[llvm] 17ebd68 - [AArch64] Fix costs of float vector compare/selects pairs.
Florian Hahn via llvm-commits
llvm-commits at lists.llvm.org
Mon Jan 31 02:18:49 PST 2022
Author: Florian Hahn
Date: 2022-01-31T10:18:29Z
New Revision: 17ebd68ae6941eb8ead8b42e07bedf12a91479cb
URL: https://github.com/llvm/llvm-project/commit/17ebd68ae6941eb8ead8b42e07bedf12a91479cb
DIFF: https://github.com/llvm/llvm-project/commit/17ebd68ae6941eb8ead8b42e07bedf12a91479cb.diff
LOG: [AArch64] Fix costs of float vector compare/selects pairs.
The current cost-model overestimates the cost of vector compares &
selects for ordered floating point compares. This patch fixes that by
extending the existing logic for integer predicates.
Reviewed By: dmgreen
Differential Revision: https://reviews.llvm.org/D118256
Added:
Modified:
llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
llvm/test/Analysis/CostModel/AArch64/vector-select.ll
Removed:
################################################################################
diff --git a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
index a4d666a0a3c29..b2ffdf949d8b1 100644
--- a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
+++ b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
@@ -1886,14 +1886,21 @@ InstructionCost AArch64TTIImpl::getCmpSelInstrCost(unsigned Opcode, Type *ValTy,
m_Value())))
VecPred = CurrentPred;
}
- // Check if we have a compare/select chain that can be lowered using CMxx &
- // BFI pair.
- if (CmpInst::isIntPredicate(VecPred)) {
- static const auto ValidMinMaxTys = {MVT::v8i8, MVT::v16i8, MVT::v4i16,
- MVT::v8i16, MVT::v2i32, MVT::v4i32,
- MVT::v2i64};
+ // Check if we have a compare/select chain that can be lowered using
+ // a (F)CMxx & BFI pair.
+ if (CmpInst::isIntPredicate(VecPred) || VecPred == CmpInst::FCMP_OLE ||
+ VecPred == CmpInst::FCMP_OLT || VecPred == CmpInst::FCMP_OGT ||
+ VecPred == CmpInst::FCMP_OGE || VecPred == CmpInst::FCMP_OEQ ||
+ VecPred == CmpInst::FCMP_UNE) {
+ static const auto ValidMinMaxTys = {
+ MVT::v8i8, MVT::v16i8, MVT::v4i16, MVT::v8i16, MVT::v2i32,
+ MVT::v4i32, MVT::v2i64, MVT::v2f32, MVT::v4f32, MVT::v2f64};
+ static const auto ValidFP16MinMaxTys = {MVT::v4f16, MVT::v8f16};
+
auto LT = TLI->getTypeLegalizationCost(DL, ValTy);
- if (any_of(ValidMinMaxTys, [<](MVT M) { return M == LT.second; }))
+ if (any_of(ValidMinMaxTys, [<](MVT M) { return M == LT.second; }) ||
+ (ST->hasFullFP16() &&
+ any_of(ValidFP16MinMaxTys, [<](MVT M) { return M == LT.second; })))
return LT.first;
}
diff --git a/llvm/test/Analysis/CostModel/AArch64/vector-select.ll b/llvm/test/Analysis/CostModel/AArch64/vector-select.ll
index dcfbc879b27df..04d94acf1296b 100644
--- a/llvm/test/Analysis/CostModel/AArch64/vector-select.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/vector-select.ll
@@ -158,7 +158,7 @@ define <4 x half> @v4f16_select_ogt(<4 x half> %a, <4 x half> %b, <4 x half> %c)
; COST-NOFP16-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %cmp.1 = fcmp ogt <4 x half> %a, %b
; COST-NOFP16-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %s.1 = select <4 x i1> %cmp.1, <4 x half> %a, <4 x half> %c
; COST-FULLFP16-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp ogt <4 x half> %a, %b
-; COST-FULLFP16-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %s.1 = select <4 x i1> %cmp.1, <4 x half> %a, <4 x half> %c
+; COST-FULLFP16-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %s.1 = select <4 x i1> %cmp.1, <4 x half> %a, <4 x half> %c
;
; CODE-LABEL: v4f16_select_ogt
; CODE: bb.0
@@ -176,7 +176,7 @@ define <8 x half> @v8f16_select_ogt(<8 x half> %a, <8 x half> %b, <8 x half> %c)
; COST-NOFP16-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %cmp.1 = fcmp ogt <8 x half> %a, %b
