[llvm] [SLP]Fix/improve potential masked gather loads analysis. (PR #83472)
via llvm-commits
llvm-commits at lists.llvm.org
Thu Feb 29 12:02:43 PST 2024
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-llvm-transforms
Author: Alexey Bataev (alexey-bataev)
<details>
<summary>Changes</summary>
When do the analysis for the (potential) masked gather node, we check
that not greater than half of the pointer operands are loop invariants
or potentially vectorizable.
Need to check actually, that not less than half of pointer operands are
invariants and do better check for the potentially vectorizable
pointers.
---
Patch is 68.26 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/83472.diff
3 Files Affected:
- (modified) llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp (+4-2)
- (modified) llvm/test/Transforms/SLPVectorizer/RISCV/complex-loads.ll (+316-310)
- (modified) llvm/test/Transforms/SLPVectorizer/X86/split-load8_2-unord.ll (+34-31)
``````````diff
diff --git a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
index 94b7c4952f055e..df48fc1f7cf8dd 100644
--- a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
+++ b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
@@ -4102,12 +4102,14 @@ static LoadsState canVectorizeLoads(ArrayRef<Value *> VL, const Value *VL0,
bool ProfitableGatherPointers =
static_cast<unsigned>(count_if(
PointerOps,
- [L](Value *V) { return L && L->isLoopInvariant(V); })) <= Sz / 2 &&
+ [L](Value *V) { return L && L->isLoopInvariant(V); })) >= Sz / 2 &&
Sz > 2;
if (ProfitableGatherPointers || all_of(PointerOps, [IsSorted](Value *P) {
auto *GEP = dyn_cast<GetElementPtrInst>(P);
return (IsSorted && !GEP && doesNotNeedToBeScheduled(P)) ||
- (GEP && GEP->getNumOperands() == 2);
+ (GEP && GEP->getNumOperands() == 2 &&
+ (isa<Constant>(GEP->getOperand(1)) ||
+ isa<Instruction>(GEP->getOperand(1))));
})) {
Align CommonAlignment = computeCommonAlignment<LoadInst>(VL);
if (TTI.isLegalMaskedGather(VecTy, CommonAlignment) &&
diff --git a/llvm/test/Transforms/SLPVectorizer/RISCV/complex-loads.ll b/llvm/test/Transforms/SLPVectorizer/RISCV/complex-loads.ll
index e167b6a47af592..97008ac6785961 100644
--- a/llvm/test/Transforms/SLPVectorizer/RISCV/complex-loads.ll
+++ b/llvm/test/Transforms/SLPVectorizer/RISCV/complex-loads.ll
@@ -17,353 +17,359 @@ define i32 @test(ptr %pix1, ptr %pix2, i64 %idx.ext, i64 %idx.ext63, ptr %add.pt
; CHECK-NEXT: [[ARRAYIDX20:%.*]] = getelementptr i8, ptr [[PIX1]], i64 2
; CHECK-NEXT: [[ARRAYIDX22:%.*]] = getelementptr i8, ptr [[PIX2]], i64 2
; CHECK-NEXT: [[ADD_PTR3:%.*]] = getelementptr i8, ptr [[PIX1]], i64 [[IDX_EXT]]
