maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[AArch64] Adjust the cost of integer sum reductions 

This changes the cost to (LT.first-1) * cost(add) + 2, where the cost of
an add is assumed to be 1. This brings it inline with the other
reductions.

Differential Revision: https://reviews.llvm.org/D106240
This commit is contained in:
David Green 2021-07-22 18:19:54 +01:00
parent e1bdb57958
commit c9cebda772
5 changed files with 30 additions and 29 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
View File

@ -1966,18 +1966,19 @@ AArch64TTIImpl::getArithmeticReductionCost(unsigned Opcode, VectorType *ValTy,
assert(ISD && "Invalid opcode");
// Horizontal adds can use the 'addv' instruction. We model the cost of these
// instructions as normal vector adds. This is the only arithmetic vector
// reduction operation for which we have an instruction.
// instructions as twice a normal vector add, plus 1 for each legalization
// step (LT.first). This is the only arithmetic vector reduction operation for
// which we have an instruction.
// OR, XOR and AND costs should match the codegen from:
// OR: llvm/test/CodeGen/AArch64/reduce-or.ll
// XOR: llvm/test/CodeGen/AArch64/reduce-xor.ll
// AND: llvm/test/CodeGen/AArch64/reduce-and.ll
static const CostTblEntry CostTblNoPairwise[]{
{ISD::ADD, MVT::v8i8, 1},
{ISD::ADD, MVT::v16i8, 1},
{ISD::ADD, MVT::v4i16, 1},
{ISD::ADD, MVT::v8i16, 1},
{ISD::ADD, MVT::v4i32, 1},
{ISD::ADD, MVT::v8i8, 2},
{ISD::ADD, MVT::v16i8, 2},
{ISD::ADD, MVT::v4i16, 2},
{ISD::ADD, MVT::v8i16, 2},
{ISD::ADD, MVT::v4i32, 2},
{ISD::OR, MVT::v8i8, 15},
{ISD::OR, MVT::v16i8, 17},
{ISD::OR, MVT::v4i16, 7},
@ -2005,7 +2006,7 @@ AArch64TTIImpl::getArithmeticReductionCost(unsigned Opcode, VectorType *ValTy,
break;
case ISD::ADD:
if (const auto *Entry = CostTableLookup(CostTblNoPairwise, ISD, MTy))
return LT.first * Entry->Cost;
return (LT.first - 1) + Entry->Cost;
break;
case ISD::XOR:
case ISD::AND:

24
llvm/test/Analysis/CostModel/AArch64/reduce-add.ll
View File

@ -3,20 +3,20 @@
define void @reduce() {
; CHECK-LABEL: 'reduce'
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1i8 = call i8 @llvm.vector.reduce.add.v1i8(<1 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V3i8 = call i8 @llvm.vector.reduce.add.v3i8(<3 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4i8 = call i8 @llvm.vector.reduce.add.v4i8(<4 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8i8 = call i8 @llvm.vector.reduce.add.v8i8(<8 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V16i8 = call i8 @llvm.vector.reduce.add.v16i8(<16 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V32i8 = call i8 @llvm.vector.reduce.add.v32i8(<32 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V64i8 = call i8 @llvm.vector.reduce.add.v64i8(<64 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1i8 = call i8 @llvm.vector.reduce.add.v1i8(<1 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V3i8 = call i8 @llvm.vector.reduce.add.v3i8(<3 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4i8 = call i8 @llvm.vector.reduce.add.v4i8(<4 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8i8 = call i8 @llvm.vector.reduce.add.v8i8(<8 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16i8 = call i8 @llvm.vector.reduce.add.v16i8(<16 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V32i8 = call i8 @llvm.vector.reduce.add.v32i8(<32 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V64i8 = call i8 @llvm.vector.reduce.add.v64i8(<64 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i16 = call i16 @llvm.vector.reduce.add.v2i16(<2 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4i16 = call i16 @llvm.vector.reduce.add.v4i16(<4 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8i16 = call i16 @llvm.vector.reduce.add.v8i16(<8 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16i16 = call i16 @llvm.vector.reduce.add.v16i16(<16 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4i16 = call i16 @llvm.vector.reduce.add.v4i16(<4 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8i16 = call i16 @llvm.vector.reduce.add.v8i16(<8 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V16i16 = call i16 @llvm.vector.reduce.add.v16i16(<16 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i32 = call i32 @llvm.vector.reduce.add.v2i32(<2 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4i32 = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8i32 = call i32 @llvm.vector.reduce.add.v8i32(<8 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4i32 = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V8i32 = call i32 @llvm.vector.reduce.add.v8i32(<8 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i64 = call i64 @llvm.vector.reduce.add.v2i64(<2 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V4i64 = call i64 @llvm.vector.reduce.add.v4i64(<4 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void