; COST-NOFP16-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %s.1 = select <8 x i1> %cmp.1, <8 x half> %a, <8 x half> %c
; COST-FULLFP16-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp ogt <8 x half> %a, %b
-; COST-FULLFP16-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %s.1 = select <8 x i1> %cmp.1, <8 x half> %a, <8 x half> %c
+; COST-FULLFP16-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %s.1 = select <8 x i1> %cmp.1, <8 x half> %a, <8 x half> %c
;
; CODE-LABEL: v8f16_select_ogt
; CODE: bb.0
@@ -192,7 +192,7 @@ define <8 x half> @v8f16_select_ogt(<8 x half> %a, <8 x half> %b, <8 x half> %c)
define <2 x float> @v2f32_select_ogt(<2 x float> %a, <2 x float> %b, <2 x float> %c) {
; COST-LABEL: v2f32_select_ogt
; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp ogt <2 x float> %a, %b
-; COST-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %s.1 = select <2 x i1> %cmp.1, <2 x float> %a, <2 x float> %c
+; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %s.1 = select <2 x i1> %cmp.1, <2 x float> %a, <2 x float> %c
;
; CODE-LABEL: v2f32_select_ogt
; CODE: bb.0
@@ -208,7 +208,7 @@ define <2 x float> @v2f32_select_ogt(<2 x float> %a, <2 x float> %b, <2 x float>
define <4 x float> @v4f32_select_ogt(<4 x float> %a, <4 x float> %b, <4 x float> %c) {
; COST-LABEL: v4f32_select_ogt
; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp ogt <4 x float> %a, %b
-; COST-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %s.1 = select <4 x i1> %cmp.1, <4 x float> %a, <4 x float> %c
+; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %s.1 = select <4 x i1> %cmp.1, <4 x float> %a, <4 x float> %c
;
; CODE-LABEL: v4f32_select_ogt
; CODE: bb.0
@@ -224,7 +224,7 @@ define <4 x float> @v4f32_select_ogt(<4 x float> %a, <4 x float> %b, <4 x float>
define <2 x double> @v2f64_select_ogt(<2 x double> %a, <2 x double> %b, <2 x double> %c) {
; COST-LABEL: v2f64_select_ogt
; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp ogt <2 x double> %a, %b
-; COST-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %s.1 = select <2 x i1> %cmp.1, <2 x double> %a, <2 x double> %c
+; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %s.1 = select <2 x i1> %cmp.1, <2 x double> %a, <2 x double> %c
;
; CODE-LABEL: v2f64_select_ogt
; CODE: bb.0
@@ -242,7 +242,7 @@ define <4 x half> @v4f16_select_oge(<4 x half> %a, <4 x half> %b, <4 x half> %c)
; COST-NOFP16-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %cmp.1 = fcmp oge <4 x half> %a, %b
; COST-NOFP16-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %s.1 = select <4 x i1> %cmp.1, <4 x half> %a, <4 x half> %c
; COST-FULLFP16-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp oge <4 x half> %a, %b
-; COST-FULLFP16-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %s.1 = select <4 x i1> %cmp.1, <4 x half> %a, <4 x half> %c
+; COST-FULLFP16-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %s.1 = select <4 x i1> %cmp.1, <4 x half> %a, <4 x half> %c
;
; CODE-LABEL: v4f16_select_oge
; CODE: bb.0
@@ -260,7 +260,7 @@ define <8 x half> @v8f16_select_oge(<8 x half> %a, <8 x half> %b, <8 x half> %c)
; COST-NOFP16-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %cmp.1 = fcmp oge <8 x half> %a, %b
; COST-NOFP16-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %s.1 = select <8 x i1> %cmp.1, <8 x half> %a, <8 x half> %c
; COST-FULLFP16-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp oge <8 x half> %a, %b
-; COST-FULLFP16-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %s.1 = select <8 x i1> %cmp.1, <8 x half> %a, <8 x half> %c
+; COST-FULLFP16-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %s.1 = select <8 x i1> %cmp.1, <8 x half> %a, <8 x half> %c