+; CHECK-NEXT: [[ADD_PTR644:%.*]] = getelementptr i8, ptr [[PIX2]], i64 [[IDX_EXT63]]
; CHECK-NEXT: [[TMP9:%.*]] = load i8, ptr [[ADD_PTR3]], align 1
; CHECK-NEXT: [[CONV_1:%.*]] = zext i8 [[TMP9]] to i32
+; CHECK-NEXT: [[TMP10:%.*]] = load i8, ptr [[ADD_PTR644]], align 1
; CHECK-NEXT: [[ARRAYIDX8_1:%.*]] = getelementptr i8, ptr [[ADD_PTR3]], i64 1
+; CHECK-NEXT: [[ARRAYIDX22_1:%.*]] = getelementptr i8, ptr [[ADD_PTR644]], i64 2
+; CHECK-NEXT: [[TMP11:%.*]] = load i8, ptr [[ARRAYIDX22_1]], align 1
; CHECK-NEXT: [[ARRAYIDX32_1:%.*]] = getelementptr i8, ptr [[ADD_PTR3]], i64 3
-; CHECK-NEXT: [[TMP10:%.*]] = load i8, ptr [[ARRAYIDX32_1]], align 1
-; CHECK-NEXT: [[CONV33_1:%.*]] = zext i8 [[TMP10]] to i32
+; CHECK-NEXT: [[TMP12:%.*]] = load i8, ptr [[ARRAYIDX32_1]], align 1
+; CHECK-NEXT: [[CONV33_1:%.*]] = zext i8 [[TMP12]] to i32
; CHECK-NEXT: [[ADD_PTR_1:%.*]] = getelementptr i8, ptr [[ADD_PTR]], i64 [[IDX_EXT]]
; CHECK-NEXT: [[ADD_PTR64_1:%.*]] = getelementptr i8, ptr [[ADD_PTR64]], i64 [[IDX_EXT63]]
+; CHECK-NEXT: [[TMP13:%.*]] = load i8, ptr [[ADD_PTR_1]], align 1
+; CHECK-NEXT: [[TMP14:%.*]] = load i8, ptr [[ADD_PTR64_1]], align 1
; CHECK-NEXT: [[ARRAYIDX20_2:%.*]] = getelementptr i8, ptr [[ADD_PTR_1]], i64 2
-; CHECK-NEXT: [[TMP11:%.*]] = insertelement <2 x ptr> poison, ptr [[ADD_PTR_1]], i32 0
-; CHECK-NEXT: [[TMP12:%.*]] = insertelement <2 x ptr> [[TMP11]], ptr [[ARRAYIDX20_2]], i32 1
-; CHECK-NEXT: [[TMP13:%.*]] = call <2 x i8> @llvm.masked.gather.v2i8.v2p0(<2 x ptr> [[TMP12]], i32 1, <2 x i1> <i1 true, i1 true>, <2 x i8> poison)
-; CHECK-NEXT: [[TMP14:%.*]] = zext <2 x i8> [[TMP13]] to <2 x i32>
+; CHECK-NEXT: [[TMP15:%.*]] = load i8, ptr [[ARRAYIDX20_2]], align 1
; CHECK-NEXT: [[ARRAYIDX22_2:%.*]] = getelementptr i8, ptr [[ADD_PTR64_1]], i64 2
-; CHECK-NEXT: [[TMP15:%.*]] = insertelement <2 x ptr> poison, ptr [[ADD_PTR64_1]], i32 0
-; CHECK-NEXT: [[TMP16:%.*]] = insertelement <2 x ptr> [[TMP15]], ptr [[ARRAYIDX22_2]], i32 1
-; CHECK-NEXT: [[TMP17:%.*]] = call <2 x i8> @llvm.masked.gather.v2i8.v2p0(<2 x ptr> [[TMP16]], i32 1, <2 x i1> <i1 true, i1 true>, <2 x i8> poison)
-; CHECK-NEXT: [[TMP18:%.*]] = zext <2 x i8> [[TMP17]] to <2 x i32>
-; CHECK-NEXT: [[TMP19:%.*]] = sub <2 x i32> [[TMP14]], [[TMP18]]
-; CHECK-NEXT: [[TMP20:%.*]] = shufflevector <2 x ptr> [[TMP12]], <2 x ptr> poison, <2 x i32> zeroinitializer
-; CHECK-NEXT: [[TMP21:%.*]] = getelementptr i8, <2 x ptr> [[TMP20]], <2 x i64> <i64 4, i64 6>
-; CHECK-NEXT: [[TMP22:%.*]] = call <2 x i8> @llvm.masked.gather.v2i8.v2p0(<2 x ptr> [[TMP21]], i32 1, <2 x i1> <i1 true, i1 true>, <2 x i8> poison)
