [[TMP32:%.*]] = sitofp <4 x i32> [[WIDE_LOAD]] to <4 x double> -; AVX-NEXT: [[TMP33:%.*]] = sitofp <4 x i32> [[WIDE_LOAD12]] to <4 x double> -; AVX-NEXT: [[TMP34:%.*]] = sitofp <4 x i32> [[WIDE_LOAD13]] to <4 x double> -; AVX-NEXT: [[TMP35:%.*]] = sitofp <4 x i32> [[WIDE_LOAD14]] to <4 x double> +; AVX-NEXT: [[TMP33:%.*]] = sitofp <4 x i32> [[WIDE_LOAD15]] to <4 x double> +; AVX-NEXT: [[TMP34:%.*]] = sitofp <4 x i32> [[WIDE_LOAD16]] to <4 x double> +; AVX-NEXT: [[TMP35:%.*]] = sitofp <4 x i32> [[WIDE_LOAD17]] to <4 x double> ; AVX-NEXT: [[TMP36:%.*]] = fadd <4 x double> [[WIDE_MASKED_LOAD]], [[TMP32]] -; AVX-NEXT: [[TMP37:%.*]] = fadd <4 x double> [[WIDE_MASKED_LOAD15]], [[TMP33]] -; AVX-NEXT: [[TMP38:%.*]] = fadd <4 x double> [[WIDE_MASKED_LOAD16]], [[TMP34]] -; AVX-NEXT: [[TMP39:%.*]] = fadd <4 x double> [[WIDE_MASKED_LOAD17]], [[TMP35]] +; AVX-NEXT: [[TMP37:%.*]] = fadd <4 x double> [[WIDE_MASKED_LOAD18]], [[TMP33]] +; AVX-NEXT: [[TMP38:%.*]] = fadd <4 x double> [[WIDE_MASKED_LOAD19]], [[TMP34]] +; AVX-NEXT: [[TMP39:%.*]] = fadd <4 x double> [[WIDE_MASKED_LOAD20]], [[TMP35]] ; AVX-NEXT: [[TMP40:%.*]] = getelementptr inbounds double, double* [[A]], i64 [[TMP0]] ; AVX-NEXT: [[TMP41:%.*]] = getelementptr inbounds double, double* [[A]], i64 [[TMP1]] ; AVX-NEXT: [[TMP42:%.*]] = getelementptr inbounds double, double* [[A]], i64 [[TMP2]] @@ -1185,6 +1236,12 @@ define void @foo3(double* nocapture %A, double* nocapture readonly %B, i32* noca ; AVX512-NEXT: br label [[VECTOR_BODY:%.*]] ; AVX512: vector.body: ; AVX512-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ] +; AVX512-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <8 x i64> undef, i64 [[INDEX]], i32 0 +; AVX512-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <8 x i64> [[BROADCAST_SPLATINSERT]], <8 x i64> undef, <8 x i32> zeroinitializer +; AVX512-NEXT: [[INDUCTION:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], +; AVX512-NEXT: [[INDUCTION12:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], +; AVX512-NEXT: [[INDUCTION13:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], +; AVX512-NEXT: [[INDUCTION14:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], ; AVX512-NEXT: [[TMP0:%.*]] = add i64 [[INDEX]], 0 ; AVX512-NEXT: [[TMP1:%.*]] = add i64 [[INDEX]], 8 ; AVX512-NEXT: [[TMP2:%.*]] = add i64 [[INDEX]], 16 @@ -1198,17 +1255,17 @@ define void @foo3(double* nocapture %A, double* nocapture readonly %B, i32* noca ; AVX512-NEXT: [[WIDE_LOAD:%.*]] = load <8 x i32>, <8 x i32>* [[TMP9]], align 4, !alias.scope !31 ; AVX512-NEXT: [[TMP10:%.*]] = getelementptr inbounds i32, i32* [[TMP4]], i32 8 ; AVX512-NEXT: [[TMP11:%.*]] = bitcast i32* [[TMP10]] to <8 x i32>* -; AVX512-NEXT: [[WIDE_LOAD12:%.*]] = load <8 x i32>, <8 x i32>* [[TMP11]], align 4, !alias.scope !31 +; AVX512-NEXT: [[WIDE_LOAD15:%.*]] = load <8 x i32>, <8 x i32>* [[TMP11]], align 4, !alias.scope !31 ; AVX512-NEXT: [[TMP12:%.*]] = getelementptr inbounds i32, i32* [[TMP4]], i32 16 ; AVX512-NEXT: [[TMP13:%.*]] = bitcast i32* [[TMP12]] to <8 x i32>* -; AVX512-NEXT: [[WIDE_LOAD13:%.*]] = load <8 x i32>, <8 x i32>* [[TMP13]], align 4, !alias.scope !31 +; AVX512-NEXT: [[WIDE_LOAD16:%.*]] = load <8 x i32>, <8 x i32>* [[TMP13]], align 4, !alias.scope !31 ; AVX512-NEXT: [[TMP14:%.*]] = getelementptr inbounds i32, i32* [[TMP4]], i32 24 ; AVX512-NEXT: [[TMP15:%.*]] = bitcast i32* [[TMP14]] to <8 x i32>* -; AVX512-NEXT: [[WIDE_LOAD14:%.*]] = load <8 x i32>, <8 x i32>* [[TMP15]], align 4, !alias.scope !31 +; AVX512-NEXT: [[WIDE_LOAD17:%.*]] = load <8 x i32>, <8 x i32>* [[TMP15]], align 4, !alias.scope !31 ; AVX512-NEXT: [[TMP16:%.*]] = icmp slt <8 x i32> [[WIDE_LOAD]], -; AVX512-NEXT: [[TMP17:%.*]] = icmp slt <8 x i32> [[WIDE_LOAD12]], -; AVX512-NEXT: [[TMP18:%.*]] = icmp slt <8 x i32> [[WIDE_LOAD13]], -; AVX512-NEXT: [[TMP19:%.*]] = icmp slt <8 x i32> [[WIDE_LOAD14]], +; AVX512-NEXT: [[TMP17:%.*]] = icmp slt <8 x i32> [[WIDE_LOAD15]], +; AVX512-NEXT: [[TMP18:%.*]] = icmp slt <8 x i32> [[WIDE_LOAD16]], +; AVX512-NEXT: [[TMP19:%.*]] = icmp slt <8 x i32> [[WIDE_LOAD17]], ; AVX512-NEXT: [[TMP20:%.*]] = getelementptr inbounds double, double* [[B]], i64 [[TMP0]] ; AVX512-NEXT: [[TMP21:%.*]] = getelementptr inbounds double, double* [[B]], i64 [[TMP1]] ; AVX512-NEXT: [[TMP22:%.*]] = getelementptr inbounds double, double* [[B]], i64 [[TMP2]] @@ -1218,21 +1275,21 @@ define void @foo3(double* nocapture %A, double* nocapture readonly %B, i32* noca ; AVX512-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <8 x double> @llvm.masked.load.v8f64.p0v8f64(<8 x double>* [[TMP25]], i32 8, <8 x i1> [[TMP16]], <8 x double> undef), !alias.scope !34 ; AVX512-NEXT: [[TMP26:%.*]] = getelementptr inbounds double, double* [[TMP20]], i32 8 ; AVX512-NEXT: [[TMP27:%.*]] = bitcast double* [[TMP26]] to <8 x double>* -; AVX512-NEXT: [[WIDE_MASKED_LOAD15:%.*]] = call <8 x double> @llvm.masked.load.v8f64.p0v8f64(<8 x double>* [[TMP27]], i32 8, <8 x i1> [[TMP17]], <8 x double> undef), !alias.scope !34 +; AVX512-NEXT: [[WIDE_MASKED_LOAD18:%.*]] = call <8 x double> @llvm.masked.load.v8f64.p0v8f64(<8 x double>* [[TMP27]], i32 8, <8 x i1> [[TMP17]], <8 x double> undef), !alias.scope !34 ; AVX512-NEXT: [[TMP28:%.*]] = getelementptr inbounds double, double* [[TMP20]], i32 16 ; AVX512-NEXT: [[TMP29:%.*]] = bitcast double* [[TMP28]] to <8 x double>* -; AVX512-NEXT: [[WIDE_MASKED_LOAD16:%.*]] = call <8 x double> @llvm.masked.load.v8f64.p0v8f64(<8 x double>* [[TMP29]], i32 8, <8 x i1> [[TMP18]], <8 x double> undef), !alias.scope !34 +; AVX512-NEXT: [[WIDE_MASKED_LOAD19:%.*]] = call <8 x double> @llvm.masked.load.v8f64.p0v8f64(<8 x double>* [[TMP29]], i32 8, <8 x i1> [[TMP18]], <8 x double> undef), !alias.scope !34 ; AVX512-NEXT: [[TMP30:%.*]] = getelementptr inbounds double, double* [[TMP20]], i32 24 ; AVX512-NEXT: [[TMP31:%.*]] = bitcast double* [[TMP30]] to <8 x double>* -; AVX512-NEXT: [[WIDE_MASKED_LOAD17:%.*]] = call <8 x double> @llvm.masked.load.v8f64.p0v8f64(<8 x double>* [[TMP31]], i32 8, <8 x i1> [[TMP19]], <8 x double> undef), !alias.scope !34 +; AVX512-NEXT: [[WIDE_MASKED_LOAD20:%.*]] = call <8 x double> @llvm.masked.load.v8f64.p0v8f64(<8 x double>* [[TMP31]], i32 8, <8 x i1> [[TMP19]], <8 x double> undef), !alias.scope !34 ; AVX512-NEXT: [[TMP32:%.*]] = sitofp <8 x i32> [[WIDE_LOAD]] to <8 x double> -; AVX512-NEXT: [[TMP33:%.*]] = sitofp <8 x i32> [[WIDE_LOAD12]] to <8 x double> -; AVX512-NEXT: [[TMP34:%.*]] = sitofp <8 x i32> [[WIDE_LOAD13]] to <8 x double> -; AVX512-NEXT: [[TMP35:%.*]] = sitofp <8 x i32> [[WIDE_LOAD14]] to <8 x double> +; AVX512-NEXT: [[TMP33:%.*]] = sitofp <8 x i32> [[WIDE_LOAD15]] to <8 x double> +; AVX512-NEXT: [[TMP34:%.*]] = sitofp <8 x i32> [[WIDE_LOAD16]] to <8 x double> +; AVX512-NEXT: [[TMP35:%.*]] = sitofp <8 x i32> [[WIDE_LOAD17]] to <8 x double> ; AVX512-NEXT: [[TMP36:%.*]] = fadd <8 x double> [[WIDE_MASKED_LOAD]], [[TMP32]] -; AVX512-NEXT: [[TMP37:%.*]] = fadd <8 x double> [[WIDE_MASKED_LOAD15]], [[TMP33]] -; AVX512-NEXT: [[TMP38:%.*]] = fadd <8 x double> [[WIDE_MASKED_LOAD16]], [[TMP34]] -; AVX512-NEXT: [[TMP39:%.*]] = fadd <8 x double> [[WIDE_MASKED_LOAD17]], [[TMP35]] +; AVX512-NEXT: [[TMP37:%.*]] = fadd <8 x double> [[WIDE_MASKED_LOAD18]], [[TMP33]] +; AVX512-NEXT: [[TMP38:%.*]] = fadd <8 x double> [[WIDE_MASKED_LOAD19]], [[TMP34]] +; AVX512-NEXT: [[TMP39:%.*]] = fadd <8 x double> [[WIDE_MASKED_LOAD20]], [[TMP35]] ; AVX512-NEXT: [[TMP40:%.*]] = getelementptr inbounds double, double* [[A]], i64 [[TMP0]] ; AVX512-NEXT: [[TMP41:%.*]] = getelementptr inbounds double, double* [[A]], i64 [[TMP1]] ; AVX512-NEXT: [[TMP42:%.*]] = getelementptr inbounds double, double* [[A]], i64 [[TMP2]] @@ -1574,6 +1631,12 @@ define void @foo6(double* nocapture readonly %in, double* nocapture %out, i32 %s ; AVX2: vector.body: ; AVX2-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ] ; AVX2-NEXT: [[OFFSET_IDX:%.*]] = sub i64 4095, [[INDEX]] +; AVX2-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i64> undef, i64 [[OFFSET_IDX]], i32 0 +; AVX2-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT]], <4 x i64> undef, <4 x i32> zeroinitializer +; AVX2-NEXT: [[INDUCTION:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], +; AVX2-NEXT: [[INDUCTION12:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], +; AVX2-NEXT: [[INDUCTION13:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], +; AVX2-NEXT: [[INDUCTION14:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], ; AVX2-NEXT: [[TMP0:%.*]] = add i64 [[OFFSET_IDX]], 0 ; AVX2-NEXT: [[TMP1:%.*]] = add i64 [[OFFSET_IDX]], -4 ; AVX2-NEXT: [[TMP2:%.*]] = add i64 [[OFFSET_IDX]], -8 @@ -1590,78 +1653,78 @@ define void @foo6(double* nocapture readonly %in, double* nocapture %out, i32 %s ; AVX2-NEXT: [[TMP11:%.*]] = getelementptr inbounds i32, i32* [[TMP4]], i32 -4 ; AVX2-NEXT: [[TMP12:%.*]] = getelementptr inbounds i32, i32* [[TMP11]], i32 -3 ; AVX2-NEXT: [[TMP13:%.*]] = bitcast i32* [[TMP12]] to <4 x i32>* -; AVX2-NEXT: [[WIDE_LOAD12:%.*]] = load <4 x i32>, <4 x i32>* [[TMP13]], align 4, !alias.scope !41 -; AVX2-NEXT: [[REVERSE13:%.*]] = shufflevector <4 x i32> [[WIDE_LOAD12]], <4 x i32> undef, <4 x i32> +; AVX2-NEXT: [[WIDE_LOAD15:%.*]] = load <4 x i32>, <4 x i32>* [[TMP13]], align 4, !alias.scope !41 +; AVX2-NEXT: [[REVERSE16:%.*]] = shufflevector <4 x i32> [[WIDE_LOAD15]], <4 x i32> undef, <4 x i32> ; AVX2-NEXT: [[TMP14:%.*]] = getelementptr inbounds i32, i32* [[TMP4]], i32 -8 ; AVX2-NEXT: [[TMP15:%.*]] = getelementptr inbounds i32, i32* [[TMP14]], i32 -3 ; AVX2-NEXT: [[TMP16:%.*]] = bitcast i32* [[TMP15]] to <4 x i32>* -; AVX2-NEXT: [[WIDE_LOAD14:%.*]] = load <4 x i32>, <4 x i32>* [[TMP16]], align 4, !alias.scope !41 -; AVX2-NEXT: [[REVERSE15:%.*]] = shufflevector <4 x i32> [[WIDE_LOAD14]], <4 x i32> undef, <4 x i32> +; AVX2-NEXT: [[WIDE_LOAD17:%.*]] = load <4 x i32>, <4 x i32>* [[TMP16]], align 4, !alias.scope !41 +; AVX2-NEXT: [[REVERSE18:%.*]] = shufflevector <4 x i32> [[WIDE_LOAD17]], <4 x i32> undef, <4 x i32> ; AVX2-NEXT: [[TMP17:%.*]] = getelementptr inbounds i32, i32* [[TMP4]], i32 -12 ; AVX2-NEXT: [[TMP18:%.*]] = getelementptr inbounds i32, i32* [[TMP17]], i32 -3 ; AVX2-NEXT: [[TMP19:%.*]] = bitcast i32* [[TMP18]] to <4 x i32>* -; AVX2-NEXT: [[WIDE_LOAD16:%.*]] = load <4 x i32>, <4 x i32>* [[TMP19]], align 4, !alias.scope !41 -; AVX2-NEXT: [[REVERSE17:%.*]] = shufflevector <4 x i32> [[WIDE_LOAD16]], <4 x i32> undef, <4 x i32> +; AVX2-NEXT: [[WIDE_LOAD19:%.*]] = load <4 x i32>, <4 x i32>* [[TMP19]], align 4, !alias.scope !41 +; AVX2-NEXT: [[REVERSE20:%.*]] = shufflevector <4 x i32> [[WIDE_LOAD19]], <4 x i32> undef, <4 x i32> ; AVX2-NEXT: [[TMP20:%.*]] = icmp sgt <4 x i32> [[REVERSE]], zeroinitializer -; AVX2-NEXT: [[TMP21:%.*]] = icmp sgt <4 x i32> [[REVERSE13]], zeroinitializer -; AVX2-NEXT: [[TMP22:%.*]] = icmp sgt <4 x i32> [[REVERSE15]], zeroinitializer -; AVX2-NEXT: [[TMP23:%.*]] = icmp sgt <4 x i32> [[REVERSE17]], zeroinitializer +; AVX2-NEXT: [[TMP21:%.*]] = icmp sgt <4 x i32> [[REVERSE16]], zeroinitializer +; AVX2-NEXT: [[TMP22:%.*]] = icmp sgt <4 x i32> [[REVERSE18]], zeroinitializer +; AVX2-NEXT: [[TMP23:%.*]] = icmp sgt <4 x i32> [[REVERSE20]], zeroinitializer ; AVX2-NEXT: [[TMP24:%.*]] = getelementptr inbounds double, double* [[IN]], i64 [[TMP0]] ; AVX2-NEXT: [[TMP25:%.*]] = getelementptr inbounds double, double* [[IN]], i64 [[TMP1]] ; AVX2-NEXT: [[TMP26:%.*]] = getelementptr inbounds double, double* [[IN]], i64 [[TMP2]] ; AVX2-NEXT: [[TMP27:%.*]] = getelementptr inbounds double, double* [[IN]], i64 [[TMP3]] ; AVX2-NEXT: [[TMP28:%.*]] = getelementptr inbounds double, double* [[TMP24]], i32 0 ; AVX2-NEXT: [[TMP29:%.*]] = getelementptr inbounds double, double* [[TMP28]], i32 -3 -; AVX2-NEXT: [[REVERSE18:%.*]] = shufflevector <4 x i1> [[TMP20]], <4 x i1> undef, <4 x i32> +; AVX2-NEXT: [[REVERSE21:%.*]] = shufflevector <4 x i1> [[TMP20]], <4 x i1> undef, <4 x i32> ; AVX2-NEXT: [[TMP30:%.*]] = bitcast double* [[TMP29]] to <4 x double>* -; AVX2-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <4 x double> @llvm.masked.load.v4f64.p0v4f64(<4 x double>* [[TMP30]], i32 8, <4 x i1> [[REVERSE18]], <4 x double> undef), !alias.scope !44 -; AVX2-NEXT: [[REVERSE19:%.*]] = shufflevector <4 x double> [[WIDE_MASKED_LOAD]], <4 x double> undef, <4 x i32> +; AVX2-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <4 x double> @llvm.masked.load.v4f64.p0v4f64(<4 x double>* [[TMP30]], i32 8, <4 x i1> [[REVERSE21]], <4 x double> undef), !alias.scope !44 +; AVX2-NEXT: [[REVERSE22:%.*]] = shufflevector <4 x double> [[WIDE_MASKED_LOAD]], <4 x double> undef, <4 x i32> ; AVX2-NEXT: [[TMP31:%.*]] = getelementptr inbounds double, double* [[TMP24]], i32 -4 ; AVX2-NEXT: [[TMP32:%.*]] = getelementptr inbounds double, double* [[TMP31]], i32 -3 -; AVX2-NEXT: [[REVERSE20:%.*]] = shufflevector <4 x i1> [[TMP21]], <4 x i1> undef, <4 x i32> +; AVX2-NEXT: [[REVERSE23:%.*]] = shufflevector <4 x i1> [[TMP21]], <4 x i1> undef, <4 x i32> ; AVX2-NEXT: [[TMP33:%.*]] = bitcast double* [[TMP32]] to <4 x double>* -; AVX2-NEXT: [[WIDE_MASKED_LOAD21:%.*]] = call <4 x double> @llvm.masked.load.v4f64.p0v4f64(<4 x double>* [[TMP33]], i32 8, <4 x i1> [[REVERSE20]], <4 x double> undef), !alias.scope !44 -; AVX2-NEXT: [[REVERSE22:%.*]] = shufflevector <4 x double> [[WIDE_MASKED_LOAD21]], <4 x double> undef, <4 x i32> +; AVX2-NEXT: [[WIDE_MASKED_LOAD24:%.*]] = call <4 x double> @llvm.masked.load.v4f64.p0v4f64(<4 x double>* [[TMP33]], i32 8, <4 x i1> [[REVERSE23]], <4 x double> undef), !alias.scope !44 +; AVX2-NEXT: [[REVERSE25:%.*]] = shufflevector <4 x double> [[WIDE_MASKED_LOAD24]], <4 x double> undef, <4 x i32> ; AVX2-NEXT: [[TMP34:%.*]] = getelementptr inbounds double, double* [[TMP24]], i32 -8 ; AVX2-NEXT: [[TMP35:%.*]] = getelementptr inbounds double, double* [[TMP34]], i32 -3 -; AVX2-NEXT: [[REVERSE23:%.*]] = shufflevector <4 x i1> [[TMP22]], <4 x i1> undef, <4 x i32> +; AVX2-NEXT: [[REVERSE26:%.*]] = shufflevector <4 x i1> [[TMP22]], <4 x i1> undef, <4 x i32> ; AVX2-NEXT: [[TMP36:%.*]] = bitcast double* [[TMP35]] to <4 x double>* -; AVX2-NEXT: [[WIDE_MASKED_LOAD24:%.*]] = call <4 x double> @llvm.masked.load.v4f64.p0v4f64(<4 x double>* [[TMP36]], i32 8, <4 x i1> [[REVERSE23]], <4 x double> undef), !alias.scope !44 -; AVX2-NEXT: [[REVERSE25:%.*]] = shufflevector <4 x double> [[WIDE_MASKED_LOAD24]], <4 x double> undef, <4 x i32> +; AVX2-NEXT: [[WIDE_MASKED_LOAD27:%.*]] = call <4 x double> @llvm.masked.load.v4f64.p0v4f64(<4 x double>* [[TMP36]], i32 8, <4 x i1> [[REVERSE26]], <4 x double> undef), !alias.scope !44 +; AVX2-NEXT: [[REVERSE28:%.*]] = shufflevector <4 x double> [[WIDE_MASKED_LOAD27]], <4 x double> undef, <4 x i32> ; AVX2-NEXT: [[TMP37:%.*]] = getelementptr inbounds double, double* [[TMP24]], i32 -12 ; AVX2-NEXT: [[TMP38:%.*]] = getelementptr inbounds double, double* [[TMP37]], i32 -3 -; AVX2-NEXT: [[REVERSE26:%.*]] = shufflevector <4 x i1> [[TMP23]], <4 x i1> undef, <4 x i32> +; AVX2-NEXT: [[REVERSE29:%.*]] = shufflevector <4 x i1> [[TMP23]], <4 x i1> undef, <4 x i32> ; AVX2-NEXT: [[TMP39:%.*]] = bitcast double* [[TMP38]] to <4 x double>* -; AVX2-NEXT: [[WIDE_MASKED_LOAD27:%.*]] = call <4 x double> @llvm.masked.load.v4f64.p0v4f64(<4 x double>* [[TMP39]], i32 8, <4 x i1> [[REVERSE26]], <4 x double> undef), !alias.scope !44 -; AVX2-NEXT: [[REVERSE28:%.*]] = shufflevector <4 x double> [[WIDE_MASKED_LOAD27]], <4 x double> undef, <4 x i32> -; AVX2-NEXT: [[TMP40:%.*]] = fadd <4 x double> [[REVERSE19]], -; AVX2-NEXT: [[TMP41:%.*]] = fadd <4 x double> [[REVERSE22]], -; AVX2-NEXT: [[TMP42:%.*]] = fadd <4 x double> [[REVERSE25]], -; AVX2-NEXT: [[TMP43:%.*]] = fadd <4 x double> [[REVERSE28]], +; AVX2-NEXT: [[WIDE_MASKED_LOAD30:%.*]] = call <4 x double> @llvm.masked.load.v4f64.p0v4f64(<4 x double>* [[TMP39]], i32 8, <4 x i1> [[REVERSE29]], <4 x double> undef), !alias.scope !44 +; AVX2-NEXT: [[REVERSE31:%.*]] = shufflevector <4 x double> [[WIDE_MASKED_LOAD30]], <4 x double> undef, <4 x i32> +; AVX2-NEXT: [[TMP40:%.*]] = fadd <4 x double> [[REVERSE22]], +; AVX2-NEXT: [[TMP41:%.*]] = fadd <4 x double> [[REVERSE25]], +; AVX2-NEXT: [[TMP42:%.*]] = fadd <4 x double> [[REVERSE28]], +; AVX2-NEXT: [[TMP43:%.*]] = fadd <4 x double> [[REVERSE31]], ; AVX2-NEXT: [[TMP44:%.*]] = getelementptr inbounds double, double* [[OUT]], i64 [[TMP0]] ; AVX2-NEXT: [[TMP45:%.*]] = getelementptr inbounds double, double* [[OUT]], i64 [[TMP1]] ; AVX2-NEXT: [[TMP46:%.*]] = getelementptr inbounds double, double* [[OUT]], i64 [[TMP2]] ; AVX2-NEXT: [[TMP47:%.*]] = getelementptr inbounds double, double* [[OUT]], i64 [[TMP3]] -; AVX2-NEXT: [[REVERSE29:%.*]] = shufflevector <4 x double> [[TMP40]], <4 x double> undef, <4 x i32> +; AVX2-NEXT: [[REVERSE32:%.*]] = shufflevector <4 x double> [[TMP40]], <4 x double> undef, <4 x i32> ; AVX2-NEXT: [[TMP48:%.*]] = getelementptr inbounds double, double* [[TMP44]], i32 0 ; AVX2-NEXT: [[TMP49:%.*]] = getelementptr inbounds double, double* [[TMP48]], i32 -3 ; AVX2-NEXT: [[TMP50:%.*]] = bitcast double* [[TMP49]] to <4 x double>* -; AVX2-NEXT: call void @llvm.masked.store.v4f64.p0v4f64(<4 x double> [[REVERSE29]], <4 x double>* [[TMP50]], i32 8, <4 x i1> [[REVERSE18]]), !alias.scope !46, !noalias !48 -; AVX2-NEXT: [[REVERSE31:%.*]] = shufflevector <4 x double> [[TMP41]], <4 x double> undef, <4 x i32> +; AVX2-NEXT: call void @llvm.masked.store.v4f64.p0v4f64(<4 x double> [[REVERSE32]], <4 x double>* [[TMP50]], i32 8, <4 x i1> [[REVERSE21]]), !alias.scope !46, !noalias !48 +; AVX2-NEXT: [[REVERSE34:%.*]] = shufflevector <4 x double> [[TMP41]], <4 x double> undef, <4 x i32> ; AVX2-NEXT: [[TMP51:%.*]] = getelementptr inbounds double, double* [[TMP44]], i32 -4 ; AVX2-NEXT: [[TMP52:%.*]] = getelementptr inbounds double, double* [[TMP51]], i32 -3 ; AVX2-NEXT: [[TMP53:%.*]] = bitcast double* [[TMP52]] to <4 x double>* -; AVX2-NEXT: call void @llvm.masked.store.v4f64.p0v4f64(<4 x double> [[REVERSE31]], <4 x double>* [[TMP53]], i32 8, <4 x i1> [[REVERSE20]]), !alias.scope !46, !noalias !48 -; AVX2-NEXT: [[REVERSE33:%.*]] = shufflevector <4 x double> [[TMP42]], <4 x double> undef, <4 x i32> +; AVX2-NEXT: call void @llvm.masked.store.v4f64.p0v4f64(<4 x double> [[REVERSE34]], <4 x double>* [[TMP53]], i32 8, <4 x i1> [[REVERSE23]]), !alias.scope !46, !noalias !48 +; AVX2-NEXT: [[REVERSE36:%.*]] = shufflevector <4 x double> [[TMP42]], <4 x double> undef, <4 x i32> ; AVX2-NEXT: [[TMP54:%.*]] = getelementptr inbounds double, double* [[TMP44]], i32 -8 ; AVX2-NEXT: [[TMP55:%.*]] = getelementptr inbounds double, double* [[TMP54]], i32 -3 ; AVX2-NEXT: [[TMP56:%.*]] = bitcast double* [[TMP55]] to <4 x double>* -; AVX2-NEXT: call void @llvm.masked.store.v4f64.p0v4f64(<4 x double> [[REVERSE33]], <4 x double>* [[TMP56]], i32 8, <4 x i1> [[REVERSE23]]), !alias.scope !46, !noalias !48 -; AVX2-NEXT: [[REVERSE35:%.*]] = shufflevector <4 x double> [[TMP43]], <4 x double> undef, <4 x i32> +; AVX2-NEXT: call void @llvm.masked.store.v4f64.p0v4f64(<4 x double> [[REVERSE36]], <4 x double>* [[TMP56]], i32 8, <4 x i1> [[REVERSE26]]), !alias.scope !46, !noalias !48 +; AVX2-NEXT: [[REVERSE38:%.*]] = shufflevector <4 x double> [[TMP43]], <4 x double> undef, <4 x i32> ; AVX2-NEXT: [[TMP57:%.*]] = getelementptr inbounds double, double* [[TMP44]], i32 -12 ; AVX2-NEXT: [[TMP58:%.*]] = getelementptr inbounds double, double* [[TMP57]], i32 -3 ; AVX2-NEXT: [[TMP59:%.*]] = bitcast double* [[TMP58]] to <4 x double>* -; AVX2-NEXT: call void @llvm.masked.store.v4f64.p0v4f64(<4 x double> [[REVERSE35]], <4 x double>* [[TMP59]], i32 8, <4 x i1> [[REVERSE26]]), !alias.scope !46, !noalias !48 +; AVX2-NEXT: call void @llvm.masked.store.v4f64.p0v4f64(<4 x double> [[REVERSE38]], <4 x double>* [[TMP59]], i32 8, <4 x i1> [[REVERSE29]]), !alias.scope !46, !noalias !48 ; AVX2-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], 16 ; AVX2-NEXT: [[TMP60:%.*]] = icmp eq i64 [[INDEX_NEXT]], 4096 ; AVX2-NEXT: br i1 [[TMP60]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !49 @@ -1718,6 +1781,12 @@ define void @foo6(double* nocapture readonly %in, double* nocapture %out, i32 %s ; AVX512: vector.body: ; AVX512-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ] ; AVX512-NEXT: [[OFFSET_IDX:%.*]] = sub i64 4095, [[INDEX]] +; AVX512-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <8 x i64> undef, i64 [[OFFSET_IDX]], i32 0 +; AVX512-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <8 x i64> [[BROADCAST_SPLATINSERT]], <8 x i64> undef, <8 x i32> zeroinitializer +; AVX512-NEXT: [[INDUCTION:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], +; AVX512-NEXT: [[INDUCTION12:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], +; AVX512-NEXT: [[INDUCTION13:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], +; AVX512-NEXT: [[INDUCTION14:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], ; AVX512-NEXT: [[TMP0:%.*]] = add i64 [[OFFSET_IDX]], 0 ; AVX512-NEXT: [[TMP1:%.*]] = add i64 [[OFFSET_IDX]], -8 ; AVX512-NEXT: [[TMP2:%.*]] = add i64 [[OFFSET_IDX]], -16 @@ -1734,78 +1803,78 @@ define void @foo6(double* nocapture readonly %in, double* nocapture %out, i32 %s ; AVX512-NEXT: [[TMP11:%.*]] = getelementptr inbounds i32, i32* [[TMP4]], i32 -8 ; AVX512-NEXT: [[TMP12:%.*]] = getelementptr inbounds i32, i32* [[TMP11]], i32 -7 ; AVX512-NEXT: [[TMP13:%.*]] = bitcast i32* [[TMP12]] to <8 x i32>* -; AVX512-NEXT: [[WIDE_LOAD12:%.*]] = load <8 x i32>, <8 x i32>* [[TMP13]], align 4, !alias.scope !51 -; AVX512-NEXT: [[REVERSE13:%.*]] = shufflevector <8 x i32> [[WIDE_LOAD12]], <8 x i32> undef, <8 x i32> +; AVX512-NEXT: [[WIDE_LOAD15:%.*]] = load <8 x i32>, <8 x i32>* [[TMP13]], align 4, !alias.scope !51 +; AVX512-NEXT: [[REVERSE16:%.*]] = shufflevector <8 x i32> [[WIDE_LOAD15]], <8 x i32> undef, <8 x i32> ; AVX512-NEXT: [[TMP14:%.*]] = getelementptr inbounds i32, i32* [[TMP4]], i32 -16 ; AVX512-NEXT: [[TMP15:%.*]] = getelementptr inbounds i32, i32* [[TMP14]], i32 -7 ; AVX512-NEXT: [[TMP16:%.*]] = bitcast i32* [[TMP15]] to <8 x i32>* -; AVX512-NEXT: [[WIDE_LOAD14:%.*]] = load <8 x i32>, <8 x i32>* [[TMP16]], align 4, !alias.scope !51 -; AVX512-NEXT: [[REVERSE15:%.*]] = shufflevector <8 x i32> [[WIDE_LOAD14]], <8 x i32> undef, <8 x i32> +; AVX512-NEXT: [[WIDE_LOAD17:%.*]] = load <8 x i32>, <8 x i32>* [[TMP16]], align 4, !alias.scope !51 +; AVX512-NEXT: [[REVERSE18:%.*]] = shufflevector <8 x i32> [[WIDE_LOAD17]], <8 x i32> undef, <8 x i32> ; AVX512-NEXT: [[TMP17:%.*]] = getelementptr inbounds i32, i32* [[TMP4]], i32 -24 ; AVX512-NEXT: [[TMP18:%.*]] = getelementptr inbounds i32, i32* [[TMP17]], i32 -7 ; AVX512-NEXT: [[TMP19:%.*]] = bitcast i32* [[TMP18]] to <8 x i32>* -; AVX512-NEXT: [[WIDE_LOAD16:%.*]] = load <8 x i32>, <8 x i32>* [[TMP19]], align 4, !alias.scope !51 -; AVX512-NEXT: [[REVERSE17:%.*]] = shufflevector <8 x i32> [[WIDE_LOAD16]], <8 x i32> undef, <8 x i32> +; AVX512-NEXT: [[WIDE_LOAD19:%.*]] = load <8 x i32>, <8 x i32>* [[TMP19]], align 4, !alias.scope !51 +; AVX512-NEXT: [[REVERSE20:%.*]] = shufflevector <8 x i32> [[WIDE_LOAD19]], <8 x i32> undef, <8 x i32> ; AVX512-NEXT: [[TMP20:%.*]] = icmp sgt <8 x i32> [[REVERSE]], zeroinitializer -; AVX512-NEXT: [[TMP21:%.*]] = icmp sgt <8 x i32> [[REVERSE13]], zeroinitializer -; AVX512-NEXT: [[TMP22:%.*]] = icmp sgt <8 x i32> [[REVERSE15]], zeroinitializer -; AVX512-NEXT: [[TMP23:%.*]] = icmp sgt <8 x i32> [[REVERSE17]], zeroinitializer +; AVX512-NEXT: [[TMP21:%.*]] = icmp sgt <8 x i32> [[REVERSE16]], zeroinitializer +; AVX512-NEXT: [[TMP22:%.*]] = icmp sgt <8 x i32> [[REVERSE18]], zeroinitializer +; AVX512-NEXT: [[TMP23:%.*]] = icmp sgt <8 x i32> [[REVERSE20]], zeroinitializer ; AVX512-NEXT: [[TMP24:%.*]] = getelementptr inbounds double, double* [[IN]], i64 [[TMP0]] ; AVX512-NEXT: [[TMP25:%.*]] = getelementptr inbounds double, double* [[IN]], i64 [[TMP1]] ; AVX512-NEXT: [[TMP26:%.*]] = getelementptr inbounds double, double* [[IN]], i64 [[TMP2]] ; AVX512-NEXT: [[TMP27:%.*]] = getelementptr inbounds double, double* [[IN]], i64 [[TMP3]] ; AVX512-NEXT: [[TMP28:%.*]] = getelementptr inbounds double, double* [[TMP24]], i32 0 ; AVX512-NEXT: [[TMP29:%.*]] = getelementptr inbounds double, double* [[TMP28]], i32 -7 -; AVX512-NEXT: [[REVERSE18:%.*]] = shufflevector <8 x i1> [[TMP20]], <8 x i1> undef, <8 x i32> +; AVX512-NEXT: [[REVERSE21:%.*]] = shufflevector <8 x i1> [[TMP20]], <8 x i1> undef, <8 x i32> ; AVX512-NEXT: [[TMP30:%.*]] = bitcast double* [[TMP29]] to <8 x double>* -; AVX512-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <8 x double> @llvm.masked.load.v8f64.p0v8f64(<8 x double>* [[TMP30]], i32 8, <8 x i1> [[REVERSE18]], <8 x double> undef), !alias.scope !54 -; AVX512-NEXT: [[REVERSE19:%.*]] = shufflevector <8 x double> [[WIDE_MASKED_LOAD]], <8 x double> undef, <8 x i32> +; AVX512-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <8 x double> @llvm.masked.load.v8f64.p0v8f64(<8 x double>* [[TMP30]], i32 8, <8 x i1> [[REVERSE21]], <8 x double> undef), !alias.scope !54 +; AVX512-NEXT: [[REVERSE22:%.*]] = shufflevector <8 x double> [[WIDE_MASKED_LOAD]], <8 x double> undef, <8 x i32> ; AVX512-NEXT: [[TMP31:%.*]] = getelementptr inbounds double, double* [[TMP24]], i32 -8 ; AVX512-NEXT: [[TMP32:%.*]] = getelementptr inbounds double, double* [[TMP31]], i32 -7 -; AVX512-NEXT: [[REVERSE20:%.*]] = shufflevector <8 x i1> [[TMP21]], <8 x i1> undef, <8 x i32> +; AVX512-NEXT: [[REVERSE23:%.*]] = shufflevector <8 x i1> [[TMP21]], <8 x i1> undef, <8 x i32> ; AVX512-NEXT: [[TMP33:%.*]] = bitcast double* [[TMP32]] to <8 x double>* -; AVX512-NEXT: [[WIDE_MASKED_LOAD21:%.*]] = call <8 x double> @llvm.masked.load.v8f64.p0v8f64(<8 x double>* [[TMP33]], i32 8, <8 x i1> [[REVERSE20]], <8 x double> undef), !alias.scope !54 -; AVX512-NEXT: [[REVERSE22:%.*]] = shufflevector <8 x double> [[WIDE_MASKED_LOAD21]], <8 x double> undef, <8 x i32> +; AVX512-NEXT: [[WIDE_MASKED_LOAD24:%.*]] = call <8 x double> @llvm.masked.load.v8f64.p0v8f64(<8 x double>* [[TMP33]], i32 8, <8 x i1> [[REVERSE23]], <8 x double> undef), !alias.scope !54 +; AVX512-NEXT: [[REVERSE25:%.*]] = shufflevector <8 x double> [[WIDE_MASKED_LOAD24]], <8 x double> undef, <8 x i32> ; AVX512-NEXT: [[TMP34:%.*]] = getelementptr inbounds double, double* [[TMP24]], i32 -16 ; AVX512-NEXT: [[TMP35:%.*]] = getelementptr inbounds double, double* [[TMP34]], i32 -7 -; AVX512-NEXT: [[REVERSE23:%.