[llvm] [AArch64] Improve cost computations for odd vector mem ops. (PR #78181)
Florian Hahn via llvm-commits
llvm-commits at lists.llvm.org
Wed Jan 17 13:20:55 PST 2024
https://github.com/fhahn updated https://github.com/llvm/llvm-project/pull/78181
>From c6a0548c10bd1f9ec54622c846bb70f0d73dd382 Mon Sep 17 00:00:00 2001
From: Florian Hahn <flo at fhahn.com>
Date: Mon, 15 Jan 2024 10:57:52 +0000
Subject: [PATCH 1/2] [AArch64] Improve cost computations for odd vector mem
ops.
Improve cost computaton for odd vector mem ops by breaking them down
into smaller power-of-2 parts and sum up the cost of those parts.
This fixes the current cost estimates, which for most parts
underestimated the cos, due to using getTypeLegalizationCost, which
widens to the next power-of-2 in a single step in most cases. This
doesn't reflect the actual cost.
See https://llvm.godbolt.org/z/vMsnxMf1v for codegen for the tests.
Note that there is a special case for v3i8, for which current codegen is
pretty bad, due to automatic widening to v4i8, which in turn requires
the conversion to go through memory ops in the stack. I am planning on
fixing that as a follow-up, but I am not yet sure where to best fix
this.
At the moment, there are almost no cases in which such vector operations
will be generated automatically. The motivating case is non-power-of-2
SLP vectorization: https://github.com/llvm/llvm-project/pull/77790
---
.../AArch64/AArch64TargetTransformInfo.cpp | 49 +++++++++++---
.../Analysis/CostModel/AArch64/vec3-ops.ll | 64 +++++++++----------
2 files changed, 73 insertions(+), 40 deletions(-)
diff --git a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
index 13b5e578391deea..fd389d70bb853bd 100644
--- a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
+++ b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
@@ -3176,14 +3176,47 @@ InstructionCost AArch64TTIImpl::getMemoryOpCost(unsigned Opcode, Type *Ty,
if (Ty->isPtrOrPtrVectorTy())
return LT.first;
- // Check truncating stores and extending loads.
- if (useNeonVector(Ty) &&
- Ty->getScalarSizeInBits() != LT.second.getScalarSizeInBits()) {
- // v4i8 types are lowered to scalar a load/store and sshll/xtn.
- if (VT == MVT::v4i8)
- return 2;
- // Otherwise we need to scalarize.
- return cast<FixedVectorType>(Ty)->getNumElements() * 2;
+ if (useNeonVector(Ty)) {
+ // Check truncating stores and extending loads.
+ if (Ty->getScalarSizeInBits() != LT.second.getScalarSizeInBits()) {
+ // v4i8 types are lowered to scalar a load/store and sshll/xtn.
+ if (VT == MVT::v4i8)
+ return 2;
+ // Otherwise we need to scalarize.
+ return cast<FixedVectorType>(Ty)->getNumElements() * 2;
+ }
+ EVT EltVT = VT.getVectorElementType();
+ unsigned EltSize = EltVT.getScalarSizeInBits();
+ if (!isPowerOf2_32(EltSize) || EltSize < 8 || EltSize > 64 ||
+ VT.getVectorNumElements() >= 128 / EltSize || !Alignment ||
+ *Alignment != Align(1))
+ return LT.first;
+ // FIXME: v3i8 lowering currently is very inefficient, due to automatic
+ // widening to v4i8, which produces suboptimal results.
+ if (VT.getVectorNumElements() == 3 && EltVT == MVT::i8)
+ return LT.first;
+
+ // Check non-power-of-2 loads/stores for legal vector element types with
+ // NEON. Non-power-of-2 memory ops will get broken down to a set of
+ // operations on smaller power-of-2 ops, including ld1/st1.
