[llvm] 8865ed4 - [RISCV][TTI] Cost SK_Tranpose as a generic two element shuffle
Philip Reames via llvm-commits
llvm-commits at lists.llvm.org
Tue Apr 4 12:53:34 PDT 2023
Author: Philip Reames
Date: 2023-04-04T12:52:50-07:00
New Revision: 8865ed4dbb4e050ba3e7f45996d5c6a9d1e85280
URL: https://github.com/llvm/llvm-project/commit/8865ed4dbb4e050ba3e7f45996d5c6a9d1e85280
DIFF: https://github.com/llvm/llvm-project/commit/8865ed4dbb4e050ba3e7f45996d5c6a9d1e85280.diff
LOG: [RISCV][TTI] Cost SK_Tranpose as a generic two element shuffle
This matches the actual lowering. The previous costing was "as if" it had been fully scalarized.
Added:
Modified:
llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
llvm/test/Analysis/CostModel/RISCV/shuffle-transpose.ll
Removed:
################################################################################
diff --git a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
index 0196a0b9c3bbf..5721df58297e2 100644
--- a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
+++ b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
@@ -304,6 +304,7 @@ InstructionCost RISCVTTIImpl::getShuffleCost(TTI::ShuffleKind Kind,
}
break;
}
+ case TTI::SK_Transpose:
case TTI::SK_PermuteTwoSrc: {
if (Mask.size() >= 2 && LT.second.isFixedLengthVector()) {
// 2 x (vrgather + cost of generating the mask constant) + cost of mask
diff --git a/llvm/test/Analysis/CostModel/RISCV/shuffle-transpose.ll b/llvm/test/Analysis/CostModel/RISCV/shuffle-transpose.ll
index 1263233333fd1..90d71b4cca863 100644
--- a/llvm/test/Analysis/CostModel/RISCV/shuffle-transpose.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/shuffle-transpose.ll
@@ -7,7 +7,7 @@ target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
define <8 x i8> @trn1.v8i8(<8 x i8> %v0, <8 x i8> %v1) {
; CHECK-LABEL: 'trn1.v8i8'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %tmp0 = shufflevector <8 x i8> %v0, <8 x i8> %v1, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %tmp0 = shufflevector <8 x i8> %v0, <8 x i8> %v1, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret <8 x i8> %tmp0
;
%tmp0 = shufflevector <8 x i8> %v0, <8 x i8> %v1, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
@@ -16,7 +16,7 @@ define <8 x i8> @trn1.v8i8(<8 x i8> %v0, <8 x i8> %v1) {
define <8 x i8> @trn2.v8i8(<8 x i8> %v0, <8 x i8> %v1) {
; CHECK-LABEL: 'trn2.v8i8'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %tmp0 = shufflevector <8 x i8> %v0, <8 x i8> %v1, <8 x i32> <i32 1, i32 9, i32 3, i32 11, i32 5, i32 13, i32 7, i32 15>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %tmp0 = shufflevector <8 x i8> %v0, <8 x i8> %v1, <8 x i32> <i32 1, i32 9, i32 3, i32 11, i32 5, i32 13, i32 7, i32 15>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret <8 x i8> %tmp0
;
%tmp0 = shufflevector <8 x i8> %v0, <8 x i8> %v1, <8 x i32> <i32 1, i32 9, i32 3, i32 11, i32 5, i32 13, i32 7, i32 15>
@@ -25,7 +25,7 @@ define <8 x i8> @trn2.v8i8(<8 x i8> %v0, <8 x i8> %v1) {
define <16 x i8> @trn1.v16i8(<16 x i8> %v0, <16 x i8> %v1) {
; CHECK-LABEL: 'trn1.v16i8'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 62 for instruction: %tmp0 = shufflevector <16 x i8> %v0, <16 x i8> %v1, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %tmp0 = shufflevector <16 x i8> %v0, <16 x i8> %v1, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret <16 x i8> %tmp0