-; CHECK-NEXT: [[TMP23:%.*]] = zext <2 x i8> [[TMP22]] to <2 x i32>
-; CHECK-NEXT: [[TMP24:%.*]] = shufflevector <2 x ptr> [[TMP16]], <2 x ptr> poison, <2 x i32> zeroinitializer
-; CHECK-NEXT: [[TMP25:%.*]] = getelementptr i8, <2 x ptr> [[TMP24]], <2 x i64> <i64 4, i64 6>
-; CHECK-NEXT: [[TMP26:%.*]] = call <2 x i8> @llvm.masked.gather.v2i8.v2p0(<2 x ptr> [[TMP25]], i32 1, <2 x i1> <i1 true, i1 true>, <2 x i8> poison)
-; CHECK-NEXT: [[TMP27:%.*]] = zext <2 x i8> [[TMP26]] to <2 x i32>
-; CHECK-NEXT: [[TMP28:%.*]] = sub <2 x i32> [[TMP23]], [[TMP27]]
-; CHECK-NEXT: [[TMP29:%.*]] = shl <2 x i32> [[TMP28]], <i32 16, i32 16>
-; CHECK-NEXT: [[TMP30:%.*]] = add <2 x i32> [[TMP29]], [[TMP19]]
-; CHECK-NEXT: [[TMP31:%.*]] = getelementptr i8, <2 x ptr> [[TMP20]], <2 x i64> <i64 1, i64 3>
+; CHECK-NEXT: [[TMP16:%.*]] = load i8, ptr [[ARRAYIDX22_2]], align 1
+; CHECK-NEXT: [[TMP17:%.*]] = insertelement <2 x i8> poison, i8 [[TMP13]], i32 0
+; CHECK-NEXT: [[TMP18:%.*]] = insertelement <2 x i8> [[TMP17]], i8 [[TMP15]], i32 1
+; CHECK-NEXT: [[TMP19:%.*]] = zext <2 x i8> [[TMP18]] to <2 x i32>
+; CHECK-NEXT: [[TMP20:%.*]] = insertelement <2 x i8> poison, i8 [[TMP14]], i32 0
+; CHECK-NEXT: [[TMP21:%.*]] = insertelement <2 x i8> [[TMP20]], i8 [[TMP16]], i32 1
+; CHECK-NEXT: [[TMP22:%.*]] = zext <2 x i8> [[TMP21]] to <2 x i32>
+; CHECK-NEXT: [[TMP23:%.*]] = sub <2 x i32> [[TMP19]], [[TMP22]]
+; CHECK-NEXT: [[TMP24:%.*]] = insertelement <2 x ptr> poison, ptr [[ADD_PTR_1]], i32 0
+; CHECK-NEXT: [[TMP25:%.*]] = shufflevector <2 x ptr> [[TMP24]], <2 x ptr> poison, <2 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP26:%.*]] = getelementptr i8, <2 x ptr> [[TMP25]], <2 x i64> <i64 4, i64 6>
+; CHECK-NEXT: [[TMP27:%.*]] = call <2 x i8> @llvm.masked.gather.v2i8.v2p0(<2 x ptr> [[TMP26]], i32 1, <2 x i1> <i1 true, i1 true>, <2 x i8> poison)
+; CHECK-NEXT: [[TMP28:%.*]] = zext <2 x i8> [[TMP27]] to <2 x i32>
+; CHECK-NEXT: [[TMP29:%.*]] = insertelement <2 x ptr> poison, ptr [[ADD_PTR64_1]], i32 0
+; CHECK-NEXT: [[TMP30:%.*]] = shufflevector <2 x ptr> [[TMP29]], <2 x ptr> poison, <2 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP31:%.*]] = getelementptr i8, <2 x ptr> [[TMP30]], <2 x i64> <i64 4, i64 6>
; CHECK-NEXT: [[TMP32:%.*]] = call <2 x i8> @llvm.masked.gather.v2i8.v2p0(<2 x ptr> [[TMP31]], i32 1, <2 x i1> <i1 true, i1 true>, <2 x i8> poison)
; CHECK-NEXT: [[TMP33:%.*]] = zext <2 x i8> [[TMP32]] to <2 x i32>
-; CHECK-NEXT: [[TMP34:%.*]] = getelementptr i8, <2 x ptr> [[TMP24]], <2 x i64> <i64 1, i64 3>