*]] = shufflevector <8 x i1> [[TMP22]], <8 x i1> undef, <8 x i32> +; AVX512-NEXT: [[REVERSE26:%.*]] = shufflevector <8 x i1> [[TMP22]], <8 x i1> undef, <8 x i32> ; AVX512-NEXT: [[TMP36:%.*]] = bitcast double* [[TMP35]] to <8 x double>* -; AVX512-NEXT: [[WIDE_MASKED_LOAD24:%.*]] = call <8 x double> @llvm.masked.load.v8f64.p0v8f64(<8 x double>* [[TMP36]], i32 8, <8 x i1> [[REVERSE23]], <8 x double> undef), !alias.scope !54 -; AVX512-NEXT: [[REVERSE25:%.*]] = shufflevector <8 x double> [[WIDE_MASKED_LOAD24]], <8 x double> undef, <8 x i32> +; AVX512-NEXT: [[WIDE_MASKED_LOAD27:%.*]] = call <8 x double> @llvm.masked.load.v8f64.p0v8f64(<8 x double>* [[TMP36]], i32 8, <8 x i1> [[REVERSE26]], <8 x double> undef), !alias.scope !54 +; AVX512-NEXT: [[REVERSE28:%.*]] = shufflevector <8 x double> [[WIDE_MASKED_LOAD27]], <8 x double> undef, <8 x i32> ; AVX512-NEXT: [[TMP37:%.*]] = getelementptr inbounds double, double* [[TMP24]], i32 -24 ; AVX512-NEXT: [[TMP38:%.*]] = getelementptr inbounds double, double* [[TMP37]], i32 -7 -; AVX512-NEXT: [[REVERSE26:%.*]] = shufflevector <8 x i1> [[TMP23]], <8 x i1> undef, <8 x i32> +; AVX512-NEXT: [[REVERSE29:%.*]] = shufflevector <8 x i1> [[TMP23]], <8 x i1> undef, <8 x i32> ; AVX512-NEXT: [[TMP39:%.*]] = bitcast double* [[TMP38]] to <8 x double>* -; AVX512-NEXT: [[WIDE_MASKED_LOAD27:%.*]] = call <8 x double> @llvm.masked.load.v8f64.p0v8f64(<8 x double>* [[TMP39]], i32 8, <8 x i1> [[REVERSE26]], <8 x double> undef), !alias.scope !54 -; AVX512-NEXT: [[REVERSE28:%.*]] = shufflevector <8 x double> [[WIDE_MASKED_LOAD27]], <8 x double> undef, <8 x i32> -; AVX512-NEXT: [[TMP40:%.*]] = fadd <8 x double> [[REVERSE19]], -; AVX512-NEXT: [[TMP41:%.*]] = fadd <8 x double> [[REVERSE22]], -; AVX512-NEXT: [[TMP42:%.*]] = fadd <8 x double> [[REVERSE25]], -; AVX512-NEXT: [[TMP43:%.*]] = fadd <8 x double> [[REVERSE28]], +; AVX512-NEXT: [[WIDE_MASKED_LOAD30:%.*]] = call <8 x double> @llvm.masked.load.v8f64.p0v8f64(<8 x double>* [[TMP39]], i32 8, <8 x i1> [[REVERSE29]], <8 x double> undef), !alias.scope !54 +; AVX512-NEXT: [[REVERSE31:%.*]] = shufflevector <8 x double> [[WIDE_MASKED_LOAD30]], <8 x double> undef, <8 x i32> +; AVX512-NEXT: [[TMP40:%.*]] = fadd <8 x double> [[REVERSE22]], +; AVX512-NEXT: [[TMP41:%.*]] = fadd <8 x double> [[REVERSE25]], +; AVX512-NEXT: [[TMP42:%.*]] = fadd <8 x double> [[REVERSE28]], +; AVX512-NEXT: [[TMP43:%.*]] = fadd <8 x double> [[REVERSE31]], ; AVX512-NEXT: [[TMP44:%.*]] = getelementptr inbounds double, double* [[OUT]], i64 [[TMP0]] ; AVX512-NEXT: [[TMP45:%.*]] = getelementptr inbounds double, double* [[OUT]], i64 [[TMP1]] ; AVX512-NEXT: [[TMP46:%.*]] = getelementptr inbounds double, double* [[OUT]], i64 [[TMP2]] ; AVX512-NEXT: [[TMP47:%.*]] = getelementptr inbounds double, double* [[OUT]], i64 [[TMP3]] -; AVX512-NEXT: [[REVERSE29:%.*]] = shufflevector <8 x double> [[TMP40]], <8 x double> undef, <8 x i32> +; AVX512-NEXT: [[REVERSE32:%.*]] = shufflevector <8 x double> [[TMP40]], <8 x double> undef, <8 x i32> ; AVX512-NEXT: [[TMP48:%.*]] = getelementptr inbounds double, double* [[TMP44]], i32 0 ; AVX512-NEXT: [[TMP49:%.*]] = getelementptr inbounds double, double* [[TMP48]], i32 -7 ; AVX512-NEXT: [[TMP50:%.*]] = bitcast double* [[TMP49]] to <8 x double>* -; AVX512-NEXT: call void @llvm.masked.store.v8f64.p0v8f64(<8 x double> [[REVERSE29]], <8 x double>* [[TMP50]], i32 8, <8 x i1> [[REVERSE18]]), !alias.scope !56, !noalias !58 -; AVX512-NEXT: [[REVERSE31:%.*]] = shufflevector <8 x double> [[TMP41]], <8 x double> undef, <8 x i32> +; AVX512-NEXT: call void @llvm.masked.store.v8f64.p0v8f64(<8 x double> [[REVERSE32]], <8 x double>* [[TMP50]], i32 8, <8 x i1> [[REVERSE21]]), !alias.scope !56, !noalias !58 +; AVX512-NEXT: [[REVERSE34:%.*]] = shufflevector <8 x double> [[TMP41]], <8 x double> undef, <8 x i32> ; AVX512-NEXT: [[TMP51:%.*]] = getelementptr inbounds double, double* [[TMP44]], i32 -8 ; AVX512-NEXT: [[TMP52:%.*]] = getelementptr inbounds double, double* [[TMP51]], i32 -7 ; AVX512-NEXT: [[TMP53:%.*]] = bitcast double* [[TMP52]] to <8 x double>* -; AVX512-NEXT: call void @llvm.masked.store.v8f64.p0v8f64(<8 x double> [[REVERSE31]], <8 x double>* [[TMP53]], i32 8, <8 x i1> [[REVERSE20]]), !alias.scope !56, !noalias !58 -; AVX512-NEXT: [[REVERSE33:%.*]] = shufflevector <8 x double> [[TMP42]], <8 x double> undef, <8 x i32> +; AVX512-NEXT: call void @llvm.masked.store.v8f64.p0v8f64(<8 x double> [[REVERSE34]], <8 x double>* [[TMP53]], i32 8, <8 x i1> [[REVERSE23]]), !alias.scope !56, !noalias !58 +; AVX512-NEXT: [[REVERSE36:%.*]] = shufflevector <8 x double> [[TMP42]], <8 x double> undef, <8 x i32> ; AVX512-NEXT: [[TMP54:%.*]] = getelementptr inbounds double, double* [[TMP44]], i32 -16 ; AVX512-NEXT: [[TMP55:%.*]] = getelementptr inbounds double, double* [[TMP54]], i32 -7 ; AVX512-NEXT: [[TMP56:%.*]] = bitcast double* [[TMP55]] to <8 x double>* -; AVX512-NEXT: call void @llvm.masked.store.v8f64.p0v8f64(<8 x double> [[REVERSE33]], <8 x double>* [[TMP56]], i32 8, <8 x i1> [[REVERSE23]]), !alias.scope !56, !noalias !58 -; AVX512-NEXT: [[REVERSE35:%.*]] = shufflevector <8 x double> [[TMP43]], <8 x double> undef, <8 x i32> +; AVX512-NEXT: call void @llvm.masked.store.v8f64.p0v8f64(<8 x double> [[REVERSE36]], <8 x double>* [[TMP56]], i32 8, <8 x i1> [[REVERSE26]]), !alias.scope !56, !noalias !58 +; AVX512-NEXT: [[REVERSE38:%.*]] = shufflevector <8 x double> [[TMP43]], <8 x double> undef, <8 x i32> ; AVX512-NEXT: [[TMP57:%.*]] = getelementptr inbounds double, double* [[TMP44]], i32 -24 ; AVX512-NEXT: [[TMP58:%.*]] = getelementptr inbounds double, double* [[TMP57]], i32 -7 ; AVX512-NEXT: [[TMP59:%.*]] = bitcast double* [[TMP58]] to <8 x double>* -; AVX512-NEXT: call void @llvm.masked.store.v8f64.p0v8f64(<8 x double> [[REVERSE35]], <8 x double>* [[TMP59]], i32 8, <8 x i1> [[REVERSE26]]), !alias.scope !56, !noalias !58 +; AVX512-NEXT: call void @llvm.masked.store.v8f64.p0v8f64(<8 x double> [[REVERSE38]], <8 x double>* [[TMP59]], i32 8, <8 x i1> [[REVERSE29]]), !alias.scope !56, !noalias !58 ; AVX512-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], 32 ; AVX512-NEXT: [[TMP60:%.*]] = icmp eq i64 [[INDEX_NEXT]], 4096 ; AVX512-NEXT: br i1 [[TMP60]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !59 @@ -1885,6 +1954,12 @@ define void @foo7(double* noalias nocapture %out, double** noalias nocapture rea ; AVX1-NEXT: br label [[VECTOR_BODY:%.*]] ; AVX1: vector.body: ; AVX1-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ] +; AVX1-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i64> undef, i64 [[INDEX]], i32 0 +; AVX1-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT]], <4 x i64> undef, <4 x i32> zeroinitializer +; AVX1-NEXT: [[INDUCTION:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], +; AVX1-NEXT: [[INDUCTION1:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], +; AVX1-NEXT: [[INDUCTION2:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], +; AVX1-NEXT: [[INDUCTION3:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], ; AVX1-NEXT: [[TMP0:%.*]] = add i64 [[INDEX]], 0 ; AVX1-NEXT: [[TMP1:%.*]] = add i64 [[INDEX]], 4 ; AVX1-NEXT: [[TMP2:%.*]] = add i64 [[INDEX]], 8 @@ -1898,17 +1973,17 @@ define void @foo7(double* noalias nocapture %out, double** noalias nocapture rea ; AVX1-NEXT: [[WIDE_LOAD:%.*]] = load <4 x i8>, <4 x i8>* [[TMP9]], align 1 ; AVX1-NEXT: [[TMP10:%.*]] = getelementptr inbounds i8, i8* [[TMP4]], i32 4 ; AVX1-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to <4 x i8>* -; AVX1-NEXT: [[WIDE_LOAD1:%.*]] = load <4 x i8>, <4 x i8>* [[TMP11]], align 1 +; AVX1-NEXT: [[WIDE_LOAD4:%.*]] = load <4 x i8>, <4 x i8>* [[TMP11]], align 1 ; AVX1-NEXT: [[TMP12:%.*]] = getelementptr inbounds i8, i8* [[TMP4]], i32 8 ; AVX1-NEXT: [[TMP13:%.*]] = bitcast i8* [[TMP12]] to <4 x i8>* -; AVX1-NEXT: [[WIDE_LOAD2:%.*]] = load <4 x i8>, <4 x i8>* [[TMP13]], align 1 +; AVX1-NEXT: [[WIDE_LOAD5:%.*]] = load <4 x i8>, <4 x i8>* [[TMP13]], align 1 ; AVX1-NEXT: [[TMP14:%.*]] = getelementptr inbounds i8, i8* [[TMP4]], i32 12 ; AVX1-NEXT: [[TMP15:%.*]] = bitcast i8* [[TMP14]] to <4 x i8>* -; AVX1-NEXT: [[WIDE_LOAD3:%.*]] = load <4 x i8>, <4 x i8>* [[TMP15]], align 1 +; AVX1-NEXT: [[WIDE_LOAD6:%.*]] = load <4 x i8>, <4 x i8>* [[TMP15]], align 1 ; AVX1-NEXT: [[TMP16:%.*]] = and <4 x i8> [[WIDE_LOAD]], -; AVX1-NEXT: [[TMP17:%.*]] = and <4 x i8> [[WIDE_LOAD1]], -; AVX1-NEXT: [[TMP18:%.*]] = and <4 x i8> [[WIDE_LOAD2]], -; AVX1-NEXT: [[TMP19:%.*]] = and <4 x i8> [[WIDE_LOAD3]], +; AVX1-NEXT: [[TMP17:%.*]] = and <4 x i8> [[WIDE_LOAD4]], +; AVX1-NEXT: [[TMP18:%.*]] = and <4 x i8> [[WIDE_LOAD5]], +; AVX1-NEXT: [[TMP19:%.*]] = and <4 x i8> [[WIDE_LOAD6]], ; AVX1-NEXT: [[TMP20:%.*]] = icmp eq <4 x i8> [[TMP16]], zeroinitializer ; AVX1-NEXT: [[TMP21:%.*]] = icmp eq <4 x i8> [[TMP17]], zeroinitializer ; AVX1-NEXT: [[TMP22:%.*]] = icmp eq <4 x i8> [[TMP18]], zeroinitializer @@ -1926,17 +2001,17 @@ define void @foo7(double* noalias nocapture %out, double** noalias nocapture rea ; AVX1-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <4 x double*> @llvm.masked.load.v4p0f64.p0v4p0f64(<4 x double*>* [[TMP33]], i32 8, <4 x i1> [[TMP28]], <4 x double*> undef) ; AVX1-NEXT: [[TMP34:%.*]] = getelementptr inbounds double*, double** [[TMP24]], i32 4 ; AVX1-NEXT: [[TMP35:%.*]] = bitcast double** [[TMP34]] to <4 x double*>* -; AVX1-NEXT: [[WIDE_MASKED_LOAD4:%.*]] = call <4 x double*> @llvm.masked.load.v4p0f64.p0v4p0f64(<4 x double*>* [[TMP35]], i32 8, <4 x i1> [[TMP29]], <4 x double*> undef) +; AVX1-NEXT: [[WIDE_MASKED_LOAD7:%.*]] = call <4 x double*> @llvm.masked.load.v4p0f64.p0v4p0f64(<4 x double*>* [[TMP35]], i32 8, <4 x i1> [[TMP29]], <4 x double*> undef) ; AVX1-NEXT: [[TMP36:%.*]] = getelementptr inbounds double*, double** [[TMP24]], i32 8 ; AVX1-NEXT: [[TMP37:%.*]] = bitcast double** [[TMP36]] to <4 x double*>* -; AVX1-NEXT: [[WIDE_MASKED_LOAD5:%.*]] = call <4 x double*> @llvm.masked.load.v4p0f64.p0v4p0f64(<4 x double*>* [[TMP37]], i32 8, <4 x i1> [[TMP30]], <4 x double*> undef) +; AVX1-NEXT: [[WIDE_MASKED_LOAD8:%.*]] = call <4 x double*> @llvm.masked.load.v4p0f64.p0v4p0f64(<4 x double*>* [[TMP37]], i32 8, <4 x i1> [[TMP30]], <4 x double*> undef) ; AVX1-NEXT: [[TMP38:%.*]] = getelementptr inbounds double*, double** [[TMP24]], i32 12 ; AVX1-NEXT: [[TMP39:%.*]] = bitcast double** [[TMP38]] to <4 x double*>* -; AVX1-NEXT: [[WIDE_MASKED_LOAD6:%.*]] = call <4 x double*> @llvm.masked.load.v4p0f64.p0v4p0f64(<4 x double*>* [[TMP39]], i32 8, <4 x i1> [[TMP31]], <4 x double*> undef) +; AVX1-NEXT: [[WIDE_MASKED_LOAD9:%.*]] = call <4 x double*> @llvm.masked.load.v4p0f64.p0v4p0f64(<4 x double*>* [[TMP39]], i32 8, <4 x i1> [[TMP31]], <4 x double*> undef) ; AVX1-NEXT: [[TMP40:%.*]] = icmp eq <4 x double*> [[WIDE_MASKED_LOAD]], zeroinitializer -; AVX1-NEXT: [[TMP41:%.*]] = icmp eq <4 x double*> [[WIDE_MASKED_LOAD4]], zeroinitializer -; AVX1-NEXT: [[TMP42:%.*]] = icmp eq <4 x double*> [[WIDE_MASKED_LOAD5]], zeroinitializer -; AVX1-NEXT: [[TMP43:%.*]] = icmp eq <4 x double*> [[WIDE_MASKED_LOAD6]], zeroinitializer +; AVX1-NEXT: [[TMP41:%.*]] = icmp eq <4 x double*> [[WIDE_MASKED_LOAD7]], zeroinitializer +; AVX1-NEXT: [[TMP42:%.*]] = icmp eq <4 x double*> [[WIDE_MASKED_LOAD8]], zeroinitializer +; AVX1-NEXT: [[TMP43:%.*]] = icmp eq <4 x double*> [[WIDE_MASKED_LOAD9]], zeroinitializer ; AVX1-NEXT: [[TMP44:%.*]] = getelementptr inbounds double, double* [[OUT:%.*]], i64 [[TMP0]] ; AVX1-NEXT: [[TMP45:%.*]] = getelementptr inbounds double, double* [[OUT]], i64 [[TMP1]] ; AVX1-NEXT: [[TMP46:%.*]] = getelementptr inbounds double, double* [[OUT]], i64 [[TMP2]] @@ -2009,6 +2084,12 @@ define void @foo7(double* noalias nocapture %out, double** noalias nocapture rea ; AVX2-NEXT: br label [[VECTOR_BODY:%.*]] ; AVX2: vector.body: ; AVX2-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ] +; AVX2-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i64> undef, i64 [[INDEX]], i32 0 +; AVX2-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT]], <4 x i64> undef, <4 x i32> zeroinitializer +; AVX2-NEXT: [[INDUCTION:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], +; AVX2-NEXT: [[INDUCTION1:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], +; AVX2-NEXT: [[INDUCTION2:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], +; AVX2-NEXT: [[INDUCTION3:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], ; AVX2-NEXT: [[TMP0:%.*]] = add i64 [[INDEX]], 0 ; AVX2-NEXT: [[TMP1:%.*]] = add i64 [[INDEX]], 4 ; AVX2-NEXT: [[TMP2:%.*]] = add i64 [[INDEX]], 8 @@ -2022,17 +2103,17 @@ define void @foo7(double* noalias nocapture %out, double** noalias nocapture rea ; AVX2-NEXT: [[WIDE_LOAD:%.*]] = load <4 x i8>, <4 x i8>* [[TMP9]], align 1 ; AVX2-NEXT: [[TMP10:%.*]] = getelementptr inbounds i8, i8* [[TMP4]], i32 4 ; AVX2-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to <4 x i8>* -; AVX2-NEXT: [[WIDE_LOAD1:%.*]] = load <4 x i8>, <4 x i8>* [[TMP11]], align 1 +; AVX2-NEXT: [[WIDE_LOAD4:%.*]] = load <4 x i8>, <4 x i8>* [[TMP11]], align 1 ; AVX2-NEXT: [[TMP12:%.*]] = getelementptr inbounds i8, i8* [[TMP4]], i32 8 ; AVX2-NEXT: [[TMP13:%.*]] = bitcast i8* [[TMP12]] to <4 x i8>* -; AVX2-NEXT: [[WIDE_LOAD2:%.*]] = load <4 x i8>, <4 x i8>* [[TMP13]], align 1 +; AVX2-NEXT: [[WIDE_LOAD5:%.*]] = load <4 x i8>, <4 x i8>* [[TMP13]], align 1 ; AVX2-NEXT: [[TMP14:%.*]] = getelementptr inbounds i8, i8* [[TMP4]], i32 12 ; AVX2-NEXT: [[TMP15:%.*]] = bitcast i8* [[TMP14]] to <4 x i8>* -; AVX2-NEXT: [[WIDE_LOAD3:%.*]] = load <4 x i8>, <4 x i8>* [[TMP15]], align 1 +; AVX2-NEXT: [[WIDE_LOAD6:%.*]] = load <4 x i8>, <4 x i8>* [[TMP15]], align 1 ; AVX2-NEXT: [[TMP16:%.*]] = and <4 x i8> [[WIDE_LOAD]], -; AVX2-NEXT: [[TMP17:%.*]] = and <4 x i8> [[WIDE_LOAD1]], -; AVX2-NEXT: [[TMP18:%.*]] = and <4 x i8> [[WIDE_LOAD2]], -; AVX2-NEXT: [[TMP19:%.*]] = and <4 x i8> [[WIDE_LOAD3]], +; AVX2-NEXT: [[TMP17:%.*]] = and <4 x i8> [[WIDE_LOAD4]], +; AVX2-NEXT: [[TMP18:%.*]] = and <4 x i8> [[WIDE_LOAD5]], +; AVX2-NEXT: [[TMP19:%.*]] = and <4 x i8> [[WIDE_LOAD6]], ; AVX2-NEXT: [[TMP20:%.*]] = icmp eq <4 x i8> [[TMP16]], zeroinitializer ; AVX2-NEXT: [[TMP21:%.*]] = icmp eq <4 x i8> [[TMP17]], zeroinitializer ; AVX2-NEXT: [[TMP22:%.*]] = icmp eq <4 x i8> [[TMP18]], zeroinitializer @@ -2050,17 +2131,17 @@ define void @foo7(double* noalias nocapture %out, double** noalias nocapture rea ; AVX2-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <4 x double*> @llvm.masked.load.v4p0f64.p0v4p0f64(<4 x double*>* [[TMP33]], i32 8, <4 x i1> [[TMP28]], <4 x double*> undef) ; AVX2-NEXT: [[TMP34:%.*]] = getelementptr inbounds double*, double** [[TMP24]], i32 4 ; AVX2-NEXT: [[TMP35:%.*]] = bitcast double** [[TMP34]] to <4 x double*>* -; AVX2-NEXT: [[WIDE_MASKED_LOAD4:%.*]] = call <4 x double*> @llvm.masked.load.v4p0f64.p0v4p0f64(<4 x double*>* [[TMP35]], i32 8, <4 x i1> [[TMP29]], <4 x double*> undef) +; AVX2-NEXT: [[WIDE_MASKED_LOAD7:%.*]] = call <4 x double*> @llvm.masked.load.v4p0f64.p0v4p0f64(<4 x double*>* [[TMP35]], i32 8, <4 x i1> [[TMP29]], <4 x double*> undef) ; AVX2-NEXT: [[TMP36:%.*]] = getelementptr inbounds double*, double** [[TMP24]], i32 8 ; AVX2-NEXT: [[TMP37:%.*]] = bitcast double** [[TMP36]] to <4 x double*>* -; AVX2-NEXT: [[WIDE_MASKED_LOAD5:%.*]] = call <4 x double*> @llvm.masked.load.v4p0f64.p0v4p0f64(<4 x double*>* [[TMP37]], i32 8, <4 x i1> [[TMP30]], <4 x double*> undef) +; AVX2-NEXT: [[WIDE_MASKED_LOAD8:%.*]] = call <4 x double*> @llvm.masked.load.v4p0f64.p0v4p0f64(<4 x double*>* [[TMP37]], i32 8, <4 x i1> [[TMP30]], <4 x double*> undef) ; AVX2-NEXT: [[TMP38:%.*]] = getelementptr inbounds double*, double** [[TMP24]], i32 12 ; AVX2-NEXT: [[TMP39:%.*]] = bitcast double** [[TMP38]] to <4 x double*>* -; AVX2-NEXT: [[WIDE_MASKED_LOAD6:%.*]] = call <4 x double*> @llvm.masked.load.v4p0f64.p0v4p0f64(<4 x double*>* [[TMP39]], i32 8, <4 x i1> [[TMP31]], <4 x double*> undef) +; AVX2-NEXT: [[WIDE_MASKED_LOAD9:%.*]] = call <4 x double*> @llvm.masked.load.v4p0f64.p0v4p0f64(<4 x double*>* [[TMP39]], i32 8, <4 x i1> [[TMP31]], <4 x double*> undef) ; AVX2-NEXT: [[TMP40:%.*]] = icmp eq <4 x double*> [[WIDE_MASKED_LOAD]], zeroinitializer -; AVX2-NEXT: [[TMP41:%.*]] = icmp eq <4 x double*> [[WIDE_MASKED_LOAD4]], zeroinitializer -; AVX2-NEXT: [[TMP42:%.*]] = icmp eq <4 x double*> [[WIDE_MASKED_LOAD5]], zeroinitializer -; AVX2-NEXT: [[TMP43:%.*]] = icmp eq <4 x double*> [[WIDE_MASKED_LOAD6]], zeroinitializer +; AVX2-NEXT: [[TMP41:%.*]] = icmp eq <4 x double*> [[WIDE_MASKED_LOAD7]], zeroinitializer +; AVX2-NEXT: [[TMP42:%.*]] = icmp eq <4 x double*> [[WIDE_MASKED_LOAD8]], zeroinitializer +; AVX2-NEXT: [[TMP43:%.*]] = icmp eq <4 x double*> [[WIDE_MASKED_LOAD9]], zeroinitializer ; AVX2-NEXT: [[TMP44:%.*]] = getelementptr inbounds double, double* [[OUT:%.*]], i64 [[TMP0]] ; AVX2-NEXT: [[TMP45:%.*]] = getelementptr inbounds double, double* [[OUT]], i64 [[TMP1]] ; AVX2-NEXT: [[TMP46:%.*]] = getelementptr inbounds double, double* [[OUT]], i64 [[TMP2]] @@ -2133,6 +2214,12 @@ define void @foo7(double* noalias nocapture %out, double** noalias nocapture rea ; AVX512-NEXT: br label [[VECTOR_BODY:%.*]] ; AVX512: vector.body: ; AVX512-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ] +; AVX512-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <8 x i64> undef, i64 [[INDEX]], i32 0 +; AVX512-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <8 x i64> [[BROADCAST_SPLATINSERT]], <8 x i64> undef, <8 x i32> zeroinitializer +; AVX512-NEXT: [[INDUCTION:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], +; AVX512-NEXT: [[INDUCTION1:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], +; AVX512-NEXT: [[INDUCTION2:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], +; AVX512-NEXT: [[INDUCTION3:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], ; AVX512-NEXT: [[TMP0:%.*]] = add i64 [[INDEX]], 0 ; AVX512-NEXT: [[TMP1:%.*]] = add i64 [[INDEX]], 8 ; AVX512-NEXT: [[TMP2:%.*]] = add i64 [[INDEX]], 16 @@ -2146,17 +2233,17 @@ define void @foo7(double* noalias nocapture %out, double** noalias nocapture rea ; AVX512-NEXT: [[WIDE_LOAD:%.*]] = load <8 x i8>, <8 x i8>* [[TMP9]], align 1 ; AVX512-NEXT: [[TMP10:%.*]] = getelementptr inbounds i8, i8* [[TMP4]], i32 8 ; AVX512-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to <8 x i8>* -; AVX512-NEXT: [[WIDE_LOAD1:%.*]] = load <8 x i8>, <8 x i8>* [[TMP11]], align 1 +; AVX512-NEXT: [[WIDE_LOAD4:%.*]] = load <8 x i8>, <8 x i8>* [[TMP11]], align 1 ; AVX512-NEXT: [[TMP12:%.*]] = getelementptr inbounds i8, i8* [[TMP4]], i32 16 ; AVX512-NEXT: [[TMP13:%.*]] = bitcast i8* [[TMP12]] to <8 x i8>* -; AVX512-NEXT: [[WIDE_LOAD2:%.*]] = load <8 x i8>, <8 x i8>* [[TMP13]], align 1 +; AVX512-NEXT: [[WIDE_LOAD5:%.*]] = load <8 x i8>, <8 x i8>* [[TMP13]], align 1 ; AVX512-NEXT: [[TMP14:%.*]] = getelementptr inbounds i8, i8* [[TMP4]], i32 24 ; AVX512-NEXT: [[TMP15:%.*]] = bitcast i8* [[TMP14]] to <8 x i8>* -; AVX512-NEXT: [[WIDE_LOAD3:%.*]] = load <8 x i8>, <8 x i8>* [[TMP15]], align 1 +; AVX512-NEXT: [[WIDE_LOAD6:%.*]] = load <8 x i8>, <8 x i8>* [[TMP15]], align 1 ; AVX512-NEXT: [[TMP16:%.*]] = and <8 x i8> [[WIDE_LOAD]], -; AVX512-NEXT: [[TMP17:%.*]] = and <8 x i8> [[WIDE_LOAD1]], -; AVX512-NEXT: [[TMP18:%.*]] = and <8 x i8> [[WIDE_LOAD2]], -; AVX512-NEXT: [[TMP19:%.*]] = and <8 x i8> [[WIDE_LOAD3]], +; AVX512-NEXT: [[TMP17:%.*]] = and <8 x i8> [[WIDE_LOAD4]], +; AVX512-NEXT: [[TMP18:%.*]] = and <8 x i8> [[WIDE_LOAD5]], +; AVX512-NEXT: [[TMP19:%.*]] = and <8 x i8> [[WIDE_LOAD6]], ; AVX512-NEXT: [[TMP20:%.*]] = icmp eq <8 x i8> [[TMP16]], zeroinitializer ; AVX512-NEXT: [[TMP21:%.*]] = icmp eq <8 x i8> [[TMP17]], zeroinitializer ; AVX512-NEXT: [[TMP22:%.*]] = icmp eq <8 x i8> [[TMP18]], zeroinitializer @@ -2174,17 +2261,17 @@ define void @foo7(double* noalias nocapture %out, double** noalias nocapture rea ; AVX512-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <8 x double*> @llvm.masked.load.v8p0f64.p0v8p0f64(<8 x double*>* [[TMP33]], i32 8, <8 x i1> [[TMP28]], <8 x double*> undef) ; AVX512-NEXT: [[TMP34:%.*]] = getelementptr inbounds double*, double** [[TMP24]], i32 8 ; AVX512-NEXT: [[TMP35:%.*]] = bitcast double** [[TMP34]] to <8 x double*>* -; AVX512-NEXT: [[WIDE_MASKED_LOAD4:%.*]] = call <8 x double*> @llvm.masked.load.v8p0f64.p0v8p0f64(<8 x double*>* [[TMP35]], i32 8, <8 x i1> [[TMP29]], <8 x double*> undef) +; AVX512-NEXT: [[WIDE_MASKED_LOAD7:%.*]] = call <8 x double*> @llvm.masked.load.v8p0f64.p0v8p0f64(<8 x double*>* [[TMP35]], i32 8, <8 x i1> [[TMP29]], <8 x double*> undef) ; AVX512-NEXT: [[TMP36:%.*]] = getelementptr inbounds double*, double** [[TMP24]], i32 16 ; AVX512-NEXT: [[TMP37:%.*]] = bitcast double** [[TMP36]] to <8 x double*>* -; AVX512-NEXT: [[WIDE_MASKED_LOAD5:%.*]] = call <8 x double*> @llvm.masked.load.v8p0f64.p0v8p0f64(<8 x double*>* [[TMP37]], i32 8, <8 x i1> [[TMP30]], <8 x double*> undef) +; AVX512-NEXT: [[WIDE_MASKED_LOAD8:%.*]] = call <8 x double*> @llvm.masked.load.v8p0f64.p0v8p0f64(<8 x double*>* [[TMP37]], i32 8, <8 x i1> [[TMP30]], <8 x double*> undef) ; AVX512-NEXT: [[TMP38:%.*]] = getelementptr inbounds double*, double** [[TMP24]], i32 24 ; AVX512-NEXT: [[TMP39:%.*]] = bitcast double** [[TMP38]] to <8 x double*>* -; AVX512-NEXT: [[WIDE_MASKED_LOAD6:%.*]] = call <8 x double*> @llvm.masked.load.v8p0f64.p0v8p0f64(<8 x double*>* [[TMP39]], i32 8, <8 x i1> [[TMP31]], <8 x double*> undef) +; AVX512-NEXT: [[WIDE_MASKED_LOAD9:%.*]] = call <8 x double*> @llvm.masked.load.v8p0f64.p0v8p0f64(<8 x double*>* [[TMP39]], i32 8, <8 x i1> [[TMP31]], <8 x double*> undef) ; AVX512-NEXT: [[TMP40:%.*]] = icmp eq <8 x double*> [[WIDE_MASKED_LOAD]], zeroinitializer -; AVX512-NEXT: [[TMP41:%.*]] = icmp eq <8 x double*> [[WIDE_MASKED_LOAD4]], zeroinitializer -; AVX512-NEXT: [[TMP42:%.*]] = icmp eq <8 x double*> [[WIDE_MASKED_LOAD5]], zeroinitializer -; AVX512-NEXT: [[TMP43:%.*]] = icmp eq <8 x double*> [[WIDE_MASKED_LOAD6]], zeroinitializer +; AVX512-NEXT: [[TMP41:%.*]] = icmp eq <8 x double*> [[WIDE_MASKED_LOAD7]], zeroinitializer +; AVX512-NEXT: [[TMP42:%.*]] = icmp eq <8 x double*> [[WIDE_MASKED_LOAD8]], zeroinitializer +; AVX512-NEXT: [[TMP43:%.*]] = icmp eq <8 x double*> [[WIDE_MASKED_LOAD9]], zeroinitializer ; AVX512-NEXT: [[TMP44:%.*]] = getelementptr inbounds double, double* [[OUT:%.*]], i64 [[TMP0]] ; AVX512-NEXT: [[TMP45:%.*]] = getelementptr inbounds double, double* [[OUT]], i64 [[TMP1]] ; AVX512-NEXT: [[TMP46:%.*]] = getelementptr inbounds double, double* [[OUT]], i64 [[TMP2]] @@ -2302,6 +2389,12 @@ define void @foo8(double* noalias nocapture %out, i32 ()** noalias nocapture rea ; AVX1-NEXT: br label [[VECTOR_BODY:%.*]] ; AVX1: vector.body: ; AVX1-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ] +; AVX1-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i64> undef, i64 [[INDEX]], i32 0 +; AVX1-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT]], <4 x i64> undef, <4 x i32> zeroinitializer +; AVX1-NEXT: [[INDUCTION:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], +; AVX1-NEXT: [[INDUCTION1:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], +; AVX1-NEXT: [[INDUCTION2:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], +; AVX1-NEXT: [[INDUCTION3:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], ; AVX1-NEXT: [[TMP0:%.*]] = add i64 [[INDEX]], 0 ; AVX1-NEXT: [[TMP1:%.*]] = add i64 [[INDEX]], 4 ; AVX1-NEXT: [[TMP2:%.*]] = add i64 [[INDEX]], 8 @@ -2315,17 +2408,17 @@ define void @foo8(double* noalias nocapture %out, i32 ()** noalias nocapture rea ; AVX1-NEXT: [[WIDE_LOAD:%.*]] = load <4 x i8>, <4 x i8>* [[TMP9]], align 1 ; AVX1-NEXT: [[TMP10:%.*]] = getelementptr inbounds i8, i8* [[TMP4]], i32 4 ; AVX1-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to <4 x i8>* -; AVX1-NEXT: [[WIDE_LOAD1:%.*]] = load <4 x i8>, <4 x i8>* [[TMP11]], align 1 +; AVX1-NEXT: [[WIDE_LOAD4:%.*]] = load <4 x i8>, <4 x i8>* [[TMP11]], align 1 ; AVX1-NEXT: [[TMP12:%.*]] = getelementptr inbounds i8, i8* [[TMP4]], i32 8 ; AVX1-NEXT: [[TMP13:%.*]] = bitcast i8* [[TMP12]] to <4 x i8>* -; AVX1-NEXT: [[WIDE_LOAD2:%.*]] = load <4 x i8>, <4 x i8>* [[TMP13]], align 1 +; AVX1-NEXT: [[WIDE_LOAD5:%.*]] = load <4 x i8>, <4 x i8>* [[TMP13]], align 1 ; AVX1-NEXT: [[TMP14:%.*]] = getelementptr inbounds i8, i8* [[TMP4]], i32 12 ; AVX1-NEXT: [[TMP15:%.*]] = bitcast i8* [[TMP14]] to <4 x i8>* -; AVX1-NEXT: [[WIDE_LOAD3:%.*]] = load <4 x i8>, <4 x i8>* [[TMP15]], align 1 +; AVX1-NEXT: [[WIDE_LOAD6:%.*]] = load <4 x i8>, <4 x i8>* [[TMP15]], align 1 ; AVX1-NEXT: [[TMP16:%.*]] = and <4 x i8> [[WIDE_LOAD]], -; AVX1-NEXT: [[TMP17:%.*]] = and <4 x i8> [[WIDE_LOAD1]], -; AVX1-NEXT: [[TMP18:%.*]] = and <4 x i8> [[WIDE_LOAD2]], -; AVX1-NEXT: [[TMP19:%.*]] = and <4 x i8> [[WIDE_LOAD3]], +; AVX1-NEXT: [[TMP17:%.*]] = and <4 x i8> [[WIDE_LOAD4]], +; AVX1-NEXT: [[TMP18:%.*]] = and <4 x i8> [[WIDE_LOAD5]], +; AVX1-NEXT: [[TMP19:%.*]] = and <4 x i8> [[WIDE_LOAD6]], ; AVX1-NEXT: [[TMP20:%.*]] = icmp eq <4 x i8> [[TMP16]], zeroinitializer ; AVX1-NEXT: [[TMP21:%.*]] = icmp eq <4 x i8> [[TMP17]], zeroinitializer ; AVX1-NEXT: [[TMP22:%.*]] = icmp eq <4 x i8> [[TMP18]], zeroinitializer @@ -2343,17 +2436,17 @@ define void @foo8(double* noalias nocapture %out, i32 ()** noalias nocapture rea ; AVX1-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <4 x i32 ()*> @llvm.masked.load.v4p0f_i32f.p0v4p0f_i32f(<4 x i32 ()*>* [[TMP33]], i32 8, <4 x i1> [[TMP28]], <4 x i32 ()*> undef) ; AVX1-NEXT: [[TMP34:%.*]] = getelementptr inbounds i32 ()*, i32 ()** [[TMP24]], i32 4 ; AVX1-NEXT: [[TMP35:%.*]] = bitcast i32 ()** [[TMP34]] to <4 x i32 ()*>* -; AVX1-NEXT: [[WIDE_MASKED_LOAD4:%.*]] = call <4 x i32 ()*> @llvm.masked.load.v4p0f_i32f.p0v4p0f_i32f(<4 x i32 ()*>* [[TMP35]], i32 8, <4 x i1> [[TMP29]], <4 x i32 ()*> undef) +; AVX1-NEXT: [[WIDE_MASKED_LOAD7:%.*]] = call <4 x i32 ()*> @llvm.masked.load.v4p0f_i32f.p0v4p0f_i32f(<4 x i32 ()*>* [[TMP35]], i32 8, <4 x i1> [[TMP29]], <4 x i32 ()*> undef) ; AVX1-NEXT: [[TMP36:%.*]] = getelementptr inbounds i32 ()*, i32 ()** [[TMP24]], i32 8 ; AVX1-NEXT: [[TMP37:%.*]] = bitcast i32 ()** [[TMP36]] to <4 x i32 ()*>* -; AVX1-NEXT: [[WIDE_MASKED_LOAD5:%.*]] = call <4 x i32 ()*> @llvm.masked.load.v4p0f_i32f.p0v4p0f_i32f(<4 x i32 ()*>* [[TMP37]], i32 8, <4 x i1> [[TMP30]], <4 x i32 ()*> undef) +; AVX1-NEXT: [[WIDE_MASKED_LOAD8:%.*]] = call <4 x i32 ()*> @llvm.masked.load.v4p0f_i32f.p0v4p0f_i32f(<4 x i32 ()*>* [[TMP37]], i32 8, <4 x i1> [[TMP30]], <4 x i32 ()*> undef) ; AVX1-NEXT: [[TMP38:%.