;
; CODE-LABEL: v8f16_select_oge
; CODE: bb.0
@@ -276,7 +276,7 @@ define <8 x half> @v8f16_select_oge(<8 x half> %a, <8 x half> %b, <8 x half> %c)
define <2 x float> @v2f32_select_oge(<2 x float> %a, <2 x float> %b, <2 x float> %c) {
; COST-LABEL: v2f32_select_oge
; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp oge <2 x float> %a, %b
-; COST-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %s.1 = select <2 x i1> %cmp.1, <2 x float> %a, <2 x float> %c
+; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %s.1 = select <2 x i1> %cmp.1, <2 x float> %a, <2 x float> %c
;
; CODE-LABEL: v2f32_select_oge
; CODE: bb.0
@@ -292,7 +292,7 @@ define <2 x float> @v2f32_select_oge(<2 x float> %a, <2 x float> %b, <2 x float>
define <4 x float> @v4f32_select_oge(<4 x float> %a, <4 x float> %b, <4 x float> %c) {
; COST-LABEL: v4f32_select_oge
; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp oge <4 x float> %a, %b
-; COST-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %s.1 = select <4 x i1> %cmp.1, <4 x float> %a, <4 x float> %c
+; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %s.1 = select <4 x i1> %cmp.1, <4 x float> %a, <4 x float> %c
;
; CODE-LABEL: v4f32_select_oge
; CODE: bb.0
@@ -308,7 +308,7 @@ define <4 x float> @v4f32_select_oge(<4 x float> %a, <4 x float> %b, <4 x float>
define <2 x double> @v2f64_select_oge(<2 x double> %a, <2 x double> %b, <2 x double> %c) {
; COST-LABEL: v2f64_select_oge
; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp oge <2 x double> %a, %b
-; COST-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %s.1 = select <2 x i1> %cmp.1, <2 x double> %a, <2 x double> %c
+; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %s.1 = select <2 x i1> %cmp.1, <2 x double> %a, <2 x double> %c
;
; CODE-LABEL: v2f64_select_oge
; CODE: bb.0
@@ -326,7 +326,7 @@ define <4 x half> @v4f16_select_olt(<4 x half> %a, <4 x half> %b, <4 x half> %c)
; COST-NOFP16-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %cmp.1 = fcmp olt <4 x half> %a, %b
; COST-NOFP16-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %s.1 = select <4 x i1> %cmp.1, <4 x half> %a, <4 x half> %c
; COST-FULLFP16-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp olt <4 x half> %a, %b
-; COST-FULLFP16-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %s.1 = select <4 x i1> %cmp.1, <4 x half> %a, <4 x half> %c
+; COST-FULLFP16-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %s.1 = select <4 x i1> %cmp.1, <4 x half> %a, <4 x half> %c
;
; CODE-LABEL: v4f16_select_olt
; CODE: bb.0
@@ -344,7 +344,7 @@ define <8 x half> @v8f16_select_olt(<8 x half> %a, <8 x half> %b, <8 x half> %c)
; COST-NOFP16-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %cmp.1 = fcmp olt <8 x half> %a, %b
; COST-NOFP16-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %s.1 = select <8 x i1> %cmp.1, <8 x half> %a, <8 x half> %c
; COST-FULLFP16-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp olt <8 x half> %a, %b
-; COST-FULLFP16-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %s.1 = select <8 x i1> %cmp.1, <8 x half> %a, <8 x half> %c
+; COST-FULLFP16-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %s.1 = select <8 x i1> %cmp.1, <8 x half> %a, <8 x half> %c
;
; CODE-LABEL: v8f16_select_olt
; CODE: bb.0
@@ -360,7 +360,7 @@ define <8 x half> @v8f16_select_olt(<8 x half> %a, <8 x half> %b, <8 x half> %c)
define <2 x float> @v2f32_select_olt(<2 x float> %a, <2 x float> %b, <2 x float> %c) {
; COST-LABEL: v2f32_select_olt
; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp olt <2 x float> %a, %b
-; COST-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %s.1 = select <2 x i1> %cmp.1, <2 x float> %a, <2 x float> %c
+; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %s.1 = select <2 x i1> %cmp.1, <2 x float> %a, <2 x float> %c
;
; CODE-LABEL: v2f32_select_olt
; CODE: bb.0
@@ -376,7 +376,7 @@ define <2 x float> @v2f32_select_olt(<2 x float> %a, <2 x float> %b, <2 x float>
define <4 x float> @v4f32_select_olt(<4 x float> %a, <4 x float> %b, <4 x float> %c) {
; COST-LABEL: v4f32_select_olt
; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp olt <4 x float> %a, %b
-; COST-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %s.1 = select <4 x i1> %cmp.1, <4 x float> %a, <4 x float> %c
+; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %s.1 = select <4 x i1> %cmp.1, <4 x float> %a, <4 x float> %c
;
; CODE-LABEL: v4f32_select_olt
; CODE: bb.0
@@ -392,7 +392,7 @@ define <4 x float> @v4f32_select_olt(<4 x float> %a, <4 x float> %b, <4 x float>
define <2 x double> @v2f64_select_olt(<2 x double> %a, <2 x double> %b, <2 x double> %c) {
; COST-LABEL: v2f64_select_olt
; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp olt <2 x double> %a, %b
-; COST-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %s.1 = select <2 x i1> %cmp.1, <2 x double> %a, <2 x double> %c
+; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %s.1 = select <2 x i1> %cmp.1, <2 x double> %a, <2 x double> %c
;
; CODE-LABEL: v2f64_select_olt
; CODE: bb.0
@@ -410,7 +410,7 @@ define <4 x half> @v4f16_select_ole(<4 x half> %a, <4 x half> %b, <4 x half> %c)
; COST-NOFP16-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %cmp.1 = fcmp ole <4 x half> %a, %b
; COST-NOFP16-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %s.1 = select <4 x i1> %cmp.1, <4 x half> %a, <4 x half> %c
; COST-FULLFP16-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp ole <4 x half> %a, %b
-; COST-FULLFP16-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %s.1 = select <4 x i1> %cmp.1, <4 x half> %a, <4 x half> %c
+; COST-FULLFP16-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %s.1 = select <4 x i1> %cmp.1, <4 x half> %a, <4 x half> %c
;
; CODE-LABEL: v4f16_select_ole
; CODE: bb.0
@@ -428,7 +428,7 @@ define <8 x half> @v8f16_select_ole(<8 x half> %a, <8 x half> %b, <8 x half> %c)
; COST-NOFP16-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %cmp.1 = fcmp ole <8 x half> %a, %b
; COST-NOFP16-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %s.1 = select <8 x i1> %cmp.1, <8 x half> %a, <8 x half> %c
; COST-FULLFP16-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp ole <8 x half> %a, %b
-; COST-FULLFP16-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %s.1 = select <8 x i1> %cmp.1, <8 x half> %a, <8 x half> %c
+; COST-FULLFP16-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %s.1 = select <8 x i1> %cmp.1, <8 x half> %a, <8 x half> %c
;
; CODE-LABEL: v8f16_select_ole
; CODE: bb.0
@@ -444,7 +444,7 @@ define <8 x half> @v8f16_select_ole(<8 x half> %a, <8 x half> %b, <8 x half> %c)
define <2 x float> @v2f32_select_ole(<2 x float> %a, <2 x float> %b, <2 x float> %c) {
; COST-LABEL: v2f32_select_ole
; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp ole <2 x float> %a, %b
-; COST-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %s.1 = select <2 x i1> %cmp.1, <2 x float> %a, <2 x float> %c
+; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %s.1 = select <2 x i1> %cmp.1, <2 x float> %a, <2 x float> %c
;
; CODE-LABEL: v2f32_select_ole
; CODE: bb.0
@@ -460,7 +460,7 @@ define <2 x float> @v2f32_select_ole(<2 x float> %a, <2 x float> %b, <2 x float>
define <4 x float> @v4f32_select_ole(<4 x float> %a, <4 x float> %b, <4 x float> %c) {
; COST-LABEL: v4f32_select_ole
; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp ole <4 x float> %a, %b