-; CHECK-NEXT: [[TMP35:%.*]] = call <2 x i8> @llvm.masked.gather.v2i8.v2p0(<2 x ptr> [[TMP34]], i32 1, <2 x i1> <i1 true, i1 true>, <2 x i8> poison)
-; CHECK-NEXT: [[TMP36:%.*]] = zext <2 x i8> [[TMP35]] to <2 x i32>
-; CHECK-NEXT: [[TMP37:%.*]] = sub <2 x i32> [[TMP33]], [[TMP36]]
-; CHECK-NEXT: [[TMP38:%.*]] = getelementptr i8, <2 x ptr> [[TMP20]], <2 x i64> <i64 5, i64 7>
-; CHECK-NEXT: [[TMP39:%.*]] = call <2 x i8> @llvm.masked.gather.v2i8.v2p0(<2 x ptr> [[TMP38]], i32 1, <2 x i1> <i1 true, i1 true>, <2 x i8> poison)
-; CHECK-NEXT: [[TMP40:%.*]] = zext <2 x i8> [[TMP39]] to <2 x i32>
-; CHECK-NEXT: [[TMP41:%.*]] = getelementptr i8, <2 x ptr> [[TMP24]], <2 x i64> <i64 5, i64 7>
-; CHECK-NEXT: [[TMP42:%.*]] = call <2 x i8> @llvm.masked.gather.v2i8.v2p0(<2 x ptr> [[TMP41]], i32 1, <2 x i1> <i1 true, i1 true>, <2 x i8> poison)
-; CHECK-NEXT: [[TMP43:%.*]] = zext <2 x i8> [[TMP42]] to <2 x i32>
-; CHECK-NEXT: [[TMP44:%.*]] = sub <2 x i32> [[TMP40]], [[TMP43]]
-; CHECK-NEXT: [[TMP45:%.*]] = shl <2 x i32> [[TMP44]], <i32 16, i32 16>
-; CHECK-NEXT: [[TMP46:%.*]] = add <2 x i32> [[TMP45]], [[TMP37]]
-; CHECK-NEXT: [[TMP47:%.*]] = sub <2 x i32> [[TMP30]], [[TMP46]]
-; CHECK-NEXT: [[TMP48:%.*]] = extractelement <2 x i32> [[TMP47]], i32 0
-; CHECK-NEXT: [[TMP49:%.*]] = extractelement <2 x i32> [[TMP47]], i32 1
-; CHECK-NEXT: [[SUB59_2:%.*]] = sub i32 [[TMP48]], [[TMP49]]
-; CHECK-NEXT: [[TMP50:%.*]] = load i8, ptr null, align 1
+; CHECK-NEXT: [[TMP34:%.*]] = sub <2 x i32> [[TMP28]], [[TMP33]]
+; CHECK-NEXT: [[TMP35:%.*]] = shl <2 x i32> [[TMP34]], <i32 16, i32 16>
+; CHECK-NEXT: [[TMP36:%.*]] = add <2 x i32> [[TMP35]], [[TMP23]]
+; CHECK-NEXT: [[TMP37:%.*]] = getelementptr i8, <2 x ptr> [[TMP25]], <2 x i64> <i64 1, i64 3>
+; CHECK-NEXT: [[TMP38:%.*]] = call <2 x i8> @llvm.masked.gather.v2i8.v2p0(<2 x ptr> [[TMP37]], i32 1, <2 x i1> <i1 true, i1 true>, <2 x i8> poison)
+; CHECK-NEXT: [[TMP39:%.*]] = zext <2 x i8> [[TMP38]] to <2 x i32>
+; CHECK-NEXT: [[TMP40:%.*]] = getelementptr i8, <2 x ptr> [[TMP30]], <2 x i64> <i64 1, i64 3>
+; CHECK-NEXT: [[TMP41:%.*]] = call <2 x i8> @llvm.masked.gather.v2i8.v2p0(<2 x ptr> [[TMP40]], i32 1, <2 x i1> <i1 true, i1 true>, <2 x i8> poison)
+; CHECK-NEXT: [[TMP42:%.*]] = zext <2 x i8> [[TMP41]] to <2 x i32>
+; CHECK-NEXT: [[TMP43:%.*]] = sub <2 x i32> [[TMP39]], [[TMP42]]
+; CHECK-NEXT: [[TMP44:%.*]] = getelementptr i8, <2 x ptr> [[TMP25]], <2 x i64> <i64 5, i64 7>
+; CHECK-NEXT: [[TMP45:%.*]] = call <2 x i8> @llvm.masked.gather.v2i8.v2p0(<2 x ptr> [[TMP44]], i32 1, <2 x i1> <i1 true, i1 true>, <2 x i8> poison)