*]] = getelementptr inbounds i32 ()*, i32 ()** [[TMP24]], i32 12 ; AVX1-NEXT: [[TMP39:%.*]] = bitcast i32 ()** [[TMP38]] to <4 x i32 ()*>* -; AVX1-NEXT: [[WIDE_MASKED_LOAD6:%.*]] = call <4 x i32 ()*> @llvm.masked.load.v4p0f_i32f.p0v4p0f_i32f(<4 x i32 ()*>* [[TMP39]], i32 8, <4 x i1> [[TMP31]], <4 x i32 ()*> undef) +; AVX1-NEXT: [[WIDE_MASKED_LOAD9:%.*]] = call <4 x i32 ()*> @llvm.masked.load.v4p0f_i32f.p0v4p0f_i32f(<4 x i32 ()*>* [[TMP39]], i32 8, <4 x i1> [[TMP31]], <4 x i32 ()*> undef) ; AVX1-NEXT: [[TMP40:%.*]] = icmp eq <4 x i32 ()*> [[WIDE_MASKED_LOAD]], zeroinitializer -; AVX1-NEXT: [[TMP41:%.*]] = icmp eq <4 x i32 ()*> [[WIDE_MASKED_LOAD4]], zeroinitializer -; AVX1-NEXT: [[TMP42:%.*]] = icmp eq <4 x i32 ()*> [[WIDE_MASKED_LOAD5]], zeroinitializer -; AVX1-NEXT: [[TMP43:%.*]] = icmp eq <4 x i32 ()*> [[WIDE_MASKED_LOAD6]], zeroinitializer +; AVX1-NEXT: [[TMP41:%.*]] = icmp eq <4 x i32 ()*> [[WIDE_MASKED_LOAD7]], zeroinitializer +; AVX1-NEXT: [[TMP42:%.*]] = icmp eq <4 x i32 ()*> [[WIDE_MASKED_LOAD8]], zeroinitializer +; AVX1-NEXT: [[TMP43:%.*]] = icmp eq <4 x i32 ()*> [[WIDE_MASKED_LOAD9]], zeroinitializer ; AVX1-NEXT: [[TMP44:%.*]] = getelementptr inbounds double, double* [[OUT:%.*]], i64 [[TMP0]] ; AVX1-NEXT: [[TMP45:%.*]] = getelementptr inbounds double, double* [[OUT]], i64 [[TMP1]] ; AVX1-NEXT: [[TMP46:%.*]] = getelementptr inbounds double, double* [[OUT]], i64 [[TMP2]] @@ -2426,6 +2519,12 @@ define void @foo8(double* noalias nocapture %out, i32 ()** noalias nocapture rea ; AVX2-NEXT: br label [[VECTOR_BODY:%.*]] ; AVX2: vector.body: ; AVX2-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ] +; AVX2-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i64> undef, i64 [[INDEX]], i32 0 +; AVX2-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT]], <4 x i64> undef, <4 x i32> zeroinitializer +; AVX2-NEXT: [[INDUCTION:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], +; AVX2-NEXT: [[INDUCTION1:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], +; AVX2-NEXT: [[INDUCTION2:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], +; AVX2-NEXT: [[INDUCTION3:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], ; AVX2-NEXT: [[TMP0:%.*]] = add i64 [[INDEX]], 0 ; AVX2-NEXT: [[TMP1:%.*]] = add i64 [[INDEX]], 4 ; AVX2-NEXT: [[TMP2:%.*]] = add i64 [[INDEX]], 8 @@ -2439,17 +2538,17 @@ define void @foo8(double* noalias nocapture %out, i32 ()** noalias nocapture rea ; AVX2-NEXT: [[WIDE_LOAD:%.*]] = load <4 x i8>, <4 x i8>* [[TMP9]], align 1 ; AVX2-NEXT: [[TMP10:%.*]] = getelementptr inbounds i8, i8* [[TMP4]], i32 4 ; AVX2-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to <4 x i8>* -; AVX2-NEXT: [[WIDE_LOAD1:%.*]] = load <4 x i8>, <4 x i8>* [[TMP11]], align 1 +; AVX2-NEXT: [[WIDE_LOAD4:%.*]] = load <4 x i8>, <4 x i8>* [[TMP11]], align 1 ; AVX2-NEXT: [[TMP12:%.*]] = getelementptr inbounds i8, i8* [[TMP4]], i32 8 ; AVX2-NEXT: [[TMP13:%.*]] = bitcast i8* [[TMP12]] to <4 x i8>* -; AVX2-NEXT: [[WIDE_LOAD2:%.*]] = load <4 x i8>, <4 x i8>* [[TMP13]], align 1 +; AVX2-NEXT: [[WIDE_LOAD5:%.*]] = load <4 x i8>, <4 x i8>* [[TMP13]], align 1 ; AVX2-NEXT: [[TMP14:%.*]] = getelementptr inbounds i8, i8* [[TMP4]], i32 12 ; AVX2-NEXT: [[TMP15:%.*]] = bitcast i8* [[TMP14]] to <4 x i8>* -; AVX2-NEXT: [[WIDE_LOAD3:%.*]] = load <4 x i8>, <4 x i8>* [[TMP15]], align 1 +; AVX2-NEXT: [[WIDE_LOAD6:%.*]] = load <4 x i8>, <4 x i8>* [[TMP15]], align 1 ; AVX2-NEXT: [[TMP16:%.*]] = and <4 x i8> [[WIDE_LOAD]], -; AVX2-NEXT: [[TMP17:%.*]] = and <4 x i8> [[WIDE_LOAD1]], -; AVX2-NEXT: [[TMP18:%.*]] = and <4 x i8> [[WIDE_LOAD2]], -; AVX2-NEXT: [[TMP19:%.*]] = and <4 x i8> [[WIDE_LOAD3]], +; AVX2-NEXT: [[TMP17:%.*]] = and <4 x i8> [[WIDE_LOAD4]], +; AVX2-NEXT: [[TMP18:%.*]] = and <4 x i8> [[WIDE_LOAD5]], +; AVX2-NEXT: [[TMP19:%.*]] = and <4 x i8> [[WIDE_LOAD6]], ; AVX2-NEXT: [[TMP20:%.*]] = icmp eq <4 x i8> [[TMP16]], zeroinitializer ; AVX2-NEXT: [[TMP21:%.*]] = icmp eq <4 x i8> [[TMP17]], zeroinitializer ; AVX2-NEXT: [[TMP22:%.*]] = icmp eq <4 x i8> [[TMP18]], zeroinitializer @@ -2467,17 +2566,17 @@ define void @foo8(double* noalias nocapture %out, i32 ()** noalias nocapture rea ; AVX2-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <4 x i32 ()*> @llvm.masked.load.v4p0f_i32f.p0v4p0f_i32f(<4 x i32 ()*>* [[TMP33]], i32 8, <4 x i1> [[TMP28]], <4 x i32 ()*> undef) ; AVX2-NEXT: [[TMP34:%.*]] = getelementptr inbounds i32 ()*, i32 ()** [[TMP24]], i32 4 ; AVX2-NEXT: [[TMP35:%.*]] = bitcast i32 ()** [[TMP34]] to <4 x i32 ()*>* -; AVX2-NEXT: [[WIDE_MASKED_LOAD4:%.*]] = call <4 x i32 ()*> @llvm.masked.load.v4p0f_i32f.p0v4p0f_i32f(<4 x i32 ()*>* [[TMP35]], i32 8, <4 x i1> [[TMP29]], <4 x i32 ()*> undef) +; AVX2-NEXT: [[WIDE_MASKED_LOAD7:%.*]] = call <4 x i32 ()*> @llvm.masked.load.v4p0f_i32f.p0v4p0f_i32f(<4 x i32 ()*>* [[TMP35]], i32 8, <4 x i1> [[TMP29]], <4 x i32 ()*> undef) ; AVX2-NEXT: [[TMP36:%.*]] = getelementptr inbounds i32 ()*, i32 ()** [[TMP24]], i32 8 ; AVX2-NEXT: [[TMP37:%.*]] = bitcast i32 ()** [[TMP36]] to <4 x i32 ()*>* -; AVX2-NEXT: [[WIDE_MASKED_LOAD5:%.*]] = call <4 x i32 ()*> @llvm.masked.load.v4p0f_i32f.p0v4p0f_i32f(<4 x i32 ()*>* [[TMP37]], i32 8, <4 x i1> [[TMP30]], <4 x i32 ()*> undef) +; AVX2-NEXT: [[WIDE_MASKED_LOAD8:%.*]] = call <4 x i32 ()*> @llvm.masked.load.v4p0f_i32f.p0v4p0f_i32f(<4 x i32 ()*>* [[TMP37]], i32 8, <4 x i1> [[TMP30]], <4 x i32 ()*> undef) ; AVX2-NEXT: [[TMP38:%.*]] = getelementptr inbounds i32 ()*, i32 ()** [[TMP24]], i32 12 ; AVX2-NEXT: [[TMP39:%.*]] = bitcast i32 ()** [[TMP38]] to <4 x i32 ()*>* -; AVX2-NEXT: [[WIDE_MASKED_LOAD6:%.*]] = call <4 x i32 ()*> @llvm.masked.load.v4p0f_i32f.p0v4p0f_i32f(<4 x i32 ()*>* [[TMP39]], i32 8, <4 x i1> [[TMP31]], <4 x i32 ()*> undef) +; AVX2-NEXT: [[WIDE_MASKED_LOAD9:%.*]] = call <4 x i32 ()*> @llvm.masked.load.v4p0f_i32f.p0v4p0f_i32f(<4 x i32 ()*>* [[TMP39]], i32 8, <4 x i1> [[TMP31]], <4 x i32 ()*> undef) ; AVX2-NEXT: [[TMP40:%.*]] = icmp eq <4 x i32 ()*> [[WIDE_MASKED_LOAD]], zeroinitializer -; AVX2-NEXT: [[TMP41:%.*]] = icmp eq <4 x i32 ()*> [[WIDE_MASKED_LOAD4]], zeroinitializer -; AVX2-NEXT: [[TMP42:%.*]] = icmp eq <4 x i32 ()*> [[WIDE_MASKED_LOAD5]], zeroinitializer -; AVX2-NEXT: [[TMP43:%.*]] = icmp eq <4 x i32 ()*> [[WIDE_MASKED_LOAD6]], zeroinitializer +; AVX2-NEXT: [[TMP41:%.*]] = icmp eq <4 x i32 ()*> [[WIDE_MASKED_LOAD7]], zeroinitializer +; AVX2-NEXT: [[TMP42:%.*]] = icmp eq <4 x i32 ()*> [[WIDE_MASKED_LOAD8]], zeroinitializer +; AVX2-NEXT: [[TMP43:%.*]] = icmp eq <4 x i32 ()*> [[WIDE_MASKED_LOAD9]], zeroinitializer ; AVX2-NEXT: [[TMP44:%.*]] = getelementptr inbounds double, double* [[OUT:%.*]], i64 [[TMP0]] ; AVX2-NEXT: [[TMP45:%.*]] = getelementptr inbounds double, double* [[OUT]], i64 [[TMP1]] ; AVX2-NEXT: [[TMP46:%.*]] = getelementptr inbounds double, double* [[OUT]], i64 [[TMP2]] @@ -2550,6 +2649,12 @@ define void @foo8(double* noalias nocapture %out, i32 ()** noalias nocapture rea ; AVX512-NEXT: br label [[VECTOR_BODY:%.*]] ; AVX512: vector.body: ; AVX512-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ] +; AVX512-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <8 x i64> undef, i64 [[INDEX]], i32 0 +; AVX512-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <8 x i64> [[BROADCAST_SPLATINSERT]], <8 x i64> undef, <8 x i32> zeroinitializer +; AVX512-NEXT: [[INDUCTION:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], +; AVX512-NEXT: [[INDUCTION1:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], +; AVX512-NEXT: [[INDUCTION2:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], +; AVX512-NEXT: [[INDUCTION3:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], ; AVX512-NEXT: [[TMP0:%.*]] = add i64 [[INDEX]], 0 ; AVX512-NEXT: [[TMP1:%.*]] = add i64 [[INDEX]], 8 ; AVX512-NEXT: [[TMP2:%.*]] = add i64 [[INDEX]], 16 @@ -2563,17 +2668,17 @@ define void @foo8(double* noalias nocapture %out, i32 ()** noalias nocapture rea ; AVX512-NEXT: [[WIDE_LOAD:%.*]] = load <8 x i8>, <8 x i8>* [[TMP9]], align 1 ; AVX512-NEXT: [[TMP10:%.*]] = getelementptr inbounds i8, i8* [[TMP4]], i32 8 ; AVX512-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to <8 x i8>* -; AVX512-NEXT: [[WIDE_LOAD1:%.*]] = load <8 x i8>, <8 x i8>* [[TMP11]], align 1 +; AVX512-NEXT: [[WIDE_LOAD4:%.*]] = load <8 x i8>, <8 x i8>* [[TMP11]], align 1 ; AVX512-NEXT: [[TMP12:%.*]] = getelementptr inbounds i8, i8* [[TMP4]], i32 16 ; AVX512-NEXT: [[TMP13:%.*]] = bitcast i8* [[TMP12]] to <8 x i8>* -; AVX512-NEXT: [[WIDE_LOAD2:%.*]] = load <8 x i8>, <8 x i8>* [[TMP13]], align 1 +; AVX512-NEXT: [[WIDE_LOAD5:%.*]] = load <8 x i8>, <8 x i8>* [[TMP13]], align 1 ; AVX512-NEXT: [[TMP14:%.*]] = getelementptr inbounds i8, i8* [[TMP4]], i32 24 ; AVX512-NEXT: [[TMP15:%.*]] = bitcast i8* [[TMP14]] to <8 x i8>* -; AVX512-NEXT: [[WIDE_LOAD3:%.*]] = load <8 x i8>, <8 x i8>* [[TMP15]], align 1 +; AVX512-NEXT: [[WIDE_LOAD6:%.*]] = load <8 x i8>, <8 x i8>* [[TMP15]], align 1 ; AVX512-NEXT: [[TMP16:%.*]] = and <8 x i8> [[WIDE_LOAD]], -; AVX512-NEXT: [[TMP17:%.*]] = and <8 x i8> [[WIDE_LOAD1]], -; AVX512-NEXT: [[TMP18:%.*]] = and <8 x i8> [[WIDE_LOAD2]], -; AVX512-NEXT: [[TMP19:%.*]] = and <8 x i8> [[WIDE_LOAD3]], +; AVX512-NEXT: [[TMP17:%.*]] = and <8 x i8> [[WIDE_LOAD4]], +; AVX512-NEXT: [[TMP18:%.*]] = and <8 x i8> [[WIDE_LOAD5]], +; AVX512-NEXT: [[TMP19:%.*]] = and <8 x i8> [[WIDE_LOAD6]], ; AVX512-NEXT: [[TMP20:%.*]] = icmp eq <8 x i8> [[TMP16]], zeroinitializer ; AVX512-NEXT: [[TMP21:%.*]] = icmp eq <8 x i8> [[TMP17]], zeroinitializer ; AVX512-NEXT: [[TMP22:%.*]] = icmp eq <8 x i8> [[TMP18]], zeroinitializer @@ -2591,17 +2696,17 @@ define void @foo8(double* noalias nocapture %out, i32 ()** noalias nocapture rea ; AVX512-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <8 x i32 ()*> @llvm.masked.load.v8p0f_i32f.p0v8p0f_i32f(<8 x i32 ()*>* [[TMP33]], i32 8, <8 x i1> [[TMP28]], <8 x i32 ()*> undef) ; AVX512-NEXT: [[TMP34:%.*]] = getelementptr inbounds i32 ()*, i32 ()** [[TMP24]], i32 8 ; AVX512-NEXT: [[TMP35:%.*]] = bitcast i32 ()** [[TMP34]] to <8 x i32 ()*>* -; AVX512-NEXT: [[WIDE_MASKED_LOAD4:%.*]] = call <8 x i32 ()*> @llvm.masked.load.v8p0f_i32f.p0v8p0f_i32f(<8 x i32 ()*>* [[TMP35]], i32 8, <8 x i1> [[TMP29]], <8 x i32 ()*> undef) +; AVX512-NEXT: [[WIDE_MASKED_LOAD7:%.*]] = call <8 x i32 ()*> @llvm.masked.load.v8p0f_i32f.p0v8p0f_i32f(<8 x i32 ()*>* [[TMP35]], i32 8, <8 x i1> [[TMP29]], <8 x i32 ()*> undef) ; AVX512-NEXT: [[TMP36:%.*]] = getelementptr inbounds i32 ()*, i32 ()** [[TMP24]], i32 16 ; AVX512-NEXT: [[TMP37:%.*]] = bitcast i32 ()** [[TMP36]] to <8 x i32 ()*>* -; AVX512-NEXT: [[WIDE_MASKED_LOAD5:%.*]] = call <8 x i32 ()*> @llvm.masked.load.v8p0f_i32f.p0v8p0f_i32f(<8 x i32 ()*>* [[TMP37]], i32 8, <8 x i1> [[TMP30]], <8 x i32 ()*> undef) +; AVX512-NEXT: [[WIDE_MASKED_LOAD8:%.*]] = call <8 x i32 ()*> @llvm.masked.load.v8p0f_i32f.p0v8p0f_i32f(<8 x i32 ()*>* [[TMP37]], i32 8, <8 x i1> [[TMP30]], <8 x i32 ()*> undef) ; AVX512-NEXT: [[TMP38:%.*]] = getelementptr inbounds i32 ()*, i32 ()** [[TMP24]], i32 24 ; AVX512-NEXT: [[TMP39:%.*]] = bitcast i32 ()** [[TMP38]] to <8 x i32 ()*>* -; AVX512-NEXT: [[WIDE_MASKED_LOAD6:%.*]] = call <8 x i32 ()*> @llvm.masked.load.v8p0f_i32f.p0v8p0f_i32f(<8 x i32 ()*>* [[TMP39]], i32 8, <8 x i1> [[TMP31]], <8 x i32 ()*> undef) +; AVX512-NEXT: [[WIDE_MASKED_LOAD9:%.*]] = call <8 x i32 ()*> @llvm.masked.load.v8p0f_i32f.p0v8p0f_i32f(<8 x i32 ()*>* [[TMP39]], i32 8, <8 x i1> [[TMP31]], <8 x i32 ()*> undef) ; AVX512-NEXT: [[TMP40:%.*]] = icmp eq <8 x i32 ()*> [[WIDE_MASKED_LOAD]], zeroinitializer -; AVX512-NEXT: [[TMP41:%.*]] = icmp eq <8 x i32 ()*> [[WIDE_MASKED_LOAD4]], zeroinitializer -; AVX512-NEXT: [[TMP42:%.*]] = icmp eq <8 x i32 ()*> [[WIDE_MASKED_LOAD5]], zeroinitializer -; AVX512-NEXT: [[TMP43:%.*]] = icmp eq <8 x i32 ()*> [[WIDE_MASKED_LOAD6]], zeroinitializer +; AVX512-NEXT: [[TMP41:%.*]] = icmp eq <8 x i32 ()*> [[WIDE_MASKED_LOAD7]], zeroinitializer +; AVX512-NEXT: [[TMP42:%.*]] = icmp eq <8 x i32 ()*> [[WIDE_MASKED_LOAD8]], zeroinitializer +; AVX512-NEXT: [[TMP43:%.*]] = icmp eq <8 x i32 ()*> [[WIDE_MASKED_LOAD9]], zeroinitializer ; AVX512-NEXT: [[TMP44:%.*]] = getelementptr inbounds double, double* [[OUT:%.*]], i64 [[TMP0]] ; AVX512-NEXT: [[TMP45:%.*]] = getelementptr inbounds double, double* [[OUT]], i64 [[TMP1]] ; AVX512-NEXT: [[TMP46:%.*]] = getelementptr inbounds double, double* [[OUT]], i64 [[TMP2]] diff --git a/llvm/test/Transforms/LoopVectorize/X86/metadata-enable.ll b/llvm/test/Transforms/LoopVectorize/X86/metadata-enable.ll index 0a3a504b8ef2..1f0aab30b4dd 100644 --- a/llvm/test/Transforms/LoopVectorize/X86/metadata-enable.ll +++ b/llvm/test/Transforms/LoopVectorize/X86/metadata-enable.ll @@ -19,115 +19,115 @@ target triple = "x86_64-unknown-linux-gnu" define i32 @enabled(i32* noalias nocapture %a, i32* noalias nocapture readonly %b, i32 %N) { ; O1-LABEL: @enabled( ; O1-NEXT: entry: -; O1-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i32> undef, i32 [[N:%.*]], i32 0 -; O1-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT]], <4 x i32> undef, <4 x i32> zeroinitializer +; O1-NEXT: [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <4 x i32> undef, i32 [[N:%.*]], i32 0 +; O1-NEXT: [[BROADCAST_SPLAT2:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT1]], <4 x i32> undef, <4 x i32> zeroinitializer ; O1-NEXT: [[TMP0:%.*]] = bitcast i32* [[B:%.*]] to <4 x i32>* ; O1-NEXT: [[WIDE_LOAD:%.*]] = load <4 x i32>, <4 x i32>* [[TMP0]], align 4 -; O1-NEXT: [[TMP1:%.*]] = add nsw <4 x i32> [[WIDE_LOAD]], [[BROADCAST_SPLAT]] +; O1-NEXT: [[TMP1:%.*]] = add nsw <4 x i32> [[WIDE_LOAD]], [[BROADCAST_SPLAT2]] ; O1-NEXT: [[TMP2:%.*]] = bitcast i32* [[A:%.*]] to <4 x i32>* ; O1-NEXT: store <4 x i32> [[TMP1]], <4 x i32>* [[TMP2]], align 4 ; O1-NEXT: [[TMP3:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 4 ; O1-NEXT: [[TMP4:%.*]] = bitcast i32* [[TMP3]] to <4 x i32>* ; O1-NEXT: [[WIDE_LOAD_1:%.*]] = load <4 x i32>, <4 x i32>* [[TMP4]], align 4 -; O1-NEXT: [[TMP5:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_1]], [[BROADCAST_SPLAT]] +; O1-NEXT: [[TMP5:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_1]], [[BROADCAST_SPLAT2]] ; O1-NEXT: [[TMP6:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 4 ; O1-NEXT: [[TMP7:%.*]] = bitcast i32* [[TMP6]] to <4 x i32>* ; O1-NEXT: store <4 x i32> [[TMP5]], <4 x i32>* [[TMP7]], align 4 ; O1-NEXT: [[TMP8:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 8 ; O1-NEXT: [[TMP9:%.*]] = bitcast i32* [[TMP8]] to <4 x i32>* ; O1-NEXT: [[WIDE_LOAD_2:%.*]] = load <4 x i32>, <4 x i32>* [[TMP9]], align 4 -; O1-NEXT: [[TMP10:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_2]], [[BROADCAST_SPLAT]] +; O1-NEXT: [[TMP10:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_2]], [[BROADCAST_SPLAT2]] ; O1-NEXT: [[TMP11:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 8 ; O1-NEXT: [[TMP12:%.*]] = bitcast i32* [[TMP11]] to <4 x i32>* ; O1-NEXT: store <4 x i32> [[TMP10]], <4 x i32>* [[TMP12]], align 4 ; O1-NEXT: [[TMP13:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 12 ; O1-NEXT: [[TMP14:%.*]] = bitcast i32* [[TMP13]] to <4 x i32>* ; O1-NEXT: [[WIDE_LOAD_3:%.*]] = load <4 x i32>, <4 x i32>* [[TMP14]], align 4 -; O1-NEXT: [[TMP15:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_3]], [[BROADCAST_SPLAT]] +; O1-NEXT: [[TMP15:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_3]], [[BROADCAST_SPLAT2]] ; O1-NEXT: [[TMP16:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 12 ; O1-NEXT: [[TMP17:%.*]] = bitcast i32* [[TMP16]] to <4 x i32>* ; O1-NEXT: store <4 x i32> [[TMP15]], <4 x i32>* [[TMP17]], align 4 ; O1-NEXT: [[TMP18:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 16 ; O1-NEXT: [[TMP19:%.*]] = bitcast i32* [[TMP18]] to <4 x i32>* ; O1-NEXT: [[WIDE_LOAD_4:%.*]] = load <4 x i32>, <4 x i32>* [[TMP19]], align 4 -; O1-NEXT: [[TMP20:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_4]], [[BROADCAST_SPLAT]] +; O1-NEXT: [[TMP20:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_4]], [[BROADCAST_SPLAT2]] ; O1-NEXT: [[TMP21:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 16 ; O1-NEXT: [[TMP22:%.*]] = bitcast i32* [[TMP21]] to <4 x i32>* ; O1-NEXT: store <4 x i32> [[TMP20]], <4 x i32>* [[TMP22]], align 4 ; O1-NEXT: [[TMP23:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 20 ; O1-NEXT: [[TMP24:%.*]] = bitcast i32* [[TMP23]] to <4 x i32>* ; O1-NEXT: [[WIDE_LOAD_5:%.*]] = load <4 x i32>, <4 x i32>* [[TMP24]], align 4 -; O1-NEXT: [[TMP25:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_5]], [[BROADCAST_SPLAT]] +; O1-NEXT: [[TMP25:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_5]], [[BROADCAST_SPLAT2]] ; O1-NEXT: [[TMP26:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 20 ; O1-NEXT: [[TMP27:%.*]] = bitcast i32* [[TMP26]] to <4 x i32>* ; O1-NEXT: store <4 x i32> [[TMP25]], <4 x i32>* [[TMP27]], align 4 ; O1-NEXT: [[TMP28:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 24 ; O1-NEXT: [[TMP29:%.*]] = bitcast i32* [[TMP28]] to <4 x i32>* ; O1-NEXT: [[WIDE_LOAD_6:%.*]] = load <4 x i32>, <4 x i32>* [[TMP29]], align 4 -; O1-NEXT: [[TMP30:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_6]], [[BROADCAST_SPLAT]] +; O1-NEXT: [[TMP30:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_6]], [[BROADCAST_SPLAT2]] ; O1-NEXT: [[TMP31:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 24 ; O1-NEXT: [[TMP32:%.*]] = bitcast i32* [[TMP31]] to <4 x i32>* ; O1-NEXT: store <4 x i32> [[TMP30]], <4 x i32>* [[TMP32]], align 4 ; O1-NEXT: [[TMP33:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 28 ; O1-NEXT: [[TMP34:%.*]] = bitcast i32* [[TMP33]] to <4 x i32>* ; O1-NEXT: [[WIDE_LOAD_7:%.*]] = load <4 x i32>, <4 x i32>* [[TMP34]], align 4 -; O1-NEXT: [[TMP35:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_7]], [[BROADCAST_SPLAT]] +; O1-NEXT: [[TMP35:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_7]], [[BROADCAST_SPLAT2]] ; O1-NEXT: [[TMP36:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 28 ; O1-NEXT: [[TMP37:%.*]] = bitcast i32* [[TMP36]] to <4 x i32>* ; O1-NEXT: store <4 x i32> [[TMP35]], <4 x i32>* [[TMP37]], align 4 ; O1-NEXT: [[TMP38:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 32 ; O1-NEXT: [[TMP39:%.*]] = bitcast i32* [[TMP38]] to <4 x i32>* ; O1-NEXT: [[WIDE_LOAD_8:%.*]] = load <4 x i32>, <4 x i32>* [[TMP39]], align 4 -; O1-NEXT: [[TMP40:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_8]], [[BROADCAST_SPLAT]] +; O1-NEXT: [[TMP40:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_8]], [[BROADCAST_SPLAT2]] ; O1-NEXT: [[TMP41:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 32 ; O1-NEXT: [[TMP42:%.*]] = bitcast i32* [[TMP41]] to <4 x i32>* ; O1-NEXT: store <4 x i32> [[TMP40]], <4 x i32>* [[TMP42]], align 4 ; O1-NEXT: [[TMP43:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 36 ; O1-NEXT: [[TMP44:%.*]] = bitcast i32* [[TMP43]] to <4 x i32>* ; O1-NEXT: [[WIDE_LOAD_9:%.*]] = load <4 x i32>, <4 x i32>* [[TMP44]], align 4 -; O1-NEXT: [[TMP45:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_9]], [[BROADCAST_SPLAT]] +; O1-NEXT: [[TMP45:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_9]], [[BROADCAST_SPLAT2]] ; O1-NEXT: [[TMP46:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 36 ; O1-NEXT: [[TMP47:%.*]] = bitcast i32* [[TMP46]] to <4 x i32>* ; O1-NEXT: store <4 x i32> [[TMP45]], <4 x i32>* [[TMP47]], align 4 ; O1-NEXT: [[TMP48:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 40 ; O1-NEXT: [[TMP49:%.*]] = bitcast i32* [[TMP48]] to <4 x i32>* ; O1-NEXT: [[WIDE_LOAD_10:%.*]] = load <4 x i32>, <4 x i32>* [[TMP49]], align 4 -; O1-NEXT: [[TMP50:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_10]], [[BROADCAST_SPLAT]] +; O1-NEXT: [[TMP50:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_10]], [[BROADCAST_SPLAT2]] ; O1-NEXT: [[TMP51:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 40 ; O1-NEXT: [[TMP52:%.*]] = bitcast i32* [[TMP51]] to <4 x i32>* ; O1-NEXT: store <4 x i32> [[TMP50]], <4 x i32>* [[TMP52]], align 4 ; O1-NEXT: [[TMP53:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 44 ; O1-NEXT: [[TMP54:%.*]] = bitcast i32* [[TMP53]] to <4 x i32>* ; O1-NEXT: [[WIDE_LOAD_11:%.*]] = load <4 x i32>, <4 x i32>* [[TMP54]], align 4 -; O1-NEXT: [[TMP55:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_11]], [[BROADCAST_SPLAT]] +; O1-NEXT: [[TMP55:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_11]], [[BROADCAST_SPLAT2]] ; O1-NEXT: [[TMP56:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 44 ; O1-NEXT: [[TMP57:%.*]] = bitcast i32* [[TMP56]] to <4 x i32>* ; O1-NEXT: store <4 x i32> [[TMP55]], <4 x i32>* [[TMP57]], align 4 ; O1-NEXT: [[TMP58:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 48 ; O1-NEXT: [[TMP59:%.*]] = bitcast i32* [[TMP58]] to <4 x i32>* ; O1-NEXT: [[WIDE_LOAD_12:%.*]] = load <4 x i32>, <4 x i32>* [[TMP59]], align 4 -; O1-NEXT: [[TMP60:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_12]], [[BROADCAST_SPLAT]] +; O1-NEXT: [[TMP60:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_12]], [[BROADCAST_SPLAT2]] ; O1-NEXT: [[TMP61:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 48 ; O1-NEXT: [[TMP62:%.*]] = bitcast i32* [[TMP61]] to <4 x i32>* ; O1-NEXT: store <4 x i32> [[TMP60]], <4 x i32>* [[TMP62]], align 4 ; O1-NEXT: [[TMP63:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 52 ; O1-NEXT: [[TMP64:%.*]] = bitcast i32* [[TMP63]] to <4 x i32>* ; O1-NEXT: [[WIDE_LOAD_13:%.*]] = load <4 x i32>, <4 x i32>* [[TMP64]], align 4 -; O1-NEXT: [[TMP65:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_13]], [[BROADCAST_SPLAT]] +; O1-NEXT: [[TMP65:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_13]], [[BROADCAST_SPLAT2]] ; O1-NEXT: [[TMP66:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 52 ; O1-NEXT: [[TMP67:%.*]] = bitcast i32* [[TMP66]] to <4 x i32>* ; O1-NEXT: store <4 x i32> [[TMP65]], <4 x i32>* [[TMP67]], align 4 ; O1-NEXT: [[TMP68:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 56 ; O1-NEXT: [[TMP69:%.*]] = bitcast i32* [[TMP68]] to <4 x i32>* ; O1-NEXT: [[WIDE_LOAD_14:%.*]] = load <4 x i32>, <4 x i32>* [[TMP69]], align 4 -; O1-NEXT: [[TMP70:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_14]], [[BROADCAST_SPLAT]] +; O1-NEXT: [[TMP70:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_14]], [[BROADCAST_SPLAT2]] ; O1-NEXT: [[TMP71:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 56 ; O1-NEXT: [[TMP72:%.*]] = bitcast i32* [[TMP71]] to <4 x i32>* ; O1-NEXT: store <4 x i32> [[TMP70]], <4 x i32>* [[TMP72]], align 4 ; O1-NEXT: [[TMP73:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 60 ; O1-NEXT: [[TMP74:%.*]] = bitcast i32* [[TMP73]] to <4 x i32>* ; O1-NEXT: [[WIDE_LOAD_15:%.*]] = load <4 x i32>, <4 x i32>* [[TMP74]], align 4 -; O1-NEXT: [[TMP75:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_15]], [[BROADCAST_SPLAT]] +; O1-NEXT: [[TMP75:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_15]], [[BROADCAST_SPLAT2]] ; O1-NEXT: [[TMP76:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 60 ; O1-NEXT: [[TMP77:%.*]] = bitcast i32* [[TMP76]] to <4 x i32>* ; O1-NEXT: store <4 x i32> [[TMP75]], <4 x i32>* [[TMP77]], align 4 @@ -136,115 +136,115 @@ define i32 @enabled(i32* noalias nocapture %a, i32* noalias nocapture readonly % ; ; O2-LABEL: @enabled( ; O2-NEXT: entry: -; O2-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i32> undef, i32 [[N:%.*]], i32 0 -; O2-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT]], <4 x i32> undef, <4 x i32> zeroinitializer +; O2-NEXT: [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <4 x i32> undef, i32 [[N:%.*]], i32 0 +; O2-NEXT: [[BROADCAST_SPLAT2:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT1]], <4 x i32> undef, <4 x i32> zeroinitializer ; O2-NEXT: [[TMP0:%.*]] = bitcast i32* [[B:%.*]] to <4 x i32>* ; O2-NEXT: [[WIDE_LOAD:%.*]] = load <4 x i32>, <4 x i32>* [[TMP0]], align 4 -; O2-NEXT: [[TMP1:%.*]] = add nsw <4 x i32> [[WIDE_LOAD]], [[BROADCAST_SPLAT]] +; O2-NEXT: [[TMP1:%.*]] = add nsw <4 x i32> [[WIDE_LOAD]], [[BROADCAST_SPLAT2]] ; O2-NEXT: [[TMP2:%.*]] = bitcast i32* [[A:%.*]] to <4 x i32>* ; O2-NEXT: store <4 x i32> [[TMP1]], <4 x i32>* [[TMP2]], align 4 ; O2-NEXT: [[TMP3:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 4 ; O2-NEXT: [[TMP4:%.*]] = bitcast i32* [[TMP3]] to <4 x i32>* ; O2-NEXT: [[WIDE_LOAD_1:%.*]] = load <4 x i32>, <4 x i32>* [[TMP4]], align 4 -; O2-NEXT: [[TMP5:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_1]], [[BROADCAST_SPLAT]] +; O2-NEXT: [[TMP5:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_1]], [[BROADCAST_SPLAT2]] ; O2-NEXT: [[TMP6:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 4 ; O2-NEXT: [[TMP7:%.*]] = bitcast i32* [[TMP6]] to <4 x i32>* ; O2-NEXT: store <4 x i32> [[TMP5]], <4 x i32>* [[TMP7]], align 4 ; O2-NEXT: [[TMP8:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 8 ; O2-NEXT: [[TMP9:%.*]] = bitcast i32* [[TMP8]] to <4 x i32>* ; O2-NEXT: [[WIDE_LOAD_2:%.*]] = load <4 x i32>, <4 x i32>* [[TMP9]], align 4 -; O2-NEXT: [[TMP10:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_2]], [[BROADCAST_SPLAT]] +; O2-NEXT: [[TMP10:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_2]], [[BROADCAST_SPLAT2]] ; O2-NEXT: [[TMP11:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 8 ; O2-NEXT: [[TMP12:%.*]] = bitcast i32* [[TMP11]] to <4 x i32>* ; O2-NEXT: store <4 x i32> [[TMP10]], <4 x i32>* [[TMP12]], align 4 ; O2-NEXT: [[TMP13:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 12 ; O2-NEXT: [[TMP14:%.*]] = bitcast i32* [[TMP13]] to <4 x i32>* ; O2-NEXT: [[WIDE_LOAD_3:%.*]] = load <4 x i32>, <4 x i32>* [[TMP14]], align 4 -; O2-NEXT: [[TMP15:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_3]], [[BROADCAST_SPLAT]] +; O2-NEXT: [[TMP15:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_3]], [[BROADCAST_SPLAT2]] ; O2-NEXT: [[TMP16:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 12 ; O2-NEXT: [[TMP17:%.*]] = bitcast i32* [[TMP16]] to <4 x i32>* ; O2-NEXT: store <4 x i32> [[TMP15]], <4 x i32>* [[TMP17]], align 4 ; O2-NEXT: [[TMP18:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 16 ; O2-NEXT: [[TMP19:%.*]] = bitcast i32* [[TMP18]] to <4 x i32>* ; O2-NEXT: [[WIDE_LOAD_4:%.