+ LLVMContext &C = Ty->getContext();
+ InstructionCost Cost(0);
+ SmallVector<EVT> TypeWorklist;
+ TypeWorklist.push_back(VT);
+ while (!TypeWorklist.empty()) {
+ EVT CurrVT = TypeWorklist.pop_back_val();
+ unsigned CurrNumElements = CurrVT.getVectorNumElements();
+ if (isPowerOf2_32(CurrNumElements)) {
+ Cost += 1;
+ continue;
+ }
+
+ unsigned PrevPow2 = NextPowerOf2(CurrNumElements) / 2;
+ TypeWorklist.push_back(EVT::getVectorVT(C, EltVT, PrevPow2));
+ TypeWorklist.push_back(
+ EVT::getVectorVT(C, EltVT, CurrNumElements - PrevPow2));
+ }
+ return Cost;
}
return LT.first;
diff --git a/llvm/test/Analysis/CostModel/AArch64/vec3-ops.ll b/llvm/test/Analysis/CostModel/AArch64/vec3-ops.ll
index 3e439c2696683ee..cf80bd677228ab1 100644
--- a/llvm/test/Analysis/CostModel/AArch64/vec3-ops.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/vec3-ops.ll
@@ -3,12 +3,12 @@
define void @vec3_i32(<3 x i32> %a, <3 x i32> %b, ptr %src, ptr %dst) {
; CHECK-LABEL: 'vec3_i32'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %l = load <3 x i32>, ptr %src, align 1
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %l = load <3 x i32>, ptr %src, align 1
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %add = add <3 x i32> %l, %b
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp = icmp uge <3 x i32> %add, %a
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %sub = sub <3 x i32> %add, %a
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %sel = select <3 x i1> %cmp, <3 x i32> %add, <3 x i32> %sub
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: store <3 x i32> %sel, ptr %dst, align 1
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: store <3 x i32> %sel, ptr %dst, align 1
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%l = load <3 x i32>, ptr %src, align 1
@@ -41,12 +41,12 @@ define void @vec3_i32_default_alignment(<3 x i32> %a, <3 x i32> %b, ptr %src, pt
define void @vec3_i16(<3 x i16> %a, <3 x i16> %b, ptr %src, ptr %dst) {
; CHECK-LABEL: 'vec3_i16'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %l = load <3 x i16>, ptr %src, align 1
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %l = load <3 x i16>, ptr %src, align 1
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %add = add <3 x i16> %l, %b
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp = icmp uge <3 x i16> %add, %a
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %sub = sub <3 x i16> %add, %a
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %sel = select <3 x i1> %cmp, <3 x i16> %add, <3 x i16> %sub
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: store <3 x i16> %sel, ptr %dst, align 1
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: store <3 x i16> %sel, ptr %dst, align 1
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%l = load <3 x i16>, ptr %src, align 1
@@ -60,9 +60,9 @@ define void @vec3_i16(<3 x i16> %a, <3 x i16> %b, ptr %src, ptr %dst) {
define void @vec7_i16(ptr %src, ptr %dst) {
; CHECK-LABEL: 'vec7_i16'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %l = load <7 x i16>, ptr %src, align 1
+; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %l = load <7 x i16>, ptr %src, align 1
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %add = add <7 x i16> %l, %l
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: store <7 x i16> %add, ptr %dst, align 1
+; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: store <7 x i16> %add, ptr %dst, align 1
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%l = load <7 x i16>, ptr %src, align 1
@@ -73,9 +73,9 @@ define void @vec7_i16(ptr %src, ptr %dst) {
define void @vec6_i16(ptr %src, ptr %dst) {
; CHECK-LABEL: 'vec6_i16'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %l = load <6 x i16>, ptr %src, align 1
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %l = load <6 x i16>, ptr %src, align 1
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %add = add <6 x i16> %l, %l
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: store <6 x i16> %add, ptr %dst, align 1
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: store <6 x i16> %add, ptr %dst, align 1
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%l = load <6 x i16>, ptr %src, align 1
@@ -86,9 +86,9 @@ define void @vec6_i16(ptr %src, ptr %dst) {
define void @vec5_i16(ptr %src, ptr %dst) {
; CHECK-LABEL: 'vec5_i16'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %l = load <5 x i16>, ptr %src, align 1
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %l = load <5 x i16>, ptr %src, align 1
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %add = add <5 x i16> %l, %l
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: store <5 x i16> %add, ptr %dst, align 1
