07d284d4eb
Adds cost estimation for the variants of the permutations of the scalar
values, used in gather nodes. Currently, SLP just unconditionally emits
shuffles for the reused buildvectors, but in some cases better to leave
them as buildvectors rather than shuffles, if the cost of such
buildvectors is better.
X86, AVX512, -O3+LTO
Metric: size..text
Program size..text
results results0 diff
test-suite :: External/SPEC/CINT2006/445.gobmk/445.gobmk.test 912998.00 913238.00 0.0%
test-suite :: MultiSource/Benchmarks/MiBench/consumer-lame/consumer-lame.test 203070.00 203102.00 0.0%
test-suite :: External/SPEC/CFP2017speed/638.imagick_s/638.imagick_s.test 1396320.00 1396448.00 0.0%
test-suite :: External/SPEC/CFP2017rate/538.imagick_r/538.imagick_r.test 1396320.00 1396448.00 0.0%
test-suite :: MultiSource/Benchmarks/Bullet/bullet.test 309790.00 309678.00 -0.0%
test-suite :: External/SPEC/CFP2017rate/526.blender_r/526.blender_r.test 12477607.00 12470807.00 -0.1%
CINT2006/445.gobmk - extra code vectorized
MiBench/consumer-lame - small variations
CFP2017speed/638.imagick_s
CFP2017rate/538.imagick_r - extra vectorized code
Benchmarks/Bullet - extra code vectorized
CFP2017rate/526.blender_r - extra vector code
RISC-V, sifive-p670, -O3+LTO
CFP2006/433.milc - regressions, should be fixed by https://github.com/llvm/llvm-project/pull/115173
CFP2006/453.povray - extra vectorized code
CFP2017rate/508.namd_r - better vector code
CFP2017rate/510.parest_r - extra vectorized code
SPEC/CFP2017rate - extra/better vector code
CFP2017rate/526.blender_r - extra vectorized code
CFP2017rate/538.imagick_r - extra vectorized code
CINT2006/403.gcc - extra vectorized code
CINT2006/445.gobmk - extra vectorized code
CINT2006/464.h264ref - extra vectorized code
CINT2006/483.xalancbmk - small variations
CINT2017rate/525.x264_r - better vectorization
Reviewers: RKSimon
Reviewed By: RKSimon
Pull Request: https://github.com/llvm/llvm-project/pull/115201
68 lines
3.0 KiB
LLVM
68 lines
3.0 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: %if aarch64-registered-target %{ opt < %s -mtriple=aarch64-unknown-linux-gnu -passes=slp-vectorizer -S -slp-threshold=-1000 | FileCheck %s %}
|
|
; RUN: %if x86-registered-target %{ opt < %s -mtriple=x86_64-unknown -passes=slp-vectorizer -S -slp-threshold=-1000 | FileCheck %s %}
|
|
|
|
define void @test() {
|
|
; CHECK-LABEL: @test(
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: [[CALL37:%.*]] = load i16, ptr poison, align 2
|
|
; CHECK-NEXT: br label [[BB:%.*]]
|
|
; CHECK: bb:
|
|
; CHECK-NEXT: [[CALL:%.*]] = load i16, ptr poison, align 2
|
|
; CHECK-NEXT: [[TMP0:%.*]] = insertelement <8 x i16> <i16 0, i16 0, i16 0, i16 poison, i16 poison, i16 poison, i16 0, i16 poison>, i16 [[CALL37]], i32 3
|
|
; CHECK-NEXT: [[TMP1:%.*]] = insertelement <8 x i16> [[TMP0]], i16 [[CALL]], i32 5
|
|
; CHECK-NEXT: [[TMP2:%.*]] = shufflevector <8 x i16> [[TMP1]], <8 x i16> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 3, i32 5, i32 6, i32 3>
|
|
; CHECK-NEXT: [[TMP5:%.*]] = insertelement <8 x i16> <i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 poison, i16 poison>, i16 [[CALL37]], i32 6
|
|
; CHECK-NEXT: [[TMP3:%.*]] = insertelement <8 x i16> [[TMP5]], i16 [[CALL]], i32 7
|
|
; CHECK-NEXT: [[TMP4:%.*]] = icmp slt <8 x i16> [[TMP2]], [[TMP3]]
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
%call37 = load i16, ptr poison, align 2
|
|
br label %bb
|
|
|
|
bb:
|
|
%call = load i16, ptr poison, align 2
|
|
%0 = icmp slt i16 %call, 0
|
|
%1 = icmp slt i16 %call37, %call
|
|
%.not = icmp sgt i16 0, %call37
|
|
%2 = icmp sgt i16 %call37, 0
|
|
%3 = icmp slt i16 0, 0
|
|
%.not206 = icmp sgt i16 0, %call37
|
|
%4 = icmp sgt i16 0, 0
|
|
%5 = icmp slt i16 0, 0
|
|
ret void
|
|
}
|
|
|
|
define void @test1() {
|
|
; CHECK-LABEL: @test1(
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: [[CALL:%.*]] = load i16, ptr poison, align 2
|
|
; CHECK-NEXT: br label [[BB:%.*]]
|
|
; CHECK: bb:
|
|
; CHECK-NEXT: [[CALL37:%.*]] = load i16, ptr poison, align 2
|
|
; CHECK-NEXT: [[TMP0:%.*]] = insertelement <8 x i16> <i16 0, i16 0, i16 0, i16 poison, i16 poison, i16 poison, i16 poison, i16 0>, i16 [[CALL]], i32 3
|
|
; CHECK-NEXT: [[TMP1:%.*]] = insertelement <8 x i16> [[TMP0]], i16 [[CALL37]], i32 4
|
|
; CHECK-NEXT: [[TMP2:%.*]] = shufflevector <8 x i16> [[TMP1]], <8 x i16> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 4, i32 4, i32 7>
|
|
; CHECK-NEXT: [[TMP5:%.*]] = insertelement <8 x i16> <i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 poison, i16 poison>, i16 [[CALL]], i32 6
|
|
; CHECK-NEXT: [[TMP3:%.*]] = insertelement <8 x i16> [[TMP5]], i16 [[CALL37]], i32 7
|
|
; CHECK-NEXT: [[TMP4:%.*]] = icmp slt <8 x i16> [[TMP2]], [[TMP3]]
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
%call = load i16, ptr poison, align 2
|
|
br label %bb
|
|
|
|
bb:
|
|
%call37 = load i16, ptr poison, align 2
|
|
%0 = icmp slt i16 %call, 0
|
|
%1 = icmp slt i16 %call37, %call
|
|
%.not = icmp sgt i16 0, %call37
|
|
%2 = icmp sgt i16 %call37, 0
|
|
%3 = icmp slt i16 0, 0
|
|
%.not206 = icmp sgt i16 0, %call37
|
|
%4 = icmp sgt i16 0, 0
|
|
%5 = icmp slt i16 0, 0
|
|
ret void
|
|
}
|