[llvm] [AArch64] Enable other cost kinds for getCmpSelInstrCost. (PR #144375)
via llvm-commits
llvm-commits at lists.llvm.org
Fri Jun 27 03:29:55 PDT 2025
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-aarch64
Author: David Green (davemgreen)
<details>
<summary>Changes</summary>
This will alter the Codesize and Latency costs for icmp, fcmp and select, for the operations directly handled by AArch64TTIImpl::getCmpSelInstrCost. This version probably doesn't do enough with latency costs yet.
---
Patch is 38.68 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/144375.diff
4 Files Affected:
- (modified) llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp (+4-8)
- (modified) llvm/test/Analysis/CostModel/AArch64/cmp.ll (+2-2)
- (modified) llvm/test/Analysis/CostModel/AArch64/select.ll (+11-11)
- (modified) llvm/test/Analysis/CostModel/AArch64/vector-select.ll (+59-59)
``````````diff
diff --git a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
index 79b2dc2b3845e..b482389989bb3 100644
--- a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
+++ b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
@@ -4264,11 +4264,6 @@ InstructionCost AArch64TTIImpl::getCmpSelInstrCost(
unsigned Opcode, Type *ValTy, Type *CondTy, CmpInst::Predicate VecPred,
TTI::TargetCostKind CostKind, TTI::OperandValueInfo Op1Info,
TTI::OperandValueInfo Op2Info, const Instruction *I) const {
- // TODO: Handle other cost kinds.
- if (CostKind != TTI::TCK_RecipThroughput)
- return BaseT::getCmpSelInstrCost(Opcode, ValTy, CondTy, VecPred, CostKind,
- Op1Info, Op2Info, I);
-
int ISD = TLI->InstructionOpcodeToISD(Opcode);
// We don't lower some vector selects well that are wider than the register
// width.
@@ -4355,9 +4350,10 @@ InstructionCost AArch64TTIImpl::getCmpSelInstrCost(
// Treat the icmp in icmp(and, 0) or icmp(and, -1/1) when it can be folded to
// icmp(and, 0) as free, as we can make use of ands, but only if the
- // comparison is not unsigned.
- if (ValTy->isIntegerTy() && ISD == ISD::SETCC && I &&
- !CmpInst::isUnsigned(VecPred) &&
+ // comparison is not unsigned. FIXME: Enable for non-throughput cost kinds
+ // providing it will not cause performance regressions.
+ if (CostKind == TTI::TCK_RecipThroughput && ValTy->isIntegerTy() &&
+ ISD == ISD::SETCC && I && !CmpInst::isUnsigned(VecPred) &&
TLI->isTypeLegal(TLI->getValueType(DL, ValTy)) &&
match(I->getOperand(0), m_And(m_Value(), m_Value()))) {
if (match(I->getOperand(1), m_Zero()))
diff --git a/llvm/test/Analysis/CostModel/AArch64/cmp.ll b/llvm/test/Analysis/CostModel/AArch64/cmp.ll
index 16b3913f52028..b55a759a78cc3 100644
--- a/llvm/test/Analysis/CostModel/AArch64/cmp.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/cmp.ll
@@ -17,10 +17,10 @@ define void @cmps() {
; CHECK-NEXT: Cost Model: Found costs of 1 for: %cf32 = fcmp ogt float undef, undef
; CHECK-NEXT: Cost Model: Found costs of 1 for: %cf64 = fcmp ogt double undef, undef