-; COST-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %s.1 = select <4 x i1> %cmp.1, <4 x float> %a, <4 x float> %c
+; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %s.1 = select <4 x i1> %cmp.1, <4 x float> %a, <4 x float> %c
;
; CODE-LABEL: v4f32_select_ole
; CODE: bb.0
@@ -476,7 +476,7 @@ define <4 x float> @v4f32_select_ole(<4 x float> %a, <4 x float> %b, <4 x float>
define <2 x double> @v2f64_select_ole(<2 x double> %a, <2 x double> %b, <2 x double> %c) {
; COST-LABEL: v2f64_select_ole
; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp ole <2 x double> %a, %b
-; COST-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %s.1 = select <2 x i1> %cmp.1, <2 x double> %a, <2 x double> %c
+; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %s.1 = select <2 x i1> %cmp.1, <2 x double> %a, <2 x double> %c
;
; CODE-LABEL: v2f64_select_ole
; CODE: bb.0
@@ -494,7 +494,7 @@ define <4 x half> @v4f16_select_oeq(<4 x half> %a, <4 x half> %b, <4 x half> %c)
; COST-NOFP16-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %cmp.1 = fcmp oeq <4 x half> %a, %b
; COST-NOFP16-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %s.1 = select <4 x i1> %cmp.1, <4 x half> %a, <4 x half> %c
; COST-FULLFP16-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp oeq <4 x half> %a, %b
-; COST-FULLFP16-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %s.1 = select <4 x i1> %cmp.1, <4 x half> %a, <4 x half> %c
+; COST-FULLFP16-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %s.1 = select <4 x i1> %cmp.1, <4 x half> %a, <4 x half> %c
;
; CODE-LABEL: v4f16_select_oeq
; CODE: bb.0
@@ -512,7 +512,7 @@ define <8 x half> @v8f16_select_oeq(<8 x half> %a, <8 x half> %b, <8 x half> %c)
; COST-NOFP16-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %cmp.1 = fcmp oeq <8 x half> %a, %b
; COST-NOFP16-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %s.1 = select <8 x i1> %cmp.1, <8 x half> %a, <8 x half> %c
; COST-FULLFP16-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp oeq <8 x half> %a, %b
-; COST-FULLFP16-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %s.1 = select <8 x i1> %cmp.1, <8 x half> %a, <8 x half> %c
+; COST-FULLFP16-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %s.1 = select <8 x i1> %cmp.1, <8 x half> %a, <8 x half> %c
;
; CODE-LABEL: v8f16_select_oeq
; CODE: bb.0
@@ -528,7 +528,7 @@ define <8 x half> @v8f16_select_oeq(<8 x half> %a, <8 x half> %b, <8 x half> %c)
define <2 x float> @v2f32_select_oeq(<2 x float> %a, <2 x float> %b, <2 x float> %c) {
; COST-LABEL: v2f32_select_oeq
; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp oeq <2 x float> %a, %b
-; COST-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %s.1 = select <2 x i1> %cmp.1, <2 x float> %a, <2 x float> %c
+; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %s.1 = select <2 x i1> %cmp.1, <2 x float> %a, <2 x float> %c
;
; CODE-LABEL: v2f32_select_oeq
; CODE: bb.0
@@ -544,7 +544,7 @@ define <2 x float> @v2f32_select_oeq(<2 x float> %a, <2 x float> %b, <2 x float>
define <4 x float> @v4f32_select_oeq(<4 x float> %a, <4 x float> %b, <4 x float> %c) {
; COST-LABEL: v4f32_select_oeq
; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp oeq <4 x float> %a, %b
-; COST-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %s.1 = select <4 x i1> %cmp.1, <4 x float> %a, <4 x float> %c
+; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %s.1 = select <4 x i1> %cmp.1, <4 x float> %a, <4 x float> %c
;
; CODE-LABEL: v4f32_select_oeq
; CODE: bb.0
@@ -560,7 +560,7 @@ define <4 x float> @v4f32_select_oeq(<4 x float> %a, <4 x float> %b, <4 x float>
define <2 x double> @v2f64_select_oeq(<2 x double> %a, <2 x double> %b, <2 x double> %c) {