*]] = load <4 x i32>, <4 x i32>* [[TMP19]], align 4 -; O2-NEXT: [[TMP20:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_4]], [[BROADCAST_SPLAT]] +; O2-NEXT: [[TMP20:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_4]], [[BROADCAST_SPLAT2]] ; O2-NEXT: [[TMP21:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 16 ; O2-NEXT: [[TMP22:%.*]] = bitcast i32* [[TMP21]] to <4 x i32>* ; O2-NEXT: store <4 x i32> [[TMP20]], <4 x i32>* [[TMP22]], align 4 ; O2-NEXT: [[TMP23:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 20 ; O2-NEXT: [[TMP24:%.*]] = bitcast i32* [[TMP23]] to <4 x i32>* ; O2-NEXT: [[WIDE_LOAD_5:%.*]] = load <4 x i32>, <4 x i32>* [[TMP24]], align 4 -; O2-NEXT: [[TMP25:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_5]], [[BROADCAST_SPLAT]] +; O2-NEXT: [[TMP25:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_5]], [[BROADCAST_SPLAT2]] ; O2-NEXT: [[TMP26:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 20 ; O2-NEXT: [[TMP27:%.*]] = bitcast i32* [[TMP26]] to <4 x i32>* ; O2-NEXT: store <4 x i32> [[TMP25]], <4 x i32>* [[TMP27]], align 4 ; O2-NEXT: [[TMP28:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 24 ; O2-NEXT: [[TMP29:%.*]] = bitcast i32* [[TMP28]] to <4 x i32>* ; O2-NEXT: [[WIDE_LOAD_6:%.*]] = load <4 x i32>, <4 x i32>* [[TMP29]], align 4 -; O2-NEXT: [[TMP30:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_6]], [[BROADCAST_SPLAT]] +; O2-NEXT: [[TMP30:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_6]], [[BROADCAST_SPLAT2]] ; O2-NEXT: [[TMP31:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 24 ; O2-NEXT: [[TMP32:%.*]] = bitcast i32* [[TMP31]] to <4 x i32>* ; O2-NEXT: store <4 x i32> [[TMP30]], <4 x i32>* [[TMP32]], align 4 ; O2-NEXT: [[TMP33:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 28 ; O2-NEXT: [[TMP34:%.*]] = bitcast i32* [[TMP33]] to <4 x i32>* ; O2-NEXT: [[WIDE_LOAD_7:%.*]] = load <4 x i32>, <4 x i32>* [[TMP34]], align 4 -; O2-NEXT: [[TMP35:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_7]], [[BROADCAST_SPLAT]] +; O2-NEXT: [[TMP35:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_7]], [[BROADCAST_SPLAT2]] ; O2-NEXT: [[TMP36:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 28 ; O2-NEXT: [[TMP37:%.*]] = bitcast i32* [[TMP36]] to <4 x i32>* ; O2-NEXT: store <4 x i32> [[TMP35]], <4 x i32>* [[TMP37]], align 4 ; O2-NEXT: [[TMP38:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 32 ; O2-NEXT: [[TMP39:%.*]] = bitcast i32* [[TMP38]] to <4 x i32>* ; O2-NEXT: [[WIDE_LOAD_8:%.*]] = load <4 x i32>, <4 x i32>* [[TMP39]], align 4 -; O2-NEXT: [[TMP40:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_8]], [[BROADCAST_SPLAT]] +; O2-NEXT: [[TMP40:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_8]], [[BROADCAST_SPLAT2]] ; O2-NEXT: [[TMP41:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 32 ; O2-NEXT: [[TMP42:%.*]] = bitcast i32* [[TMP41]] to <4 x i32>* ; O2-NEXT: store <4 x i32> [[TMP40]], <4 x i32>* [[TMP42]], align 4 ; O2-NEXT: [[TMP43:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 36 ; O2-NEXT: [[TMP44:%.*]] = bitcast i32* [[TMP43]] to <4 x i32>* ; O2-NEXT: [[WIDE_LOAD_9:%.*]] = load <4 x i32>, <4 x i32>* [[TMP44]], align 4 -; O2-NEXT: [[TMP45:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_9]], [[BROADCAST_SPLAT]] +; O2-NEXT: [[TMP45:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_9]], [[BROADCAST_SPLAT2]] ; O2-NEXT: [[TMP46:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 36 ; O2-NEXT: [[TMP47:%.*]] = bitcast i32* [[TMP46]] to <4 x i32>* ; O2-NEXT: store <4 x i32> [[TMP45]], <4 x i32>* [[TMP47]], align 4 ; O2-NEXT: [[TMP48:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 40 ; O2-NEXT: [[TMP49:%.*]] = bitcast i32* [[TMP48]] to <4 x i32>* ; O2-NEXT: [[WIDE_LOAD_10:%.*]] = load <4 x i32>, <4 x i32>* [[TMP49]], align 4 -; O2-NEXT: [[TMP50:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_10]], [[BROADCAST_SPLAT]] +; O2-NEXT: [[TMP50:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_10]], [[BROADCAST_SPLAT2]] ; O2-NEXT: [[TMP51:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 40 ; O2-NEXT: [[TMP52:%.*]] = bitcast i32* [[TMP51]] to <4 x i32>* ; O2-NEXT: store <4 x i32> [[TMP50]], <4 x i32>* [[TMP52]], align 4 ; O2-NEXT: [[TMP53:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 44 ; O2-NEXT: [[TMP54:%.*]] = bitcast i32* [[TMP53]] to <4 x i32>* ; O2-NEXT: [[WIDE_LOAD_11:%.*]] = load <4 x i32>, <4 x i32>* [[TMP54]], align 4 -; O2-NEXT: [[TMP55:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_11]], [[BROADCAST_SPLAT]] +; O2-NEXT: [[TMP55:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_11]], [[BROADCAST_SPLAT2]] ; O2-NEXT: [[TMP56:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 44 ; O2-NEXT: [[TMP57:%.*]] = bitcast i32* [[TMP56]] to <4 x i32>* ; O2-NEXT: store <4 x i32> [[TMP55]], <4 x i32>* [[TMP57]], align 4 ; O2-NEXT: [[TMP58:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 48 ; O2-NEXT: [[TMP59:%.*]] = bitcast i32* [[TMP58]] to <4 x i32>* ; O2-NEXT: [[WIDE_LOAD_12:%.*]] = load <4 x i32>, <4 x i32>* [[TMP59]], align 4 -; O2-NEXT: [[TMP60:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_12]], [[BROADCAST_SPLAT]] +; O2-NEXT: [[TMP60:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_12]], [[BROADCAST_SPLAT2]] ; O2-NEXT: [[TMP61:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 48 ; O2-NEXT: [[TMP62:%.*]] = bitcast i32* [[TMP61]] to <4 x i32>* ; O2-NEXT: store <4 x i32> [[TMP60]], <4 x i32>* [[TMP62]], align 4 ; O2-NEXT: [[TMP63:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 52 ; O2-NEXT: [[TMP64:%.*]] = bitcast i32* [[TMP63]] to <4 x i32>* ; O2-NEXT: [[WIDE_LOAD_13:%.*]] = load <4 x i32>, <4 x i32>* [[TMP64]], align 4 -; O2-NEXT: [[TMP65:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_13]], [[BROADCAST_SPLAT]] +; O2-NEXT: [[TMP65:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_13]], [[BROADCAST_SPLAT2]] ; O2-NEXT: [[TMP66:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 52 ; O2-NEXT: [[TMP67:%.*]] = bitcast i32* [[TMP66]] to <4 x i32>* ; O2-NEXT: store <4 x i32> [[TMP65]], <4 x i32>* [[TMP67]], align 4 ; O2-NEXT: [[TMP68:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 56 ; O2-NEXT: [[TMP69:%.*]] = bitcast i32* [[TMP68]] to <4 x i32>* ; O2-NEXT: [[WIDE_LOAD_14:%.*]] = load <4 x i32>, <4 x i32>* [[TMP69]], align 4 -; O2-NEXT: [[TMP70:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_14]], [[BROADCAST_SPLAT]] +; O2-NEXT: [[TMP70:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_14]], [[BROADCAST_SPLAT2]] ; O2-NEXT: [[TMP71:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 56 ; O2-NEXT: [[TMP72:%.*]] = bitcast i32* [[TMP71]] to <4 x i32>* ; O2-NEXT: store <4 x i32> [[TMP70]], <4 x i32>* [[TMP72]], align 4 ; O2-NEXT: [[TMP73:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 60 ; O2-NEXT: [[TMP74:%.*]] = bitcast i32* [[TMP73]] to <4 x i32>* ; O2-NEXT: [[WIDE_LOAD_15:%.*]] = load <4 x i32>, <4 x i32>* [[TMP74]], align 4 -; O2-NEXT: [[TMP75:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_15]], [[BROADCAST_SPLAT]] +; O2-NEXT: [[TMP75:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_15]], [[BROADCAST_SPLAT2]] ; O2-NEXT: [[TMP76:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 60 ; O2-NEXT: [[TMP77:%.*]] = bitcast i32* [[TMP76]] to <4 x i32>* ; O2-NEXT: store <4 x i32> [[TMP75]], <4 x i32>* [[TMP77]], align 4 @@ -253,115 +253,115 @@ define i32 @enabled(i32* noalias nocapture %a, i32* noalias nocapture readonly % ; ; O3-LABEL: @enabled( ; O3-NEXT: entry: -; O3-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i32> undef, i32 [[N:%.*]], i32 0 -; O3-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT]], <4 x i32> undef, <4 x i32> zeroinitializer +; O3-NEXT: [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <4 x i32> undef, i32 [[N:%.*]], i32 0 +; O3-NEXT: [[BROADCAST_SPLAT2:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT1]], <4 x i32> undef, <4 x i32> zeroinitializer ; O3-NEXT: [[TMP0:%.*]] = bitcast i32* [[B:%.*]] to <4 x i32>* ; O3-NEXT: [[WIDE_LOAD:%.*]] = load <4 x i32>, <4 x i32>* [[TMP0]], align 4 -; O3-NEXT: [[TMP1:%.*]] = add nsw <4 x i32> [[WIDE_LOAD]], [[BROADCAST_SPLAT]] +; O3-NEXT: [[TMP1:%.*]] = add nsw <4 x i32> [[WIDE_LOAD]], [[BROADCAST_SPLAT2]] ; O3-NEXT: [[TMP2:%.*]] = bitcast i32* [[A:%.*]] to <4 x i32>* ; O3-NEXT: store <4 x i32> [[TMP1]], <4 x i32>* [[TMP2]], align 4 ; O3-NEXT: [[TMP3:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 4 ; O3-NEXT: [[TMP4:%.*]] = bitcast i32* [[TMP3]] to <4 x i32>* ; O3-NEXT: [[WIDE_LOAD_1:%.*]] = load <4 x i32>, <4 x i32>* [[TMP4]], align 4 -; O3-NEXT: [[TMP5:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_1]], [[BROADCAST_SPLAT]] +; O3-NEXT: [[TMP5:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_1]], [[BROADCAST_SPLAT2]] ; O3-NEXT: [[TMP6:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 4 ; O3-NEXT: [[TMP7:%.*]] = bitcast i32* [[TMP6]] to <4 x i32>* ; O3-NEXT: store <4 x i32> [[TMP5]], <4 x i32>* [[TMP7]], align 4 ; O3-NEXT: [[TMP8:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 8 ; O3-NEXT: [[TMP9:%.*]] = bitcast i32* [[TMP8]] to <4 x i32>* ; O3-NEXT: [[WIDE_LOAD_2:%.*]] = load <4 x i32>, <4 x i32>* [[TMP9]], align 4 -; O3-NEXT: [[TMP10:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_2]], [[BROADCAST_SPLAT]] +; O3-NEXT: [[TMP10:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_2]], [[BROADCAST_SPLAT2]] ; O3-NEXT: [[TMP11:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 8 ; O3-NEXT: [[TMP12:%.*]] = bitcast i32* [[TMP11]] to <4 x i32>* ; O3-NEXT: store <4 x i32> [[TMP10]], <4 x i32>* [[TMP12]], align 4 ; O3-NEXT: [[TMP13:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 12 ; O3-NEXT: [[TMP14:%.*]] = bitcast i32* [[TMP13]] to <4 x i32>* ; O3-NEXT: [[WIDE_LOAD_3:%.*]] = load <4 x i32>, <4 x i32>* [[TMP14]], align 4 -; O3-NEXT: [[TMP15:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_3]], [[BROADCAST_SPLAT]] +; O3-NEXT: [[TMP15:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_3]], [[BROADCAST_SPLAT2]] ; O3-NEXT: [[TMP16:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 12 ; O3-NEXT: [[TMP17:%.*]] = bitcast i32* [[TMP16]] to <4 x i32>* ; O3-NEXT: store <4 x i32> [[TMP15]], <4 x i32>* [[TMP17]], align 4 ; O3-NEXT: [[TMP18:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 16 ; O3-NEXT: [[TMP19:%.*]] = bitcast i32* [[TMP18]] to <4 x i32>* ; O3-NEXT: [[WIDE_LOAD_4:%.*]] = load <4 x i32>, <4 x i32>* [[TMP19]], align 4 -; O3-NEXT: [[TMP20:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_4]], [[BROADCAST_SPLAT]] +; O3-NEXT: [[TMP20:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_4]], [[BROADCAST_SPLAT2]] ; O3-NEXT: [[TMP21:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 16 ; O3-NEXT: [[TMP22:%.*]] = bitcast i32* [[TMP21]] to <4 x i32>* ; O3-NEXT: store <4 x i32> [[TMP20]], <4 x i32>* [[TMP22]], align 4 ; O3-NEXT: [[TMP23:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 20 ; O3-NEXT: [[TMP24:%.*]] = bitcast i32* [[TMP23]] to <4 x i32>* ; O3-NEXT: [[WIDE_LOAD_5:%.*]] = load <4 x i32>, <4 x i32>* [[TMP24]], align 4 -; O3-NEXT: [[TMP25:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_5]], [[BROADCAST_SPLAT]] +; O3-NEXT: [[TMP25:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_5]], [[BROADCAST_SPLAT2]] ; O3-NEXT: [[TMP26:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 20 ; O3-NEXT: [[TMP27:%.*]] = bitcast i32* [[TMP26]] to <4 x i32>* ; O3-NEXT: store <4 x i32> [[TMP25]], <4 x i32>* [[TMP27]], align 4 ; O3-NEXT: [[TMP28:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 24 ; O3-NEXT: [[TMP29:%.*]] = bitcast i32* [[TMP28]] to <4 x i32>* ; O3-NEXT: [[WIDE_LOAD_6:%.*]] = load <4 x i32>, <4 x i32>* [[TMP29]], align 4 -; O3-NEXT: [[TMP30:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_6]], [[BROADCAST_SPLAT]] +; O3-NEXT: [[TMP30:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_6]], [[BROADCAST_SPLAT2]] ; O3-NEXT: [[TMP31:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 24 ; O3-NEXT: [[TMP32:%.*]] = bitcast i32* [[TMP31]] to <4 x i32>* ; O3-NEXT: store <4 x i32> [[TMP30]], <4 x i32>* [[TMP32]], align 4 ; O3-NEXT: [[TMP33:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 28 ; O3-NEXT: [[TMP34:%.*]] = bitcast i32* [[TMP33]] to <4 x i32>* ; O3-NEXT: [[WIDE_LOAD_7:%.*]] = load <4 x i32>, <4 x i32>* [[TMP34]], align 4 -; O3-NEXT: [[TMP35:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_7]], [[BROADCAST_SPLAT]] +; O3-NEXT: [[TMP35:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_7]], [[BROADCAST_SPLAT2]] ; O3-NEXT: [[TMP36:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 28 ; O3-NEXT: [[TMP37:%.*]] = bitcast i32* [[TMP36]] to <4 x i32>* ; O3-NEXT: store <4 x i32> [[TMP35]], <4 x i32>* [[TMP37]], align 4 ; O3-NEXT: [[TMP38:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 32 ; O3-NEXT: [[TMP39:%.*]] = bitcast i32* [[TMP38]] to <4 x i32>* ; O3-NEXT: [[WIDE_LOAD_8:%.*]] = load <4 x i32>, <4 x i32>* [[TMP39]], align 4 -; O3-NEXT: [[TMP40:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_8]], [[BROADCAST_SPLAT]] +; O3-NEXT: [[TMP40:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_8]], [[BROADCAST_SPLAT2]] ; O3-NEXT: [[TMP41:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 32 ; O3-NEXT: [[TMP42:%.*]] = bitcast i32* [[TMP41]] to <4 x i32>* ; O3-NEXT: store <4 x i32> [[TMP40]], <4 x i32>* [[TMP42]], align 4 ; O3-NEXT: [[TMP43:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 36 ; O3-NEXT: [[TMP44:%.*]] = bitcast i32* [[TMP43]] to <4 x i32>* ; O3-NEXT: [[WIDE_LOAD_9:%.*]] = load <4 x i32>, <4 x i32>* [[TMP44]], align 4 -; O3-NEXT: [[TMP45:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_9]], [[BROADCAST_SPLAT]] +; O3-NEXT: [[TMP45:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_9]], [[BROADCAST_SPLAT2]] ; O3-NEXT: [[TMP46:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 36 ; O3-NEXT: [[TMP47:%.*]] = bitcast i32* [[TMP46]] to <4 x i32>* ; O3-NEXT: store <4 x i32> [[TMP45]], <4 x i32>* [[TMP47]], align 4 ; O3-NEXT: [[TMP48:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 40 ; O3-NEXT: [[TMP49:%.*]] = bitcast i32* [[TMP48]] to <4 x i32>* ; O3-NEXT: [[WIDE_LOAD_10:%.*]] = load <4 x i32>, <4 x i32>* [[TMP49]], align 4 -; O3-NEXT: [[TMP50:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_10]], [[BROADCAST_SPLAT]] +; O3-NEXT: [[TMP50:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_10]], [[BROADCAST_SPLAT2]] ; O3-NEXT: [[TMP51:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 40 ; O3-NEXT: [[TMP52:%.*]] = bitcast i32* [[TMP51]] to <4 x i32>* ; O3-NEXT: store <4 x i32> [[TMP50]], <4 x i32>* [[TMP52]], align 4 ; O3-NEXT: [[TMP53:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 44 ; O3-NEXT: [[TMP54:%.*]] = bitcast i32* [[TMP53]] to <4 x i32>* ; O3-NEXT: [[WIDE_LOAD_11:%.*]] = load <4 x i32>, <4 x i32>* [[TMP54]], align 4 -; O3-NEXT: [[TMP55:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_11]], [[BROADCAST_SPLAT]] +; O3-NEXT: [[TMP55:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_11]], [[BROADCAST_SPLAT2]] ; O3-NEXT: [[TMP56:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 44 ; O3-NEXT: [[TMP57:%.*]] = bitcast i32* [[TMP56]] to <4 x i32>* ; O3-NEXT: store <4 x i32> [[TMP55]], <4 x i32>* [[TMP57]], align 4 ; O3-NEXT: [[TMP58:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 48 ; O3-NEXT: [[TMP59:%.*]] = bitcast i32* [[TMP58]] to <4 x i32>* ; O3-NEXT: [[WIDE_LOAD_12:%.*]] = load <4 x i32>, <4 x i32>* [[TMP59]], align 4 -; O3-NEXT: [[TMP60:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_12]], [[BROADCAST_SPLAT]] +; O3-NEXT: [[TMP60:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_12]], [[BROADCAST_SPLAT2]] ; O3-NEXT: [[TMP61:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 48 ; O3-NEXT: [[TMP62:%.*]] = bitcast i32* [[TMP61]] to <4 x i32>* ; O3-NEXT: store <4 x i32> [[TMP60]], <4 x i32>* [[TMP62]], align 4 ; O3-NEXT: [[TMP63:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 52 ; O3-NEXT: [[TMP64:%.*]] = bitcast i32* [[TMP63]] to <4 x i32>* ; O3-NEXT: [[WIDE_LOAD_13:%.*]] = load <4 x i32>, <4 x i32>* [[TMP64]], align 4 -; O3-NEXT: [[TMP65:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_13]], [[BROADCAST_SPLAT]] +; O3-NEXT: [[TMP65:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_13]], [[BROADCAST_SPLAT2]] ; O3-NEXT: [[TMP66:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 52 ; O3-NEXT: [[TMP67:%.*]] = bitcast i32* [[TMP66]] to <4 x i32>* ; O3-NEXT: store <4 x i32> [[TMP65]], <4 x i32>* [[TMP67]], align 4 ; O3-NEXT: [[TMP68:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 56 ; O3-NEXT: [[TMP69:%.*]] = bitcast i32* [[TMP68]] to <4 x i32>* ; O3-NEXT: [[WIDE_LOAD_14:%.*]] = load <4 x i32>, <4 x i32>* [[TMP69]], align 4 -; O3-NEXT: [[TMP70:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_14]], [[BROADCAST_SPLAT]] +; O3-NEXT: [[TMP70:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_14]], [[BROADCAST_SPLAT2]] ; O3-NEXT: [[TMP71:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 56 ; O3-NEXT: [[TMP72:%.*]] = bitcast i32* [[TMP71]] to <4 x i32>* ; O3-NEXT: store <4 x i32> [[TMP70]], <4 x i32>* [[TMP72]], align 4 ; O3-NEXT: [[TMP73:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 60 ; O3-NEXT: [[TMP74:%.*]] = bitcast i32* [[TMP73]] to <4 x i32>* ; O3-NEXT: [[WIDE_LOAD_15:%.*]] = load <4 x i32>, <4 x i32>* [[TMP74]], align 4 -; O3-NEXT: [[TMP75:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_15]], [[BROADCAST_SPLAT]] +; O3-NEXT: [[TMP75:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_15]], [[BROADCAST_SPLAT2]] ; O3-NEXT: [[TMP76:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 60 ; O3-NEXT: [[TMP77:%.*]] = bitcast i32* [[TMP76]] to <4 x i32>* ; O3-NEXT: store <4 x i32> [[TMP75]], <4 x i32>* [[TMP77]], align 4 @@ -370,115 +370,115 @@ define i32 @enabled(i32* noalias nocapture %a, i32* noalias nocapture readonly % ; ; O3DEFAULT-LABEL: @enabled( ; O3DEFAULT-NEXT: entry: -; O3DEFAULT-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i32> undef, i32 [[N:%.*]], i32 0 -; O3DEFAULT-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT]], <4 x i32> undef, <4 x i32> zeroinitializer +; O3DEFAULT-NEXT: [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <4 x i32> undef, i32 [[N:%.*]], i32 0 +; O3DEFAULT-NEXT: [[BROADCAST_SPLAT2:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT1]], <4 x i32> undef, <4 x i32> zeroinitializer ; O3DEFAULT-NEXT: [[TMP0:%.*]] = bitcast i32* [[B:%.*]] to <4 x i32>* ; O3DEFAULT-NEXT: [[WIDE_LOAD:%.*]] = load <4 x i32>, <4 x i32>* [[TMP0]], align 4 -; O3DEFAULT-NEXT: [[TMP1:%.*]] = add nsw <4 x i32> [[WIDE_LOAD]], [[BROADCAST_SPLAT]] +; O3DEFAULT-NEXT: [[TMP1:%.*]] = add nsw <4 x i32> [[WIDE_LOAD]], [[BROADCAST_SPLAT2]] ; O3DEFAULT-NEXT: [[TMP2:%.*]] = bitcast i32* [[A:%.*]] to <4 x i32>* ; O3DEFAULT-NEXT: store <4 x i32> [[TMP1]], <4 x i32>* [[TMP2]], align 4 ; O3DEFAULT-NEXT: [[TMP3:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 4 ; O3DEFAULT-NEXT: [[TMP4:%.*]] = bitcast i32* [[TMP3]] to <4 x i32>* ; O3DEFAULT-NEXT: [[WIDE_LOAD_1:%.*]] = load <4 x i32>, <4 x i32>* [[TMP4]], align 4 -; O3DEFAULT-NEXT: [[TMP5:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_1]], [[BROADCAST_SPLAT]] +; O3DEFAULT-NEXT: [[TMP5:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_1]], [[BROADCAST_SPLAT2]] ; O3DEFAULT-NEXT: [[TMP6:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 4 ; O3DEFAULT-NEXT: [[TMP7:%.*]] = bitcast i32* [[TMP6]] to <4 x i32>* ; O3DEFAULT-NEXT: store <4 x i32> [[TMP5]], <4 x i32>* [[TMP7]], align 4 ; O3DEFAULT-NEXT: [[TMP8:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 8 ; O3DEFAULT-NEXT: [[TMP9:%.*]] = bitcast i32* [[TMP8]] to <4 x i32>* ; O3DEFAULT-NEXT: [[WIDE_LOAD_2:%.*]] = load <4 x i32>, <4 x i32>* [[TMP9]], align 4 -; O3DEFAULT-NEXT: [[TMP10:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_2]], [[BROADCAST_SPLAT]] +; O3DEFAULT-NEXT: [[TMP10:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_2]], [[BROADCAST_SPLAT2]] ; O3DEFAULT-NEXT: [[TMP11:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 8 ; O3DEFAULT-NEXT: [[TMP12:%.*]] = bitcast i32* [[TMP11]] to <4 x i32>* ; O3DEFAULT-NEXT: store <4 x i32> [[TMP10]], <4 x i32>* [[TMP12]], align 4 ; O3DEFAULT-NEXT: [[TMP13:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 12 ; O3DEFAULT-NEXT: [[TMP14:%.*]] = bitcast i32* [[TMP13]] to <4 x i32>* ; O3DEFAULT-NEXT: [[WIDE_LOAD_3:%.*]] = load <4 x i32>, <4 x i32>* [[TMP14]], align 4 -; O3DEFAULT-NEXT: [[TMP15:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_3]], [[BROADCAST_SPLAT]] +; O3DEFAULT-NEXT: [[TMP15:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_3]], [[BROADCAST_SPLAT2]] ; O3DEFAULT-NEXT: [[TMP16:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 12 ; O3DEFAULT-NEXT: [[TMP17:%.*]] = bitcast i32* [[TMP16]] to <4 x i32>* ; O3DEFAULT-NEXT: store <4 x i32> [[TMP15]], <4 x i32>* [[TMP17]], align 4 ; O3DEFAULT-NEXT: [[TMP18:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 16 ; O3DEFAULT-NEXT: [[TMP19:%.*]] = bitcast i32* [[TMP18]] to <4 x i32>* ; O3DEFAULT-NEXT: [[WIDE_LOAD_4:%.*]] = load <4 x i32>, <4 x i32>* [[TMP19]], align 4 -; O3DEFAULT-NEXT: [[TMP20:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_4]], [[BROADCAST_SPLAT]] +; O3DEFAULT-NEXT: [[TMP20:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_4]], [[BROADCAST_SPLAT2]] ; O3DEFAULT-NEXT: [[TMP21:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 16 ; O3DEFAULT-NEXT: [[TMP22:%.*]] = bitcast i32* [[TMP21]] to <4 x i32>* ; O3DEFAULT-NEXT: store <4 x i32> [[TMP20]], <4 x i32>* [[TMP22]], align 4 ; O3DEFAULT-NEXT: [[TMP23:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 20 ; O3DEFAULT-NEXT: [[TMP24:%.*]] = bitcast i32* [[TMP23]] to <4 x i32>* ; O3DEFAULT-NEXT: [[WIDE_LOAD_5:%.*]] = load <4 x i32>, <4 x i32>* [[TMP24]], align 4 -; O3DEFAULT-NEXT: [[TMP25:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_5]], [[BROADCAST_SPLAT]] +; O3DEFAULT-NEXT: [[TMP25:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_5]], [[BROADCAST_SPLAT2]] ; O3DEFAULT-NEXT: [[TMP26:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 20 ; O3DEFAULT-NEXT: [[TMP27:%.*]] = bitcast i32* [[TMP26]] to <4 x i32>* ; O3DEFAULT-NEXT: store <4 x i32> [[TMP25]], <4 x i32>* [[TMP27]], align 4 ; O3DEFAULT-NEXT: [[TMP28:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 24 ; O3DEFAULT-NEXT: [[TMP29:%.*]] = bitcast i32* [[TMP28]] to <4 x i32>* ; O3DEFAULT-NEXT: [[WIDE_LOAD_6:%.*]] = load <4 x i32>, <4 x i32>* [[TMP29]], align 4 -; O3DEFAULT-NEXT: [[TMP30:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_6]], [[BROADCAST_SPLAT]] +; O3DEFAULT-NEXT: [[TMP30:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_6]], [[BROADCAST_SPLAT2]] ; O3DEFAULT-NEXT: [[TMP31:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 24 ; O3DEFAULT-NEXT: [[TMP32:%.*]] = bitcast i32* [[TMP31]] to <4 x i32>* ; O3DEFAULT-NEXT: store <4 x i32> [[TMP30]], <4 x i32>* [[TMP32]], align 4 ; O3DEFAULT-NEXT: [[TMP33:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 28 ; O3DEFAULT-NEXT: [[TMP34:%.*]] = bitcast i32* [[TMP33]] to <4 x i32>* ; O3DEFAULT-NEXT: [[WIDE_LOAD_7:%.*]] = load <4 x i32>, <4 x i32>* [[TMP34]], align 4 -; O3DEFAULT-NEXT: [[TMP35:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_7]], [[BROADCAST_SPLAT]] +; O3DEFAULT-NEXT: [[TMP35:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_7]], [[BROADCAST_SPLAT2]] ; O3DEFAULT-NEXT: [[TMP36:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 28 ; O3DEFAULT-NEXT: [[TMP37:%.*]] = bitcast i32* [[TMP36]] to <4 x i32>* ; O3DEFAULT-NEXT: store <4 x i32> [[TMP35]], <4 x i32>* [[TMP37]], align 4 ; O3DEFAULT-NEXT: [[TMP38:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 32 ; O3DEFAULT-NEXT: [[TMP39:%.*]] = bitcast i32* [[TMP38]] to <4 x i32>* ; O3DEFAULT-NEXT: [[WIDE_LOAD_8:%.*]] = load <4 x i32>, <4 x i32>* [[TMP39]], align 4 -; O3DEFAULT-NEXT: [[TMP40:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_8]], [[BROADCAST_SPLAT]] +; O3DEFAULT-NEXT: [[TMP40:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_8]], [[BROADCAST_SPLAT2]] ; O3DEFAULT-NEXT: [[TMP41:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 32 ; O3DEFAULT-NEXT: [[TMP42:%.*]] = bitcast i32* [[TMP41]] to <4 x i32>* ; O3DEFAULT-NEXT: store <4 x i32> [[TMP40]], <4 x i32>* [[TMP42]], align 4 ; O3DEFAULT-NEXT: [[TMP43:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 36 ; O3DEFAULT-NEXT: [[TMP44:%.*]] = bitcast i32* [[TMP43]] to <4 x i32>* ; O3DEFAULT-NEXT: [[WIDE_LOAD_9:%.*]] = load <4 x i32>, <4 x i32>* [[TMP44]], align 4 -; O3DEFAULT-NEXT: [[TMP45:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_9]], [[BROADCAST_SPLAT]] +; O3DEFAULT-NEXT: [[TMP45:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_9]], [[BROADCAST_SPLAT2]] ; O3DEFAULT-NEXT: [[TMP46:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 36 ; O3DEFAULT-NEXT: [[TMP47:%.*]] = bitcast i32* [[TMP46]] to <4 x i32>* ; O3DEFAULT-NEXT: store <4 x i32> [[TMP45]], <4 x i32>* [[TMP47]], align 4 ; O3DEFAULT-NEXT: [[TMP48:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 40 ; O3DEFAULT-NEXT: [[TMP49:%.*]] = bitcast i32* [[TMP48]] to <4 x i32>* ; O3DEFAULT-NEXT: [[WIDE_LOAD_10:%.*]] = load <4 x i32>, <4 x i32>* [[TMP49]], align 4 -; O3DEFAULT-NEXT: [[TMP50:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_10]], [[BROADCAST_SPLAT]] +; O3DEFAULT-NEXT: [[TMP50:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_10]], [[BROADCAST_SPLAT2]] ; O3DEFAULT-NEXT: [[TMP51:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 40 ; O3DEFAULT-NEXT: [[TMP52:%.*]] = bitcast i32* [[TMP51]] to <4 x i32>* ; O3DEFAULT-NEXT: store <4 x i32> [[TMP50]], <4 x i32>* [[TMP52]], align 4 ; O3DEFAULT-NEXT: [[TMP53:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 44 ; O3DEFAULT-NEXT: [[TMP54:%.*]] = bitcast i32* [[TMP53]] to <4 x i32>* ; O3DEFAULT-NEXT: [[WIDE_LOAD_11:%.*]] = load <4 x i32>, <4 x i32>* [[TMP54]], align 4 -; O3DEFAULT-NEXT: [[TMP55:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_11]], [[BROADCAST_SPLAT]] +; O3DEFAULT-NEXT: [[TMP55:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_11]], [[BROADCAST_SPLAT2]] ; O3DEFAULT-NEXT: [[TMP56:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 44 ; O3DEFAULT-NEXT: [[TMP57:%.*]] = bitcast i32* [[TMP56]] to <4 x i32>* ; O3DEFAULT-NEXT: store <4 x i32> [[TMP55]], <4 x i32>* [[TMP57]], align 4 ; O3DEFAULT-NEXT: [[TMP58:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 48 ; O3DEFAULT-NEXT: [[TMP59:%.