+; CHECK-NEXT: [[TMP46:%.*]] = zext <2 x i8> [[TMP45]] to <2 x i32>
+; CHECK-NEXT: [[TMP47:%.*]] = getelementptr i8, <2 x ptr> [[TMP30]], <2 x i64> <i64 5, i64 7>
+; CHECK-NEXT: [[TMP48:%.*]] = call <2 x i8> @llvm.masked.gather.v2i8.v2p0(<2 x ptr> [[TMP47]], i32 1, <2 x i1> <i1 true, i1 true>, <2 x i8> poison)
+; CHECK-NEXT: [[TMP49:%.*]] = zext <2 x i8> [[TMP48]] to <2 x i32>
+; CHECK-NEXT: [[TMP50:%.*]] = sub <2 x i32> [[TMP46]], [[TMP49]]
+; CHECK-NEXT: [[TMP51:%.*]] = shl <2 x i32> [[TMP50]], <i32 16, i32 16>
+; CHECK-NEXT: [[TMP52:%.*]] = add <2 x i32> [[TMP51]], [[TMP43]]
+; CHECK-NEXT: [[TMP53:%.*]] = sub <2 x i32> [[TMP36]], [[TMP52]]
+; CHECK-NEXT: [[TMP54:%.*]] = extractelement <2 x i32> [[TMP53]], i32 0
+; CHECK-NEXT: [[TMP55:%.*]] = extractelement <2 x i32> [[TMP53]], i32 1
+; CHECK-NEXT: [[SUB59_2:%.*]] = sub i32 [[TMP54]], [[TMP55]]
+; CHECK-NEXT: [[TMP56:%.*]] = load i8, ptr null, align 1
; CHECK-NEXT: [[ARRAYIDX20_3:%.*]] = getelementptr i8, ptr null, i64 2
; CHECK-NEXT: [[ARRAYIDX22_3:%.*]] = getelementptr i8, ptr null, i64 2
-; CHECK-NEXT: [[TMP51:%.*]] = load i8, ptr null, align 1
-; CHECK-NEXT: [[TMP52:%.*]] = insertelement <2 x ptr> <ptr poison, ptr null>, ptr [[ARRAYIDX20_3]], i32 0
-; CHECK-NEXT: [[TMP53:%.*]] = call <2 x i8> @llvm.masked.gather.v2i8.v2p0(<2 x ptr> [[TMP52]], i32 1, <2 x i1> <i1 true, i1 true>, <2 x i8> poison)
-; CHECK-NEXT: [[TMP54:%.*]] = zext <2 x i8> [[TMP53]] to <2 x i32>
-; CHECK-NEXT: [[TMP55:%.*]] = insertelement <2 x ptr> <ptr poison, ptr null>, ptr [[ARRAYIDX22_3]], i32 0
-; CHECK-NEXT: [[TMP56:%.*]] = call <2 x i8> @llvm.masked.gather.v2i8.v2p0(<2 x ptr> [[TMP55]], i32 1, <2 x i1> <i1 true, i1 true>, <2 x i8> poison)
-; CHECK-NEXT: [[TMP57:%.*]] = zext <2 x i8> [[TMP56]] to <2 x i32>
-; CHECK-NEXT: [[TMP58:%.*]] = sub <2 x i32> [[TMP54]], [[TMP57]]
-; CHECK-NEXT: [[TMP59:%.*]] = call <2 x i8> @llvm.experimental.vp.strided.load.v2i8.p0.i64(ptr align 1 null, i64 4, <2 x i1> <i1 true, i1 true>, i32 2)
+; CHECK-NEXT: [[TMP57:%.*]] = load i8, ptr null, align 1
+; CHECK-NEXT: [[TMP58:%.*]] = insertelement <2 x ptr> <ptr poison, ptr null>, ptr [[ARRAYIDX20_3]], i32 0
+; CHECK-NEXT: [[TMP59:%.*]] = call <2 x i8> @llvm.masked.gather.v2i8.v2p0(<2 x ptr> [[TMP58]], i32 1, <2 x i1> <i1 true, i1 true>, <2 x i8> poison)
; CHECK-NEXT: [[TMP60:%.*]] = zext <2 x i8> [[TMP59]] to <2 x i32>
-; CHECK-NEXT: [[TMP61:%.*]] = call <2 x i8> @llvm.masked.gather.v2i8.v2p0(<2 x ptr> getelementptr (i8, <2 x ptr> zeroinitializer, <2 x i64> <i64 6, i64 4>), i32 1, <2 x i1> <i1 true, i1 true>, <2 x i8> poison)
-; CHECK-NEXT: [[TMP62:%.*]] = zext <2 x i8> [[TMP61]] to <2 x i32>
