894935cb51
We can stop using a graph representation of the SLP structure and switch
directly to tree by relying on a single user of each tree node. If the
node has multiple uses, other uses must be represented as a separate
gather/buildvector node, which then will be combined with the existing
vectorized node(s) uoon cost estimation/codegen.
This allow to simplify inner structure and turn in some extra
optimizations, which could not be turned on for the nodes with multi
users (reordering, minbitwidth analysis).
AVX512, -O3+LTO
Metric: size..text
results results0 diff
test-suite :: MultiSource/Benchmarks/ASCI_Purple/SMG2000/smg2000.test 253453.00 254253.00 0.3%
test-suite :: External/SPEC/CFP2006/444.namd/444.namd.test 251411.00 252051.00 0.3%
test-suite :: SingleSource/Benchmarks/Misc/oourafft.test 19114.00 19146.00 0.2%
test-suite :: External/SPEC/CFP2017speed/638.imagick_s/638.imagick_s.test 1399200.00 1399520.00 0.0%
test-suite :: External/SPEC/CFP2017rate/538.imagick_r/538.imagick_r.test 1399200.00 1399520.00 0.0%
test-suite :: MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test 304310.00 304326.00 0.0%
test-suite :: MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test 304662.00 304678.00 0.0%
test-suite :: External/SPEC/CFP2017rate/526.blender_r/526.blender_r.test 12566919.00 12567511.00 0.0%
test-suite :: External/SPEC/CFP2006/453.povray/453.povray.test 1146300.00 1146316.00 0.0%
test-suite :: External/SPEC/CFP2017rate/511.povray_r/511.povray_r.test 1159864.00 1159880.00 0.0%
test-suite :: External/SPEC/CINT2017rate/502.gcc_r/502.gcc_r.test 9407880.00 9407864.00 -0.0%
test-suite :: External/SPEC/CINT2017speed/602.gcc_s/602.gcc_s.test 9407880.00 9407864.00 -0.0%
test-suite :: MultiSource/Benchmarks/tramp3d-v4/tramp3d-v4.test 1011612.00 1011596.00 -0.0%
test-suite :: MultiSource/Benchmarks/Prolangs-C/TimberWolfMC/timberwolfmc.test 280584.00 280536.00 -0.0%
test-suite :: MultiSource/Benchmarks/DOE-ProxyApps-C++/miniFE/miniFE.test 93016.00 93000.00 -0.0%
ASCI_Purple/SMG2000 - extra code vectorized, small variations
CFP2006/444.namd - small variations, less shuffles
Benchmarks/Misc/oourafft - small variations
CFP2017rate/538.imagick_r
CFP2017speed/638.imagick_s - small variations, less shuffles
LCALS/SubsetALambdaLoops - less shuffles
LCALS/SubsetARawLoops - less shuffles
CFP2017rate/526.blender_r - small variations, extra vector code
CFP2006/453.povray - small variations
CFP2017rate/511.povray_r - small variations
CINT2017rate/502.gcc_r
CINT2017speed/602.gcc_s - small variations
Benchmarks/tramp3d-v4 - small variations
Prolangs-C/TimberWolfMC - small variations
DOE-ProxyApps-C++/miniFE - extra code vectorized, small variations
DOE-ProxyApps-C++/CLAMR - extra code vectorized, small variations
ASCI_Purple/SMG2000 - no significant changes
RISCV, -O3+LTO
Metric: size..text
results results0 diff
test-suite :: SingleSource/Regression/C/gcc-c-torture/execute/GCC-C-execute-pr28982b.test 1812.00 1866.00 3.0%
test-suite :: MultiSource/Benchmarks/Olden/health/health.test 3946.00 4016.00 1.8%
test-suite :: External/SPEC/CINT2017speed/625.x264_s/625.x264_s.test 513180.00 513550.00 0.1%
test-suite :: External/SPEC/CINT2017rate/525.x264_r/525.x264_r.test 513180.00 513550.00 0.1%
test-suite :: External/SPEC/CINT2017rate/502.gcc_r/502.gcc_r.test 7672198.00 7672202.00 0.0%
test-suite :: External/SPEC/CINT2017speed/602.gcc_s/602.gcc_s.test 7672198.00 7672202.00 0.0%
test-suite :: External/SPEC/CFP2017rate/508.namd_r/508.namd_r.test 746060.00 746044.00 -0.0%
test-suite :: External/SPEC/CFP2017rate/526.blender_r/526.blender_r.test 9497716.00 9497364.00 -0.0%
test-suite :: External/SPEC/CFP2006/453.povray/453.povray.test 948266.00 948214.00 -0.0%
test-suite :: External/SPEC/CFP2006/433.milc/433.milc.test 89874.00 89862.00 -0.0%
test-suite :: MultiSource/Benchmarks/7zip/7zip-benchmark.test 835492.00 835346.00 -0.0%