;
%tmp0 = shufflevector <16 x i8> %v0, <16 x i8> %v1, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
@@ -34,7 +34,7 @@ define <16 x i8> @trn1.v16i8(<16 x i8> %v0, <16 x i8> %v1) {
define <16 x i8> @trn2.v16i8(<16 x i8> %v0, <16 x i8> %v1) {
; CHECK-LABEL: 'trn2.v16i8'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 62 for instruction: %tmp0 = shufflevector <16 x i8> %v0, <16 x i8> %v1, <16 x i32> <i32 1, i32 17, i32 3, i32 19, i32 5, i32 21, i32 7, i32 23, i32 9, i32 25, i32 11, i32 27, i32 13, i32 29, i32 15, i32 31>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %tmp0 = shufflevector <16 x i8> %v0, <16 x i8> %v1, <16 x i32> <i32 1, i32 17, i32 3, i32 19, i32 5, i32 21, i32 7, i32 23, i32 9, i32 25, i32 11, i32 27, i32 13, i32 29, i32 15, i32 31>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret <16 x i8> %tmp0
;
%tmp0 = shufflevector <16 x i8> %v0, <16 x i8> %v1, <16 x i32> <i32 1, i32 17, i32 3, i32 19, i32 5, i32 21, i32 7, i32 23, i32 9, i32 25, i32 11, i32 27, i32 13, i32 29, i32 15, i32 31>
@@ -43,7 +43,7 @@ define <16 x i8> @trn2.v16i8(<16 x i8> %v0, <16 x i8> %v1) {
define <4 x i16> @trn1.v4i16(<4 x i16> %v0, <4 x i16> %v1) {
; CHECK-LABEL: 'trn1.v4i16'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %tmp0 = shufflevector <4 x i16> %v0, <4 x i16> %v1, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %tmp0 = shufflevector <4 x i16> %v0, <4 x i16> %v1, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret <4 x i16> %tmp0
;
%tmp0 = shufflevector <4 x i16> %v0, <4 x i16> %v1, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
@@ -52,7 +52,7 @@ define <4 x i16> @trn1.v4i16(<4 x i16> %v0, <4 x i16> %v1) {
define <4 x i16> @trn2.v4i16(<4 x i16> %v0, <4 x i16> %v1) {
; CHECK-LABEL: 'trn2.v4i16'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %tmp0 = shufflevector <4 x i16> %v0, <4 x i16> %v1, <4 x i32> <i32 1, i32 5, i32 3, i32 7>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %tmp0 = shufflevector <4 x i16> %v0, <4 x i16> %v1, <4 x i32> <i32 1, i32 5, i32 3, i32 7>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret <4 x i16> %tmp0
;
%tmp0 = shufflevector <4 x i16> %v0, <4 x i16> %v1, <4 x i32> <i32 1, i32 5, i32 3, i32 7>
@@ -61,7 +61,7 @@ define <4 x i16> @trn2.v4i16(<4 x i16> %v0, <4 x i16> %v1) {
define <8 x i16> @trn1.v8i16(<8 x i16> %v0, <8 x i16> %v1) {
; CHECK-LABEL: 'trn1.v8i16'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %tmp0 = shufflevector <8 x i16> %v0, <8 x i16> %v1, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %tmp0 = shufflevector <8 x i16> %v0, <8 x i16> %v1, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret <8 x i16> %tmp0
;
%tmp0 = shufflevector <8 x i16> %v0, <8 x i16> %v1, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
@@ -70,7 +70,7 @@ define <8 x i16> @trn1.v8i16(<8 x i16> %v0, <8 x i16> %v1) {
define <8 x i16> @trn2.v8i16(<8 x i16> %v0, <8 x i16> %v1) {
; CHECK-LABEL: 'trn2.v8i16'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %tmp0 = shufflevector <8 x i16> %v0, <8 x i16> %v1, <8 x i32> <i32 1, i32 9, i32 3, i32 11, i32 5, i32 13, i32 7, i32 15>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %tmp0 = shufflevector <8 x i16> %v0, <8 x i16> %v1, <8 x i32> <i32 1, i32 9, i32 3, i32 11, i32 5, i32 13, i32 7, i32 15>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret <8 x i16> %tmp0
