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

[TTI][X86] update costs of interleaved load\store of i64\double 

This patch contains more accurate cost of interelaved load\store of stride 2 for the types int64\double on AVX2.

Reviewers: delena, RKSimon, craig.topper, dorit

Reviewed By: dorit

Differential Revision: https://reviews.llvm.org/D40008

llvm-svn: 318385
This commit is contained in:
Mohammed Agabaria 2017-11-16 09:38:32 +00:00
parent fe3eda9137
commit 6e6d5326a1
3 changed files with 86 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
llvm/lib/Target/X86/X86TargetTransformInfo.cpp
View File

@ -2647,6 +2647,9 @@ int X86TTIImpl::getInterleavedMemoryOpCostAVX2(unsigned Opcode, Type *VecTy,
// The cost of the loads/stores is accounted for separately.
//
static const CostTblEntry AVX2InterleavedLoadTbl[] = {
{ 2, MVT::v4i64, 6 }, //(load 8i64 and) deinterleave into 2 x 4i64
{ 2, MVT::v4f64, 6 }, //(load 8f64 and) deinterleave into 2 x 4f64
{ 3, MVT::v2i8, 10 }, //(load 6i8 and) deinterleave into 3 x 2i8
{ 3, MVT::v4i8, 4 }, //(load 12i8 and) deinterleave into 3 x 4i8
{ 3, MVT::v8i8, 9 }, //(load 24i8 and) deinterleave into 3 x 8i8
@ -2664,6 +2667,9 @@ int X86TTIImpl::getInterleavedMemoryOpCostAVX2(unsigned Opcode, Type *VecTy,
};
static const CostTblEntry AVX2InterleavedStoreTbl[] = {
{ 2, MVT::v4i64, 6 }, //interleave into 2 x 4i64 into 8i64 (and store)
{ 2, MVT::v4f64, 6 }, //interleave into 2 x 4f64 into 8f64 (and store)
{ 3, MVT::v2i8, 7 }, //interleave 3 x 2i8 into 6i8 (and store)
{ 3, MVT::v4i8, 8 }, //interleave 3 x 4i8 into 12i8 (and store)
{ 3, MVT::v8i8, 11 }, //interleave 3 x 8i8 into 24i8 (and store)

40
llvm/test/Analysis/CostModel/X86/interleaved-load-store-double.ll Normal file
View File

@ -0,0 +1,40 @@
; REQUIRES: asserts
; RUN: opt -S -loop-vectorize -debug-only=loop-vectorize -mcpu=skylake %s 2>&1 | FileCheck %s
target datalayout = "e-m:e-p:32:32-f64:32:64-f80:32-n8:16:32-S128"
target triple = "i386-unknown-linux-gnu"
@doublesrc = common local_unnamed_addr global [120 x double] zeroinitializer, align 4
@doubledst = common local_unnamed_addr global [120 x double] zeroinitializer, align 4
; Function Attrs: norecurse nounwind
define void @stride2double(double %k, i32 %width_) {
entry:
; CHECK: Found an estimated cost of 8 for VF 4 For instruction: %0 = load double
; CHECK: Found an estimated cost of 8 for VF 4 For instruction: store double
%cmp27 = icmp sgt i32 %width_, 0
br i1 %cmp27, label %for.body.lr.ph, label %for.cond.cleanup
for.body.lr.ph: ; preds = %entry
br label %for.body
for.cond.cleanup: ; preds = %for.body, %entry
ret void
for.body: ; preds = %for.body.lr.ph, %for.body
%i.028 = phi i32 [ 0, %for.body.lr.ph ], [ %add16, %for.body ]
%arrayidx = getelementptr inbounds [120 x double], [120 x double]* @doublesrc, i32 0, i32 %i.028
%0 = load double, double* %arrayidx, align 4
%arrayidx2 = getelementptr inbounds [120 x double], [120 x double]* @doubledst, i32 0, i32 %i.028
store double %0, double* %arrayidx2, align 4
%add4 = add nuw nsw i32 %i.028, 1
%arrayidx5 = getelementptr inbounds [120 x double], [120 x double]* @doublesrc, i32 0, i32 %add4
%1 = load double, double* %arrayidx5, align 4
%arrayidx8 = getelementptr inbounds [120 x double], [120 x double]* @doubledst, i32 0, i32 %add4
store double %1, double* %arrayidx8, align 4
%add16 = add nuw nsw i32 %i.028, 2
%cmp = icmp slt i32 %add16, %width_
br i1 %cmp, label %for.body, label %for.cond.cleanup
}

40
llvm/test/Analysis/CostModel/X86/interleaved-load-store-i64.ll Normal file
View File

@ -0,0 +1,40 @@
; REQUIRES: asserts
; RUN: opt -S -loop-vectorize -debug-only=loop-vectorize -mcpu=core-avx2 %s 2>&1 | FileCheck %s
target datalayout = "e-m:e-p:32:32-f64:32:64-f80:32-n8:16:32-S128"
target triple = "i386-unknown-linux-gnu"
@i64src = common local_unnamed_addr global [120 x i64] zeroinitializer, align 4
@i64dst = common local_unnamed_addr global [120 x i64] zeroinitializer, align 4
; Function Attrs: norecurse nounwind
define void @stride2i64(i64 %k, i32 %width_) {
entry:
; CHECK: Found an estimated cost of 8 for VF 4 For instruction: %0 = load i64
; CHECK: Found an estimated cost of 8 for VF 4 For instruction: store i64
%cmp27 = icmp sgt i32 %width_, 0
br i1 %cmp27, label %for.body.lr.ph, label %for.cond.cleanup
for.body.lr.ph: ; preds = %entry
br label %for.body
for.cond.cleanup: ; preds = %for.body, %entry
ret void
for.body:
%i.028 = phi i32 [ 0, %for.body.lr.ph ], [ %add16, %for.body ]
%arrayidx = getelementptr inbounds [120 x i64], [120 x i64]* @i64src, i32 0, i32 %i.028
%0 = load i64, i64* %arrayidx, align 4
%arrayidx2 = getelementptr inbounds [120 x i64], [120 x i64]* @i64dst, i32 0, i32 %i.028
store i64 %0, i64* %arrayidx2, align 4
%add4 = add nuw nsw i32 %i.028, 1
%arrayidx5 = getelementptr inbounds [120 x i64], [120 x i64]* @i64src, i32 0, i32 %add4
%1 = load i64, i64* %arrayidx5, align 4
%arrayidx8 = getelementptr inbounds [120 x i64], [120 x i64]* @i64dst, i32 0, i32 %add4
store i64 %1, i64* %arrayidx8, align 4
%add16 = add nuw nsw i32 %i.028, 2
%cmp = icmp slt i32 %add16, %width_
br i1 %cmp, label %for.body, label %for.cond.cleanup
}