test-suite :: MultiSource/Benchmarks/DOE-ProxyApps-C++/miniFE/miniFE.test 66230.00 66202.00 -0.0%
test-suite :: External/SPEC/CFP2017rate/511.povray_r/511.povray_r.test 946090.00 944206.00 -0.2%
test-suite :: External/SPEC/CFP2017speed/638.imagick_s/638.imagick_s.test 1136404.00 1131854.00 -0.4%
test-suite :: External/SPEC/CFP2017rate/538.imagick_r/538.imagick_r.test 1136404.00 1131854.00 -0.4%
gcc-c-torture/execute/GCC-C-execute-pr28982b - better vector code
Olden/health - extra vector code
CINT2017speed/625.x264_s
CINT2017rate/525.x264_r - small variation + improvements in reordering, @pixel_hadamard_ac stopped
being vectorized because of some non-effective shuffle recognition by
the compiler
CINT2017rate/502.gcc_r
CINT2017speed/602.gcc_s - small variations
CFP2017rate/508.namd_r - small variations
CFP2017rate/526.blender_r - small variations
CFP2006/453.povray - extra vector code
Benchmarks/7zip - extra vector code
DOE-ProxyApps-C++/miniFE - small variations
CFP2017rate/511.povray_r - extra vector code
CFP2017speed/638.imagick_s
CFP2017rate/538.imagick_r - extra vector code
Reviewers: RKSimon, hiraditya
Reviewed By: RKSimon
Pull Request: https://github.com/llvm/llvm-project/pull/126771
52 lines
2.5 KiB
LLVM
52 lines
2.5 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
|
|
; RUN: opt -S --passes=slp-vectorizer -mtriple=x86_64-unknown-linux-gnu < %s | FileCheck %s
|
|
|
|
define i32 @test(ptr %c, i16 %a, i16 %0) {
|
|
; CHECK-LABEL: define i32 @test(
|
|
; CHECK-SAME: ptr [[C:%.*]], i16 [[A:%.*]], i16 [[TMP0:%.*]]) {
|
|
; CHECK-NEXT: [[ENTRY:.*:]]
|
|
; CHECK-NEXT: [[TMP1:%.*]] = insertelement <4 x i16> poison, i16 [[A]], i32 0
|
|
; CHECK-NEXT: [[TMP2:%.*]] = shufflevector <4 x i16> [[TMP1]], <4 x i16> poison, <4 x i32> zeroinitializer
|
|
; CHECK-NEXT: [[TMP3:%.*]] = icmp ne <4 x i16> [[TMP2]], zeroinitializer
|
|
; CHECK-NEXT: [[TMP16:%.*]] = zext <4 x i1> [[TMP3]] to <4 x i8>
|
|
; CHECK-NEXT: [[TMP5:%.*]] = shufflevector <4 x i16> [[TMP2]], <4 x i16> poison, <2 x i32> <i32 poison, i32 0>
|
|
; CHECK-NEXT: [[TMP6:%.*]] = insertelement <2 x i16> [[TMP5]], i16 [[TMP0]], i32 0
|
|
; CHECK-NEXT: [[TMP7:%.*]] = shufflevector <2 x i16> [[TMP6]], <2 x i16> poison, <4 x i32> <i32 0, i32 0, i32 0, i32 1>
|
|
; CHECK-NEXT: [[TMP4:%.*]] = zext <4 x i8> [[TMP16]] to <4 x i16>
|
|
; CHECK-NEXT: [[TMP8:%.*]] = icmp ugt <4 x i16> [[TMP7]], [[TMP4]]
|
|
; CHECK-NEXT: [[TMP9:%.*]] = icmp ult i16 [[A]], -2
|
|
; CHECK-NEXT: [[TMP10:%.*]] = shufflevector <4 x i1> [[TMP3]], <4 x i1> poison, <8 x i32> <i32 poison, i32 poison, i32 poison, i32 poison, i32 0, i32 1, i32 2, i32 poison>
|
|
; CHECK-NEXT: [[TMP11:%.*]] = insertelement <8 x i1> [[TMP10]], i1 [[TMP9]], i32 7
|
|
; CHECK-NEXT: [[TMP12:%.*]] = call <8 x i1> @llvm.vector.insert.v8i1.v4i1(<8 x i1> [[TMP11]], <4 x i1> [[TMP8]], i64 0)
|
|
; CHECK-NEXT: [[TMP13:%.*]] = freeze <8 x i1> [[TMP12]]
|
|
; CHECK-NEXT: [[TMP14:%.*]] = call i1 @llvm.vector.reduce.and.v8i1(<8 x i1> [[TMP13]])
|
|
; CHECK-NEXT: [[TMP15:%.*]] = zext i1 [[TMP14]] to i32
|
|
; CHECK-NEXT: store i32 [[TMP15]], ptr [[C]], align 4
|
|
; CHECK-NEXT: ret i32 0
|
|
;
|
|
entry:
|
|
%tobool = icmp ne i16 %a, 0
|
|
%1 = zext i1 %tobool to i16
|
|
%cmp3 = icmp ugt i16 %0, %1
|
|
%2 = and i1 %tobool, %cmp3
|
|
%tobool.1 = icmp ne i16 %a, 0
|
|
%3 = zext i1 %tobool.1 to i16
|
|
%cmp3.1 = icmp ugt i16 %0, %3
|
|
%4 = and i1 %tobool.1, %cmp3.1
|
|
%5 = select i1 %2, i1 %4, i1 false
|
|
%tobool.2 = icmp ne i16 %a, 0
|
|
%6 = zext i1 %tobool.2 to i16
|
|
%cmp3.2 = icmp ugt i16 %0, %6
|
|
%7 = and i1 %tobool.2, %cmp3.2
|
|
%8 = select i1 %5, i1 %7, i1 false
|
|
%tobool.3 = icmp ne i16 %a, 0
|
|
%9 = zext i1 %tobool.3 to i16
|
|
%cmp3.3 = icmp ugt i16 %a, %9
|
|
%10 = icmp ult i16 %a, -2
|
|
%11 = and i1 %10, %cmp3.3
|
|
%12 = select i1 %8, i1 %11, i1 false
|
|
%13 = zext i1 %12 to i32
|
|
store i32 %13, ptr %c, align 4
|
|
ret i32 0
|
|
}
|