;
%tmp0 = shufflevector <8 x i16> %v0, <8 x i16> %v1, <8 x i32> <i32 1, i32 9, i32 3, i32 11, i32 5, i32 13, i32 7, i32 15>
@@ -79,7 +79,7 @@ define <8 x i16> @trn2.v8i16(<8 x i16> %v0, <8 x i16> %v1) {
define <2 x i32> @trn1.v2i32(<2 x i32> %v0, <2 x i32> %v1) {
; CHECK-LABEL: 'trn1.v2i32'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %tmp0 = shufflevector <2 x i32> %v0, <2 x i32> %v1, <2 x i32> <i32 0, i32 2>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %tmp0 = shufflevector <2 x i32> %v0, <2 x i32> %v1, <2 x i32> <i32 0, i32 2>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret <2 x i32> %tmp0
;
%tmp0 = shufflevector <2 x i32> %v0, <2 x i32> %v1, <2 x i32> <i32 0, i32 2>
@@ -88,7 +88,7 @@ define <2 x i32> @trn1.v2i32(<2 x i32> %v0, <2 x i32> %v1) {
define <2 x i32> @trn2.v2i32(<2 x i32> %v0, <2 x i32> %v1) {
; CHECK-LABEL: 'trn2.v2i32'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %tmp0 = shufflevector <2 x i32> %v0, <2 x i32> %v1, <2 x i32> <i32 1, i32 3>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %tmp0 = shufflevector <2 x i32> %v0, <2 x i32> %v1, <2 x i32> <i32 1, i32 3>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret <2 x i32> %tmp0
;
%tmp0 = shufflevector <2 x i32> %v0, <2 x i32> %v1, <2 x i32> <i32 1, i32 3>
@@ -97,7 +97,7 @@ define <2 x i32> @trn2.v2i32(<2 x i32> %v0, <2 x i32> %v1) {
define <4 x i32> @trn1.v4i32(<4 x i32> %v0, <4 x i32> %v1) {
; CHECK-LABEL: 'trn1.v4i32'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %tmp0 = shufflevector <4 x i32> %v0, <4 x i32> %v1, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %tmp0 = shufflevector <4 x i32> %v0, <4 x i32> %v1, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret <4 x i32> %tmp0
;
%tmp0 = shufflevector <4 x i32> %v0, <4 x i32> %v1, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
@@ -106,7 +106,7 @@ define <4 x i32> @trn1.v4i32(<4 x i32> %v0, <4 x i32> %v1) {
define <4 x i32> @trn2.v4i32(<4 x i32> %v0, <4 x i32> %v1) {
; CHECK-LABEL: 'trn2.v4i32'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %tmp0 = shufflevector <4 x i32> %v0, <4 x i32> %v1, <4 x i32> <i32 1, i32 5, i32 3, i32 7>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %tmp0 = shufflevector <4 x i32> %v0, <4 x i32> %v1, <4 x i32> <i32 1, i32 5, i32 3, i32 7>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret <4 x i32> %tmp0
;
%tmp0 = shufflevector <4 x i32> %v0, <4 x i32> %v1, <4 x i32> <i32 1, i32 5, i32 3, i32 7>
@@ -115,7 +115,7 @@ define <4 x i32> @trn2.v4i32(<4 x i32> %v0, <4 x i32> %v1) {
define <2 x i64> @trn1.v2i64(<2 x i64> %v0, <2 x i64> %v1) {
; CHECK-LABEL: 'trn1.v2i64'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %tmp0 = shufflevector <2 x i64> %v0, <2 x i64> %v1, <2 x i32> <i32 0, i32 2>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %tmp0 = shufflevector <2 x i64> %v0, <2 x i64> %v1, <2 x i32> <i32 0, i32 2>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret <2 x i64> %tmp0
;
%tmp0 = shufflevector <2 x i64> %v0, <2 x i64> %v1, <2 x i32> <i32 0, i32 2>
@@ -124,7 +124,7 @@ define <2 x i64> @trn1.v2i64(<2 x i64> %v0, <2 x i64> %v1) {
define <2 x i64> @trn2.v2i64(<2 x i64> %v0, <2 x i64> %v1) {