-; CHECK-NEXT: [[TMP63:%.*]] = sub <2 x i32> [[TMP60]], [[TMP62]]
-; CHECK-NEXT: [[TMP64:%.*]] = shl <2 x i32> [[TMP63]], <i32 16, i32 16>
-; CHECK-NEXT: [[TMP65:%.*]] = add <2 x i32> [[TMP64]], [[TMP58]]
-; CHECK-NEXT: [[TMP66:%.*]] = call <2 x i8> @llvm.masked.gather.v2i8.v2p0(<2 x ptr> getelementptr (i8, <2 x ptr> zeroinitializer, <2 x i64> <i64 3, i64 1>), i32 1, <2 x i1> <i1 true, i1 true>, <2 x i8> poison)
-; CHECK-NEXT: [[TMP67:%.*]] = zext <2 x i8> [[TMP66]] to <2 x i32>
-; CHECK-NEXT: [[TMP68:%.*]] = call <2 x i8> @llvm.masked.gather.v2i8.v2p0(<2 x ptr> getelementptr (i8, <2 x ptr> zeroinitializer, <2 x i64> <i64 3, i64 1>), i32 1, <2 x i1> <i1 true, i1 true>, <2 x i8> poison)
-; CHECK-NEXT: [[TMP69:%.*]] = zext <2 x i8> [[TMP68]] to <2 x i32>
-; CHECK-NEXT: [[TMP70:%.*]] = sub <2 x i32> [[TMP67]], [[TMP69]]
-; CHECK-NEXT: [[TMP71:%.*]] = insertelement <2 x i8> poison, i8 [[TMP51]], i32 0
-; CHECK-NEXT: [[TMP72:%.*]] = insertelement <2 x i8> [[TMP71]], i8 [[TMP50]], i32 1
+; CHECK-NEXT: [[TMP61:%.*]] = insertelement <2 x ptr> <ptr poison, ptr null>, ptr [[ARRAYIDX22_3]], i32 0
+; CHECK-NEXT: [[TMP62:%.*]] = call <2 x i8> @llvm.masked.gather.v2i8.v2p0(<2 x ptr> [[TMP61]], i32 1, <2 x i1> <i1 true, i1 true>, <2 x i8> poison)
+; CHECK-NEXT: [[TMP63:%.*]] = zext <2 x i8> [[TMP62]] to <2 x i32>
+; CHECK-NEXT: [[TMP64:%.*]] = sub <2 x i32> [[TMP60]], [[TMP63]]
+; CHECK-NEXT: [[TMP65:%.*]] = call <2 x i8> @llvm.experimental.vp.strided.load.v2i8.p0.i64(ptr align 1 null, i64 4, <2 x i1> <i1 true, i1 true>, i32 2)
+; CHECK-NEXT: [[TMP66:%.*]] = zext <2 x i8> [[TMP65]] to <2 x i32>
+; CHECK-NEXT: [[TMP67:%.*]] = call <2 x i8> @llvm.masked.gather.v2i8.v2p0(<2 x ptr> getelementptr (i8, <2 x ptr> zeroinitializer, <2 x i64> <i64 6, i64 4>), i32 1, <2 x i1> <i1 true, i1 true>, <2 x i8> poison)
+; CHECK-NEXT: [[TMP68:%.*]] = zext <2 x i8> [[TMP67]] to <2 x i32>
+; CHECK-NEXT: [[TMP69:%.*]] = sub <2 x i32> [[TMP66]], [[TMP68]]
+; CHECK-NEXT: [[TMP70:%.*]] = shl <2 x i32> [[TMP69]], <i32 16, i32 16>
+; CHECK-NEXT: [[TMP71:%.*]] = add <2 x i32> [[TMP70]], [[TMP64]]
+; CHECK-NEXT: [[TMP72:%.*]] = call <2 x i8> @llvm.masked.gather.v2i8.v2p0(<2 x ptr> getelementptr (i8, <2 x ptr> zeroinitializer, <2 x i64> <i64 3, i64 1>), i32 1, <2 x i1> <i1 true, i1 true>, <2 x i8> poison)
; CHECK-NEXT: [[TMP73:%.*]] = zext <2 x i8> [[TMP72]] to <2 x i32>
-; CHECK-NEXT: [[TMP74:%.*]] = call <2 x i8> @llvm.masked.gather.v2i8.v2p0(<2 x ptr> getelementptr (i8, <2 x ptr> zeroinitializer, <2 x i64> <i64 7, i64 5>), i32 1, <2 x i1> <i1 true, i1 true>, <2 x i8> poison)