; CHECK-NEXT: Cost Model: Found costs of 1 for: %cbf64 = fcmp ogt bfloat undef, undef
-; CHECK-NEXT: Cost Model: Found costs of RThru:7 CodeSize:1 Lat:1 SizeLat:1 for: %cfv816 = fcmp olt <8 x half> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:7 CodeSize:4 Lat:4 SizeLat:4 for: %cfv816 = fcmp olt <8 x half> undef, undef
; CHECK-NEXT: Cost Model: Found costs of 1 for: %cfv432 = fcmp oge <4 x float> undef, undef
; CHECK-NEXT: Cost Model: Found costs of 1 for: %cfv264 = fcmp oge <2 x double> undef, undef
-; CHECK-NEXT: Cost Model: Found costs of RThru:7 CodeSize:1 Lat:1 SizeLat:1 for: %cbfv816 = fcmp olt <8 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:7 CodeSize:4 Lat:4 SizeLat:4 for: %cbfv816 = fcmp olt <8 x bfloat> undef, undef
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
%c8 = icmp slt i8 undef, undef
diff --git a/llvm/test/Analysis/CostModel/AArch64/select.ll b/llvm/test/Analysis/CostModel/AArch64/select.ll
index 76bd5c9bb0af6..c0f469d7d9165 100644
--- a/llvm/test/Analysis/CostModel/AArch64/select.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/select.ll
@@ -11,17 +11,17 @@ define void @select() {
; CHECK-NEXT: Cost Model: Found costs of 1 for: %v4 = select i1 undef, i64 undef, i64 undef
; CHECK-NEXT: Cost Model: Found costs of 1 for: %v5 = select i1 undef, float undef, float undef
; CHECK-NEXT: Cost Model: Found costs of 1 for: %v6 = select i1 undef, double undef, double undef
-; CHECK-NEXT: Cost Model: Found costs of RThru:16 CodeSize:1 Lat:1 SizeLat:1 for: %v13b = select <16 x i1> undef, <16 x i16> undef, <16 x i16> undef
-; CHECK-NEXT: Cost Model: Found costs of RThru:8 CodeSize:1 Lat:1 SizeLat:1 for: %v15b = select <8 x i1> undef, <8 x i32> undef, <8 x i32> undef
-; CHECK-NEXT: Cost Model: Found costs of RThru:16 CodeSize:1 Lat:1 SizeLat:1 for: %v15c = select <16 x i1> undef, <16 x i32> undef, <16 x i32> undef
-; CHECK-NEXT: Cost Model: Found costs of RThru:80 CodeSize:1 Lat:1 SizeLat:1 for: %v16a = select <4 x i1> undef, <4 x i64> undef, <4 x i64> undef
-; CHECK-NEXT: Cost Model: Found costs of RThru:160 CodeSize:1 Lat:1 SizeLat:1 for: %v16b = select <8 x i1> undef, <8 x i64> undef, <8 x i64> undef
-; CHECK-NEXT: Cost Model: Found costs of RThru:320 CodeSize:1 Lat:1 SizeLat:1 for: %v16c = select <16 x i1> undef, <16 x i64> undef, <16 x i64> undef
-; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:1 SizeLat:1 for: %v2float = select <2 x i1> undef, <2 x float> undef, <2 x float> undef
-; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:1 SizeLat:1 for: %v4float = select <4 x i1> undef, <4 x float> undef, <4 x float> undef
-; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:1 SizeLat:1 for: %v2double = select <2 x i1> undef, <2 x double> undef, <2 x double> undef
-; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:1 SizeLat:1 for: %v4half = select <4 x i1> undef, <4 x half> undef, <4 x half> undef
-; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:1 SizeLat:1 for: %v8half = select <8 x i1> undef, <8 x half> undef, <8 x half> undef
+; CHECK-NEXT: Cost Model: Found costs of 16 for: %v13b = select <16 x i1> undef, <16 x i16> undef, <16 x i16> undef
+; CHECK-NEXT: Cost Model: Found costs of 8 for: %v15b = select <8 x i1> undef, <8 x i32> undef, <8 x i32> undef
+; CHECK-NEXT: Cost Model: Found costs of 16 for: %v15c = select <16 x i1> undef, <16 x i32> undef, <16 x i32> undef
+; CHECK-NEXT: Cost Model: Found costs of 80 for: %v16a = select <4 x i1> undef, <4 x i64> undef, <4 x i64> undef
+; CHECK-NEXT: Cost Model: Found costs of 160 for: %v16b = select <8 x i1> undef, <8 x i64> undef, <8 x i64> undef
+; CHECK-NEXT: Cost Model: Found costs of 320 for: %v16c = select <16 x i1> undef, <16 x i64> undef, <16 x i64> undef
+; CHECK-NEXT: Cost Model: Found costs of 2 for: %v2float = select <2 x i1> undef, <2 x float> undef, <2 x float> undef
+; CHECK-NEXT: Cost Model: Found costs of 2 for: %v4float = select <4 x i1> undef, <4 x float> undef, <4 x float> undef
+; CHECK-NEXT: Cost Model: Found costs of 2 for: %v2double = select <2 x i1> undef, <2 x double> undef, <2 x double> undef
+; CHECK-NEXT: Cost Model: Found costs of 2 for: %v4half = select <4 x i1> undef, <4 x half> undef, <4 x half> undef
+; CHECK-NEXT: Cost Model: Found costs of 2 for: %v8half = select <8 x i1> undef, <8 x half> undef, <8 x half> undef
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
%v1 = select i1 undef, i8 undef, i8 undef
diff --git a/llvm/test/Analysis/CostModel/AArch64/vector-select.ll b/llvm/test/Analysis/CostModel/AArch64/vector-select.ll
index d568f4b2c0b5c..a317d6da4028d 100644
--- a/llvm/test/Analysis/CostModel/AArch64/vector-select.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/vector-select.ll
@@ -84,7 +84,7 @@ define <2 x i64> @v2i64_select_sle(<2 x i64> %a, <2 x i64> %b, <2 x i64> %c) {
define <3 x i64> @v3i64_select_sle(<3 x i64> %a, <3 x i64> %b, <3 x i64> %c) {
; COST-LABEL: 'v3i64_select_sle'
; COST-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:1 SizeLat:1 for: %cmp.1 = icmp sle <3 x i64> %a, %b
-; COST-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:1 SizeLat:1 for: %s.1 = select <3 x i1> %cmp.1, <3 x i64> %a, <3 x i64> %c
+; COST-NEXT: Cost Model: Found costs of 2 for: %s.1 = select <3 x i1> %cmp.1, <3 x i64> %a, <3 x i64> %c
; COST-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <3 x i64> %s.1
;
%cmp.1 = icmp sle <3 x i64> %a, %b
@@ -103,8 +103,8 @@ define <2 x i64> @v2i64_select_no_cmp(<2 x i64> %a, <2 x i64> %b, <2 x i1> %cond
define <4 x half> @v4f16_select_ogt(<4 x half> %a, <4 x half> %b, <4 x half> %c) {
; COST-NOFP16-LABEL: 'v4f16_select_ogt'
-; COST-NOFP16-NEXT: Cost Model: Found costs of RThru:4 CodeSize:1 Lat:1 SizeLat:1 for: %cmp.1 = fcmp ogt <4 x half> %a, %b
-; COST-NOFP16-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:1 SizeLat:1 for: %s.1 = select <4 x i1> %cmp.1, <4 x half> %a, <4 x half> %c