; CHECK-LABEL: 'trn2.v2i64'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %tmp0 = shufflevector <2 x i64> %v0, <2 x i64> %v1, <2 x i32> <i32 1, i32 3>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %tmp0 = shufflevector <2 x i64> %v0, <2 x i64> %v1, <2 x i32> <i32 1, i32 3>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret <2 x i64> %tmp0
;
%tmp0 = shufflevector <2 x i64> %v0, <2 x i64> %v1, <2 x i32> <i32 1, i32 3>
@@ -133,7 +133,7 @@ define <2 x i64> @trn2.v2i64(<2 x i64> %v0, <2 x i64> %v1) {
define <2 x float> @trn1.v2f32(<2 x float> %v0, <2 x float> %v1) {
; CHECK-LABEL: 'trn1.v2f32'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %tmp0 = shufflevector <2 x float> %v0, <2 x float> %v1, <2 x i32> <i32 0, i32 2>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %tmp0 = shufflevector <2 x float> %v0, <2 x float> %v1, <2 x i32> <i32 0, i32 2>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret <2 x float> %tmp0
;
%tmp0 = shufflevector <2 x float> %v0, <2 x float> %v1, <2 x i32> <i32 0, i32 2>
@@ -142,7 +142,7 @@ define <2 x float> @trn1.v2f32(<2 x float> %v0, <2 x float> %v1) {
define <2 x float> @trn2.v2f32(<2 x float> %v0, <2 x float> %v1) {
; CHECK-LABEL: 'trn2.v2f32'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %tmp0 = shufflevector <2 x float> %v0, <2 x float> %v1, <2 x i32> <i32 1, i32 3>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %tmp0 = shufflevector <2 x float> %v0, <2 x float> %v1, <2 x i32> <i32 1, i32 3>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret <2 x float> %tmp0
;
%tmp0 = shufflevector <2 x float> %v0, <2 x float> %v1, <2 x i32> <i32 1, i32 3>
@@ -151,7 +151,7 @@ define <2 x float> @trn2.v2f32(<2 x float> %v0, <2 x float> %v1) {
define <4 x float> @trn1.v4f32(<4 x float> %v0, <4 x float> %v1) {
; CHECK-LABEL: 'trn1.v4f32'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %tmp0 = shufflevector <4 x float> %v0, <4 x float> %v1, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %tmp0 = shufflevector <4 x float> %v0, <4 x float> %v1, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret <4 x float> %tmp0
;
%tmp0 = shufflevector <4 x float> %v0, <4 x float> %v1, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
@@ -160,7 +160,7 @@ define <4 x float> @trn1.v4f32(<4 x float> %v0, <4 x float> %v1) {
define <4 x float> @trn2.v4f32(<4 x float> %v0, <4 x float> %v1) {
; CHECK-LABEL: 'trn2.v4f32'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %tmp0 = shufflevector <4 x float> %v0, <4 x float> %v1, <4 x i32> <i32 1, i32 5, i32 3, i32 7>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %tmp0 = shufflevector <4 x float> %v0, <4 x float> %v1, <4 x i32> <i32 1, i32 5, i32 3, i32 7>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret <4 x float> %tmp0
;
%tmp0 = shufflevector <4 x float> %v0, <4 x float> %v1, <4 x i32> <i32 1, i32 5, i32 3, i32 7>
@@ -169,7 +169,7 @@ define <4 x float> @trn2.v4f32(<4 x float> %v0, <4 x float> %v1) {
define <2 x double> @trn1.v2f64(<2 x double> %v0, <2 x double> %v1) {
; CHECK-LABEL: 'trn1.v2f64'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %tmp0 = shufflevector <2 x double> %v0, <2 x double> %v1, <2 x i32> <i32 0, i32 2>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %tmp0 = shufflevector <2 x double> %v0, <2 x double> %v1, <2 x i32> <i32 0, i32 2>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret <2 x double> %tmp0
