[llvm] [PowerPC] adjust cost for vector insert/extract with non const index (PR #79092)
Chen Zheng via llvm-commits
llvm-commits at lists.llvm.org
Mon Jan 22 20:17:29 PST 2024
https://github.com/chenzheng1030 created https://github.com/llvm/llvm-project/pull/79092
P9 has vxform `Vector Extract Element Instructions` like `vextuwrx` and P10 has vxform `Vector Insert Element instructions` like `vinsd`. Update the instruction cost reflecting these instructions.
Fixes https://github.com/llvm/llvm-project/issues/50249
>From 60b6553cdf1470b621542614a2f1b0d7ac71ce49 Mon Sep 17 00:00:00 2001
From: Chen Zheng <czhengsz at cn.ibm.com>
Date: Mon, 22 Jan 2024 23:11:21 -0500
Subject: [PATCH] [PowerPC] adjust cost for vector insert/extract with non
const index
---
.../Target/PowerPC/PPCTargetTransformInfo.cpp | 56 +++++++++++--------
.../CostModel/PowerPC/insert_extract.ll | 36 ++++++------
2 files changed, 51 insertions(+), 41 deletions(-)
diff --git a/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.cpp b/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.cpp
index 062b53e24a0d793..4768d0a1ba693e5 100644
--- a/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.cpp
+++ b/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.cpp
@@ -697,34 +697,44 @@ InstructionCost PPCTTIImpl::getVectorInstrCost(unsigned Opcode, Type *Val,
return Cost;
- } else if (Val->getScalarType()->isIntegerTy() && Index != -1U) {
+ } else if (Val->getScalarType()->isIntegerTy()) {
unsigned EltSize = Val->getScalarSizeInBits();
// Computing on 1 bit values requires extra mask or compare operations.
unsigned MaskCost = VecMaskCost && EltSize == 1 ? 1 : 0;
if (ST->hasP9Altivec()) {
- if (ISD == ISD::INSERT_VECTOR_ELT)
- // A move-to VSR and a permute/insert. Assume vector operation cost
- // for both (cost will be 2x on P9).
- return 2 * CostFactor;
-
- // It's an extract. Maybe we can do a cheap move-from VSR.
- unsigned EltSize = Val->getScalarSizeInBits();
- if (EltSize == 64) {
- unsigned MfvsrdIndex = ST->isLittleEndian() ? 1 : 0;
- if (Index == MfvsrdIndex)
- return 1;
- } else if (EltSize == 32) {
- unsigned MfvsrwzIndex = ST->isLittleEndian() ? 2 : 1;
- if (Index == MfvsrwzIndex)
- return 1;
- }
-
- // We need a vector extract (or mfvsrld). Assume vector operation cost.
- // The cost of the load constant for a vector extract is disregarded
- // (invariant, easily schedulable).
- return CostFactor + MaskCost;
+ // P10 has vxform insert which can handle non const index. The MaskCost is
+ // for masking the index.
+ // P9 has insert for const index. A move-to VSR and a permute/insert.
+ // Assume vector operation cost for both (cost will be 2x on P9).
+ if (ISD == ISD::INSERT_VECTOR_ELT) {
+ if (ST->isISA3_1())
+ return CostFactor + MaskCost;
+ else if (Index != -1U)
+ return 2 * CostFactor;
+ } else if (ISD == ISD::EXTRACT_VECTOR_ELT) {
+ // It's an extract. Maybe we can do a cheap move-from VSR.
+ unsigned EltSize = Val->getScalarSizeInBits();
+ if (EltSize == 64) {
+ // FIXME: no need to worry about endian, P9 has both mfvsrd/mfvsrld.
+ unsigned MfvsrdIndex = ST->isLittleEndian() ? 1 : 0;
+ if (Index == MfvsrdIndex)
+ return 1;
+ } else if (EltSize == 32) {
+ unsigned MfvsrwzIndex = ST->isLittleEndian() ? 2 : 1;
+ if (Index == MfvsrwzIndex)
+ return 1;
+
+ // For other indexs like non const, P9 has vxform extract. The
+ // MaskCost is for masking the index.