+; COST-NOFP16-NEXT: Cost Model: Found costs of 4 for: %cmp.1 = fcmp ogt <4 x half> %a, %b
+; COST-NOFP16-NEXT: Cost Model: Found costs of 2 for: %s.1 = select <4 x i1> %cmp.1, <4 x half> %a, <4 x half> %c
; COST-NOFP16-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <4 x half> %s.1
;
; COST-FULLFP16-LABEL: 'v4f16_select_ogt'
@@ -119,8 +119,8 @@ define <4 x half> @v4f16_select_ogt(<4 x half> %a, <4 x half> %b, <4 x half> %c)
define <8 x half> @v8f16_select_ogt(<8 x half> %a, <8 x half> %b, <8 x half> %c) {
; COST-NOFP16-LABEL: 'v8f16_select_ogt'
-; COST-NOFP16-NEXT: Cost Model: Found costs of RThru:7 CodeSize:1 Lat:1 SizeLat:1 for: %cmp.1 = fcmp ogt <8 x half> %a, %b
-; COST-NOFP16-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:1 SizeLat:1 for: %s.1 = select <8 x i1> %cmp.1, <8 x half> %a, <8 x half> %c
+; COST-NOFP16-NEXT: Cost Model: Found costs of RThru:7 CodeSize:4 Lat:4 SizeLat:4 for: %cmp.1 = fcmp ogt <8 x half> %a, %b
+; COST-NOFP16-NEXT: Cost Model: Found costs of 2 for: %s.1 = select <8 x i1> %cmp.1, <8 x half> %a, <8 x half> %c
; COST-NOFP16-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <8 x half> %s.1
;
; COST-FULLFP16-LABEL: 'v8f16_select_ogt'
@@ -168,7 +168,7 @@ define <2 x double> @v2f64_select_ogt(<2 x double> %a, <2 x double> %b, <2 x dou
define <4 x bfloat> @v4bf16_select_ogt(<4 x bfloat> %a, <4 x bfloat> %b, <4 x bfloat> %c) {
; COST-LABEL: 'v4bf16_select_ogt'
-; COST-NEXT: Cost Model: Found costs of RThru:4 CodeSize:1 Lat:1 SizeLat:1 for: %cmp.1 = fcmp ogt <4 x bfloat> %a, %b
+; COST-NEXT: Cost Model: Found costs of 4 for: %cmp.1 = fcmp ogt <4 x bfloat> %a, %b
; COST-NEXT: Cost Model: Found costs of RThru:10 CodeSize:1 Lat:1 SizeLat:1 for: %s.1 = select <4 x i1> %cmp.1, <4 x bfloat> %a, <4 x bfloat> %c
; COST-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <4 x bfloat> %s.1
;
@@ -179,7 +179,7 @@ define <4 x bfloat> @v4bf16_select_ogt(<4 x bfloat> %a, <4 x bfloat> %b, <4 x bf
define <8 x bfloat> @v8bf16_select_ogt(<8 x bfloat> %a, <8 x bfloat> %b, <8 x bfloat> %c) {
; COST-LABEL: 'v8bf16_select_ogt'
-; COST-NEXT: Cost Model: Found costs of RThru:7 CodeSize:1 Lat:1 SizeLat:1 for: %cmp.1 = fcmp ogt <8 x bfloat> %a, %b
+; COST-NEXT: Cost Model: Found costs of RThru:7 CodeSize:4 Lat:4 SizeLat:4 for: %cmp.1 = fcmp ogt <8 x bfloat> %a, %b
; COST-NEXT: Cost Model: Found costs of RThru:22 CodeSize:1 Lat:1 SizeLat:1 for: %s.1 = select <8 x i1> %cmp.1, <8 x bfloat> %a, <8 x bfloat> %c
; COST-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <8 x bfloat> %s.1
;
@@ -190,8 +190,8 @@ define <8 x bfloat> @v8bf16_select_ogt(<8 x bfloat> %a, <8 x bfloat> %b, <8 x bf
define <4 x half> @v4f16_select_oge(<4 x half> %a, <4 x half> %b, <4 x half> %c) {
; COST-NOFP16-LABEL: 'v4f16_select_oge'
-; COST-NOFP16-NEXT: Cost Model: Found costs of RThru:4 CodeSize:1 Lat:1 SizeLat:1 for: %cmp.1 = fcmp oge <4 x half> %a, %b