+; CHECK-NEXT: [[TMP74:%.*]] = call <2 x i8> @llvm.masked.gather.v2i8.v2p0(<2 x ptr> getelementptr (i8, <2 x ptr> zeroinitializer, <2 x i64> <i64 3, i64 1>), i32 1, <2 x i1> <i1 true, i1 true>, <2 x i8> poison)
; CHECK-NEXT: [[TMP75:%.*]] = zext <2 x i8> [[TMP74]] to <2 x i32>
; CHECK-NEXT: [[TMP76:%.*]] = sub <2 x i32> [[TMP73]], [[TMP75]]
-; CHECK-NEXT: [[TMP77:%.*]] = shl <2 x i32> [[TMP76]], <i32 16, i32 16>
-; CHECK-NEXT: [[TMP78:%.*]] = add <2 x i32> [[TMP77]], [[TMP70]]
-; CHECK-NEXT: [[TMP79:%.*]] = sub <2 x i32> [[TMP65]], [[TMP78]]
-; CHECK-NEXT: [[TMP80:%.*]] = shufflevector <2 x i32> [[TMP78]], <2 x i32> [[TMP46]], <2 x i32> <i32 1, i32 2>
-; CHECK-NEXT: [[TMP81:%.*]] = shufflevector <2 x i32> [[TMP65]], <2 x i32> [[TMP30]], <2 x i32> <i32 1, i32 2>
-; CHECK-NEXT: [[TMP82:%.*]] = add <2 x i32> [[TMP80]], [[TMP81]]
-; CHECK-NEXT: [[TMP83:%.*]] = shufflevector <2 x i32> [[TMP78]], <2 x i32> [[TMP46]], <2 x i32> <i32 0, i32 3>
-; CHECK-NEXT: [[TMP84:%.*]] = shufflevector <2 x i32> [[TMP65]], <2 x i32> [[TMP30]], <2 x i32> <i32 0, i32 3>
-; CHECK-NEXT: [[TMP85:%.*]] = add <2 x i32> [[TMP83]], [[TMP84]]
-; CHECK-NEXT: [[TMP86:%.*]] = add <2 x i32> [[TMP85]], [[TMP82]]
-; CHECK-NEXT: [[TMP87:%.*]] = sub <2 x i32> [[TMP82]], [[TMP85]]
-; CHECK-NEXT: [[TMP88:%.*]] = extractelement <2 x i32> [[TMP79]], i32 0
-; CHECK-NEXT: [[TMP89:%.*]] = extractelement <2 x i32> [[TMP79]], i32 1
-; CHECK-NEXT: [[SUB59_3:%.*]] = sub i32 [[TMP89]], [[TMP88]]
-; CHECK-NEXT: [[TMP90:%.*]] = extractelement <2 x i32> [[TMP86]], i32 0
-; CHECK-NEXT: [[TMP91:%.*]] = extractelement <2 x i32> [[TMP86]], i32 1
-; CHECK-NEXT: [[ADD94:%.*]] = add i32 [[TMP90]], [[TMP91]]
-; CHECK-NEXT: [[SUB102:%.*]] = sub i32 [[TMP91]], [[TMP90]]
-; CHECK-NEXT: [[TMP92:%.*]] = extractelement <2 x i32> [[TMP54]], i32 1
-; CHECK-NEXT: [[SHR_I:%.*]] = lshr i32 [[TMP92]], 15
+; CHECK-NEXT: [[TMP77:%.*]] = insertelement <2 x i8> poison, i8 [[TMP57]], i32 0
+; CHECK-NEXT: [[TMP78:%.*]] = insertelement <2 x i8> [[TMP77]], i8 [[TMP56]], i32 1
+; CHECK-NEXT: [[TMP79:%.*]] = zext <2 x i8> [[TMP78]] to <2 x i32>
+; CHECK-NEXT: [[TMP80:%.*]] = call <2 x i8> @llvm.masked.gather.v2i8.v2p0(<2 x ptr> getelementptr (i8, <2 x ptr> zeroinitializer, <2 x i64> <i64 7, i64 5>), i32 1, <2 x i1> <i1 true, i1 true>, <2 x i8> poison)
+; CHECK-NEXT: [[TMP81:%.*]] = zext <2 x i8> [[TMP80]] to <2 x i32>
+; CHECK-NEXT: [[TMP82:%.*]] = sub <2 x i32> [[TMP79]], [[TMP81]]
+; CHECK-NEXT: [[TMP83:%.*]] = shl <2 x i32> [[TMP82]], <i32 16, i32 16>
+; CHECK-NEXT: [[TMP84:%.*]] = add <2 x i32> [[TMP83]], [[TMP76]]