; COST-LABEL: v2f64_select_oeq
; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp oeq <2 x double> %a, %b
-; COST-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %s.1 = select <2 x i1> %cmp.1, <2 x double> %a, <2 x double> %c
+; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %s.1 = select <2 x i1> %cmp.1, <2 x double> %a, <2 x double> %c
;
; CODE-LABEL: v2f64_select_oeq
; CODE: bb.0
@@ -672,7 +672,7 @@ define <4 x half> @v4f16_select_une(<4 x half> %a, <4 x half> %b, <4 x half> %c)
; COST-NOFP16-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %cmp.1 = fcmp une <4 x half> %a, %b
; COST-NOFP16-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %s.1 = select <4 x i1> %cmp.1, <4 x half> %a, <4 x half> %c
; COST-FULLFP16-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp une <4 x half> %a, %b
-; COST-FULLFP16-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %s.1 = select <4 x i1> %cmp.1, <4 x half> %a, <4 x half> %c
+; COST-FULLFP16-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %s.1 = select <4 x i1> %cmp.1, <4 x half> %a, <4 x half> %c
;
; CODE-LABEL: v4f16_select_une
; CODE: bb.0
@@ -690,7 +690,7 @@ define <8 x half> @v8f16_select_une(<8 x half> %a, <8 x half> %b, <8 x half> %c)
; COST-NOFP16-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %cmp.1 = fcmp une <8 x half> %a, %b
; COST-NOFP16-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %s.1 = select <8 x i1> %cmp.1, <8 x half> %a, <8 x half> %c
; COST-FULLFP16-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp une <8 x half> %a, %b
-; COST-FULLFP16-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %s.1 = select <8 x i1> %cmp.1, <8 x half> %a, <8 x half> %c
+; COST-FULLFP16-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %s.1 = select <8 x i1> %cmp.1, <8 x half> %a, <8 x half> %c
;
; CODE-LABEL: v8f16_select_une
; CODE: bb.0
@@ -706,7 +706,7 @@ define <8 x half> @v8f16_select_une(<8 x half> %a, <8 x half> %b, <8 x half> %c)
define <2 x float> @v2f32_select_une(<2 x float> %a, <2 x float> %b, <2 x float> %c) {
; COST-LABEL: v2f32_select_une
; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp une <2 x float> %a, %b
-; COST-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %s.1 = select <2 x i1> %cmp.1, <2 x float> %a, <2 x float> %c
+; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %s.1 = select <2 x i1> %cmp.1, <2 x float> %a, <2 x float> %c
;
; CODE-LABEL: v2f32_select_une
; CODE: bb.0
@@ -722,7 +722,7 @@ define <2 x float> @v2f32_select_une(<2 x float> %a, <2 x float> %b, <2 x float>
define <4 x float> @v4f32_select_une(<4 x float> %a, <4 x float> %b, <4 x float> %c) {
; COST-LABEL: v4f32_select_une
; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp une <4 x float> %a, %b
-; COST-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %s.1 = select <4 x i1> %cmp.1, <4 x float> %a, <4 x float> %c
+; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %s.1 = select <4 x i1> %cmp.1, <4 x float> %a, <4 x float> %c
;
; CODE-LABEL: v4f32_select_une
; CODE: bb.0
@@ -738,7 +738,7 @@ define <4 x float> @v4f32_select_une(<4 x float> %a, <4 x float> %b, <4 x float>
define <2 x double> @v2f64_select_une(<2 x double> %a, <2 x double> %b, <2 x double> %c) {
; COST-LABEL: v2f64_select_une
; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp une <2 x double> %a, %b
-; COST-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %s.1 = select <2 x i1> %cmp.1, <2 x double> %a, <2 x double> %c
+; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %s.1 = select <2 x i1> %cmp.1, <2 x double> %a, <2 x double> %c
;
; CODE-LABEL: v2f64_select_une
; CODE: bb.0
More information about the llvm-commits
mailing list