-; COST-NOFP16-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:1 SizeLat:1 for: %s.1 = select <4 x i1> %cmp.1, <4 x half> %a, <4 x half> %c
+; COST-NOFP16-NEXT: Cost Model: Found costs of 4 for: %cmp.1 = fcmp oge <4 x half> %a, %b
+; COST-NOFP16-NEXT: Cost Model: Found costs of 2 for: %s.1 = select <4 x i1> %cmp.1, <4 x half> %a, <4 x half> %c
; COST-NOFP16-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <4 x half> %s.1
;
; COST-FULLFP16-LABEL: 'v4f16_select_oge'
@@ -206,8 +206,8 @@ define <4 x half> @v4f16_select_oge(<4 x half> %a, <4 x half> %b, <4 x half> %c)
define <8 x half> @v8f16_select_oge(<8 x half> %a, <8 x half> %b, <8 x half> %c) {
; COST-NOFP16-LABEL: 'v8f16_select_oge'
-; COST-NOFP16-NEXT: Cost Model: Found costs of RThru:7 CodeSize:1 Lat:1 SizeLat:1 for: %cmp.1 = fcmp oge <8 x half> %a, %b
-; COST-NOFP16-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:1 SizeLat:1 for: %s.1 = select <8 x i1> %cmp.1, <8 x half> %a, <8 x half> %c
+; COST-NOFP16-NEXT: Cost Model: Found costs of RThru:7 CodeSize:4 Lat:4 SizeLat:4 for: %cmp.1 = fcmp oge <8 x half> %a, %b
+; COST-NOFP16-NEXT: Cost Model: Found costs of 2 for: %s.1 = select <8 x i1> %cmp.1, <8 x half> %a, <8 x half> %c
; COST-NOFP16-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <8 x half> %s.1
;
; COST-FULLFP16-LABEL: 'v8f16_select_oge'
@@ -255,7 +255,7 @@ define <2 x double> @v2f64_select_oge(<2 x double> %a, <2 x double> %b, <2 x dou
define <4 x bfloat> @v4bf16_select_oge(<4 x bfloat> %a, <4 x bfloat> %b, <4 x bfloat> %c) {
; COST-LABEL: 'v4bf16_select_oge'
-; COST-NEXT: Cost Model: Found costs of RThru:4 CodeSize:1 Lat:1 SizeLat:1 for: %cmp.1 = fcmp oge <4 x bfloat> %a, %b
+; COST-NEXT: Cost Model: Found costs of 4 for: %cmp.1 = fcmp oge <4 x bfloat> %a, %b
; COST-NEXT: Cost Model: Found costs of RThru:10 CodeSize:1 Lat:1 SizeLat:1 for: %s.1 = select <4 x i1> %cmp.1, <4 x bfloat> %a, <4 x bfloat> %c
; COST-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <4 x bfloat> %s.1
;
@@ -266,7 +266,7 @@ define <4 x bfloat> @v4bf16_select_oge(<4 x bfloat> %a, <4 x bfloat> %b, <4 x bf
define <8 x bfloat> @v8bf16_select_oge(<8 x bfloat> %a, <8 x bfloat> %b, <8 x bfloat> %c) {
; COST-LABEL: 'v8bf16_select_oge'
-; COST-NEXT: Cost Model: Found costs of RThru:7 CodeSize:1 Lat:1 SizeLat:1 for: %cmp.1 = fcmp oge <8 x bfloat> %a, %b
+; COST-NEXT: Cost Model: Found costs of RThru:7 CodeSize:4 Lat:4 SizeLat:4 for: %cmp.1 = fcmp oge <8 x bfloat> %a, %b
; COST-NEXT: Cost Model: Found costs of RThru:22 CodeSize:1 Lat:1 SizeLat:1 for: %s.1 = select <8 x i1> %cmp.1, <8 x bfloat> %a, <8 x bfloat> %c
; COST-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <8 x bfloat> %s.1
;
@@ -277,8 +277,8 @@ define <8 x bfloat> @v8bf16_select_oge(<8 x bfloat> %a, <8 x bfloat> %b, <8 x bf
define <4 x half> @v4f16_select_olt(<4 x half> %a, <4 x half> %b, <4 x half> %c) {
; COST-NOFP16-LABEL: 'v4f16_select_olt'