+; CHECK-NEXT: [[TMP85:%.*]] = sub <2 x i32> [[TMP71]], [[TMP84]]
+; CHECK-NEXT: [[TMP86:%.*]] = shufflevector <2 x i32> [[TMP84]], <2 x i32> [[TMP52]], <2 x i32> <i32 1, i32 2>
+; CHECK-NEXT: [[TMP87:%.*]] = shufflevector <2 x i32> [[TMP71]], <2 x i32> [[TMP36]], <2 x i32> <i32 1, i32 2>
+; CHECK-NEXT: [[TMP88:%.*]] = add <2 x i32> [[TMP86]], [[TMP87]]
+; CHECK-NEXT: [[TMP89:%.*]] = shufflevector <2 x i32> [[TMP84]], <2 x i32> [[TMP52]], <2 x i32> <i32 0, i32 3>
+; CHECK-NEXT: [[TMP90:%.*]] = shufflevector <2 x i32> [[TMP71]], <2 x i32> [[TMP36]], <2 x i32> <i32 0, i32 3>
+; CHECK-NEXT: [[TMP91:%.*]] = add <2 x i32> [[TMP89]], [[TMP90]]
+; CHECK-NEXT: [[TMP92:%.*]] = add <2 x i32> [[TMP91]], [[TMP88]]
+; CHECK-NEXT: [[TMP93:%.*]] = sub <2 x i32> [[TMP88]], [[TMP91]]
+; CHECK-NEXT: [[TMP94:%.*]] = extractelement <2 x i32> [[TMP85]], i32 0
+; CHECK-NEXT: [[TMP95:%.*]] = extractelement <2 x i32> [[TMP85]], i32 1
+; CHECK-NEXT: [[SUB59_3:%.*]] = sub i32 [[TMP95]], [[TMP94]]
+; CHECK-NEXT: [[TMP96:%.*]] = extractelement <2 x i32> [[TMP92]], i32 0
+; CHECK-NEXT: [[TMP97:%.*]] = extractelement <2 x i32> [[TMP92]], i32 1
+; CHECK-NEXT: [[ADD94:%.*]] = add i32 [[TMP96]], [[TMP97]]
+; CHECK-NEXT: [[SUB102:%.*]] = sub i32 [[TMP97]], [[TMP96]]
+; CHECK-NEXT: [[TMP98:%.*]] = extractelement <2 x i32> [[TMP60]], i32 1
+; CHECK-NEXT: [[SHR_I:%.*]] = lshr i32 [[TMP98]], 15
; CHECK-NEXT: [[AND_I:%.*]] = and i32 [[SHR_I]], 65537
; CHECK-NEXT: [[MUL_I:%.*]] = mul i32 [[AND_I]], 65535
-; CHECK-NEXT: [[TMP93:%.*]] = extractelement <2 x i32> [[TMP85]], i32 1
-; CHECK-NEXT: [[SHR_I49:%.*]] = lshr i32 [[TMP93]], 15
+; CHECK-NEXT: [[TMP99:%.*]] = extractelement <2 x i32> [[TMP91]], i32 1
+; CHECK-NEXT: [[SHR_I49:%.*]] = lshr i32 [[TMP99]], 15
; CHECK-NEXT: [[AND_I50:%.*]] = and i32 [[SHR_I49]], 65537
; CHECK-NEXT: [[MUL_I51:%.*]] = mul i32 [[AND_I50]], 65535
-; CHECK-NEXT: [[TMP94:%.*]] = extractelement <2 x i32> [[TMP87]], i32 0
-; CHECK-NEXT: [[TMP95:%.*]] = extractelement <2 x i32> [[TMP87]], i32 1
-; CHECK-NEXT: [[ADD94_2:%.*]] = add i32 [[TMP94]], [[TMP95]]
-; CHECK-NEXT: [[TMP96:%.*]] = load <2 x i8>, ptr [[ARRAYIDX20]], align 1
-; CHECK-NEXT: [[TMP97:%.*]] = zext <2 x i8> [[TMP96]] to <2 x i32>
-; CHECK-NEXT: [[TMP98:%.*]] = insertelement <2 x i32> poison, i32 [[SUB59_2]], i32 0
-; CHECK-NEXT: [[TMP99:%.*]] = shufflevector <2 x i32> [[TMP98]], <2 x i32> poison, <2 x i32> zeroinitializer
-; CHECK-NEXT: [[TMP100:%.*]] = insertelement <2 x i32> po...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/83472
More information about the llvm-commits
mailing list