*]] = bitcast i32* [[TMP58]] to <4 x i32>* ; O3DEFAULT-NEXT: [[WIDE_LOAD_12:%.*]] = load <4 x i32>, <4 x i32>* [[TMP59]], align 4 -; O3DEFAULT-NEXT: [[TMP60:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_12]], [[BROADCAST_SPLAT]] +; O3DEFAULT-NEXT: [[TMP60:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_12]], [[BROADCAST_SPLAT2]] ; O3DEFAULT-NEXT: [[TMP61:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 48 ; O3DEFAULT-NEXT: [[TMP62:%.*]] = bitcast i32* [[TMP61]] to <4 x i32>* ; O3DEFAULT-NEXT: store <4 x i32> [[TMP60]], <4 x i32>* [[TMP62]], align 4 ; O3DEFAULT-NEXT: [[TMP63:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 52 ; O3DEFAULT-NEXT: [[TMP64:%.*]] = bitcast i32* [[TMP63]] to <4 x i32>* ; O3DEFAULT-NEXT: [[WIDE_LOAD_13:%.*]] = load <4 x i32>, <4 x i32>* [[TMP64]], align 4 -; O3DEFAULT-NEXT: [[TMP65:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_13]], [[BROADCAST_SPLAT]] +; O3DEFAULT-NEXT: [[TMP65:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_13]], [[BROADCAST_SPLAT2]] ; O3DEFAULT-NEXT: [[TMP66:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 52 ; O3DEFAULT-NEXT: [[TMP67:%.*]] = bitcast i32* [[TMP66]] to <4 x i32>* ; O3DEFAULT-NEXT: store <4 x i32> [[TMP65]], <4 x i32>* [[TMP67]], align 4 ; O3DEFAULT-NEXT: [[TMP68:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 56 ; O3DEFAULT-NEXT: [[TMP69:%.*]] = bitcast i32* [[TMP68]] to <4 x i32>* ; O3DEFAULT-NEXT: [[WIDE_LOAD_14:%.*]] = load <4 x i32>, <4 x i32>* [[TMP69]], align 4 -; O3DEFAULT-NEXT: [[TMP70:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_14]], [[BROADCAST_SPLAT]] +; O3DEFAULT-NEXT: [[TMP70:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_14]], [[BROADCAST_SPLAT2]] ; O3DEFAULT-NEXT: [[TMP71:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 56 ; O3DEFAULT-NEXT: [[TMP72:%.*]] = bitcast i32* [[TMP71]] to <4 x i32>* ; O3DEFAULT-NEXT: store <4 x i32> [[TMP70]], <4 x i32>* [[TMP72]], align 4 ; O3DEFAULT-NEXT: [[TMP73:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 60 ; O3DEFAULT-NEXT: [[TMP74:%.*]] = bitcast i32* [[TMP73]] to <4 x i32>* ; O3DEFAULT-NEXT: [[WIDE_LOAD_15:%.*]] = load <4 x i32>, <4 x i32>* [[TMP74]], align 4 -; O3DEFAULT-NEXT: [[TMP75:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_15]], [[BROADCAST_SPLAT]] +; O3DEFAULT-NEXT: [[TMP75:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_15]], [[BROADCAST_SPLAT2]] ; O3DEFAULT-NEXT: [[TMP76:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 60 ; O3DEFAULT-NEXT: [[TMP77:%.*]] = bitcast i32* [[TMP76]] to <4 x i32>* ; O3DEFAULT-NEXT: store <4 x i32> [[TMP75]], <4 x i32>* [[TMP77]], align 4 @@ -487,115 +487,115 @@ define i32 @enabled(i32* noalias nocapture %a, i32* noalias nocapture readonly % ; ; Os-LABEL: @enabled( ; Os-NEXT: entry: -; Os-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i32> undef, i32 [[N:%.*]], i32 0 -; Os-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT]], <4 x i32> undef, <4 x i32> zeroinitializer +; Os-NEXT: [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <4 x i32> undef, i32 [[N:%.*]], i32 0 +; Os-NEXT: [[BROADCAST_SPLAT2:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT1]], <4 x i32> undef, <4 x i32> zeroinitializer ; Os-NEXT: [[TMP0:%.*]] = bitcast i32* [[B:%.*]] to <4 x i32>* ; Os-NEXT: [[WIDE_LOAD:%.*]] = load <4 x i32>, <4 x i32>* [[TMP0]], align 4 -; Os-NEXT: [[TMP1:%.*]] = add nsw <4 x i32> [[WIDE_LOAD]], [[BROADCAST_SPLAT]] +; Os-NEXT: [[TMP1:%.*]] = add nsw <4 x i32> [[WIDE_LOAD]], [[BROADCAST_SPLAT2]] ; Os-NEXT: [[TMP2:%.*]] = bitcast i32* [[A:%.*]] to <4 x i32>* ; Os-NEXT: store <4 x i32> [[TMP1]], <4 x i32>* [[TMP2]], align 4 ; Os-NEXT: [[TMP3:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 4 ; Os-NEXT: [[TMP4:%.*]] = bitcast i32* [[TMP3]] to <4 x i32>* ; Os-NEXT: [[WIDE_LOAD_1:%.*]] = load <4 x i32>, <4 x i32>* [[TMP4]], align 4 -; Os-NEXT: [[TMP5:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_1]], [[BROADCAST_SPLAT]] +; Os-NEXT: [[TMP5:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_1]], [[BROADCAST_SPLAT2]] ; Os-NEXT: [[TMP6:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 4 ; Os-NEXT: [[TMP7:%.*]] = bitcast i32* [[TMP6]] to <4 x i32>* ; Os-NEXT: store <4 x i32> [[TMP5]], <4 x i32>* [[TMP7]], align 4 ; Os-NEXT: [[TMP8:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 8 ; Os-NEXT: [[TMP9:%.*]] = bitcast i32* [[TMP8]] to <4 x i32>* ; Os-NEXT: [[WIDE_LOAD_2:%.*]] = load <4 x i32>, <4 x i32>* [[TMP9]], align 4 -; Os-NEXT: [[TMP10:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_2]], [[BROADCAST_SPLAT]] +; Os-NEXT: [[TMP10:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_2]], [[BROADCAST_SPLAT2]] ; Os-NEXT: [[TMP11:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 8 ; Os-NEXT: [[TMP12:%.*]] = bitcast i32* [[TMP11]] to <4 x i32>* ; Os-NEXT: store <4 x i32> [[TMP10]], <4 x i32>* [[TMP12]], align 4 ; Os-NEXT: [[TMP13:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 12 ; Os-NEXT: [[TMP14:%.*]] = bitcast i32* [[TMP13]] to <4 x i32>* ; Os-NEXT: [[WIDE_LOAD_3:%.*]] = load <4 x i32>, <4 x i32>* [[TMP14]], align 4 -; Os-NEXT: [[TMP15:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_3]], [[BROADCAST_SPLAT]] +; Os-NEXT: [[TMP15:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_3]], [[BROADCAST_SPLAT2]] ; Os-NEXT: [[TMP16:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 12 ; Os-NEXT: [[TMP17:%.*]] = bitcast i32* [[TMP16]] to <4 x i32>* ; Os-NEXT: store <4 x i32> [[TMP15]], <4 x i32>* [[TMP17]], align 4 ; Os-NEXT: [[TMP18:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 16 ; Os-NEXT: [[TMP19:%.*]] = bitcast i32* [[TMP18]] to <4 x i32>* ; Os-NEXT: [[WIDE_LOAD_4:%.*]] = load <4 x i32>, <4 x i32>* [[TMP19]], align 4 -; Os-NEXT: [[TMP20:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_4]], [[BROADCAST_SPLAT]] +; Os-NEXT: [[TMP20:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_4]], [[BROADCAST_SPLAT2]] ; Os-NEXT: [[TMP21:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 16 ; Os-NEXT: [[TMP22:%.*]] = bitcast i32* [[TMP21]] to <4 x i32>* ; Os-NEXT: store <4 x i32> [[TMP20]], <4 x i32>* [[TMP22]], align 4 ; Os-NEXT: [[TMP23:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 20 ; Os-NEXT: [[TMP24:%.*]] = bitcast i32* [[TMP23]] to <4 x i32>* ; Os-NEXT: [[WIDE_LOAD_5:%.*]] = load <4 x i32>, <4 x i32>* [[TMP24]], align 4 -; Os-NEXT: [[TMP25:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_5]], [[BROADCAST_SPLAT]] +; Os-NEXT: [[TMP25:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_5]], [[BROADCAST_SPLAT2]] ; Os-NEXT: [[TMP26:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 20 ; Os-NEXT: [[TMP27:%.*]] = bitcast i32* [[TMP26]] to <4 x i32>* ; Os-NEXT: store <4 x i32> [[TMP25]], <4 x i32>* [[TMP27]], align 4 ; Os-NEXT: [[TMP28:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 24 ; Os-NEXT: [[TMP29:%.*]] = bitcast i32* [[TMP28]] to <4 x i32>* ; Os-NEXT: [[WIDE_LOAD_6:%.*]] = load <4 x i32>, <4 x i32>* [[TMP29]], align 4 -; Os-NEXT: [[TMP30:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_6]], [[BROADCAST_SPLAT]] +; Os-NEXT: [[TMP30:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_6]], [[BROADCAST_SPLAT2]] ; Os-NEXT: [[TMP31:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 24 ; Os-NEXT: [[TMP32:%.*]] = bitcast i32* [[TMP31]] to <4 x i32>* ; Os-NEXT: store <4 x i32> [[TMP30]], <4 x i32>* [[TMP32]], align 4 ; Os-NEXT: [[TMP33:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 28 ; Os-NEXT: [[TMP34:%.*]] = bitcast i32* [[TMP33]] to <4 x i32>* ; Os-NEXT: [[WIDE_LOAD_7:%.*]] = load <4 x i32>, <4 x i32>* [[TMP34]], align 4 -; Os-NEXT: [[TMP35:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_7]], [[BROADCAST_SPLAT]] +; Os-NEXT: [[TMP35:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_7]], [[BROADCAST_SPLAT2]] ; Os-NEXT: [[TMP36:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 28 ; Os-NEXT: [[TMP37:%.*]] = bitcast i32* [[TMP36]] to <4 x i32>* ; Os-NEXT: store <4 x i32> [[TMP35]], <4 x i32>* [[TMP37]], align 4 ; Os-NEXT: [[TMP38:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 32 ; Os-NEXT: [[TMP39:%.*]] = bitcast i32* [[TMP38]] to <4 x i32>* ; Os-NEXT: [[WIDE_LOAD_8:%.*]] = load <4 x i32>, <4 x i32>* [[TMP39]], align 4 -; Os-NEXT: [[TMP40:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_8]], [[BROADCAST_SPLAT]] +; Os-NEXT: [[TMP40:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_8]], [[BROADCAST_SPLAT2]] ; Os-NEXT: [[TMP41:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 32 ; Os-NEXT: [[TMP42:%.*]] = bitcast i32* [[TMP41]] to <4 x i32>* ; Os-NEXT: store <4 x i32> [[TMP40]], <4 x i32>* [[TMP42]], align 4 ; Os-NEXT: [[TMP43:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 36 ; Os-NEXT: [[TMP44:%.*]] = bitcast i32* [[TMP43]] to <4 x i32>* ; Os-NEXT: [[WIDE_LOAD_9:%.*]] = load <4 x i32>, <4 x i32>* [[TMP44]], align 4 -; Os-NEXT: [[TMP45:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_9]], [[BROADCAST_SPLAT]] +; Os-NEXT: [[TMP45:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_9]], [[BROADCAST_SPLAT2]] ; Os-NEXT: [[TMP46:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 36 ; Os-NEXT: [[TMP47:%.*]] = bitcast i32* [[TMP46]] to <4 x i32>* ; Os-NEXT: store <4 x i32> [[TMP45]], <4 x i32>* [[TMP47]], align 4 ; Os-NEXT: [[TMP48:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 40 ; Os-NEXT: [[TMP49:%.*]] = bitcast i32* [[TMP48]] to <4 x i32>* ; Os-NEXT: [[WIDE_LOAD_10:%.*]] = load <4 x i32>, <4 x i32>* [[TMP49]], align 4 -; Os-NEXT: [[TMP50:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_10]], [[BROADCAST_SPLAT]] +; Os-NEXT: [[TMP50:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_10]], [[BROADCAST_SPLAT2]] ; Os-NEXT: [[TMP51:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 40 ; Os-NEXT: [[TMP52:%.*]] = bitcast i32* [[TMP51]] to <4 x i32>* ; Os-NEXT: store <4 x i32> [[TMP50]], <4 x i32>* [[TMP52]], align 4 ; Os-NEXT: [[TMP53:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 44 ; Os-NEXT: [[TMP54:%.*]] = bitcast i32* [[TMP53]] to <4 x i32>* ; Os-NEXT: [[WIDE_LOAD_11:%.*]] = load <4 x i32>, <4 x i32>* [[TMP54]], align 4 -; Os-NEXT: [[TMP55:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_11]], [[BROADCAST_SPLAT]] +; Os-NEXT: [[TMP55:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_11]], [[BROADCAST_SPLAT2]] ; Os-NEXT: [[TMP56:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 44 ; Os-NEXT: [[TMP57:%.*]] = bitcast i32* [[TMP56]] to <4 x i32>* ; Os-NEXT: store <4 x i32> [[TMP55]], <4 x i32>* [[TMP57]], align 4 ; Os-NEXT: [[TMP58:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 48 ; Os-NEXT: [[TMP59:%.*]] = bitcast i32* [[TMP58]] to <4 x i32>* ; Os-NEXT: [[WIDE_LOAD_12:%.*]] = load <4 x i32>, <4 x i32>* [[TMP59]], align 4 -; Os-NEXT: [[TMP60:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_12]], [[BROADCAST_SPLAT]] +; Os-NEXT: [[TMP60:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_12]], [[BROADCAST_SPLAT2]] ; Os-NEXT: [[TMP61:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 48 ; Os-NEXT: [[TMP62:%.*]] = bitcast i32* [[TMP61]] to <4 x i32>* ; Os-NEXT: store <4 x i32> [[TMP60]], <4 x i32>* [[TMP62]], align 4 ; Os-NEXT: [[TMP63:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 52 ; Os-NEXT: [[TMP64:%.*]] = bitcast i32* [[TMP63]] to <4 x i32>* ; Os-NEXT: [[WIDE_LOAD_13:%.*]] = load <4 x i32>, <4 x i32>* [[TMP64]], align 4 -; Os-NEXT: [[TMP65:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_13]], [[BROADCAST_SPLAT]] +; Os-NEXT: [[TMP65:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_13]], [[BROADCAST_SPLAT2]] ; Os-NEXT: [[TMP66:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 52 ; Os-NEXT: [[TMP67:%.*]] = bitcast i32* [[TMP66]] to <4 x i32>* ; Os-NEXT: store <4 x i32> [[TMP65]], <4 x i32>* [[TMP67]], align 4 ; Os-NEXT: [[TMP68:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 56 ; Os-NEXT: [[TMP69:%.*]] = bitcast i32* [[TMP68]] to <4 x i32>* ; Os-NEXT: [[WIDE_LOAD_14:%.*]] = load <4 x i32>, <4 x i32>* [[TMP69]], align 4 -; Os-NEXT: [[TMP70:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_14]], [[BROADCAST_SPLAT]] +; Os-NEXT: [[TMP70:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_14]], [[BROADCAST_SPLAT2]] ; Os-NEXT: [[TMP71:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 56 ; Os-NEXT: [[TMP72:%.*]] = bitcast i32* [[TMP71]] to <4 x i32>* ; Os-NEXT: store <4 x i32> [[TMP70]], <4 x i32>* [[TMP72]], align 4 ; Os-NEXT: [[TMP73:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 60 ; Os-NEXT: [[TMP74:%.*]] = bitcast i32* [[TMP73]] to <4 x i32>* ; Os-NEXT: [[WIDE_LOAD_15:%.*]] = load <4 x i32>, <4 x i32>* [[TMP74]], align 4 -; Os-NEXT: [[TMP75:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_15]], [[BROADCAST_SPLAT]] +; Os-NEXT: [[TMP75:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_15]], [[BROADCAST_SPLAT2]] ; Os-NEXT: [[TMP76:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 60 ; Os-NEXT: [[TMP77:%.*]] = bitcast i32* [[TMP76]] to <4 x i32>* ; Os-NEXT: store <4 x i32> [[TMP75]], <4 x i32>* [[TMP77]], align 4 @@ -604,115 +604,115 @@ define i32 @enabled(i32* noalias nocapture %a, i32* noalias nocapture readonly % ; ; Oz-LABEL: @enabled( ; Oz-NEXT: entry: -; Oz-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i32> undef, i32 [[N:%.*]], i32 0 -; Oz-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT]], <4 x i32> undef, <4 x i32> zeroinitializer +; Oz-NEXT: [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <4 x i32> undef, i32 [[N:%.*]], i32 0 +; Oz-NEXT: [[BROADCAST_SPLAT2:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT1]], <4 x i32> undef, <4 x i32> zeroinitializer ; Oz-NEXT: [[TMP0:%.*]] = bitcast i32* [[B:%.*]] to <4 x i32>* ; Oz-NEXT: [[WIDE_LOAD:%.*]] = load <4 x i32>, <4 x i32>* [[TMP0]], align 4 -; Oz-NEXT: [[TMP1:%.*]] = add nsw <4 x i32> [[WIDE_LOAD]], [[BROADCAST_SPLAT]] +; Oz-NEXT: [[TMP1:%.*]] = add nsw <4 x i32> [[WIDE_LOAD]], [[BROADCAST_SPLAT2]] ; Oz-NEXT: [[TMP2:%.*]] = bitcast i32* [[A:%.*]] to <4 x i32>* ; Oz-NEXT: store <4 x i32> [[TMP1]], <4 x i32>* [[TMP2]], align 4 ; Oz-NEXT: [[TMP3:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 4 ; Oz-NEXT: [[TMP4:%.*]] = bitcast i32* [[TMP3]] to <4 x i32>* ; Oz-NEXT: [[WIDE_LOAD_1:%.*]] = load <4 x i32>, <4 x i32>* [[TMP4]], align 4 -; Oz-NEXT: [[TMP5:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_1]], [[BROADCAST_SPLAT]] +; Oz-NEXT: [[TMP5:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_1]], [[BROADCAST_SPLAT2]] ; Oz-NEXT: [[TMP6:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 4 ; Oz-NEXT: [[TMP7:%.*]] = bitcast i32* [[TMP6]] to <4 x i32>* ; Oz-NEXT: store <4 x i32> [[TMP5]], <4 x i32>* [[TMP7]], align 4 ; Oz-NEXT: [[TMP8:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 8 ; Oz-NEXT: [[TMP9:%.*]] = bitcast i32* [[TMP8]] to <4 x i32>* ; Oz-NEXT: [[WIDE_LOAD_2:%.*]] = load <4 x i32>, <4 x i32>* [[TMP9]], align 4 -; Oz-NEXT: [[TMP10:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_2]], [[BROADCAST_SPLAT]] +; Oz-NEXT: [[TMP10:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_2]], [[BROADCAST_SPLAT2]] ; Oz-NEXT: [[TMP11:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 8 ; Oz-NEXT: [[TMP12:%.*]] = bitcast i32* [[TMP11]] to <4 x i32>* ; Oz-NEXT: store <4 x i32> [[TMP10]], <4 x i32>* [[TMP12]], align 4 ; Oz-NEXT: [[TMP13:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 12 ; Oz-NEXT: [[TMP14:%.*]] = bitcast i32* [[TMP13]] to <4 x i32>* ; Oz-NEXT: [[WIDE_LOAD_3:%.*]] = load <4 x i32>, <4 x i32>* [[TMP14]], align 4 -; Oz-NEXT: [[TMP15:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_3]], [[BROADCAST_SPLAT]] +; Oz-NEXT: [[TMP15:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_3]], [[BROADCAST_SPLAT2]] ; Oz-NEXT: [[TMP16:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 12 ; Oz-NEXT: [[TMP17:%.*]] = bitcast i32* [[TMP16]] to <4 x i32>* ; Oz-NEXT: store <4 x i32> [[TMP15]], <4 x i32>* [[TMP17]], align 4 ; Oz-NEXT: [[TMP18:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 16 ; Oz-NEXT: [[TMP19:%.*]] = bitcast i32* [[TMP18]] to <4 x i32>* ; Oz-NEXT: [[WIDE_LOAD_4:%.*]] = load <4 x i32>, <4 x i32>* [[TMP19]], align 4 -; Oz-NEXT: [[TMP20:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_4]], [[BROADCAST_SPLAT]] +; Oz-NEXT: [[TMP20:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_4]], [[BROADCAST_SPLAT2]] ; Oz-NEXT: [[TMP21:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 16 ; Oz-NEXT: [[TMP22:%.*]] = bitcast i32* [[TMP21]] to <4 x i32>* ; Oz-NEXT: store <4 x i32> [[TMP20]], <4 x i32>* [[TMP22]], align 4 ; Oz-NEXT: [[TMP23:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 20 ; Oz-NEXT: [[TMP24:%.*]] = bitcast i32* [[TMP23]] to <4 x i32>* ; Oz-NEXT: [[WIDE_LOAD_5:%.*]] = load <4 x i32>, <4 x i32>* [[TMP24]], align 4 -; Oz-NEXT: [[TMP25:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_5]], [[BROADCAST_SPLAT]] +; Oz-NEXT: [[TMP25:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_5]], [[BROADCAST_SPLAT2]] ; Oz-NEXT: [[TMP26:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 20 ; Oz-NEXT: [[TMP27:%.*]] = bitcast i32* [[TMP26]] to <4 x i32>* ; Oz-NEXT: store <4 x i32> [[TMP25]], <4 x i32>* [[TMP27]], align 4 ; Oz-NEXT: [[TMP28:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 24 ; Oz-NEXT: [[TMP29:%.*]] = bitcast i32* [[TMP28]] to <4 x i32>* ; Oz-NEXT: [[WIDE_LOAD_6:%.*]] = load <4 x i32>, <4 x i32>* [[TMP29]], align 4 -; Oz-NEXT: [[TMP30:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_6]], [[BROADCAST_SPLAT]] +; Oz-NEXT: [[TMP30:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_6]], [[BROADCAST_SPLAT2]] ; Oz-NEXT: [[TMP31:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 24 ; Oz-NEXT: [[TMP32:%.*]] = bitcast i32* [[TMP31]] to <4 x i32>* ; Oz-NEXT: store <4 x i32> [[TMP30]], <4 x i32>* [[TMP32]], align 4 ; Oz-NEXT: [[TMP33:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 28 ; Oz-NEXT: [[TMP34:%.*]] = bitcast i32* [[TMP33]] to <4 x i32>* ; Oz-NEXT: [[WIDE_LOAD_7:%.*]] = load <4 x i32>, <4 x i32>* [[TMP34]], align 4 -; Oz-NEXT: [[TMP35:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_7]], [[BROADCAST_SPLAT]] +; Oz-NEXT: [[TMP35:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_7]], [[BROADCAST_SPLAT2]] ; Oz-NEXT: [[TMP36:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 28 ; Oz-NEXT: [[TMP37:%.*]] = bitcast i32* [[TMP36]] to <4 x i32>* ; Oz-NEXT: store <4 x i32> [[TMP35]], <4 x i32>* [[TMP37]], align 4 ; Oz-NEXT: [[TMP38:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 32 ; Oz-NEXT: [[TMP39:%.*]] = bitcast i32* [[TMP38]] to <4 x i32>* ; Oz-NEXT: [[WIDE_LOAD_8:%.*]] = load <4 x i32>, <4 x i32>* [[TMP39]], align 4 -; Oz-NEXT: [[TMP40:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_8]], [[BROADCAST_SPLAT]] +; Oz-NEXT: [[TMP40:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_8]], [[BROADCAST_SPLAT2]] ; Oz-NEXT: [[TMP41:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 32 ; Oz-NEXT: [[TMP42:%.*]] = bitcast i32* [[TMP41]] to <4 x i32>* ; Oz-NEXT: store <4 x i32> [[TMP40]], <4 x i32>* [[TMP42]], align 4 ; Oz-NEXT: [[TMP43:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 36 ; Oz-NEXT: [[TMP44:%.*]] = bitcast i32* [[TMP43]] to <4 x i32>* ; Oz-NEXT: [[WIDE_LOAD_9:%.*]] = load <4 x i32>, <4 x i32>* [[TMP44]], align 4 -; Oz-NEXT: [[TMP45:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_9]], [[BROADCAST_SPLAT]] +; Oz-NEXT: [[TMP45:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_9]], [[BROADCAST_SPLAT2]] ; Oz-NEXT: [[TMP46:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 36 ; Oz-NEXT: [[TMP47:%.*]] = bitcast i32* [[TMP46]] to <4 x i32>* ; Oz-NEXT: store <4 x i32> [[TMP45]], <4 x i32>* [[TMP47]], align 4 ; Oz-NEXT: [[TMP48:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 40 ; Oz-NEXT: [[TMP49:%.*]] = bitcast i32* [[TMP48]] to <4 x i32>* ; Oz-NEXT: [[WIDE_LOAD_10:%.*]] = load <4 x i32>, <4 x i32>* [[TMP49]], align 4 -; Oz-NEXT: [[TMP50:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_10]], [[BROADCAST_SPLAT]] +; Oz-NEXT: [[TMP50:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_10]], [[BROADCAST_SPLAT2]] ; Oz-NEXT: [[TMP51:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 40 ; Oz-NEXT: [[TMP52:%.*]] = bitcast i32* [[TMP51]] to <4 x i32>* ; Oz-NEXT: store <4 x i32> [[TMP50]], <4 x i32>* [[TMP52]], align 4 ; Oz-NEXT: [[TMP53:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 44 ; Oz-NEXT: [[TMP54:%.*]] = bitcast i32* [[TMP53]] to <4 x i32>* ; Oz-NEXT: [[WIDE_LOAD_11:%.*]] = load <4 x i32>, <4 x i32>* [[TMP54]], align 4 -; Oz-NEXT: [[TMP55:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_11]], [[BROADCAST_SPLAT]] +; Oz-NEXT: [[TMP55:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_11]], [[BROADCAST_SPLAT2]] ; Oz-NEXT: [[TMP56:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 44 ; Oz-NEXT: [[TMP57:%.*]] = bitcast i32* [[TMP56]] to <4 x i32>* ; Oz-NEXT: store <4 x i32> [[TMP55]], <4 x i32>* [[TMP57]], align 4 ; Oz-NEXT: [[TMP58:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 48 ; Oz-NEXT: [[TMP59:%.*]] = bitcast i32* [[TMP58]] to <4 x i32>* ; Oz-NEXT: [[WIDE_LOAD_12:%.*]] = load <4 x i32>, <4 x i32>* [[TMP59]], align 4 -; Oz-NEXT: [[TMP60:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_12]], [[BROADCAST_SPLAT]] +; Oz-NEXT: [[TMP60:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_12]], [[BROADCAST_SPLAT2]] ; Oz-NEXT: [[TMP61:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 48 ; Oz-NEXT: [[TMP62:%.*]] = bitcast i32* [[TMP61]] to <4 x i32>* ; Oz-NEXT: store <4 x i32> [[TMP60]], <4 x i32>* [[TMP62]], align 4 ; Oz-NEXT: [[TMP63:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 52 ; Oz-NEXT: [[TMP64:%.*]] = bitcast i32* [[TMP63]] to <4 x i32>* ; Oz-NEXT: [[WIDE_LOAD_13:%.*]] = load <4 x i32>, <4 x i32>* [[TMP64]], align 4 -; Oz-NEXT: [[TMP65:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_13]], [[BROADCAST_SPLAT]] +; Oz-NEXT: [[TMP65:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_13]], [[BROADCAST_SPLAT2]] ; Oz-NEXT: [[TMP66:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 52 ; Oz-NEXT: [[TMP67:%.*]] = bitcast i32* [[TMP66]] to <4 x i32>* ; Oz-NEXT: store <4 x i32> [[TMP65]], <4 x i32>* [[TMP67]], align 4 ; Oz-NEXT: [[TMP68:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 56 ; Oz-NEXT: [[TMP69:%.*]] = bitcast i32* [[TMP68]] to <4 x i32>* ; Oz-NEXT: [[WIDE_LOAD_14:%.*]] = load <4 x i32>, <4 x i32>* [[TMP69]], align 4 -; Oz-NEXT: [[TMP70:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_14]], [[BROADCAST_SPLAT]] +; Oz-NEXT: [[TMP70:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_14]], [[BROADCAST_SPLAT2]] ; Oz-NEXT: [[TMP71:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 56 ; Oz-NEXT: [[TMP72:%.*]] = bitcast i32* [[TMP71]] to <4 x i32>* ; Oz-NEXT: store <4 x i32> [[TMP70]], <4 x i32>* [[TMP72]], align 4 ; Oz-NEXT: [[TMP73:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 60 ; Oz-NEXT: [[TMP74:%.*]] = bitcast i32* [[TMP73]] to <4 x i32>* ; Oz-NEXT: [[WIDE_LOAD_15:%.*]] = load <4 x i32>, <4 x i32>* [[TMP74]], align 4 -; Oz-NEXT: [[TMP75:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_15]], [[BROADCAST_SPLAT]] +; Oz-NEXT: [[TMP75:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_15]], [[BROADCAST_SPLAT2]] ; Oz-NEXT: [[TMP76:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 60 ; Oz-NEXT: [[TMP77:%.*]] = bitcast i32* [[TMP76]] to <4 x i32>* ; Oz-NEXT: store <4 x i32> [[TMP75]], <4 x i32>* [[TMP77]], align 4 @@ -721,115 +721,115 @@ define i32 @enabled(i32* noalias nocapture %a, i32* noalias nocapture readonly % ; ; O1VEC2-LABEL: @enabled( ; O1VEC2-NEXT: entry: -; O1VEC2-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i32> undef, i32 [[N:%.*]], i32 0 -; O1VEC2-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT]], <4 x i32> undef, <4 x i32> zeroinitializer +; O1VEC2-NEXT: [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <4 x i32> undef, i32 [[N:%.*]], i32 0 +; O1VEC2-NEXT: [[BROADCAST_SPLAT2:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT1]], <4 x i32> undef, <4 x i32> zeroinitializer ; O1VEC2-NEXT: [[TMP0:%.*]] = bitcast i32* [[B:%.*]] to <4 x i32>* ; O1VEC2-NEXT: [[WIDE_LOAD:%.*]] = load <4 x i32>, <4 x i32>* [[TMP0]], align 4 -; O1VEC2-NEXT: [[TMP1:%.*]] = add nsw <4 x i32> [[WIDE_LOAD]], [[BROADCAST_SPLAT]] +; O1VEC2-NEXT: [[TMP1:%.*]] = add nsw <4 x i32> [[WIDE_LOAD]], [[BROADCAST_SPLAT2]] ; O1VEC2-NEXT: [[TMP2:%.*]] = bitcast i32* [[A:%.*]] to <4 x i32>* ; O1VEC2-NEXT: store <4 x i32> [[TMP1]], <4 x i32>* [[TMP2]], align 4 ; O1VEC2-NEXT: [[TMP3:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 4 ; O1VEC2-NEXT: [[TMP4:%.*]] = bitcast i32* [[TMP3]] to <4 x i32>* ; O1VEC2-NEXT: [[WIDE_LOAD_1:%.*]] = load <4 x i32>, <4 x i32>* [[TMP4]], align 4 -; O1VEC2-NEXT: [[TMP5:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_1]], [[BROADCAST_SPLAT]] +; O1VEC2-NEXT: [[TMP5:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_1]], [[BROADCAST_SPLAT2]] ; O1VEC2-NEXT: [[TMP6:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 4 ; O1VEC2-NEXT: [[TMP7:%.*]] = bitcast i32* [[TMP6]] to <4 x i32>* ; O1VEC2-NEXT: store <4 x i32> [[TMP5]], <4 x i32>* [[TMP7]], align 4 ; O1VEC2-NEXT: [[TMP8:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 8 ; O1VEC2-NEXT: [[TMP9:%.*]] = bitcast i32* [[TMP8]] to <4 x i32>* ; O1VEC2-NEXT: [[WIDE_LOAD_2:%.*]] = load <4 x i32>, <4 x i32>* [[TMP9]], align 4 -; O1VEC2-NEXT: [[TMP10:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_2]], [[BROADCAST_SPLAT]] +; O1VEC2-NEXT: [[TMP10:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_2]], [[BROADCAST_SPLAT2]] ; O1VEC2-NEXT: [[TMP11:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 8 ; O1VEC2-NEXT: [[TMP12:%.*]] = bitcast i32* [[TMP11]] to <4 x i32>* ; O1VEC2-NEXT: store <4 x i32> [[TMP10]], <4 x i32>* [[TMP12]], align 4 ; O1VEC2-NEXT: [[TMP13:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 12 ; O1VEC2-NEXT: [[TMP14:%.*]] = bitcast i32* [[TMP13]] to <4 x i32>* ; O1VEC2-NEXT: [[WIDE_LOAD_3:%.*]] = load <4 x i32>, <4 x i32>* [[TMP14]], align 4 -; O1VEC2-NEXT: [[TMP15:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_3]], [[BROADCAST_SPLAT]] +; O1VEC2-NEXT: [[TMP15:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_3]], [[BROADCAST_SPLAT2]] ; O1VEC2-NEXT: [[TMP16:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 12 ; O1VEC2-NEXT: [[TMP17:%.