-; COST-NOFP16-NEXT: Cost Model: Found costs of RThru:4 CodeSize:1 Lat:1 SizeLat:1 for: %cmp.1 = fcmp olt <4 x half> %a, %b
-; COST-NOFP16-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:1 SizeLat:1 for: %s.1 = select <4 x i1> %cmp.1, <4 x half> %a, <4 x half> %c
+; COST-NOFP16-NEXT: Cost Model: Found costs of 4 for: %cmp.1 = fcmp olt <4 x half> %a, %b
+; COST-NOFP16-NEXT: Cost Model: Found costs of 2 for: %s.1 = select <4 x i1> %cmp.1, <4 x half> %a, <4 x half> %c
; COST-NOFP16-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <4 x half> %s.1
;
; COST-FULLFP16-LABEL: 'v4f16_select_olt'
@@ -293,8 +293,8 @@ define <4 x half> @v4f16_select_olt(<4 x half> %a, <4 x half> %b, <4 x half> %c)
define <8 x half> @v8f16_select_olt(<8 x half> %a, <8 x half> %b, <8 x half> %c) {
; COST-NOFP16-LABEL: 'v8f16_select_olt'
-; COST-NOFP16-NEXT: Cost Model: Found costs of RThru:7 CodeSize:1 Lat:1 SizeLat:1 for: %cmp.1 = fcmp olt <8 x half> %a, %b
-; COST-NOFP16-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:1 SizeLat:1 for: %s.1 = select <8 x i1> %cmp.1, <8 x half> %a, <8 x half> %c
+; COST-NOFP16-NEXT: Cost Model: Found costs of RThru:7 CodeSize:4 Lat:4 SizeLat:4 for: %cmp.1 = fcmp olt <8 x half> %a, %b
+; COST-NOFP16-NEXT: Cost Model: Found costs of 2 for: %s.1 = select <8 x i1> %cmp.1, <8 x half> %a, <8 x half> %c
; COST-NOFP16-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <8 x half> %s.1
;
; COST-FULLFP16-LABEL: 'v8f16_select_olt'
@@ -342,7 +342,7 @@ define <2 x double> @v2f64_select_olt(<2 x double> %a, <2 x double> %b, <2 x dou
define <4 x bfloat> @v4bf16_select_olt(<4 x bfloat> %a, <4 x bfloat> %b, <4 x bfloat> %c) {
; COST-LABEL: 'v4bf16_select_olt'
-; COST-NEXT: Cost Model: Found costs of RThru:4 CodeSize:1 Lat:1 SizeLat:1 for: %cmp.1 = fcmp olt <4 x bfloat> %a, %b
+; COST-NEXT: Cost Model: Found costs of 4 for: %cmp.1 = fcmp olt <4 x bfloat> %a, %b
; COST-NEXT: Cost Model: Found costs of RThru:10 CodeSize:1 Lat:1 SizeLat:1 for: %s.1 = select <4 x i1> %cmp.1, <4 x bfloat> %a, <4 x bfloat> %c
; COST-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <4 x bfloat> %s.1
;
@@ -353,7 +353,7 @@ define <4 x bfloat> @v4bf16_select_olt(<4 x bfloat> %a, <4 x bfloat> %b, <4 x bf
define <8 x bfloat> @v8bf16_select_olt(<8 x bfloat> %a, <8 x bfloat> %b, <8 x bfloat> %c) {
; COST-LABEL: 'v8bf16_select_olt'
-; COST-NEXT: Cost Model: Found costs of RThru:7 CodeSize:1 Lat:1 SizeLat:1 for: %cmp.1 = fcmp olt <8 x bfloat> %a, %b
+; COST-NEXT: Cost Model: Found costs of RThru:7 CodeSize:4 Lat:4 SizeLat:4 for: %cmp.1 = fcmp olt <8 x bfloat> %a, %b
; COST-NEXT: Cost Model: Found costs of RThru:22 CodeSize:1 Lat:1 SizeLat:1 for: %s.1 = select <8 x i1> %cmp.1, <8 x bfloat> %a, <8 x bfloat> %c
; COST-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <8 x bfloat> %s.1
;
@@ -364,8 +364,8 @@ define <8 x bfloat> @v8bf16_select_olt(<8 x bfloat> %a, <8 x bfloat> %b, <8 x bf
define <4 x half> @v4f16_select_ole(<4 x half> %a, <4 x half> %b, <4 x half> %c) {