10
llvm/test/Analysis/CostModel/AArch64/vector-reduce.ll
View File

@ -3,7 +3,7 @@
define i8 @add.i8.v8i8(<8 x i8> %v) {
; COST-LABEL: 'add.i8.v8i8'
; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %r = call i8 @llvm.vector.reduce.add.v8i8(<8 x i8> %v)
; COST-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %r = call i8 @llvm.vector.reduce.add.v8i8(<8 x i8> %v)
; COST-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i8 %r
;
%r = call i8 @llvm.vector.reduce.add.v8i8(<8 x i8> %v)
@ -12,7 +12,7 @@ define i8 @add.i8.v8i8(<8 x i8> %v) {
define i8 @add.i8.v16i8(<16 x i8> %v) {
; COST-LABEL: 'add.i8.v16i8'
; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %r = call i8 @llvm.vector.reduce.add.v16i8(<16 x i8> %v)
; COST-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %r = call i8 @llvm.vector.reduce.add.v16i8(<16 x i8> %v)
; COST-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i8 %r
;
%r = call i8 @llvm.vector.reduce.add.v16i8(<16 x i8> %v)
@ -21,7 +21,7 @@ define i8 @add.i8.v16i8(<16 x i8> %v) {
define i16 @add.i16.v4i16(<4 x i16> %v) {
; COST-LABEL: 'add.i16.v4i16'
; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %r = call i16 @llvm.vector.reduce.add.v4i16(<4 x i16> %v)
; COST-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %r = call i16 @llvm.vector.reduce.add.v4i16(<4 x i16> %v)
; COST-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i16 %r
;
%r = call i16 @llvm.vector.reduce.add.v4i16(<4 x i16> %v)
@ -30,7 +30,7 @@ define i16 @add.i16.v4i16(<4 x i16> %v) {
define i16 @add.i16.v8i16(<8 x i16> %v) {
; COST-LABEL: 'add.i16.v8i16'
; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %r = call i16 @llvm.vector.reduce.add.v8i16(<8 x i16> %v)
; COST-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %r = call i16 @llvm.vector.reduce.add.v8i16(<8 x i16> %v)
; COST-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i16 %r
;
%r = call i16 @llvm.vector.reduce.add.v8i16(<8 x i16> %v)
@ -39,7 +39,7 @@ define i16 @add.i16.v8i16(<8 x i16> %v) {
define i32 @add.i32.v4i32(<4 x i32> %v) {
; COST-LABEL: 'add.i32.v4i32'
; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %r = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> %v)
; COST-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %r = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> %v)
; COST-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r
;
%r = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> %v)

2
llvm/test/Transforms/SLPVectorizer/AArch64/gather-cost.ll
View File

@ -10,7 +10,7 @@ target triple = "aarch64--linux-gnu"
; REMARK-LABEL: Function: gather_multiple_use
; REMARK: Args:
; REMARK-NEXT: - String: 'Vectorized horizontal reduction with cost '
; REMARK-NEXT: - Cost: '-7'
; REMARK-NEXT: - Cost: '-6'
;
; REMARK-NOT: Function: gather_load

6
llvm/test/Transforms/SLPVectorizer/AArch64/horizontal.ll
View File

@ -15,7 +15,7 @@ target triple = "aarch64--linux"
; YAML-NEXT: Function: test_select
; YAML-NEXT: Args:
; YAML-NEXT: - String: 'Vectorized horizontal reduction with cost '
; YAML-NEXT: - Cost: '-20'
; YAML-NEXT: - Cost: '-19'
; YAML-NEXT: - String: ' and with tree size '
; YAML-NEXT: - TreeSize: '8'
@ -143,7 +143,7 @@ define i32 @reduction_with_br(i32* noalias nocapture readonly %blk1, i32* noalia
; YAML-NEXT: Function: reduction_with_br
; YAML-NEXT: Args:
; YAML-NEXT: - String: 'Vectorized horizontal reduction with cost '
; YAML-NEXT: - Cost: '-11'
; YAML-NEXT: - Cost: '-10'
; YAML-NEXT: - String: ' and with tree size '
; YAML-NEXT: - TreeSize: '3'
; CHECK-LABEL: @reduction_with_br(
@ -244,7 +244,7 @@ for.end: ; preds = %for.end.loopexit, %
; YAML-NEXT: Function: test_unrolled_select
; YAML-NEXT: Args:
; YAML-NEXT: - String: 'Vectorized horizontal reduction with cost '
; YAML-NEXT: - Cost: '-37'
; YAML-NEXT: - Cost: '-36'
; YAML-NEXT: - String: ' and with tree size '
; YAML-NEXT: - TreeSize: '10'