*]] = bitcast i32* [[TMP16]] to <4 x i32>* ; O1VEC2-NEXT: store <4 x i32> [[TMP15]], <4 x i32>* [[TMP17]], align 4 ; O1VEC2-NEXT: [[TMP18:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 16 ; O1VEC2-NEXT: [[TMP19:%.*]] = bitcast i32* [[TMP18]] to <4 x i32>* ; O1VEC2-NEXT: [[WIDE_LOAD_4:%.*]] = load <4 x i32>, <4 x i32>* [[TMP19]], align 4 -; O1VEC2-NEXT: [[TMP20:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_4]], [[BROADCAST_SPLAT]] +; O1VEC2-NEXT: [[TMP20:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_4]], [[BROADCAST_SPLAT2]] ; O1VEC2-NEXT: [[TMP21:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 16 ; O1VEC2-NEXT: [[TMP22:%.*]] = bitcast i32* [[TMP21]] to <4 x i32>* ; O1VEC2-NEXT: store <4 x i32> [[TMP20]], <4 x i32>* [[TMP22]], align 4 ; O1VEC2-NEXT: [[TMP23:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 20 ; O1VEC2-NEXT: [[TMP24:%.*]] = bitcast i32* [[TMP23]] to <4 x i32>* ; O1VEC2-NEXT: [[WIDE_LOAD_5:%.*]] = load <4 x i32>, <4 x i32>* [[TMP24]], align 4 -; O1VEC2-NEXT: [[TMP25:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_5]], [[BROADCAST_SPLAT]] +; O1VEC2-NEXT: [[TMP25:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_5]], [[BROADCAST_SPLAT2]] ; O1VEC2-NEXT: [[TMP26:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 20 ; O1VEC2-NEXT: [[TMP27:%.*]] = bitcast i32* [[TMP26]] to <4 x i32>* ; O1VEC2-NEXT: store <4 x i32> [[TMP25]], <4 x i32>* [[TMP27]], align 4 ; O1VEC2-NEXT: [[TMP28:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 24 ; O1VEC2-NEXT: [[TMP29:%.*]] = bitcast i32* [[TMP28]] to <4 x i32>* ; O1VEC2-NEXT: [[WIDE_LOAD_6:%.*]] = load <4 x i32>, <4 x i32>* [[TMP29]], align 4 -; O1VEC2-NEXT: [[TMP30:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_6]], [[BROADCAST_SPLAT]] +; O1VEC2-NEXT: [[TMP30:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_6]], [[BROADCAST_SPLAT2]] ; O1VEC2-NEXT: [[TMP31:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 24 ; O1VEC2-NEXT: [[TMP32:%.*]] = bitcast i32* [[TMP31]] to <4 x i32>* ; O1VEC2-NEXT: store <4 x i32> [[TMP30]], <4 x i32>* [[TMP32]], align 4 ; O1VEC2-NEXT: [[TMP33:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 28 ; O1VEC2-NEXT: [[TMP34:%.*]] = bitcast i32* [[TMP33]] to <4 x i32>* ; O1VEC2-NEXT: [[WIDE_LOAD_7:%.*]] = load <4 x i32>, <4 x i32>* [[TMP34]], align 4 -; O1VEC2-NEXT: [[TMP35:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_7]], [[BROADCAST_SPLAT]] +; O1VEC2-NEXT: [[TMP35:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_7]], [[BROADCAST_SPLAT2]] ; O1VEC2-NEXT: [[TMP36:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 28 ; O1VEC2-NEXT: [[TMP37:%.*]] = bitcast i32* [[TMP36]] to <4 x i32>* ; O1VEC2-NEXT: store <4 x i32> [[TMP35]], <4 x i32>* [[TMP37]], align 4 ; O1VEC2-NEXT: [[TMP38:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 32 ; O1VEC2-NEXT: [[TMP39:%.*]] = bitcast i32* [[TMP38]] to <4 x i32>* ; O1VEC2-NEXT: [[WIDE_LOAD_8:%.*]] = load <4 x i32>, <4 x i32>* [[TMP39]], align 4 -; O1VEC2-NEXT: [[TMP40:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_8]], [[BROADCAST_SPLAT]] +; O1VEC2-NEXT: [[TMP40:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_8]], [[BROADCAST_SPLAT2]] ; O1VEC2-NEXT: [[TMP41:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 32 ; O1VEC2-NEXT: [[TMP42:%.*]] = bitcast i32* [[TMP41]] to <4 x i32>* ; O1VEC2-NEXT: store <4 x i32> [[TMP40]], <4 x i32>* [[TMP42]], align 4 ; O1VEC2-NEXT: [[TMP43:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 36 ; O1VEC2-NEXT: [[TMP44:%.*]] = bitcast i32* [[TMP43]] to <4 x i32>* ; O1VEC2-NEXT: [[WIDE_LOAD_9:%.*]] = load <4 x i32>, <4 x i32>* [[TMP44]], align 4 -; O1VEC2-NEXT: [[TMP45:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_9]], [[BROADCAST_SPLAT]] +; O1VEC2-NEXT: [[TMP45:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_9]], [[BROADCAST_SPLAT2]] ; O1VEC2-NEXT: [[TMP46:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 36 ; O1VEC2-NEXT: [[TMP47:%.*]] = bitcast i32* [[TMP46]] to <4 x i32>* ; O1VEC2-NEXT: store <4 x i32> [[TMP45]], <4 x i32>* [[TMP47]], align 4 ; O1VEC2-NEXT: [[TMP48:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 40 ; O1VEC2-NEXT: [[TMP49:%.*]] = bitcast i32* [[TMP48]] to <4 x i32>* ; O1VEC2-NEXT: [[WIDE_LOAD_10:%.*]] = load <4 x i32>, <4 x i32>* [[TMP49]], align 4 -; O1VEC2-NEXT: [[TMP50:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_10]], [[BROADCAST_SPLAT]] +; O1VEC2-NEXT: [[TMP50:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_10]], [[BROADCAST_SPLAT2]] ; O1VEC2-NEXT: [[TMP51:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 40 ; O1VEC2-NEXT: [[TMP52:%.*]] = bitcast i32* [[TMP51]] to <4 x i32>* ; O1VEC2-NEXT: store <4 x i32> [[TMP50]], <4 x i32>* [[TMP52]], align 4 ; O1VEC2-NEXT: [[TMP53:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 44 ; O1VEC2-NEXT: [[TMP54:%.*]] = bitcast i32* [[TMP53]] to <4 x i32>* ; O1VEC2-NEXT: [[WIDE_LOAD_11:%.*]] = load <4 x i32>, <4 x i32>* [[TMP54]], align 4 -; O1VEC2-NEXT: [[TMP55:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_11]], [[BROADCAST_SPLAT]] +; O1VEC2-NEXT: [[TMP55:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_11]], [[BROADCAST_SPLAT2]] ; O1VEC2-NEXT: [[TMP56:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 44 ; O1VEC2-NEXT: [[TMP57:%.*]] = bitcast i32* [[TMP56]] to <4 x i32>* ; O1VEC2-NEXT: store <4 x i32> [[TMP55]], <4 x i32>* [[TMP57]], align 4 ; O1VEC2-NEXT: [[TMP58:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 48 ; O1VEC2-NEXT: [[TMP59:%.*]] = bitcast i32* [[TMP58]] to <4 x i32>* ; O1VEC2-NEXT: [[WIDE_LOAD_12:%.*]] = load <4 x i32>, <4 x i32>* [[TMP59]], align 4 -; O1VEC2-NEXT: [[TMP60:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_12]], [[BROADCAST_SPLAT]] +; O1VEC2-NEXT: [[TMP60:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_12]], [[BROADCAST_SPLAT2]] ; O1VEC2-NEXT: [[TMP61:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 48 ; O1VEC2-NEXT: [[TMP62:%.*]] = bitcast i32* [[TMP61]] to <4 x i32>* ; O1VEC2-NEXT: store <4 x i32> [[TMP60]], <4 x i32>* [[TMP62]], align 4 ; O1VEC2-NEXT: [[TMP63:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 52 ; O1VEC2-NEXT: [[TMP64:%.*]] = bitcast i32* [[TMP63]] to <4 x i32>* ; O1VEC2-NEXT: [[WIDE_LOAD_13:%.*]] = load <4 x i32>, <4 x i32>* [[TMP64]], align 4 -; O1VEC2-NEXT: [[TMP65:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_13]], [[BROADCAST_SPLAT]] +; O1VEC2-NEXT: [[TMP65:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_13]], [[BROADCAST_SPLAT2]] ; O1VEC2-NEXT: [[TMP66:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 52 ; O1VEC2-NEXT: [[TMP67:%.*]] = bitcast i32* [[TMP66]] to <4 x i32>* ; O1VEC2-NEXT: store <4 x i32> [[TMP65]], <4 x i32>* [[TMP67]], align 4 ; O1VEC2-NEXT: [[TMP68:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 56 ; O1VEC2-NEXT: [[TMP69:%.*]] = bitcast i32* [[TMP68]] to <4 x i32>* ; O1VEC2-NEXT: [[WIDE_LOAD_14:%.*]] = load <4 x i32>, <4 x i32>* [[TMP69]], align 4 -; O1VEC2-NEXT: [[TMP70:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_14]], [[BROADCAST_SPLAT]] +; O1VEC2-NEXT: [[TMP70:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_14]], [[BROADCAST_SPLAT2]] ; O1VEC2-NEXT: [[TMP71:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 56 ; O1VEC2-NEXT: [[TMP72:%.*]] = bitcast i32* [[TMP71]] to <4 x i32>* ; O1VEC2-NEXT: store <4 x i32> [[TMP70]], <4 x i32>* [[TMP72]], align 4 ; O1VEC2-NEXT: [[TMP73:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 60 ; O1VEC2-NEXT: [[TMP74:%.*]] = bitcast i32* [[TMP73]] to <4 x i32>* ; O1VEC2-NEXT: [[WIDE_LOAD_15:%.*]] = load <4 x i32>, <4 x i32>* [[TMP74]], align 4 -; O1VEC2-NEXT: [[TMP75:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_15]], [[BROADCAST_SPLAT]] +; O1VEC2-NEXT: [[TMP75:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_15]], [[BROADCAST_SPLAT2]] ; O1VEC2-NEXT: [[TMP76:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 60 ; O1VEC2-NEXT: [[TMP77:%.*]] = bitcast i32* [[TMP76]] to <4 x i32>* ; O1VEC2-NEXT: store <4 x i32> [[TMP75]], <4 x i32>* [[TMP77]], align 4 @@ -838,115 +838,115 @@ define i32 @enabled(i32* noalias nocapture %a, i32* noalias nocapture readonly % ; ; OzVEC2-LABEL: @enabled( ; OzVEC2-NEXT: entry: -; OzVEC2-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i32> undef, i32 [[N:%.*]], i32 0 -; OzVEC2-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT]], <4 x i32> undef, <4 x i32> zeroinitializer +; OzVEC2-NEXT: [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <4 x i32> undef, i32 [[N:%.*]], i32 0 +; OzVEC2-NEXT: [[BROADCAST_SPLAT2:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT1]], <4 x i32> undef, <4 x i32> zeroinitializer ; OzVEC2-NEXT: [[TMP0:%.*]] = bitcast i32* [[B:%.*]] to <4 x i32>* ; OzVEC2-NEXT: [[WIDE_LOAD:%.*]] = load <4 x i32>, <4 x i32>* [[TMP0]], align 4 -; OzVEC2-NEXT: [[TMP1:%.*]] = add nsw <4 x i32> [[WIDE_LOAD]], [[BROADCAST_SPLAT]] +; OzVEC2-NEXT: [[TMP1:%.*]] = add nsw <4 x i32> [[WIDE_LOAD]], [[BROADCAST_SPLAT2]] ; OzVEC2-NEXT: [[TMP2:%.*]] = bitcast i32* [[A:%.*]] to <4 x i32>* ; OzVEC2-NEXT: store <4 x i32> [[TMP1]], <4 x i32>* [[TMP2]], align 4 ; OzVEC2-NEXT: [[TMP3:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 4 ; OzVEC2-NEXT: [[TMP4:%.*]] = bitcast i32* [[TMP3]] to <4 x i32>* ; OzVEC2-NEXT: [[WIDE_LOAD_1:%.*]] = load <4 x i32>, <4 x i32>* [[TMP4]], align 4 -; OzVEC2-NEXT: [[TMP5:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_1]], [[BROADCAST_SPLAT]] +; OzVEC2-NEXT: [[TMP5:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_1]], [[BROADCAST_SPLAT2]] ; OzVEC2-NEXT: [[TMP6:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 4 ; OzVEC2-NEXT: [[TMP7:%.*]] = bitcast i32* [[TMP6]] to <4 x i32>* ; OzVEC2-NEXT: store <4 x i32> [[TMP5]], <4 x i32>* [[TMP7]], align 4 ; OzVEC2-NEXT: [[TMP8:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 8 ; OzVEC2-NEXT: [[TMP9:%.*]] = bitcast i32* [[TMP8]] to <4 x i32>* ; OzVEC2-NEXT: [[WIDE_LOAD_2:%.*]] = load <4 x i32>, <4 x i32>* [[TMP9]], align 4 -; OzVEC2-NEXT: [[TMP10:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_2]], [[BROADCAST_SPLAT]] +; OzVEC2-NEXT: [[TMP10:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_2]], [[BROADCAST_SPLAT2]] ; OzVEC2-NEXT: [[TMP11:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 8 ; OzVEC2-NEXT: [[TMP12:%.*]] = bitcast i32* [[TMP11]] to <4 x i32>* ; OzVEC2-NEXT: store <4 x i32> [[TMP10]], <4 x i32>* [[TMP12]], align 4 ; OzVEC2-NEXT: [[TMP13:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 12 ; OzVEC2-NEXT: [[TMP14:%.*]] = bitcast i32* [[TMP13]] to <4 x i32>* ; OzVEC2-NEXT: [[WIDE_LOAD_3:%.*]] = load <4 x i32>, <4 x i32>* [[TMP14]], align 4 -; OzVEC2-NEXT: [[TMP15:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_3]], [[BROADCAST_SPLAT]] +; OzVEC2-NEXT: [[TMP15:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_3]], [[BROADCAST_SPLAT2]] ; OzVEC2-NEXT: [[TMP16:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 12 ; OzVEC2-NEXT: [[TMP17:%.*]] = bitcast i32* [[TMP16]] to <4 x i32>* ; OzVEC2-NEXT: store <4 x i32> [[TMP15]], <4 x i32>* [[TMP17]], align 4 ; OzVEC2-NEXT: [[TMP18:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 16 ; OzVEC2-NEXT: [[TMP19:%.*]] = bitcast i32* [[TMP18]] to <4 x i32>* ; OzVEC2-NEXT: [[WIDE_LOAD_4:%.*]] = load <4 x i32>, <4 x i32>* [[TMP19]], align 4 -; OzVEC2-NEXT: [[TMP20:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_4]], [[BROADCAST_SPLAT]] +; OzVEC2-NEXT: [[TMP20:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_4]], [[BROADCAST_SPLAT2]] ; OzVEC2-NEXT: [[TMP21:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 16 ; OzVEC2-NEXT: [[TMP22:%.*]] = bitcast i32* [[TMP21]] to <4 x i32>* ; OzVEC2-NEXT: store <4 x i32> [[TMP20]], <4 x i32>* [[TMP22]], align 4 ; OzVEC2-NEXT: [[TMP23:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 20 ; OzVEC2-NEXT: [[TMP24:%.*]] = bitcast i32* [[TMP23]] to <4 x i32>* ; OzVEC2-NEXT: [[WIDE_LOAD_5:%.*]] = load <4 x i32>, <4 x i32>* [[TMP24]], align 4 -; OzVEC2-NEXT: [[TMP25:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_5]], [[BROADCAST_SPLAT]] +; OzVEC2-NEXT: [[TMP25:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_5]], [[BROADCAST_SPLAT2]] ; OzVEC2-NEXT: [[TMP26:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 20 ; OzVEC2-NEXT: [[TMP27:%.*]] = bitcast i32* [[TMP26]] to <4 x i32>* ; OzVEC2-NEXT: store <4 x i32> [[TMP25]], <4 x i32>* [[TMP27]], align 4 ; OzVEC2-NEXT: [[TMP28:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 24 ; OzVEC2-NEXT: [[TMP29:%.*]] = bitcast i32* [[TMP28]] to <4 x i32>* ; OzVEC2-NEXT: [[WIDE_LOAD_6:%.*]] = load <4 x i32>, <4 x i32>* [[TMP29]], align 4 -; OzVEC2-NEXT: [[TMP30:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_6]], [[BROADCAST_SPLAT]] +; OzVEC2-NEXT: [[TMP30:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_6]], [[BROADCAST_SPLAT2]] ; OzVEC2-NEXT: [[TMP31:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 24 ; OzVEC2-NEXT: [[TMP32:%.*]] = bitcast i32* [[TMP31]] to <4 x i32>* ; OzVEC2-NEXT: store <4 x i32> [[TMP30]], <4 x i32>* [[TMP32]], align 4 ; OzVEC2-NEXT: [[TMP33:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 28 ; OzVEC2-NEXT: [[TMP34:%.*]] = bitcast i32* [[TMP33]] to <4 x i32>* ; OzVEC2-NEXT: [[WIDE_LOAD_7:%.*]] = load <4 x i32>, <4 x i32>* [[TMP34]], align 4 -; OzVEC2-NEXT: [[TMP35:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_7]], [[BROADCAST_SPLAT]] +; OzVEC2-NEXT: [[TMP35:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_7]], [[BROADCAST_SPLAT2]] ; OzVEC2-NEXT: [[TMP36:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 28 ; OzVEC2-NEXT: [[TMP37:%.*]] = bitcast i32* [[TMP36]] to <4 x i32>* ; OzVEC2-NEXT: store <4 x i32> [[TMP35]], <4 x i32>* [[TMP37]], align 4 ; OzVEC2-NEXT: [[TMP38:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 32 ; OzVEC2-NEXT: [[TMP39:%.*]] = bitcast i32* [[TMP38]] to <4 x i32>* ; OzVEC2-NEXT: [[WIDE_LOAD_8:%.*]] = load <4 x i32>, <4 x i32>* [[TMP39]], align 4 -; OzVEC2-NEXT: [[TMP40:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_8]], [[BROADCAST_SPLAT]] +; OzVEC2-NEXT: [[TMP40:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_8]], [[BROADCAST_SPLAT2]] ; OzVEC2-NEXT: [[TMP41:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 32 ; OzVEC2-NEXT: [[TMP42:%.*]] = bitcast i32* [[TMP41]] to <4 x i32>* ; OzVEC2-NEXT: store <4 x i32> [[TMP40]], <4 x i32>* [[TMP42]], align 4 ; OzVEC2-NEXT: [[TMP43:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 36 ; OzVEC2-NEXT: [[TMP44:%.*]] = bitcast i32* [[TMP43]] to <4 x i32>* ; OzVEC2-NEXT: [[WIDE_LOAD_9:%.*]] = load <4 x i32>, <4 x i32>* [[TMP44]], align 4 -; OzVEC2-NEXT: [[TMP45:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_9]], [[BROADCAST_SPLAT]] +; OzVEC2-NEXT: [[TMP45:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_9]], [[BROADCAST_SPLAT2]] ; OzVEC2-NEXT: [[TMP46:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 36 ; OzVEC2-NEXT: [[TMP47:%.*]] = bitcast i32* [[TMP46]] to <4 x i32>* ; OzVEC2-NEXT: store <4 x i32> [[TMP45]], <4 x i32>* [[TMP47]], align 4 ; OzVEC2-NEXT: [[TMP48:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 40 ; OzVEC2-NEXT: [[TMP49:%.*]] = bitcast i32* [[TMP48]] to <4 x i32>* ; OzVEC2-NEXT: [[WIDE_LOAD_10:%.*]] = load <4 x i32>, <4 x i32>* [[TMP49]], align 4 -; OzVEC2-NEXT: [[TMP50:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_10]], [[BROADCAST_SPLAT]] +; OzVEC2-NEXT: [[TMP50:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_10]], [[BROADCAST_SPLAT2]] ; OzVEC2-NEXT: [[TMP51:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 40 ; OzVEC2-NEXT: [[TMP52:%.*]] = bitcast i32* [[TMP51]] to <4 x i32>* ; OzVEC2-NEXT: store <4 x i32> [[TMP50]], <4 x i32>* [[TMP52]], align 4 ; OzVEC2-NEXT: [[TMP53:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 44 ; OzVEC2-NEXT: [[TMP54:%.*]] = bitcast i32* [[TMP53]] to <4 x i32>* ; OzVEC2-NEXT: [[WIDE_LOAD_11:%.*]] = load <4 x i32>, <4 x i32>* [[TMP54]], align 4 -; OzVEC2-NEXT: [[TMP55:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_11]], [[BROADCAST_SPLAT]] +; OzVEC2-NEXT: [[TMP55:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_11]], [[BROADCAST_SPLAT2]] ; OzVEC2-NEXT: [[TMP56:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 44 ; OzVEC2-NEXT: [[TMP57:%.*]] = bitcast i32* [[TMP56]] to <4 x i32>* ; OzVEC2-NEXT: store <4 x i32> [[TMP55]], <4 x i32>* [[TMP57]], align 4 ; OzVEC2-NEXT: [[TMP58:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 48 ; OzVEC2-NEXT: [[TMP59:%.*]] = bitcast i32* [[TMP58]] to <4 x i32>* ; OzVEC2-NEXT: [[WIDE_LOAD_12:%.*]] = load <4 x i32>, <4 x i32>* [[TMP59]], align 4 -; OzVEC2-NEXT: [[TMP60:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_12]], [[BROADCAST_SPLAT]] +; OzVEC2-NEXT: [[TMP60:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_12]], [[BROADCAST_SPLAT2]] ; OzVEC2-NEXT: [[TMP61:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 48 ; OzVEC2-NEXT: [[TMP62:%.*]] = bitcast i32* [[TMP61]] to <4 x i32>* ; OzVEC2-NEXT: store <4 x i32> [[TMP60]], <4 x i32>* [[TMP62]], align 4 ; OzVEC2-NEXT: [[TMP63:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 52 ; OzVEC2-NEXT: [[TMP64:%.*]] = bitcast i32* [[TMP63]] to <4 x i32>* ; OzVEC2-NEXT: [[WIDE_LOAD_13:%.*]] = load <4 x i32>, <4 x i32>* [[TMP64]], align 4 -; OzVEC2-NEXT: [[TMP65:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_13]], [[BROADCAST_SPLAT]] +; OzVEC2-NEXT: [[TMP65:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_13]], [[BROADCAST_SPLAT2]] ; OzVEC2-NEXT: [[TMP66:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 52 ; OzVEC2-NEXT: [[TMP67:%.*]] = bitcast i32* [[TMP66]] to <4 x i32>* ; OzVEC2-NEXT: store <4 x i32> [[TMP65]], <4 x i32>* [[TMP67]], align 4 ; OzVEC2-NEXT: [[TMP68:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 56 ; OzVEC2-NEXT: [[TMP69:%.*]] = bitcast i32* [[TMP68]] to <4 x i32>* ; OzVEC2-NEXT: [[WIDE_LOAD_14:%.*]] = load <4 x i32>, <4 x i32>* [[TMP69]], align 4 -; OzVEC2-NEXT: [[TMP70:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_14]], [[BROADCAST_SPLAT]] +; OzVEC2-NEXT: [[TMP70:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_14]], [[BROADCAST_SPLAT2]] ; OzVEC2-NEXT: [[TMP71:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 56 ; OzVEC2-NEXT: [[TMP72:%.*]] = bitcast i32* [[TMP71]] to <4 x i32>* ; OzVEC2-NEXT: store <4 x i32> [[TMP70]], <4 x i32>* [[TMP72]], align 4 ; OzVEC2-NEXT: [[TMP73:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 60 ; OzVEC2-NEXT: [[TMP74:%.*]] = bitcast i32* [[TMP73]] to <4 x i32>* ; OzVEC2-NEXT: [[WIDE_LOAD_15:%.*]] = load <4 x i32>, <4 x i32>* [[TMP74]], align 4 -; OzVEC2-NEXT: [[TMP75:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_15]], [[BROADCAST_SPLAT]] +; OzVEC2-NEXT: [[TMP75:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_15]], [[BROADCAST_SPLAT2]] ; OzVEC2-NEXT: [[TMP76:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 60 ; OzVEC2-NEXT: [[TMP77:%.*]] = bitcast i32* [[TMP76]] to <4 x i32>* ; OzVEC2-NEXT: store <4 x i32> [[TMP75]], <4 x i32>* [[TMP77]], align 4 @@ -955,115 +955,115 @@ define i32 @enabled(i32* noalias nocapture %a, i32* noalias nocapture readonly % ; ; O3DIS-LABEL: @enabled( ; O3DIS-NEXT: entry: -; O3DIS-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i32> undef, i32 [[N:%.*]], i32 0 -; O3DIS-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT]], <4 x i32> undef, <4 x i32> zeroinitializer +; O3DIS-NEXT: [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <4 x i32> undef, i32 [[N:%.*]], i32 0 +; O3DIS-NEXT: [[BROADCAST_SPLAT2:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT1]], <4 x i32> undef, <4 x i32> zeroinitializer ; O3DIS-NEXT: [[TMP0:%.*]] = bitcast i32* [[B:%.*]] to <4 x i32>* ; O3DIS-NEXT: [[WIDE_LOAD:%.*]] = load <4 x i32>, <4 x i32>* [[TMP0]], align 4 -; O3DIS-NEXT: [[TMP1:%.*]] = add nsw <4 x i32> [[WIDE_LOAD]], [[BROADCAST_SPLAT]] +; O3DIS-NEXT: [[TMP1:%.*]] = add nsw <4 x i32> [[WIDE_LOAD]], [[BROADCAST_SPLAT2]] ; O3DIS-NEXT: [[TMP2:%.*]] = bitcast i32* [[A:%.*]] to <4 x i32>* ; O3DIS-NEXT: store <4 x i32> [[TMP1]], <4 x i32>* [[TMP2]], align 4 ; O3DIS-NEXT: [[TMP3:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 4 ; O3DIS-NEXT: [[TMP4:%.*]] = bitcast i32* [[TMP3]] to <4 x i32>* ; O3DIS-NEXT: [[WIDE_LOAD_1:%.*]] = load <4 x i32>, <4 x i32>* [[TMP4]], align 4 -; O3DIS-NEXT: [[TMP5:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_1]], [[BROADCAST_SPLAT]] +; O3DIS-NEXT: [[TMP5:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_1]], [[BROADCAST_SPLAT2]] ; O3DIS-NEXT: [[TMP6:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 4 ; O3DIS-NEXT: [[TMP7:%.*]] = bitcast i32* [[TMP6]] to <4 x i32>* ; O3DIS-NEXT: store <4 x i32> [[TMP5]], <4 x i32>* [[TMP7]], align 4 ; O3DIS-NEXT: [[TMP8:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 8 ; O3DIS-NEXT: [[TMP9:%.*]] = bitcast i32* [[TMP8]] to <4 x i32>* ; O3DIS-NEXT: [[WIDE_LOAD_2:%.*]] = load <4 x i32>, <4 x i32>* [[TMP9]], align 4 -; O3DIS-NEXT: [[TMP10:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_2]], [[BROADCAST_SPLAT]] +; O3DIS-NEXT: [[TMP10:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_2]], [[BROADCAST_SPLAT2]] ; O3DIS-NEXT: [[TMP11:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 8 ; O3DIS-NEXT: [[TMP12:%.*]] = bitcast i32* [[TMP11]] to <4 x i32>* ; O3DIS-NEXT: store <4 x i32> [[TMP10]], <4 x i32>* [[TMP12]], align 4 ; O3DIS-NEXT: [[TMP13:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 12 ; O3DIS-NEXT: [[TMP14:%.*]] = bitcast i32* [[TMP13]] to <4 x i32>* ; O3DIS-NEXT: [[WIDE_LOAD_3:%.*]] = load <4 x i32>, <4 x i32>* [[TMP14]], align 4 -; O3DIS-NEXT: [[TMP15:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_3]], [[BROADCAST_SPLAT]] +; O3DIS-NEXT: [[TMP15:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_3]], [[BROADCAST_SPLAT2]] ; O3DIS-NEXT: [[TMP16:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 12 ; O3DIS-NEXT: [[TMP17:%.*]] = bitcast i32* [[TMP16]] to <4 x i32>* ; O3DIS-NEXT: store <4 x i32> [[TMP15]], <4 x i32>* [[TMP17]], align 4 ; O3DIS-NEXT: [[TMP18:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 16 ; O3DIS-NEXT: [[TMP19:%.*]] = bitcast i32* [[TMP18]] to <4 x i32>* ; O3DIS-NEXT: [[WIDE_LOAD_4:%.*]] = load <4 x i32>, <4 x i32>* [[TMP19]], align 4 -; O3DIS-NEXT: [[TMP20:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_4]], [[BROADCAST_SPLAT]] +; O3DIS-NEXT: [[TMP20:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_4]], [[BROADCAST_SPLAT2]] ; O3DIS-NEXT: [[TMP21:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 16 ; O3DIS-NEXT: [[TMP22:%.*]] = bitcast i32* [[TMP21]] to <4 x i32>* ; O3DIS-NEXT: store <4 x i32> [[TMP20]], <4 x i32>* [[TMP22]], align 4 ; O3DIS-NEXT: [[TMP23:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 20 ; O3DIS-NEXT: [[TMP24:%.*]] = bitcast i32* [[TMP23]] to <4 x i32>* ; O3DIS-NEXT: [[WIDE_LOAD_5:%.*]] = load <4 x i32>, <4 x i32>* [[TMP24]], align 4 -; O3DIS-NEXT: [[TMP25:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_5]], [[BROADCAST_SPLAT]] +; O3DIS-NEXT: [[TMP25:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_5]], [[BROADCAST_SPLAT2]] ; O3DIS-NEXT: [[TMP26:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 20 ; O3DIS-NEXT: [[TMP27:%.*]] = bitcast i32* [[TMP26]] to <4 x i32>* ; O3DIS-NEXT: store <4 x i32> [[TMP25]], <4 x i32>* [[TMP27]], align 4 ; O3DIS-NEXT: [[TMP28:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 24 ; O3DIS-NEXT: [[TMP29:%.*]] = bitcast i32* [[TMP28]] to <4 x i32>* ; O3DIS-NEXT: [[WIDE_LOAD_6:%.*]] = load <4 x i32>, <4 x i32>* [[TMP29]], align 4 -; O3DIS-NEXT: [[TMP30:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_6]], [[BROADCAST_SPLAT]] +; O3DIS-NEXT: [[TMP30:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_6]], [[BROADCAST_SPLAT2]] ; O3DIS-NEXT: [[TMP31:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 24 ; O3DIS-NEXT: [[TMP32:%.*]] = bitcast i32* [[TMP31]] to <4 x i32>* ; O3DIS-NEXT: store <4 x i32> [[TMP30]], <4 x i32>* [[TMP32]], align 4 ; O3DIS-NEXT: [[TMP33:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 28 ; O3DIS-NEXT: [[TMP34:%.*]] = bitcast i32* [[TMP33]] to <4 x i32>* ; O3DIS-NEXT: [[WIDE_LOAD_7:%.*]] = load <4 x i32>, <4 x i32>* [[TMP34]], align 4 -; O3DIS-NEXT: [[TMP35:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_7]], [[BROADCAST_SPLAT]] +; O3DIS-NEXT: [[TMP35:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_7]], [[BROADCAST_SPLAT2]] ; O3DIS-NEXT: [[TMP36:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 28 ; O3DIS-NEXT: [[TMP37:%.*]] = bitcast i32* [[TMP36]] to <4 x i32>* ; O3DIS-NEXT: store <4 x i32> [[TMP35]], <4 x i32>* [[TMP37]], align 4 ; O3DIS-NEXT: [[TMP38:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 32 ; O3DIS-NEXT: [[TMP39:%.*]] = bitcast i32* [[TMP38]] to <4 x i32>* ; O3DIS-NEXT: [[WIDE_LOAD_8:%.*]] = load <4 x i32>, <4 x i32>* [[TMP39]], align 4 -; O3DIS-NEXT: [[TMP40:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_8]], [[BROADCAST_SPLAT]] +; O3DIS-NEXT: [[TMP40:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_8]], [[BROADCAST_SPLAT2]] ; O3DIS-NEXT: [[TMP41:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 32 ; O3DIS-NEXT: [[TMP42:%.*]] = bitcast i32* [[TMP41]] to <4 x i32>* ; O3DIS-NEXT: store <4 x i32> [[TMP40]], <4 x i32>* [[TMP42]], align 4 ; O3DIS-NEXT: [[TMP43:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 36 ; O3DIS-NEXT: [[TMP44:%.*]] = bitcast i32* [[TMP43]] to <4 x i32>* ; O3DIS-NEXT: [[WIDE_LOAD_9:%.*]] = load <4 x i32>, <4 x i32>* [[TMP44]], align 4 -; O3DIS-NEXT: [[TMP45:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_9]], [[BROADCAST_SPLAT]] +; O3DIS-NEXT: [[TMP45:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_9]], [[BROADCAST_SPLAT2]] ; O3DIS-NEXT: [[TMP46:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 36 ; O3DIS-NEXT: [[TMP47:%.*]] = bitcast i32* [[TMP46]] to <4 x i32>* ; O3DIS-NEXT: store <4 x i32> [[TMP45]], <4 x i32>* [[TMP47]], align 4 ; O3DIS-NEXT: [[TMP48:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 40 ; O3DIS-NEXT: [[TMP49:%.*]] = bitcast i32* [[TMP48]] to <4 x i32>* ; O3DIS-NEXT: [[WIDE_LOAD_10:%.