; COST-NOFP16-LABEL: 'v4f16_select_ole'
-; COST-NOFP16-NEXT: Cost Model: Found costs of RThru:4 CodeSize:1 Lat:1 SizeLat:1 for: %cmp.1 = fcmp ole <4 x half> %a, %b
-; COST-NOFP16-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:1 SizeLat:1 for: %s.1 = select <4 x i1> %cmp.1, <4 x half> %a, <4 x half> %c
+; COST-NOFP16-NEXT: Cost Model: Found costs of 4 for: %cmp.1 = fcmp ole <4 x half> %a, %b
+; COST-NOFP16-NEXT: Cost Model: Found costs of 2 for: %s.1 = select <4 x i1> %cmp.1, <4 x half> %a, <4 x half> %c
; COST-NOFP16-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <4 x half> %s.1
;
; COST-FULLFP16-LABEL: 'v4f16_select_ole'
@@ -380,8 +380,8 @@ define <4 x half> @v4f16_select_ole(<4 x half> %a, <4 x half> %b, <4 x half> %c)
define <8 x half> @v8f16_select_ole(<8 x half> %a, <8 x half> %b, <8 x half> %c) {
; COST-NOFP16-LABEL: 'v8f16_select_ole'
-; COST-NOFP16-NEXT: Cost Model: Found costs of RThru:7 CodeSize:1 Lat:1 SizeLat:1 for: %cmp.1 = fcmp ole <8 x half> %a, %b
-; COST-NOFP16-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:1 SizeLat:1 for: %s.1 = select <8 x i1> %cmp.1, <8 x half> %a, <8 x half> %c
+; COST-NOFP16-NEXT: Cost Model: Found costs of RThru:7 CodeSize:4 Lat:4 SizeLat:4 for: %cmp.1 = fcmp ole <8 x half> %a, %b
+; COST-NOFP16-NEXT: Cost Model: Found costs of 2 for: %s.1 = select <8 x i1> %cmp.1, <8 x half> %a, <8 x half> %c
; COST-NOFP16-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <8 x half> %s.1
;
; COST-FULLFP16-LABEL: 'v8f16_select_ole'
@@ -429,7 +429,7 @@ define <2 x double> @v2f64_select_ole(<2 x double> %a, <2 x double> %b, <2 x dou
define <4 x bfloat> @v4bf16_select_ole(<4 x bfloat> %a, <4 x bfloat> %b, <4 x bfloat> %c) {
; COST-LABEL: 'v4bf16_select_ole'
-; COST-NEXT: Cost Model: Found costs of RThru:4 CodeSize:1 Lat:1 SizeLat:1 for: %cmp.1 = fcmp ole <4 x bfloat> %a, %b
+; COST-NEXT: Cost Model: Found costs of 4 for: %cmp.1 = fcmp ole <4 x bfloat> %a, %b
; COST-NEXT: Cost Model: Found costs of RThru:10 CodeSize:1 Lat:1 SizeLat:1 for: %s.1 = select <4 x i1> %cmp.1, <4 x bfloat> %a, <4 x bfloat> %c
; COST-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <4 x bfloat> %s.1
;
@@ -440,7 +440,7 @@ define <4 x bfloat> @v4bf16_select_ole(<4 x bfloat> %a, <4 x bfloat> %b, <4 x bf
define <8 x bfloat> @v8bf16_select_ole(<8 x bfloat> %a, <8 x bfloat> %b, <8 x bfloat> %c) {
; COST-LABEL: 'v8bf16_select_ole'
-; COST-NEXT: Cost Model: Found costs of RThru:7 CodeSize:1 Lat:1 SizeLat:1 for: %cmp.1 = fcmp ole <8 x bfloat> %a, %b
+; COST-NEXT: Cost Model: Found costs of RThru:7 CodeSize:4 Lat:4 SizeLat:4 for: %cmp.1 = fcmp ole <8 x bfloat> %a, %b
; COST-NEXT: Cost Model: Found costs of RThru:22 CodeSize:1 Lat:1 SizeLat:1 for: %s.1 = select <8 x i1> %cmp.1, <8 x bfloat> %a, <8 x bfloat> %c
; COST-NEXT: Cost Model: Found costs of RThru:0 C...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/144375
More information about the llvm-commits
mailing list