+ return CostFactor + MaskCost;
+ }
- } else if (ST->hasDirectMove()) {
+ // We need a vector extract (or mfvsrld). Assume vector operation cost.
+ // The cost of the load constant for a vector extract is disregarded
+ // (invariant, easily schedulable).
+ return CostFactor + MaskCost;
+ }
+ } else if (ST->hasDirectMove() && Index != -1U) {
// Assume permute has standard cost.
// Assume move-to/move-from VSR have 2x standard cost.
if (ISD == ISD::INSERT_VECTOR_ELT)
diff --git a/llvm/test/Analysis/CostModel/PowerPC/insert_extract.ll b/llvm/test/Analysis/CostModel/PowerPC/insert_extract.ll
index 607d15790b5f311..512c83f01823770 100644
--- a/llvm/test/Analysis/CostModel/PowerPC/insert_extract.ll
+++ b/llvm/test/Analysis/CostModel/PowerPC/insert_extract.ll
@@ -27,7 +27,7 @@ define i32 @insert(i32 %arg) {
; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; CHECK-P10-LABEL: 'insert'
-; CHECK-P10-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %x = insertelement <4 x i32> undef, i32 %arg, i32 0
+; CHECK-P10-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %x = insertelement <4 x i32> undef, i32 %arg, i32 0
; CHECK-P10-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
%x = insertelement <4 x i32> undef, i32 %arg, i32 0
@@ -109,7 +109,7 @@ define void @test4xi32(<4 x i32> %v1, i32 %x1) {
; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; CHECK-P10-LABEL: 'test4xi32'
-; CHECK-P10-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v2 = insertelement <4 x i32> %v1, i32 %x1, i32 2
+; CHECK-P10-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2 = insertelement <4 x i32> %v1, i32 %x1, i32 2
; CHECK-P10-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%v2 = insertelement <4 x i32> %v1, i32 %x1, i32 2
@@ -239,7 +239,7 @@ define <2 x i64> @insert_i64_x(<2 x i64> %dest, i64 %arg, i32 %idx) {
; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %x
;
; CHECK-P10-LABEL: 'insert_i64_x'
-; CHECK-P10-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %x = insertelement <2 x i64> %dest, i64 %arg, i32 %idx
+; CHECK-P10-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %x = insertelement <2 x i64> %dest, i64 %arg, i32 %idx
; CHECK-P10-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %x
;
%x = insertelement <2 x i64> %dest, i64 %arg, i32 %idx
@@ -264,7 +264,7 @@ define <4 x i32> @insert_i32_x(<4 x i32> %dest, i32 %arg, i32 %idx) {
; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %x
;
; CHECK-P10-LABEL: 'insert_i32_x'
-; CHECK-P10-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %x = insertelement <4 x i32> %dest, i32 %arg, i32 %idx
+; CHECK-P10-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %x = insertelement <4 x i32> %dest, i32 %arg, i32 %idx
; CHECK-P10-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %x
;
%x = insertelement <4 x i32> %dest, i32 %arg, i32 %idx
@@ -289,7 +289,7 @@ define <8 x i16> @insert_i16_x(<8 x i16> %dest, i16 %arg, i32 %idx) {
; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %x
;
; CHECK-P10-LABEL: 'insert_i16_x'
-; CHECK-P10-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %x = insertelement <8 x i16> %dest, i16 %arg, i32 %idx
+; CHECK-P10-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %x = insertelement <8 x i16> %dest, i16 %arg, i32 %idx
; CHECK-P10-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %x
;
%x = insertelement <8 x i16> %dest, i16 %arg, i32 %idx
@@ -314,7 +314,7 @@ define <16 x i8> @insert_i8_x(<16 x i8> %dest, i8 %arg, i32 %idx) {
; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %x
;
; CHECK-P10-LABEL: 'insert_i8_x'
-; CHECK-P10-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %x = insertelement <16 x i8> %dest, i8 %arg, i32 %idx
+; CHECK-P10-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %x = insertelement <16 x i8> %dest, i8 %arg, i32 %idx
; CHECK-P10-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %x
;
%x = insertelement <16 x i8> %dest, i8 %arg, i32 %idx
@@ -331,15 +331,15 @@ define i64 @extract_i64_x(<2 x i64> %arg, i32 %idx) {
; CHECK-P8LE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i64 %x
;
; CHECK-P9BE-LABEL: 'extract_i64_x'
-; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %x = extractelement <2 x i64> %arg, i32 %idx
+; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %x = extractelement <2 x i64> %arg, i32 %idx
; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i64 %x
;
; CHECK-P9LE-LABEL: 'extract_i64_x'
-; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %x = extractelement <2 x i64> %arg, i32 %idx
+; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %x = extractelement <2 x i64> %arg, i32 %idx
; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i64 %x
;
; CHECK-P10-LABEL: 'extract_i64_x'
-; CHECK-P10-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %x = extractelement <2 x i64> %arg, i32 %idx
+; CHECK-P10-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %x = extractelement <2 x i64> %arg, i32 %idx
; CHECK-P10-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i64 %x
;
%x = extractelement <2 x i64> %arg, i32 %idx
@@ -356,15 +356,15 @@ define i32 @extract_i32_x(<4 x i32> %arg, i32 %idx) {
; CHECK-P8LE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %x
;
; CHECK-P9BE-LABEL: 'extract_i32_x'
-; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %x = extractelement <4 x i32> %arg, i32 %idx
+; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %x = extractelement <4 x i32> %arg, i32 %idx
; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %x
;
; CHECK-P9LE-LABEL: 'extract_i32_x'
-; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %x = extractelement <4 x i32> %arg, i32 %idx
+; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %x = extractelement <4 x i32> %arg, i32 %idx
; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %x
;
; CHECK-P10-LABEL: 'extract_i32_x'
-; CHECK-P10-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %x = extractelement <4 x i32> %arg, i32 %idx
+; CHECK-P10-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %x = extractelement <4 x i32> %arg, i32 %idx
; CHECK-P10-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %x
;
%x = extractelement <4 x i32> %arg, i32 %idx
@@ -381,15 +381,15 @@ define i16 @extract_i16_x(<8 x i16> %arg, i32 %idx) {
; CHECK-P8LE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i16 %x
;
; CHECK-P9BE-LABEL: 'extract_i16_x'
-; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %x = extractelement <8 x i16> %arg, i32 %idx
+; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %x = extractelement <8 x i16> %arg, i32 %idx
; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i16 %x
;
; CHECK-P9LE-LABEL: 'extract_i16_x'
-; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %x = extractelement <8 x i16> %arg, i32 %idx
+; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %x = extractelement <8 x i16> %arg, i32 %idx
; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i16 %x
;
; CHECK-P10-LABEL: 'extract_i16_x'
-; CHECK-P10-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %x = extractelement <8 x i16> %arg, i32 %idx
+; CHECK-P10-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %x = extractelement <8 x i16> %arg, i32 %idx
; CHECK-P10-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i16 %x
;
%x = extractelement <8 x i16> %arg, i32 %idx
@@ -406,15 +406,15 @@ define i8 @extract_i8_x(<16 x i8> %arg, i32 %idx) {
; CHECK-P8LE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i8 %x
;
; CHECK-P9BE-LABEL: 'extract_i8_x'
-; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %x = extractelement <16 x i8> %arg, i32 %idx
+; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %x = extractelement <16 x i8> %arg, i32 %idx
; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i8 %x
;
; CHECK-P9LE-LABEL: 'extract_i8_x'
-; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %x = extractelement <16 x i8> %arg, i32 %idx
+; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %x = extractelement <16 x i8> %arg, i32 %idx
; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i8 %x
;
; CHECK-P10-LABEL: 'extract_i8_x'
-; CHECK-P10-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %x = extractelement <16 x i8> %arg, i32 %idx
+; CHECK-P10-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %x = extractelement <16 x i8> %arg, i32 %idx
; CHECK-P10-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i8 %x
;
%x = extractelement <16 x i8> %arg, i32 %idx
More information about the llvm-commits
mailing list