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: store <5 x i16> %add, ptr %dst, align 1
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%l = load <5 x i16>, ptr %src, align 1
@@ -99,12 +99,12 @@ define void @vec5_i16(ptr %src, ptr %dst) {
define void @vec3_i16_zext_i32(<3 x i32> %a, <3 x i32> %b, ptr %src, ptr %dst) {
; CHECK-LABEL: 'vec3_i16_zext_i32'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %l = load <3 x i16>, ptr %src, align 1
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %l = load <3 x i16>, ptr %src, align 1
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %l.ext = zext <3 x i16> %l to <3 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %add = add <3 x i32> %l.ext, %b
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %sub = sub <3 x i32> %add, %a
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %sub.trunc = trunc <3 x i32> %sub to <3 x i16>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: store <3 x i16> %sub.trunc, ptr %dst, align 1
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: store <3 x i16> %sub.trunc, ptr %dst, align 1
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%l = load <3 x i16>, ptr %src, align 1
@@ -190,10 +190,10 @@ define void @vec3_i30(<3 x i30> %a, <3 x i30> %b, ptr %src, ptr %dst) {
define void @vec3_float(<3 x float> %a, <3 x float> %b, ptr %src, ptr %dst) {
; CHECK-LABEL: 'vec3_float'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %l = load <3 x float>, ptr %src, align 1
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %l = load <3 x float>, ptr %src, align 1
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %add = fadd <3 x float> %l, %b
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %sub = fsub <3 x float> %add, %a
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: store <3 x float> %sub, ptr %dst, align 1
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: store <3 x float> %sub, ptr %dst, align 1
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%l = load <3 x float>, ptr %src, align 1
@@ -205,10 +205,10 @@ define void @vec3_float(<3 x float> %a, <3 x float> %b, ptr %src, ptr %dst) {
define void @vec3_half(<3 x half> %a, <3 x half> %b, ptr %src, ptr %dst) {
; CHECK-LABEL: 'vec3_half'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %l = load <3 x half>, ptr %src, align 1
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %l = load <3 x half>, ptr %src, align 1
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %add = fadd <3 x half> %l, %b
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %sub = fsub <3 x half> %add, %a
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: store <3 x half> %sub, ptr %dst, align 1
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: store <3 x half> %sub, ptr %dst, align 1
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%l = load <3 x half>, ptr %src, align 1
@@ -220,9 +220,9 @@ define void @vec3_half(<3 x half> %a, <3 x half> %b, ptr %src, ptr %dst) {
define void @vec15_i8(ptr %src, ptr %dst) {
; CHECK-LABEL: 'vec15_i8'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %l = load <15 x i8>, ptr %src, align 1
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %l = load <15 x i8>, ptr %src, align 1
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %add = add <15 x i8> %l, %l
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: store <15 x i8> %add, ptr %dst, align 1
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: store <15 x i8> %add, ptr %dst, align 1
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%l = load <15 x i8>, ptr %src, align 1
@@ -233,9 +233,9 @@ define void @vec15_i8(ptr %src, ptr %dst) {
define void @vec14_i8(ptr %src, ptr %dst) {
; CHECK-LABEL: 'vec14_i8'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %l = load <14 x i8>, ptr %src, align 1
+; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %l = load <14 x i8>, ptr %src, align 1
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %add = add <14 x i8> %l, %l
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: store <14 x i8> %add, ptr %dst, align 1
+; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: store <14 x i8> %add, ptr %dst, align 1
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%l = load <14 x i8>, ptr %src, align 1
@@ -246,9 +246,9 @@ define void @vec14_i8(ptr %src, ptr %dst) {
define void @vec13_i8(ptr %src, ptr %dst) {
; CHECK-LABEL: 'vec13_i8'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %l = load <13 x i8>, ptr %src, align 1
+; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %l = load <13 x i8>, ptr %src, align 1
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %add = add <13 x i8> %l, %l
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: store <13 x i8> %add, ptr %dst, align 1
+; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: store <13 x i8> %add, ptr %dst, align 1
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%l = load <13 x i8>, ptr %src, align 1
@@ -259,9 +259,9 @@ define void @vec13_i8(ptr %src, ptr %dst) {
define void @vec12_i8(ptr %src, ptr %dst) {
; CHECK-LABEL: 'vec12_i8'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %l = load <12 x i8>, ptr %src, align 1
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %l = load <12 x i8>, ptr %src, align 1
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %add = add <12 x i8> %l, %l
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: store <12 x i8> %add, ptr %dst, align 1
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: store <12 x i8> %add, ptr %dst, align 1
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%l = load <12 x i8>, ptr %src, align 1
@@ -272,9 +272,9 @@ define void @vec12_i8(ptr %src, ptr %dst) {
define void @vec11_i8(ptr %src, ptr %dst) {
; CHECK-LABEL: 'vec11_i8'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %l = load <11 x i8>, ptr %src, align 1
+; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %l = load <11 x i8>, ptr %src, align 1
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %add = add <11 x i8> %l, %l
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: store <11 x i8> %add, ptr %dst, align 1
+; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: store <11 x i8> %add, ptr %dst, align 1
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%l = load <11 x i8>, ptr %src, align 1
@@ -285,10 +285,10 @@ define void @vec11_i8(ptr %src, ptr %dst) {
define void @vec7_i8(<7 x i8> %a, <7 x i8> %b, ptr %src, ptr %dst) {
; CHECK-LABEL: 'vec7_i8'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %l = load <7 x i8>, ptr %src, align 1
+; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %l = load <7 x i8>, ptr %src, align 1
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %add = add <7 x i8> %l, %b
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %sub = sub <7 x i8> %add, %a
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: store <7 x i8> %sub, ptr %dst, align 1
+; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: store <7 x i8> %sub, ptr %dst, align 1
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%l = load <7 x i8>, ptr %src, align 1
@@ -300,9 +300,9 @@ define void @vec7_i8(<7 x i8> %a, <7 x i8> %b, ptr %src, ptr %dst) {
define void @vec6_i8(ptr %src, ptr %dst) {
; CHECK-LABEL: 'vec6_i8'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %l = load <6 x i8>, ptr %src, align 1
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %l = load <6 x i8>, ptr %src, align 1
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %add = add <6 x i8> %l, %l
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: store <6 x i8> %add, ptr %dst, align 1
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: store <6 x i8> %add, ptr %dst, align 1
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%l = load <6 x i8>, ptr %src, align 1
@@ -313,9 +313,9 @@ define void @vec6_i8(ptr %src, ptr %dst) {
define void @vec5_i8(ptr %src, ptr %dst) {
; CHECK-LABEL: 'vec5_i8'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %l = load <5 x i8>, ptr %src, align 1
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %l = load <5 x i8>, ptr %src, align 1
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %add = add <5 x i8> %l, %l
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: store <5 x i8> %add, ptr %dst, align 1
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: store <5 x i8> %add, ptr %dst, align 1
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%l = load <5 x i8>, ptr %src, align 1
>From 2a558097d950439ec8f460177ca3857cf3824293 Mon Sep 17 00:00:00 2001
From: Florian Hahn <flo at fhahn.com>
Date: Wed, 17 Jan 2024 21:14:30 +0000
Subject: [PATCH 2/2] !fixup add () to help readability.
---
llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
index fd389d70bb853bd..d358a5c8bd9499f 100644
--- a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
+++ b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
@@ -3188,7 +3188,7 @@ InstructionCost AArch64TTIImpl::getMemoryOpCost(unsigned Opcode, Type *Ty,
EVT EltVT = VT.getVectorElementType();
unsigned EltSize = EltVT.getScalarSizeInBits();
if (!isPowerOf2_32(EltSize) || EltSize < 8 || EltSize > 64 ||
- VT.getVectorNumElements() >= 128 / EltSize || !Alignment ||
+ VT.getVectorNumElements() >= (128 / EltSize) || !Alignment ||
*Alignment != Align(1))
return LT.first;
// FIXME: v3i8 lowering currently is very inefficient, due to automatic
More information about the llvm-commits
mailing list