*]] = load <4 x i32>, <4 x i32>* [[TMP49]], align 4 -; O3DIS-NEXT: [[TMP50:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_10]], [[BROADCAST_SPLAT]] +; O3DIS-NEXT: [[TMP50:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_10]], [[BROADCAST_SPLAT2]] ; O3DIS-NEXT: [[TMP51:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 40 ; O3DIS-NEXT: [[TMP52:%.*]] = bitcast i32* [[TMP51]] to <4 x i32>* ; O3DIS-NEXT: store <4 x i32> [[TMP50]], <4 x i32>* [[TMP52]], align 4 ; O3DIS-NEXT: [[TMP53:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 44 ; O3DIS-NEXT: [[TMP54:%.*]] = bitcast i32* [[TMP53]] to <4 x i32>* ; O3DIS-NEXT: [[WIDE_LOAD_11:%.*]] = load <4 x i32>, <4 x i32>* [[TMP54]], align 4 -; O3DIS-NEXT: [[TMP55:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_11]], [[BROADCAST_SPLAT]] +; O3DIS-NEXT: [[TMP55:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_11]], [[BROADCAST_SPLAT2]] ; O3DIS-NEXT: [[TMP56:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 44 ; O3DIS-NEXT: [[TMP57:%.*]] = bitcast i32* [[TMP56]] to <4 x i32>* ; O3DIS-NEXT: store <4 x i32> [[TMP55]], <4 x i32>* [[TMP57]], align 4 ; O3DIS-NEXT: [[TMP58:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 48 ; O3DIS-NEXT: [[TMP59:%.*]] = bitcast i32* [[TMP58]] to <4 x i32>* ; O3DIS-NEXT: [[WIDE_LOAD_12:%.*]] = load <4 x i32>, <4 x i32>* [[TMP59]], align 4 -; O3DIS-NEXT: [[TMP60:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_12]], [[BROADCAST_SPLAT]] +; O3DIS-NEXT: [[TMP60:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_12]], [[BROADCAST_SPLAT2]] ; O3DIS-NEXT: [[TMP61:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 48 ; O3DIS-NEXT: [[TMP62:%.*]] = bitcast i32* [[TMP61]] to <4 x i32>* ; O3DIS-NEXT: store <4 x i32> [[TMP60]], <4 x i32>* [[TMP62]], align 4 ; O3DIS-NEXT: [[TMP63:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 52 ; O3DIS-NEXT: [[TMP64:%.*]] = bitcast i32* [[TMP63]] to <4 x i32>* ; O3DIS-NEXT: [[WIDE_LOAD_13:%.*]] = load <4 x i32>, <4 x i32>* [[TMP64]], align 4 -; O3DIS-NEXT: [[TMP65:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_13]], [[BROADCAST_SPLAT]] +; O3DIS-NEXT: [[TMP65:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_13]], [[BROADCAST_SPLAT2]] ; O3DIS-NEXT: [[TMP66:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 52 ; O3DIS-NEXT: [[TMP67:%.*]] = bitcast i32* [[TMP66]] to <4 x i32>* ; O3DIS-NEXT: store <4 x i32> [[TMP65]], <4 x i32>* [[TMP67]], align 4 ; O3DIS-NEXT: [[TMP68:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 56 ; O3DIS-NEXT: [[TMP69:%.*]] = bitcast i32* [[TMP68]] to <4 x i32>* ; O3DIS-NEXT: [[WIDE_LOAD_14:%.*]] = load <4 x i32>, <4 x i32>* [[TMP69]], align 4 -; O3DIS-NEXT: [[TMP70:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_14]], [[BROADCAST_SPLAT]] +; O3DIS-NEXT: [[TMP70:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_14]], [[BROADCAST_SPLAT2]] ; O3DIS-NEXT: [[TMP71:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 56 ; O3DIS-NEXT: [[TMP72:%.*]] = bitcast i32* [[TMP71]] to <4 x i32>* ; O3DIS-NEXT: store <4 x i32> [[TMP70]], <4 x i32>* [[TMP72]], align 4 ; O3DIS-NEXT: [[TMP73:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 60 ; O3DIS-NEXT: [[TMP74:%.*]] = bitcast i32* [[TMP73]] to <4 x i32>* ; O3DIS-NEXT: [[WIDE_LOAD_15:%.*]] = load <4 x i32>, <4 x i32>* [[TMP74]], align 4 -; O3DIS-NEXT: [[TMP75:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_15]], [[BROADCAST_SPLAT]] +; O3DIS-NEXT: [[TMP75:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_15]], [[BROADCAST_SPLAT2]] ; O3DIS-NEXT: [[TMP76:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 60 ; O3DIS-NEXT: [[TMP77:%.*]] = bitcast i32* [[TMP76]] to <4 x i32>* ; O3DIS-NEXT: store <4 x i32> [[TMP75]], <4 x i32>* [[TMP77]], align 4 @@ -1109,115 +1109,115 @@ define i32 @nopragma(i32* noalias nocapture %a, i32* noalias nocapture readonly ; ; O2-LABEL: @nopragma( ; O2-NEXT: entry: -; O2-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i32> undef, i32 [[N:%.*]], i32 0 -; O2-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT]], <4 x i32> undef, <4 x i32> zeroinitializer +; O2-NEXT: [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <4 x i32> undef, i32 [[N:%.*]], i32 0 +; O2-NEXT: [[BROADCAST_SPLAT2:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT1]], <4 x i32> undef, <4 x i32> zeroinitializer ; O2-NEXT: [[TMP0:%.*]] = bitcast i32* [[B:%.*]] to <4 x i32>* ; O2-NEXT: [[WIDE_LOAD:%.*]] = load <4 x i32>, <4 x i32>* [[TMP0]], align 4 -; O2-NEXT: [[TMP1:%.*]] = add nsw <4 x i32> [[WIDE_LOAD]], [[BROADCAST_SPLAT]] +; O2-NEXT: [[TMP1:%.*]] = add nsw <4 x i32> [[WIDE_LOAD]], [[BROADCAST_SPLAT2]] ; O2-NEXT: [[TMP2:%.*]] = bitcast i32* [[A:%.*]] to <4 x i32>* ; O2-NEXT: store <4 x i32> [[TMP1]], <4 x i32>* [[TMP2]], align 4 ; O2-NEXT: [[TMP3:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 4 ; O2-NEXT: [[TMP4:%.*]] = bitcast i32* [[TMP3]] to <4 x i32>* ; O2-NEXT: [[WIDE_LOAD_1:%.*]] = load <4 x i32>, <4 x i32>* [[TMP4]], align 4 -; O2-NEXT: [[TMP5:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_1]], [[BROADCAST_SPLAT]] +; O2-NEXT: [[TMP5:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_1]], [[BROADCAST_SPLAT2]] ; O2-NEXT: [[TMP6:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 4 ; O2-NEXT: [[TMP7:%.*]] = bitcast i32* [[TMP6]] to <4 x i32>* ; O2-NEXT: store <4 x i32> [[TMP5]], <4 x i32>* [[TMP7]], align 4 ; O2-NEXT: [[TMP8:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 8 ; O2-NEXT: [[TMP9:%.*]] = bitcast i32* [[TMP8]] to <4 x i32>* ; O2-NEXT: [[WIDE_LOAD_2:%.*]] = load <4 x i32>, <4 x i32>* [[TMP9]], align 4 -; O2-NEXT: [[TMP10:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_2]], [[BROADCAST_SPLAT]] +; O2-NEXT: [[TMP10:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_2]], [[BROADCAST_SPLAT2]] ; O2-NEXT: [[TMP11:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 8 ; O2-NEXT: [[TMP12:%.*]] = bitcast i32* [[TMP11]] to <4 x i32>* ; O2-NEXT: store <4 x i32> [[TMP10]], <4 x i32>* [[TMP12]], align 4 ; O2-NEXT: [[TMP13:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 12 ; O2-NEXT: [[TMP14:%.*]] = bitcast i32* [[TMP13]] to <4 x i32>* ; O2-NEXT: [[WIDE_LOAD_3:%.*]] = load <4 x i32>, <4 x i32>* [[TMP14]], align 4 -; O2-NEXT: [[TMP15:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_3]], [[BROADCAST_SPLAT]] +; O2-NEXT: [[TMP15:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_3]], [[BROADCAST_SPLAT2]] ; O2-NEXT: [[TMP16:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 12 ; O2-NEXT: [[TMP17:%.*]] = bitcast i32* [[TMP16]] to <4 x i32>* ; O2-NEXT: store <4 x i32> [[TMP15]], <4 x i32>* [[TMP17]], align 4 ; O2-NEXT: [[TMP18:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 16 ; O2-NEXT: [[TMP19:%.*]] = bitcast i32* [[TMP18]] to <4 x i32>* ; O2-NEXT: [[WIDE_LOAD_4:%.*]] = load <4 x i32>, <4 x i32>* [[TMP19]], align 4 -; O2-NEXT: [[TMP20:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_4]], [[BROADCAST_SPLAT]] +; O2-NEXT: [[TMP20:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_4]], [[BROADCAST_SPLAT2]] ; O2-NEXT: [[TMP21:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 16 ; O2-NEXT: [[TMP22:%.*]] = bitcast i32* [[TMP21]] to <4 x i32>* ; O2-NEXT: store <4 x i32> [[TMP20]], <4 x i32>* [[TMP22]], align 4 ; O2-NEXT: [[TMP23:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 20 ; O2-NEXT: [[TMP24:%.*]] = bitcast i32* [[TMP23]] to <4 x i32>* ; O2-NEXT: [[WIDE_LOAD_5:%.*]] = load <4 x i32>, <4 x i32>* [[TMP24]], align 4 -; O2-NEXT: [[TMP25:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_5]], [[BROADCAST_SPLAT]] +; O2-NEXT: [[TMP25:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_5]], [[BROADCAST_SPLAT2]] ; O2-NEXT: [[TMP26:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 20 ; O2-NEXT: [[TMP27:%.*]] = bitcast i32* [[TMP26]] to <4 x i32>* ; O2-NEXT: store <4 x i32> [[TMP25]], <4 x i32>* [[TMP27]], align 4 ; O2-NEXT: [[TMP28:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 24 ; O2-NEXT: [[TMP29:%.*]] = bitcast i32* [[TMP28]] to <4 x i32>* ; O2-NEXT: [[WIDE_LOAD_6:%.*]] = load <4 x i32>, <4 x i32>* [[TMP29]], align 4 -; O2-NEXT: [[TMP30:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_6]], [[BROADCAST_SPLAT]] +; O2-NEXT: [[TMP30:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_6]], [[BROADCAST_SPLAT2]] ; O2-NEXT: [[TMP31:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 24 ; O2-NEXT: [[TMP32:%.*]] = bitcast i32* [[TMP31]] to <4 x i32>* ; O2-NEXT: store <4 x i32> [[TMP30]], <4 x i32>* [[TMP32]], align 4 ; O2-NEXT: [[TMP33:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 28 ; O2-NEXT: [[TMP34:%.*]] = bitcast i32* [[TMP33]] to <4 x i32>* ; O2-NEXT: [[WIDE_LOAD_7:%.*]] = load <4 x i32>, <4 x i32>* [[TMP34]], align 4 -; O2-NEXT: [[TMP35:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_7]], [[BROADCAST_SPLAT]] +; O2-NEXT: [[TMP35:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_7]], [[BROADCAST_SPLAT2]] ; O2-NEXT: [[TMP36:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 28 ; O2-NEXT: [[TMP37:%.*]] = bitcast i32* [[TMP36]] to <4 x i32>* ; O2-NEXT: store <4 x i32> [[TMP35]], <4 x i32>* [[TMP37]], align 4 ; O2-NEXT: [[TMP38:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 32 ; O2-NEXT: [[TMP39:%.*]] = bitcast i32* [[TMP38]] to <4 x i32>* ; O2-NEXT: [[WIDE_LOAD_8:%.*]] = load <4 x i32>, <4 x i32>* [[TMP39]], align 4 -; O2-NEXT: [[TMP40:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_8]], [[BROADCAST_SPLAT]] +; O2-NEXT: [[TMP40:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_8]], [[BROADCAST_SPLAT2]] ; O2-NEXT: [[TMP41:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 32 ; O2-NEXT: [[TMP42:%.*]] = bitcast i32* [[TMP41]] to <4 x i32>* ; O2-NEXT: store <4 x i32> [[TMP40]], <4 x i32>* [[TMP42]], align 4 ; O2-NEXT: [[TMP43:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 36 ; O2-NEXT: [[TMP44:%.*]] = bitcast i32* [[TMP43]] to <4 x i32>* ; O2-NEXT: [[WIDE_LOAD_9:%.*]] = load <4 x i32>, <4 x i32>* [[TMP44]], align 4 -; O2-NEXT: [[TMP45:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_9]], [[BROADCAST_SPLAT]] +; O2-NEXT: [[TMP45:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_9]], [[BROADCAST_SPLAT2]] ; O2-NEXT: [[TMP46:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 36 ; O2-NEXT: [[TMP47:%.*]] = bitcast i32* [[TMP46]] to <4 x i32>* ; O2-NEXT: store <4 x i32> [[TMP45]], <4 x i32>* [[TMP47]], align 4 ; O2-NEXT: [[TMP48:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 40 ; O2-NEXT: [[TMP49:%.*]] = bitcast i32* [[TMP48]] to <4 x i32>* ; O2-NEXT: [[WIDE_LOAD_10:%.*]] = load <4 x i32>, <4 x i32>* [[TMP49]], align 4 -; O2-NEXT: [[TMP50:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_10]], [[BROADCAST_SPLAT]] +; O2-NEXT: [[TMP50:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_10]], [[BROADCAST_SPLAT2]] ; O2-NEXT: [[TMP51:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 40 ; O2-NEXT: [[TMP52:%.*]] = bitcast i32* [[TMP51]] to <4 x i32>* ; O2-NEXT: store <4 x i32> [[TMP50]], <4 x i32>* [[TMP52]], align 4 ; O2-NEXT: [[TMP53:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 44 ; O2-NEXT: [[TMP54:%.*]] = bitcast i32* [[TMP53]] to <4 x i32>* ; O2-NEXT: [[WIDE_LOAD_11:%.*]] = load <4 x i32>, <4 x i32>* [[TMP54]], align 4 -; O2-NEXT: [[TMP55:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_11]], [[BROADCAST_SPLAT]] +; O2-NEXT: [[TMP55:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_11]], [[BROADCAST_SPLAT2]] ; O2-NEXT: [[TMP56:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 44 ; O2-NEXT: [[TMP57:%.*]] = bitcast i32* [[TMP56]] to <4 x i32>* ; O2-NEXT: store <4 x i32> [[TMP55]], <4 x i32>* [[TMP57]], align 4 ; O2-NEXT: [[TMP58:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 48 ; O2-NEXT: [[TMP59:%.*]] = bitcast i32* [[TMP58]] to <4 x i32>* ; O2-NEXT: [[WIDE_LOAD_12:%.*]] = load <4 x i32>, <4 x i32>* [[TMP59]], align 4 -; O2-NEXT: [[TMP60:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_12]], [[BROADCAST_SPLAT]] +; O2-NEXT: [[TMP60:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_12]], [[BROADCAST_SPLAT2]] ; O2-NEXT: [[TMP61:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 48 ; O2-NEXT: [[TMP62:%.*]] = bitcast i32* [[TMP61]] to <4 x i32>* ; O2-NEXT: store <4 x i32> [[TMP60]], <4 x i32>* [[TMP62]], align 4 ; O2-NEXT: [[TMP63:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 52 ; O2-NEXT: [[TMP64:%.*]] = bitcast i32* [[TMP63]] to <4 x i32>* ; O2-NEXT: [[WIDE_LOAD_13:%.*]] = load <4 x i32>, <4 x i32>* [[TMP64]], align 4 -; O2-NEXT: [[TMP65:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_13]], [[BROADCAST_SPLAT]] +; O2-NEXT: [[TMP65:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_13]], [[BROADCAST_SPLAT2]] ; O2-NEXT: [[TMP66:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 52 ; O2-NEXT: [[TMP67:%.*]] = bitcast i32* [[TMP66]] to <4 x i32>* ; O2-NEXT: store <4 x i32> [[TMP65]], <4 x i32>* [[TMP67]], align 4 ; O2-NEXT: [[TMP68:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 56 ; O2-NEXT: [[TMP69:%.*]] = bitcast i32* [[TMP68]] to <4 x i32>* ; O2-NEXT: [[WIDE_LOAD_14:%.*]] = load <4 x i32>, <4 x i32>* [[TMP69]], align 4 -; O2-NEXT: [[TMP70:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_14]], [[BROADCAST_SPLAT]] +; O2-NEXT: [[TMP70:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_14]], [[BROADCAST_SPLAT2]] ; O2-NEXT: [[TMP71:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 56 ; O2-NEXT: [[TMP72:%.*]] = bitcast i32* [[TMP71]] to <4 x i32>* ; O2-NEXT: store <4 x i32> [[TMP70]], <4 x i32>* [[TMP72]], align 4 ; O2-NEXT: [[TMP73:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 60 ; O2-NEXT: [[TMP74:%.*]] = bitcast i32* [[TMP73]] to <4 x i32>* ; O2-NEXT: [[WIDE_LOAD_15:%.*]] = load <4 x i32>, <4 x i32>* [[TMP74]], align 4 -; O2-NEXT: [[TMP75:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_15]], [[BROADCAST_SPLAT]] +; O2-NEXT: [[TMP75:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_15]], [[BROADCAST_SPLAT2]] ; O2-NEXT: [[TMP76:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 60 ; O2-NEXT: [[TMP77:%.*]] = bitcast i32* [[TMP76]] to <4 x i32>* ; O2-NEXT: store <4 x i32> [[TMP75]], <4 x i32>* [[TMP77]], align 4 @@ -1226,115 +1226,115 @@ define i32 @nopragma(i32* noalias nocapture %a, i32* noalias nocapture readonly ; ; O3-LABEL: @nopragma( ; O3-NEXT: entry: -; O3-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i32> undef, i32 [[N:%.*]], i32 0 -; O3-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT]], <4 x i32> undef, <4 x i32> zeroinitializer +; O3-NEXT: [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <4 x i32> undef, i32 [[N:%.*]], i32 0 +; O3-NEXT: [[BROADCAST_SPLAT2:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT1]], <4 x i32> undef, <4 x i32> zeroinitializer ; O3-NEXT: [[TMP0:%.*]] = bitcast i32* [[B:%.*]] to <4 x i32>* ; O3-NEXT: [[WIDE_LOAD:%.*]] = load <4 x i32>, <4 x i32>* [[TMP0]], align 4 -; O3-NEXT: [[TMP1:%.*]] = add nsw <4 x i32> [[WIDE_LOAD]], [[BROADCAST_SPLAT]] +; O3-NEXT: [[TMP1:%.*]] = add nsw <4 x i32> [[WIDE_LOAD]], [[BROADCAST_SPLAT2]] ; O3-NEXT: [[TMP2:%.*]] = bitcast i32* [[A:%.*]] to <4 x i32>* ; O3-NEXT: store <4 x i32> [[TMP1]], <4 x i32>* [[TMP2]], align 4 ; O3-NEXT: [[TMP3:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 4 ; O3-NEXT: [[TMP4:%.*]] = bitcast i32* [[TMP3]] to <4 x i32>* ; O3-NEXT: [[WIDE_LOAD_1:%.*]] = load <4 x i32>, <4 x i32>* [[TMP4]], align 4 -; O3-NEXT: [[TMP5:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_1]], [[BROADCAST_SPLAT]] +; O3-NEXT: [[TMP5:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_1]], [[BROADCAST_SPLAT2]] ; O3-NEXT: [[TMP6:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 4 ; O3-NEXT: [[TMP7:%.*]] = bitcast i32* [[TMP6]] to <4 x i32>* ; O3-NEXT: store <4 x i32> [[TMP5]], <4 x i32>* [[TMP7]], align 4 ; O3-NEXT: [[TMP8:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 8 ; O3-NEXT: [[TMP9:%.*]] = bitcast i32* [[TMP8]] to <4 x i32>* ; O3-NEXT: [[WIDE_LOAD_2:%.*]] = load <4 x i32>, <4 x i32>* [[TMP9]], align 4 -; O3-NEXT: [[TMP10:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_2]], [[BROADCAST_SPLAT]] +; O3-NEXT: [[TMP10:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_2]], [[BROADCAST_SPLAT2]] ; O3-NEXT: [[TMP11:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 8 ; O3-NEXT: [[TMP12:%.*]] = bitcast i32* [[TMP11]] to <4 x i32>* ; O3-NEXT: store <4 x i32> [[TMP10]], <4 x i32>* [[TMP12]], align 4 ; O3-NEXT: [[TMP13:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 12 ; O3-NEXT: [[TMP14:%.*]] = bitcast i32* [[TMP13]] to <4 x i32>* ; O3-NEXT: [[WIDE_LOAD_3:%.*]] = load <4 x i32>, <4 x i32>* [[TMP14]], align 4 -; O3-NEXT: [[TMP15:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_3]], [[BROADCAST_SPLAT]] +; O3-NEXT: [[TMP15:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_3]], [[BROADCAST_SPLAT2]] ; O3-NEXT: [[TMP16:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 12 ; O3-NEXT: [[TMP17:%.*]] = bitcast i32* [[TMP16]] to <4 x i32>* ; O3-NEXT: store <4 x i32> [[TMP15]], <4 x i32>* [[TMP17]], align 4 ; O3-NEXT: [[TMP18:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 16 ; O3-NEXT: [[TMP19:%.*]] = bitcast i32* [[TMP18]] to <4 x i32>* ; O3-NEXT: [[WIDE_LOAD_4:%.*]] = load <4 x i32>, <4 x i32>* [[TMP19]], align 4 -; O3-NEXT: [[TMP20:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_4]], [[BROADCAST_SPLAT]] +; O3-NEXT: [[TMP20:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_4]], [[BROADCAST_SPLAT2]] ; O3-NEXT: [[TMP21:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 16 ; O3-NEXT: [[TMP22:%.*]] = bitcast i32* [[TMP21]] to <4 x i32>* ; O3-NEXT: store <4 x i32> [[TMP20]], <4 x i32>* [[TMP22]], align 4 ; O3-NEXT: [[TMP23:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 20 ; O3-NEXT: [[TMP24:%.*]] = bitcast i32* [[TMP23]] to <4 x i32>* ; O3-NEXT: [[WIDE_LOAD_5:%.*]] = load <4 x i32>, <4 x i32>* [[TMP24]], align 4 -; O3-NEXT: [[TMP25:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_5]], [[BROADCAST_SPLAT]] +; O3-NEXT: [[TMP25:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_5]], [[BROADCAST_SPLAT2]] ; O3-NEXT: [[TMP26:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 20 ; O3-NEXT: [[TMP27:%.*]] = bitcast i32* [[TMP26]] to <4 x i32>* ; O3-NEXT: store <4 x i32> [[TMP25]], <4 x i32>* [[TMP27]], align 4 ; O3-NEXT: [[TMP28:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 24 ; O3-NEXT: [[TMP29:%.*]] = bitcast i32* [[TMP28]] to <4 x i32>* ; O3-NEXT: [[WIDE_LOAD_6:%.*]] = load <4 x i32>, <4 x i32>* [[TMP29]], align 4 -; O3-NEXT: [[TMP30:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_6]], [[BROADCAST_SPLAT]] +; O3-NEXT: [[TMP30:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_6]], [[BROADCAST_SPLAT2]] ; O3-NEXT: [[TMP31:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 24 ; O3-NEXT: [[TMP32:%.*]] = bitcast i32* [[TMP31]] to <4 x i32>* ; O3-NEXT: store <4 x i32> [[TMP30]], <4 x i32>* [[TMP32]], align 4 ; O3-NEXT: [[TMP33:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 28 ; O3-NEXT: [[TMP34:%.*]] = bitcast i32* [[TMP33]] to <4 x i32>* ; O3-NEXT: [[WIDE_LOAD_7:%.*]] = load <4 x i32>, <4 x i32>* [[TMP34]], align 4 -; O3-NEXT: [[TMP35:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_7]], [[BROADCAST_SPLAT]] +; O3-NEXT: [[TMP35:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_7]], [[BROADCAST_SPLAT2]] ; O3-NEXT: [[TMP36:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 28 ; O3-NEXT: [[TMP37:%.*]] = bitcast i32* [[TMP36]] to <4 x i32>* ; O3-NEXT: store <4 x i32> [[TMP35]], <4 x i32>* [[TMP37]], align 4 ; O3-NEXT: [[TMP38:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 32 ; O3-NEXT: [[TMP39:%.*]] = bitcast i32* [[TMP38]] to <4 x i32>* ; O3-NEXT: [[WIDE_LOAD_8:%.*]] = load <4 x i32>, <4 x i32>* [[TMP39]], align 4 -; O3-NEXT: [[TMP40:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_8]], [[BROADCAST_SPLAT]] +; O3-NEXT: [[TMP40:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_8]], [[BROADCAST_SPLAT2]] ; O3-NEXT: [[TMP41:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 32 ; O3-NEXT: [[TMP42:%.*]] = bitcast i32* [[TMP41]] to <4 x i32>* ; O3-NEXT: store <4 x i32> [[TMP40]], <4 x i32>* [[TMP42]], align 4 ; O3-NEXT: [[TMP43:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 36 ; O3-NEXT: [[TMP44:%.*]] = bitcast i32* [[TMP43]] to <4 x i32>* ; O3-NEXT: [[WIDE_LOAD_9:%.*]] = load <4 x i32>, <4 x i32>* [[TMP44]], align 4 -; O3-NEXT: [[TMP45:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_9]], [[BROADCAST_SPLAT]] +; O3-NEXT: [[TMP45:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_9]], [[BROADCAST_SPLAT2]] ; O3-NEXT: [[TMP46:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 36 ; O3-NEXT: [[TMP47:%.*]] = bitcast i32* [[TMP46]] to <4 x i32>* ; O3-NEXT: store <4 x i32> [[TMP45]], <4 x i32>* [[TMP47]], align 4 ; O3-NEXT: [[TMP48:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 40 ; O3-NEXT: [[TMP49:%.*]] = bitcast i32* [[TMP48]] to <4 x i32>* ; O3-NEXT: [[WIDE_LOAD_10:%.*]] = load <4 x i32>, <4 x i32>* [[TMP49]], align 4 -; O3-NEXT: [[TMP50:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_10]], [[BROADCAST_SPLAT]] +; O3-NEXT: [[TMP50:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_10]], [[BROADCAST_SPLAT2]] ; O3-NEXT: [[TMP51:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 40 ; O3-NEXT: [[TMP52:%.*]] = bitcast i32* [[TMP51]] to <4 x i32>* ; O3-NEXT: store <4 x i32> [[TMP50]], <4 x i32>* [[TMP52]], align 4 ; O3-NEXT: [[TMP53:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 44 ; O3-NEXT: [[TMP54:%.*]] = bitcast i32* [[TMP53]] to <4 x i32>* ; O3-NEXT: [[WIDE_LOAD_11:%.*]] = load <4 x i32>, <4 x i32>* [[TMP54]], align 4 -; O3-NEXT: [[TMP55:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_11]], [[BROADCAST_SPLAT]] +; O3-NEXT: [[TMP55:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_11]], [[BROADCAST_SPLAT2]] ; O3-NEXT: [[TMP56:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 44 ; O3-NEXT: [[TMP57:%.*]] = bitcast i32* [[TMP56]] to <4 x i32>* ; O3-NEXT: store <4 x i32> [[TMP55]], <4 x i32>* [[TMP57]], align 4 ; O3-NEXT: [[TMP58:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 48 ; O3-NEXT: [[TMP59:%.*]] = bitcast i32* [[TMP58]] to <4 x i32>* ; O3-NEXT: [[WIDE_LOAD_12:%.*]] = load <4 x i32>, <4 x i32>* [[TMP59]], align 4 -; O3-NEXT: [[TMP60:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_12]], [[BROADCAST_SPLAT]] +; O3-NEXT: [[TMP60:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_12]], [[BROADCAST_SPLAT2]] ; O3-NEXT: [[TMP61:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 48 ; O3-NEXT: [[TMP62:%.*]] = bitcast i32* [[TMP61]] to <4 x i32>* ; O3-NEXT: store <4 x i32> [[TMP60]], <4 x i32>* [[TMP62]], align 4 ; O3-NEXT: [[TMP63:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 52 ; O3-NEXT: [[TMP64:%.*]] = bitcast i32* [[TMP63]] to <4 x i32>* ; O3-NEXT: [[WIDE_LOAD_13:%.*]] = load <4 x i32>, <4 x i32>* [[TMP64]], align 4 -; O3-NEXT: [[TMP65:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_13]], [[BROADCAST_SPLAT]] +; O3-NEXT: [[TMP65:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_13]], [[BROADCAST_SPLAT2]] ; O3-NEXT: [[TMP66:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 52 ; O3-NEXT: [[TMP67:%.*]] = bitcast i32* [[TMP66]] to <4 x i32>* ; O3-NEXT: store <4 x i32> [[TMP65]], <4 x i32>* [[TMP67]], align 4 ; O3-NEXT: [[TMP68:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 56 ; O3-NEXT: [[TMP69:%.*]] = bitcast i32* [[TMP68]] to <4 x i32>* ; O3-NEXT: [[WIDE_LOAD_14:%.*]] = load <4 x i32>, <4 x i32>* [[TMP69]], align 4 -; O3-NEXT: [[TMP70:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_14]], [[BROADCAST_SPLAT]] +; O3-NEXT: [[TMP70:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_14]], [[BROADCAST_SPLAT2]] ; O3-NEXT: [[TMP71:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 56 ; O3-NEXT: [[TMP72:%.*]] = bitcast i32* [[TMP71]] to <4 x i32>* ; O3-NEXT: store <4 x i32> [[TMP70]], <4 x i32>* [[TMP72]], align 4 ; O3-NEXT: [[TMP73:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 60 ; O3-NEXT: [[TMP74:%.*]] = bitcast i32* [[TMP73]] to <4 x i32>* ; O3-NEXT: [[WIDE_LOAD_15:%.*]] = load <4 x i32>, <4 x i32>* [[TMP74]], align 4 -; O3-NEXT: [[TMP75:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_15]], [[BROADCAST_SPLAT]] +; O3-NEXT: [[TMP75:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_15]], [[BROADCAST_SPLAT2]] ; O3-NEXT: [[TMP76:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 60 ; O3-NEXT: [[TMP77:%.*]] = bitcast i32* [[TMP76]] to <4 x i32>* ; O3-NEXT: store <4 x i32> [[TMP75]], <4 x i32>* [[TMP77]], align 4 @@ -1343,115 +1343,115 @@ define i32 @nopragma(i32* noalias nocapture %a, i32* noalias nocapture readonly ; ; O3DEFAULT-LABEL: @nopragma( ; O3DEFAULT-NEXT: entry: -; O3DEFAULT-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i32> undef, i32 [[N:%.*]], i32 0 -; O3DEFAULT-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT]], <4 x i32> undef, <4 x i32> zeroinitializer +; O3DEFAULT-NEXT: [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <4 x i32> undef, i32 [[N:%.*]], i32 0 +; O3DEFAULT-NEXT: [[BROADCAST_SPLAT2:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT1]], <4 x i32> undef, <4 x i32> zeroinitializer ; O3DEFAULT-NEXT: [[TMP0:%.*]] = bitcast i32* [[B:%.*]] to <4 x i32>* ; O3DEFAULT-NEXT: [[WIDE_LOAD:%.*]] = load <4 x i32>, <4 x i32>* [[TMP0]], align 4 -; O3DEFAULT-NEXT: [[TMP1:%.*]] = add nsw <4 x i32> [[WIDE_LOAD]], [[BROADCAST_SPLAT]] +; O3DEFAULT-NEXT: [[TMP1:%.*]] = add nsw <4 x i32> [[WIDE_LOAD]], [[BROADCAST_SPLAT2]] ; O3DEFAULT-NEXT: [[TMP2:%.*]] = bitcast i32* [[A:%.*]] to <4 x i32>* ; O3DEFAULT-NEXT: store <4 x i32> [[TMP1]], <4 x i32>* [[TMP2]], align 4 ; O3DEFAULT-NEXT: [[TMP3:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 4 ; O3DEFAULT-NEXT: [[TMP4:%.*]] = bitcast i32* [[TMP3]] to <4 x i32>* ; O3DEFAULT-NEXT: [[WIDE_LOAD_1:%.*]] = load <4 x i32>, <4 x i32>* [[TMP4]], align 4 -; O3DEFAULT-NEXT: [[TMP5:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_1]], [[BROADCAST_SPLAT]] +; O3DEFAULT-NEXT: [[TMP5:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_1]], [[BROADCAST_SPLAT2]] ; O3DEFAULT-NEXT: [[TMP6:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 4 ; O3DEFAULT-NEXT: [[TMP7:%.*]] = bitcast i32* [[TMP6]] to <4 x i32>* ; O3DEFAULT-NEXT: store <4 x i32> [[TMP5]], <4 x i32>* [[TMP7]], align 4 ; O3DEFAULT-NEXT: [[TMP8:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 8 ; O3DEFAULT-NEXT: [[TMP9:%.