;
%tmp0 = shufflevector <2 x double> %v0, <2 x double> %v1, <2 x i32> <i32 0, i32 2>
@@ -178,7 +178,7 @@ define <2 x double> @trn1.v2f64(<2 x double> %v0, <2 x double> %v1) {
define <2 x double> @trn2.v2f64(<2 x double> %v0, <2 x double> %v1) {
; CHECK-LABEL: 'trn2.v2f64'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %tmp0 = shufflevector <2 x double> %v0, <2 x double> %v1, <2 x i32> <i32 1, i32 3>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %tmp0 = shufflevector <2 x double> %v0, <2 x double> %v1, <2 x i32> <i32 1, i32 3>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret <2 x double> %tmp0
;
%tmp0 = shufflevector <2 x double> %v0, <2 x double> %v1, <2 x i32> <i32 1, i32 3>
@@ -187,7 +187,7 @@ define <2 x double> @trn2.v2f64(<2 x double> %v0, <2 x double> %v1) {
define <4 x half> @trn1.v4f16(<4 x half> %v0, <4 x half> %v1) {
; CHECK-LABEL: 'trn1.v4f16'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %tmp0 = shufflevector <4 x half> %v0, <4 x half> %v1, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %tmp0 = shufflevector <4 x half> %v0, <4 x half> %v1, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret <4 x half> %tmp0
;
%tmp0 = shufflevector <4 x half> %v0, <4 x half> %v1, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
@@ -196,7 +196,7 @@ define <4 x half> @trn1.v4f16(<4 x half> %v0, <4 x half> %v1) {
define <4 x half> @trn2.v4f16(<4 x half> %v0, <4 x half> %v1) {
; CHECK-LABEL: 'trn2.v4f16'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %tmp0 = shufflevector <4 x half> %v0, <4 x half> %v1, <4 x i32> <i32 1, i32 5, i32 3, i32 7>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %tmp0 = shufflevector <4 x half> %v0, <4 x half> %v1, <4 x i32> <i32 1, i32 5, i32 3, i32 7>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret <4 x half> %tmp0
;
%tmp0 = shufflevector <4 x half> %v0, <4 x half> %v1, <4 x i32> <i32 1, i32 5, i32 3, i32 7>
@@ -205,7 +205,7 @@ define <4 x half> @trn2.v4f16(<4 x half> %v0, <4 x half> %v1) {
define <8 x half> @trn1.v8f16(<8 x half> %v0, <8 x half> %v1) {
; CHECK-LABEL: 'trn1.v8f16'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %tmp0 = shufflevector <8 x half> %v0, <8 x half> %v1, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %tmp0 = shufflevector <8 x half> %v0, <8 x half> %v1, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret <8 x half> %tmp0
;
%tmp0 = shufflevector <8 x half> %v0, <8 x half> %v1, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
@@ -214,7 +214,7 @@ define <8 x half> @trn1.v8f16(<8 x half> %v0, <8 x half> %v1) {
define <8 x half> @trn2.v8f16(<8 x half> %v0, <8 x half> %v1) {
; CHECK-LABEL: 'trn2.v8f16'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %tmp0 = shufflevector <8 x half> %v0, <8 x half> %v1, <8 x i32> <i32 1, i32 9, i32 3, i32 11, i32 5, i32 13, i32 7, i32 15>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %tmp0 = shufflevector <8 x half> %v0, <8 x half> %v1, <8 x i32> <i32 1, i32 9, i32 3, i32 11, i32 5, i32 13, i32 7, i32 15>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret <8 x half> %tmp0
;
%tmp0 = shufflevector <8 x half> %v0, <8 x half> %v1, <8 x i32> <i32 1, i32 9, i32 3, i32 11, i32 5, i32 13, i32 7, i32 15>
More information about the llvm-commits
mailing list