*]] = bitcast i32* [[TMP8]] to <4 x i32>* ; O3DEFAULT-NEXT: [[WIDE_LOAD_2:%.*]] = load <4 x i32>, <4 x i32>* [[TMP9]], align 4 -; O3DEFAULT-NEXT: [[TMP10:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_2]], [[BROADCAST_SPLAT]] +; O3DEFAULT-NEXT: [[TMP10:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_2]], [[BROADCAST_SPLAT2]] ; O3DEFAULT-NEXT: [[TMP11:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 8 ; O3DEFAULT-NEXT: [[TMP12:%.*]] = bitcast i32* [[TMP11]] to <4 x i32>* ; O3DEFAULT-NEXT: store <4 x i32> [[TMP10]], <4 x i32>* [[TMP12]], align 4 ; O3DEFAULT-NEXT: [[TMP13:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 12 ; O3DEFAULT-NEXT: [[TMP14:%.*]] = bitcast i32* [[TMP13]] to <4 x i32>* ; O3DEFAULT-NEXT: [[WIDE_LOAD_3:%.*]] = load <4 x i32>, <4 x i32>* [[TMP14]], align 4 -; O3DEFAULT-NEXT: [[TMP15:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_3]], [[BROADCAST_SPLAT]] +; O3DEFAULT-NEXT: [[TMP15:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_3]], [[BROADCAST_SPLAT2]] ; O3DEFAULT-NEXT: [[TMP16:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 12 ; O3DEFAULT-NEXT: [[TMP17:%.*]] = bitcast i32* [[TMP16]] to <4 x i32>* ; O3DEFAULT-NEXT: store <4 x i32> [[TMP15]], <4 x i32>* [[TMP17]], align 4 ; O3DEFAULT-NEXT: [[TMP18:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 16 ; O3DEFAULT-NEXT: [[TMP19:%.*]] = bitcast i32* [[TMP18]] to <4 x i32>* ; O3DEFAULT-NEXT: [[WIDE_LOAD_4:%.*]] = load <4 x i32>, <4 x i32>* [[TMP19]], align 4 -; O3DEFAULT-NEXT: [[TMP20:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_4]], [[BROADCAST_SPLAT]] +; O3DEFAULT-NEXT: [[TMP20:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_4]], [[BROADCAST_SPLAT2]] ; O3DEFAULT-NEXT: [[TMP21:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 16 ; O3DEFAULT-NEXT: [[TMP22:%.*]] = bitcast i32* [[TMP21]] to <4 x i32>* ; O3DEFAULT-NEXT: store <4 x i32> [[TMP20]], <4 x i32>* [[TMP22]], align 4 ; O3DEFAULT-NEXT: [[TMP23:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 20 ; O3DEFAULT-NEXT: [[TMP24:%.*]] = bitcast i32* [[TMP23]] to <4 x i32>* ; O3DEFAULT-NEXT: [[WIDE_LOAD_5:%.*]] = load <4 x i32>, <4 x i32>* [[TMP24]], align 4 -; O3DEFAULT-NEXT: [[TMP25:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_5]], [[BROADCAST_SPLAT]] +; O3DEFAULT-NEXT: [[TMP25:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_5]], [[BROADCAST_SPLAT2]] ; O3DEFAULT-NEXT: [[TMP26:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 20 ; O3DEFAULT-NEXT: [[TMP27:%.*]] = bitcast i32* [[TMP26]] to <4 x i32>* ; O3DEFAULT-NEXT: store <4 x i32> [[TMP25]], <4 x i32>* [[TMP27]], align 4 ; O3DEFAULT-NEXT: [[TMP28:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 24 ; O3DEFAULT-NEXT: [[TMP29:%.*]] = bitcast i32* [[TMP28]] to <4 x i32>* ; O3DEFAULT-NEXT: [[WIDE_LOAD_6:%.*]] = load <4 x i32>, <4 x i32>* [[TMP29]], align 4 -; O3DEFAULT-NEXT: [[TMP30:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_6]], [[BROADCAST_SPLAT]] +; O3DEFAULT-NEXT: [[TMP30:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_6]], [[BROADCAST_SPLAT2]] ; O3DEFAULT-NEXT: [[TMP31:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 24 ; O3DEFAULT-NEXT: [[TMP32:%.*]] = bitcast i32* [[TMP31]] to <4 x i32>* ; O3DEFAULT-NEXT: store <4 x i32> [[TMP30]], <4 x i32>* [[TMP32]], align 4 ; O3DEFAULT-NEXT: [[TMP33:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 28 ; O3DEFAULT-NEXT: [[TMP34:%.*]] = bitcast i32* [[TMP33]] to <4 x i32>* ; O3DEFAULT-NEXT: [[WIDE_LOAD_7:%.*]] = load <4 x i32>, <4 x i32>* [[TMP34]], align 4 -; O3DEFAULT-NEXT: [[TMP35:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_7]], [[BROADCAST_SPLAT]] +; O3DEFAULT-NEXT: [[TMP35:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_7]], [[BROADCAST_SPLAT2]] ; O3DEFAULT-NEXT: [[TMP36:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 28 ; O3DEFAULT-NEXT: [[TMP37:%.*]] = bitcast i32* [[TMP36]] to <4 x i32>* ; O3DEFAULT-NEXT: store <4 x i32> [[TMP35]], <4 x i32>* [[TMP37]], align 4 ; O3DEFAULT-NEXT: [[TMP38:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 32 ; O3DEFAULT-NEXT: [[TMP39:%.*]] = bitcast i32* [[TMP38]] to <4 x i32>* ; O3DEFAULT-NEXT: [[WIDE_LOAD_8:%.*]] = load <4 x i32>, <4 x i32>* [[TMP39]], align 4 -; O3DEFAULT-NEXT: [[TMP40:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_8]], [[BROADCAST_SPLAT]] +; O3DEFAULT-NEXT: [[TMP40:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_8]], [[BROADCAST_SPLAT2]] ; O3DEFAULT-NEXT: [[TMP41:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 32 ; O3DEFAULT-NEXT: [[TMP42:%.*]] = bitcast i32* [[TMP41]] to <4 x i32>* ; O3DEFAULT-NEXT: store <4 x i32> [[TMP40]], <4 x i32>* [[TMP42]], align 4 ; O3DEFAULT-NEXT: [[TMP43:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 36 ; O3DEFAULT-NEXT: [[TMP44:%.*]] = bitcast i32* [[TMP43]] to <4 x i32>* ; O3DEFAULT-NEXT: [[WIDE_LOAD_9:%.*]] = load <4 x i32>, <4 x i32>* [[TMP44]], align 4 -; O3DEFAULT-NEXT: [[TMP45:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_9]], [[BROADCAST_SPLAT]] +; O3DEFAULT-NEXT: [[TMP45:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_9]], [[BROADCAST_SPLAT2]] ; O3DEFAULT-NEXT: [[TMP46:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 36 ; O3DEFAULT-NEXT: [[TMP47:%.*]] = bitcast i32* [[TMP46]] to <4 x i32>* ; O3DEFAULT-NEXT: store <4 x i32> [[TMP45]], <4 x i32>* [[TMP47]], align 4 ; O3DEFAULT-NEXT: [[TMP48:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 40 ; O3DEFAULT-NEXT: [[TMP49:%.*]] = bitcast i32* [[TMP48]] to <4 x i32>* ; O3DEFAULT-NEXT: [[WIDE_LOAD_10:%.*]] = load <4 x i32>, <4 x i32>* [[TMP49]], align 4 -; O3DEFAULT-NEXT: [[TMP50:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_10]], [[BROADCAST_SPLAT]] +; O3DEFAULT-NEXT: [[TMP50:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_10]], [[BROADCAST_SPLAT2]] ; O3DEFAULT-NEXT: [[TMP51:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 40 ; O3DEFAULT-NEXT: [[TMP52:%.*]] = bitcast i32* [[TMP51]] to <4 x i32>* ; O3DEFAULT-NEXT: store <4 x i32> [[TMP50]], <4 x i32>* [[TMP52]], align 4 ; O3DEFAULT-NEXT: [[TMP53:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 44 ; O3DEFAULT-NEXT: [[TMP54:%.*]] = bitcast i32* [[TMP53]] to <4 x i32>* ; O3DEFAULT-NEXT: [[WIDE_LOAD_11:%.*]] = load <4 x i32>, <4 x i32>* [[TMP54]], align 4 -; O3DEFAULT-NEXT: [[TMP55:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_11]], [[BROADCAST_SPLAT]] +; O3DEFAULT-NEXT: [[TMP55:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_11]], [[BROADCAST_SPLAT2]] ; O3DEFAULT-NEXT: [[TMP56:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 44 ; O3DEFAULT-NEXT: [[TMP57:%.*]] = bitcast i32* [[TMP56]] to <4 x i32>* ; O3DEFAULT-NEXT: store <4 x i32> [[TMP55]], <4 x i32>* [[TMP57]], align 4 ; O3DEFAULT-NEXT: [[TMP58:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 48 ; O3DEFAULT-NEXT: [[TMP59:%.*]] = bitcast i32* [[TMP58]] to <4 x i32>* ; O3DEFAULT-NEXT: [[WIDE_LOAD_12:%.*]] = load <4 x i32>, <4 x i32>* [[TMP59]], align 4 -; O3DEFAULT-NEXT: [[TMP60:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_12]], [[BROADCAST_SPLAT]] +; O3DEFAULT-NEXT: [[TMP60:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_12]], [[BROADCAST_SPLAT2]] ; O3DEFAULT-NEXT: [[TMP61:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 48 ; O3DEFAULT-NEXT: [[TMP62:%.*]] = bitcast i32* [[TMP61]] to <4 x i32>* ; O3DEFAULT-NEXT: store <4 x i32> [[TMP60]], <4 x i32>* [[TMP62]], align 4 ; O3DEFAULT-NEXT: [[TMP63:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 52 ; O3DEFAULT-NEXT: [[TMP64:%.*]] = bitcast i32* [[TMP63]] to <4 x i32>* ; O3DEFAULT-NEXT: [[WIDE_LOAD_13:%.*]] = load <4 x i32>, <4 x i32>* [[TMP64]], align 4 -; O3DEFAULT-NEXT: [[TMP65:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_13]], [[BROADCAST_SPLAT]] +; O3DEFAULT-NEXT: [[TMP65:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_13]], [[BROADCAST_SPLAT2]] ; O3DEFAULT-NEXT: [[TMP66:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 52 ; O3DEFAULT-NEXT: [[TMP67:%.*]] = bitcast i32* [[TMP66]] to <4 x i32>* ; O3DEFAULT-NEXT: store <4 x i32> [[TMP65]], <4 x i32>* [[TMP67]], align 4 ; O3DEFAULT-NEXT: [[TMP68:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 56 ; O3DEFAULT-NEXT: [[TMP69:%.*]] = bitcast i32* [[TMP68]] to <4 x i32>* ; O3DEFAULT-NEXT: [[WIDE_LOAD_14:%.*]] = load <4 x i32>, <4 x i32>* [[TMP69]], align 4 -; O3DEFAULT-NEXT: [[TMP70:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_14]], [[BROADCAST_SPLAT]] +; O3DEFAULT-NEXT: [[TMP70:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_14]], [[BROADCAST_SPLAT2]] ; O3DEFAULT-NEXT: [[TMP71:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 56 ; O3DEFAULT-NEXT: [[TMP72:%.*]] = bitcast i32* [[TMP71]] to <4 x i32>* ; O3DEFAULT-NEXT: store <4 x i32> [[TMP70]], <4 x i32>* [[TMP72]], align 4 ; O3DEFAULT-NEXT: [[TMP73:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 60 ; O3DEFAULT-NEXT: [[TMP74:%.*]] = bitcast i32* [[TMP73]] to <4 x i32>* ; O3DEFAULT-NEXT: [[WIDE_LOAD_15:%.*]] = load <4 x i32>, <4 x i32>* [[TMP74]], align 4 -; O3DEFAULT-NEXT: [[TMP75:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_15]], [[BROADCAST_SPLAT]] +; O3DEFAULT-NEXT: [[TMP75:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_15]], [[BROADCAST_SPLAT2]] ; O3DEFAULT-NEXT: [[TMP76:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 60 ; O3DEFAULT-NEXT: [[TMP77:%.*]] = bitcast i32* [[TMP76]] to <4 x i32>* ; O3DEFAULT-NEXT: store <4 x i32> [[TMP75]], <4 x i32>* [[TMP77]], align 4 @@ -1460,115 +1460,115 @@ define i32 @nopragma(i32* noalias nocapture %a, i32* noalias nocapture readonly ; ; Os-LABEL: @nopragma( ; Os-NEXT: entry: -; Os-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i32> undef, i32 [[N:%.*]], i32 0 -; Os-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT]], <4 x i32> undef, <4 x i32> zeroinitializer +; Os-NEXT: [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <4 x i32> undef, i32 [[N:%.*]], i32 0 +; Os-NEXT: [[BROADCAST_SPLAT2:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT1]], <4 x i32> undef, <4 x i32> zeroinitializer ; Os-NEXT: [[TMP0:%.*]] = bitcast i32* [[B:%.*]] to <4 x i32>* ; Os-NEXT: [[WIDE_LOAD:%.*]] = load <4 x i32>, <4 x i32>* [[TMP0]], align 4 -; Os-NEXT: [[TMP1:%.*]] = add nsw <4 x i32> [[WIDE_LOAD]], [[BROADCAST_SPLAT]] +; Os-NEXT: [[TMP1:%.*]] = add nsw <4 x i32> [[WIDE_LOAD]], [[BROADCAST_SPLAT2]] ; Os-NEXT: [[TMP2:%.*]] = bitcast i32* [[A:%.*]] to <4 x i32>* ; Os-NEXT: store <4 x i32> [[TMP1]], <4 x i32>* [[TMP2]], align 4 ; Os-NEXT: [[TMP3:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 4 ; Os-NEXT: [[TMP4:%.*]] = bitcast i32* [[TMP3]] to <4 x i32>* ; Os-NEXT: [[WIDE_LOAD_1:%.*]] = load <4 x i32>, <4 x i32>* [[TMP4]], align 4 -; Os-NEXT: [[TMP5:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_1]], [[BROADCAST_SPLAT]] +; Os-NEXT: [[TMP5:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_1]], [[BROADCAST_SPLAT2]] ; Os-NEXT: [[TMP6:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 4 ; Os-NEXT: [[TMP7:%.*]] = bitcast i32* [[TMP6]] to <4 x i32>* ; Os-NEXT: store <4 x i32> [[TMP5]], <4 x i32>* [[TMP7]], align 4 ; Os-NEXT: [[TMP8:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 8 ; Os-NEXT: [[TMP9:%.*]] = bitcast i32* [[TMP8]] to <4 x i32>* ; Os-NEXT: [[WIDE_LOAD_2:%.*]] = load <4 x i32>, <4 x i32>* [[TMP9]], align 4 -; Os-NEXT: [[TMP10:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_2]], [[BROADCAST_SPLAT]] +; Os-NEXT: [[TMP10:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_2]], [[BROADCAST_SPLAT2]] ; Os-NEXT: [[TMP11:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 8 ; Os-NEXT: [[TMP12:%.*]] = bitcast i32* [[TMP11]] to <4 x i32>* ; Os-NEXT: store <4 x i32> [[TMP10]], <4 x i32>* [[TMP12]], align 4 ; Os-NEXT: [[TMP13:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 12 ; Os-NEXT: [[TMP14:%.*]] = bitcast i32* [[TMP13]] to <4 x i32>* ; Os-NEXT: [[WIDE_LOAD_3:%.*]] = load <4 x i32>, <4 x i32>* [[TMP14]], align 4 -; Os-NEXT: [[TMP15:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_3]], [[BROADCAST_SPLAT]] +; Os-NEXT: [[TMP15:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_3]], [[BROADCAST_SPLAT2]] ; Os-NEXT: [[TMP16:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 12 ; Os-NEXT: [[TMP17:%.*]] = bitcast i32* [[TMP16]] to <4 x i32>* ; Os-NEXT: store <4 x i32> [[TMP15]], <4 x i32>* [[TMP17]], align 4 ; Os-NEXT: [[TMP18:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 16 ; Os-NEXT: [[TMP19:%.*]] = bitcast i32* [[TMP18]] to <4 x i32>* ; Os-NEXT: [[WIDE_LOAD_4:%.*]] = load <4 x i32>, <4 x i32>* [[TMP19]], align 4 -; Os-NEXT: [[TMP20:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_4]], [[BROADCAST_SPLAT]] +; Os-NEXT: [[TMP20:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_4]], [[BROADCAST_SPLAT2]] ; Os-NEXT: [[TMP21:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 16 ; Os-NEXT: [[TMP22:%.*]] = bitcast i32* [[TMP21]] to <4 x i32>* ; Os-NEXT: store <4 x i32> [[TMP20]], <4 x i32>* [[TMP22]], align 4 ; Os-NEXT: [[TMP23:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 20 ; Os-NEXT: [[TMP24:%.*]] = bitcast i32* [[TMP23]] to <4 x i32>* ; Os-NEXT: [[WIDE_LOAD_5:%.*]] = load <4 x i32>, <4 x i32>* [[TMP24]], align 4 -; Os-NEXT: [[TMP25:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_5]], [[BROADCAST_SPLAT]] +; Os-NEXT: [[TMP25:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_5]], [[BROADCAST_SPLAT2]] ; Os-NEXT: [[TMP26:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 20 ; Os-NEXT: [[TMP27:%.*]] = bitcast i32* [[TMP26]] to <4 x i32>* ; Os-NEXT: store <4 x i32> [[TMP25]], <4 x i32>* [[TMP27]], align 4 ; Os-NEXT: [[TMP28:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 24 ; Os-NEXT: [[TMP29:%.*]] = bitcast i32* [[TMP28]] to <4 x i32>* ; Os-NEXT: [[WIDE_LOAD_6:%.*]] = load <4 x i32>, <4 x i32>* [[TMP29]], align 4 -; Os-NEXT: [[TMP30:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_6]], [[BROADCAST_SPLAT]] +; Os-NEXT: [[TMP30:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_6]], [[BROADCAST_SPLAT2]] ; Os-NEXT: [[TMP31:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 24 ; Os-NEXT: [[TMP32:%.*]] = bitcast i32* [[TMP31]] to <4 x i32>* ; Os-NEXT: store <4 x i32> [[TMP30]], <4 x i32>* [[TMP32]], align 4 ; Os-NEXT: [[TMP33:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 28 ; Os-NEXT: [[TMP34:%.*]] = bitcast i32* [[TMP33]] to <4 x i32>* ; Os-NEXT: [[WIDE_LOAD_7:%.*]] = load <4 x i32>, <4 x i32>* [[TMP34]], align 4 -; Os-NEXT: [[TMP35:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_7]], [[BROADCAST_SPLAT]] +; Os-NEXT: [[TMP35:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_7]], [[BROADCAST_SPLAT2]] ; Os-NEXT: [[TMP36:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 28 ; Os-NEXT: [[TMP37:%.*]] = bitcast i32* [[TMP36]] to <4 x i32>* ; Os-NEXT: store <4 x i32> [[TMP35]], <4 x i32>* [[TMP37]], align 4 ; Os-NEXT: [[TMP38:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 32 ; Os-NEXT: [[TMP39:%.*]] = bitcast i32* [[TMP38]] to <4 x i32>* ; Os-NEXT: [[WIDE_LOAD_8:%.*]] = load <4 x i32>, <4 x i32>* [[TMP39]], align 4 -; Os-NEXT: [[TMP40:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_8]], [[BROADCAST_SPLAT]] +; Os-NEXT: [[TMP40:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_8]], [[BROADCAST_SPLAT2]] ; Os-NEXT: [[TMP41:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 32 ; Os-NEXT: [[TMP42:%.*]] = bitcast i32* [[TMP41]] to <4 x i32>* ; Os-NEXT: store <4 x i32> [[TMP40]], <4 x i32>* [[TMP42]], align 4 ; Os-NEXT: [[TMP43:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 36 ; Os-NEXT: [[TMP44:%.*]] = bitcast i32* [[TMP43]] to <4 x i32>* ; Os-NEXT: [[WIDE_LOAD_9:%.*]] = load <4 x i32>, <4 x i32>* [[TMP44]], align 4 -; Os-NEXT: [[TMP45:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_9]], [[BROADCAST_SPLAT]] +; Os-NEXT: [[TMP45:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_9]], [[BROADCAST_SPLAT2]] ; Os-NEXT: [[TMP46:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 36 ; Os-NEXT: [[TMP47:%.*]] = bitcast i32* [[TMP46]] to <4 x i32>* ; Os-NEXT: store <4 x i32> [[TMP45]], <4 x i32>* [[TMP47]], align 4 ; Os-NEXT: [[TMP48:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 40 ; Os-NEXT: [[TMP49:%.*]] = bitcast i32* [[TMP48]] to <4 x i32>* ; Os-NEXT: [[WIDE_LOAD_10:%.*]] = load <4 x i32>, <4 x i32>* [[TMP49]], align 4 -; Os-NEXT: [[TMP50:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_10]], [[BROADCAST_SPLAT]] +; Os-NEXT: [[TMP50:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_10]], [[BROADCAST_SPLAT2]] ; Os-NEXT: [[TMP51:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 40 ; Os-NEXT: [[TMP52:%.*]] = bitcast i32* [[TMP51]] to <4 x i32>* ; Os-NEXT: store <4 x i32> [[TMP50]], <4 x i32>* [[TMP52]], align 4 ; Os-NEXT: [[TMP53:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 44 ; Os-NEXT: [[TMP54:%.*]] = bitcast i32* [[TMP53]] to <4 x i32>* ; Os-NEXT: [[WIDE_LOAD_11:%.*]] = load <4 x i32>, <4 x i32>* [[TMP54]], align 4 -; Os-NEXT: [[TMP55:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_11]], [[BROADCAST_SPLAT]] +; Os-NEXT: [[TMP55:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_11]], [[BROADCAST_SPLAT2]] ; Os-NEXT: [[TMP56:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 44 ; Os-NEXT: [[TMP57:%.*]] = bitcast i32* [[TMP56]] to <4 x i32>* ; Os-NEXT: store <4 x i32> [[TMP55]], <4 x i32>* [[TMP57]], align 4 ; Os-NEXT: [[TMP58:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 48 ; Os-NEXT: [[TMP59:%.*]] = bitcast i32* [[TMP58]] to <4 x i32>* ; Os-NEXT: [[WIDE_LOAD_12:%.*]] = load <4 x i32>, <4 x i32>* [[TMP59]], align 4 -; Os-NEXT: [[TMP60:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_12]], [[BROADCAST_SPLAT]] +; Os-NEXT: [[TMP60:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_12]], [[BROADCAST_SPLAT2]] ; Os-NEXT: [[TMP61:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 48 ; Os-NEXT: [[TMP62:%.*]] = bitcast i32* [[TMP61]] to <4 x i32>* ; Os-NEXT: store <4 x i32> [[TMP60]], <4 x i32>* [[TMP62]], align 4 ; Os-NEXT: [[TMP63:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 52 ; Os-NEXT: [[TMP64:%.*]] = bitcast i32* [[TMP63]] to <4 x i32>* ; Os-NEXT: [[WIDE_LOAD_13:%.*]] = load <4 x i32>, <4 x i32>* [[TMP64]], align 4 -; Os-NEXT: [[TMP65:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_13]], [[BROADCAST_SPLAT]] +; Os-NEXT: [[TMP65:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_13]], [[BROADCAST_SPLAT2]] ; Os-NEXT: [[TMP66:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 52 ; Os-NEXT: [[TMP67:%.*]] = bitcast i32* [[TMP66]] to <4 x i32>* ; Os-NEXT: store <4 x i32> [[TMP65]], <4 x i32>* [[TMP67]], align 4 ; Os-NEXT: [[TMP68:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 56 ; Os-NEXT: [[TMP69:%.*]] = bitcast i32* [[TMP68]] to <4 x i32>* ; Os-NEXT: [[WIDE_LOAD_14:%.*]] = load <4 x i32>, <4 x i32>* [[TMP69]], align 4 -; Os-NEXT: [[TMP70:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_14]], [[BROADCAST_SPLAT]] +; Os-NEXT: [[TMP70:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_14]], [[BROADCAST_SPLAT2]] ; Os-NEXT: [[TMP71:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 56 ; Os-NEXT: [[TMP72:%.*]] = bitcast i32* [[TMP71]] to <4 x i32>* ; Os-NEXT: store <4 x i32> [[TMP70]], <4 x i32>* [[TMP72]], align 4 ; Os-NEXT: [[TMP73:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 60 ; Os-NEXT: [[TMP74:%.*]] = bitcast i32* [[TMP73]] to <4 x i32>* ; Os-NEXT: [[WIDE_LOAD_15:%.*]] = load <4 x i32>, <4 x i32>* [[TMP74]], align 4 -; Os-NEXT: [[TMP75:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_15]], [[BROADCAST_SPLAT]] +; Os-NEXT: [[TMP75:%.*]] = add nsw <4 x i32> [[WIDE_LOAD_15]], [[BROADCAST_SPLAT2]] ; Os-NEXT: [[TMP76:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 60 ; Os-NEXT: [[TMP77:%.*]] = bitcast i32* [[TMP76]] to <4 x i32>* ; Os-NEXT: store <4 x i32> [[TMP75]], <4 x i32>* [[TMP77]], align 4 @@ -1596,17 +1596,20 @@ define i32 @nopragma(i32* noalias nocapture %a, i32* noalias nocapture readonly ; O1VEC2-NEXT: entry: ; O1VEC2-NEXT: br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]] ; O1VEC2: vector.ph: -; O1VEC2-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i32> undef, i32 [[N:%.*]], i32 0 -; O1VEC2-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT]], <4 x i32> undef, <4 x i32> zeroinitializer +; O1VEC2-NEXT: [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <4 x i32> undef, i32 [[N:%.*]], i32 0 +; O1VEC2-NEXT: [[BROADCAST_SPLAT2:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT1]], <4 x i32> undef, <4 x i32> zeroinitializer ; O1VEC2-NEXT: br label [[VECTOR_BODY:%.*]] ; O1VEC2: vector.body: ; O1VEC2-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ] +; O1VEC2-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i64> undef, i64 [[INDEX]], i32 0 +; O1VEC2-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT]], <4 x i64> undef, <4 x i32> zeroinitializer +; O1VEC2-NEXT: [[INDUCTION:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], ; O1VEC2-NEXT: [[TMP0:%.*]] = add i64 [[INDEX]], 0 ; O1VEC2-NEXT: [[TMP1:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i64 [[TMP0]] ; O1VEC2-NEXT: [[TMP2:%.*]] = getelementptr inbounds i32, i32* [[TMP1]], i32 0 ; O1VEC2-NEXT: [[TMP3:%.*]] = bitcast i32* [[TMP2]] to <4 x i32>* ; O1VEC2-NEXT: [[WIDE_LOAD:%.*]] = load <4 x i32>, <4 x i32>* [[TMP3]], align 4 -; O1VEC2-NEXT: [[TMP4:%.*]] = add nsw <4 x i32> [[WIDE_LOAD]], [[BROADCAST_SPLAT]] +; O1VEC2-NEXT: [[TMP4:%.*]] = add nsw <4 x i32> [[WIDE_LOAD]], [[BROADCAST_SPLAT2]] ; O1VEC2-NEXT: [[TMP5:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i64 [[TMP0]] ; O1VEC2-NEXT: [[TMP6:%.*]] = getelementptr inbounds i32, i32* [[TMP5]], i32 0 ; O1VEC2-NEXT: [[TMP7:%.*]] = bitcast i32* [[TMP6]] to <4 x i32>* @@ -1638,17 +1641,20 @@ define i32 @nopragma(i32* noalias nocapture %a, i32* noalias nocapture readonly ; OzVEC2-NEXT: entry: ; OzVEC2-NEXT: br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]] ; OzVEC2: vector.ph: -; OzVEC2-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i32> undef, i32 [[N:%.*]], i32 0 -; OzVEC2-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT]], <4 x i32> undef, <4 x i32> zeroinitializer +; OzVEC2-NEXT: [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <4 x i32> undef, i32 [[N:%.*]], i32 0 +; OzVEC2-NEXT: [[BROADCAST_SPLAT2:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT1]], <4 x i32> undef, <4 x i32> zeroinitializer ; OzVEC2-NEXT: br label [[VECTOR_BODY:%.*]] ; OzVEC2: vector.body: ; OzVEC2-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ] +; OzVEC2-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i64> undef, i64 [[INDEX]], i32 0 +; OzVEC2-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT]], <4 x i64> undef, <4 x i32> zeroinitializer +; OzVEC2-NEXT: [[INDUCTION:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], ; OzVEC2-NEXT: [[TMP0:%.*]] = add i64 [[INDEX]], 0 ; OzVEC2-NEXT: [[TMP1:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i64 [[TMP0]] ; OzVEC2-NEXT: [[TMP2:%.*]] = getelementptr inbounds i32, i32* [[TMP1]], i32 0 ; OzVEC2-NEXT: [[TMP3:%.*]] = bitcast i32* [[TMP2]] to <4 x i32>* ; OzVEC2-NEXT: [[WIDE_LOAD:%.*]] = load <4 x i32>, <4 x i32>* [[TMP3]], align 4 -; OzVEC2-NEXT: [[TMP4:%.*]] = add nsw <4 x i32> [[WIDE_LOAD]], [[BROADCAST_SPLAT]] +; OzVEC2-NEXT: [[TMP4:%.*]] = add nsw <4 x i32> [[WIDE_LOAD]], [[BROADCAST_SPLAT2]] ; OzVEC2-NEXT: [[TMP5:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i64 [[TMP0]] ; OzVEC2-NEXT: [[TMP6:%.*]] = getelementptr inbounds i32, i32* [[TMP5]], i32 0 ; OzVEC2-NEXT: [[TMP7:%.*]] = bitcast i32* [[TMP6]] to <4 x i32>* diff --git a/llvm/test/Transforms/LoopVectorize/X86/optsize.ll b/llvm/test/Transforms/LoopVectorize/X86/optsize.ll index b5d5220f19f1..9fa65534f320 100644 --- a/llvm/test/Transforms/LoopVectorize/X86/optsize.ll +++ b/llvm/test/Transforms/LoopVectorize/X86/optsize.ll @@ -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]], +; 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]], +; CHECK-NEXT: [[TMP2:%.*]] = icmp ule <64 x i32> [[INDUCTION]], ; 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]], -; 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> , <32 x i8> -; 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]], +; 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]], +; CHECK-NEXT: [[TMP2:%.*]] = icmp ule <64 x i32> [[INDUCTION]], ; 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]], -; 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> , <32 x i8> -; 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 diff --git a/llvm/test/Transforms/LoopVectorize/X86/pr35432.ll b/llvm/test/Transforms/LoopVectorize/X86/pr35432.ll index 74cc86bc8635..6aaa13c183a0 100644 --- a/llvm/test/Transforms/LoopVectorize/X86/pr35432.ll +++ b/llvm/test/Transforms/LoopVectorize/X86/pr35432.ll @@ -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]], +; CHECK-NEXT: [[INDUCTION3:%.*]] = add <4 x i8> [[BROADCAST_SPLAT]], ; 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]], @@ -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> -; 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> -; 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> +; 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: diff --git a/llvm/test/Transforms/LoopVectorize/X86/pr36524.ll b/llvm/test/Transforms/LoopVectorize/X86/pr36524.ll index 2cd24131197b..51d70d773a64 100644 --- a/llvm/test/Transforms/LoopVectorize/X86/pr36524.ll +++ b/llvm/test/Transforms/LoopVectorize/X86/pr36524.ll @@ -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]], ; 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]], diff --git a/llvm/test/Transforms/LoopVectorize/X86/small-size.ll b/llvm/test/Transforms/LoopVectorize/X86/small-size.ll index a13e6dc52176..c87b5dfc14db 100644 --- a/llvm/test/Transforms/LoopVectorize/X86/small-size.ll +++ b/llvm/test/Transforms/LoopVectorize/X86/small-size.ll @@ -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> [ , [[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]], +; 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]], -; 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]], -; 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]], -; 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]], +; 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 ;