RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2025-03-01 16:59:14 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

[ThinLTO] Pass CodeGenOpts like UnrollLoops/VectorizeLoop/VectorizeSLP

Browse Source 
down to pass builder in ltobackend.

Currently CodeGenOpts like UnrollLoops/VectorizeLoop/VectorizeSLP in clang
are not passed down to pass builder in ltobackend when new pass manager is
used. This is inconsistent with the behavior when new pass manager is used
and thinlto is not used. Such inconsistency causes slp vectorization pass
not being enabled in ltobackend for O3 + thinlto right now. This patch
fixes that.

Differential Revision: https://reviews.llvm.org/D72386
This commit is contained in:
Wei Mi 2020-01-09 20:58:31 -08:00
parent 88236fd641
commit a2a8575704
10 changed files with 153 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
include/llvm/LTO/Config.h
View File

@ -18,6 +18,7 @@
#include "llvm/IR/DiagnosticInfo.h"
#include "llvm/IR/GlobalValue.h"
#include "llvm/IR/LLVMContext.h"
#include "llvm/Passes/PassBuilder.h"
#include "llvm/Support/CodeGen.h"
#include "llvm/Target/TargetOptions.h"
@ -128,6 +129,9 @@ struct Config {
/// with llvm-lto2.
std::unique_ptr<raw_ostream> ResolutionFile;
/// Tunable parameters for passes in the default pipelines.
PipelineTuningOptions PTO;
/// The following callbacks deal with tasks, which normally represent the
/// entire optimization and code generation pipeline for what will become a
/// single native object file. Each task has a unique identifier between 0 and

2
lib/LTO/LTOBackend.cpp
View File

@ -172,7 +172,7 @@ static void runNewPMPasses(Config &Conf, Module &Mod, TargetMachine *TM,
PassInstrumentationCallbacks PIC;
StandardInstrumentations SI;
SI.registerCallbacks(PIC);
PassBuilder PB(TM, PipelineTuningOptions(),PGOOpt, &PIC);
PassBuilder PB(TM, Conf.PTO, PGOOpt, &PIC);
AAManager AA;
// Parse a custom AA pipeline if asked to.

6
lib/Passes/PassBuilder.cpp
View File

@ -1902,6 +1902,12 @@ Error PassBuilder::parseModulePass(ModulePassManager &MPM,
return Error::success();
}
// This is consistent with old pass manager invoked via opt, but
// inconsistent with clang. Clang doesn't enable loop vectorization
// but does enable slp vectorization at Oz.
PTO.LoopVectorization = L > O1 && L < Oz;
PTO.SLPVectorization = L > O1 && L < Oz;
if (Matches[1] == "default") {
MPM.addPass(buildPerModuleDefaultPipeline(L, DebugLogging));
} else if (Matches[1] == "thinlto-pre-link") {

3
test/Other/new-pm-defaults.ll
View File

@ -251,6 +251,9 @@
; CHECK-O-NEXT: Running analysis: LoopAccessAnalysis
; CHECK-O-NEXT: Running pass: InstCombinePass
; CHECK-O-NEXT: Running pass: SimplifyCFGPass
; CHECK-O2-NEXT: Running pass: SLPVectorizerPass
; CHECK-O3-NEXT: Running pass: SLPVectorizerPass
; CHECK-Os-NEXT: Running pass: SLPVectorizerPass
; CHECK-O-NEXT: Running pass: InstCombinePass
; CHECK-O-NEXT: Running pass: LoopUnrollPass
; CHECK-O-NEXT: Running pass: WarnMissedTransformationsPass

3
test/Other/new-pm-thinlto-defaults.ll
View File

@ -221,6 +221,9 @@
; CHECK-POSTLINK-O-NEXT: Running analysis: LoopAccessAnalysis
; CHECK-POSTLINK-O-NEXT: Running pass: InstCombinePass
; CHECK-POSTLINK-O-NEXT: Running pass: SimplifyCFGPass
; CHECK-POSTLINK-O2-NEXT: Running pass: SLPVectorizerPass
; CHECK-POSTLINK-O3-NEXT: Running pass: SLPVectorizerPass
; CHECK-POSTLINK-Os-NEXT: Running pass: SLPVectorizerPass
; CHECK-POSTLINK-O-NEXT: Running pass: InstCombinePass
; CHECK-POSTLINK-O-NEXT: Running pass: LoopUnrollPass
; CHECK-POSTLINK-O-NEXT: Running pass: WarnMissedTransformationsPass

79
test/tools/gold/X86/slp-vectorize-pm.ll Normal file
View File

@ -0,0 +1,79 @@
; RUN: opt -module-summary %s -o %t.o
; Test SLP and Loop Vectorization are enabled by default at O2 and O3.
; RUN: %gold -m elf_x86_64 -plugin %llvmshlibdir/LLVMgold%shlibext \
; RUN: --plugin-opt=thinlto \
; RUN: --plugin-opt=new-pass-manager \
; RUN: --plugin-opt=debug-pass-manager \
; RUN: --plugin-opt=cache-dir=%t.cache \
; RUN: --plugin-opt=O0 \
; RUN: --plugin-opt=save-temps \
; RUN: -shared \
; RUN: -o %t2.o %t.o 2>&1 | FileCheck %s --check-prefix=CHECK-O0-SLP
; RUN: llvm-dis %t.o.4.opt.bc -o - | FileCheck %s --check-prefix=CHECK-O0-LPV
; RUN: %gold -m elf_x86_64 -plugin %llvmshlibdir/LLVMgold%shlibext \
; RUN: --plugin-opt=thinlto \
; RUN: --plugin-opt=new-pass-manager \
; RUN: --plugin-opt=debug-pass-manager \
; RUN: --plugin-opt=cache-dir=%t.cache \
; RUN: --plugin-opt=O1 \
; RUN: --plugin-opt=save-temps \
; RUN: -shared \
; RUN: -o %t3.o %t.o 2>&1 | FileCheck %s --check-prefix=CHECK-O1-SLP
; RUN: llvm-dis %t.o.4.opt.bc -o - | FileCheck %s --check-prefix=CHECK-O1-LPV
; RUN: %gold -m elf_x86_64 -plugin %llvmshlibdir/LLVMgold%shlibext \
; RUN: --plugin-opt=thinlto \
; RUN: --plugin-opt=new-pass-manager \
; RUN: --plugin-opt=debug-pass-manager \
; RUN: --plugin-opt=cache-dir=%t.cache \
; RUN: --plugin-opt=O2 \
; RUN: --plugin-opt=save-temps \
; RUN: -shared \
; RUN: -o %t4.o %t.o 2>&1 | FileCheck %s --check-prefix=CHECK-O2-SLP
; RUN: llvm-dis %t.o.4.opt.bc -o - | FileCheck %s --check-prefix=CHECK-O2-LPV
; RUN: %gold -m elf_x86_64 -plugin %llvmshlibdir/LLVMgold%shlibext \
; RUN: --plugin-opt=thinlto \
; RUN: --plugin-opt=new-pass-manager \
; RUN: --plugin-opt=debug-pass-manager \
; RUN: --plugin-opt=cache-dir=%t.cache \
; RUN: --plugin-opt=O3 \
; RUN: --plugin-opt=save-temps \
; RUN: -shared \
; RUN: -o %t5.o %t.o 2>&1 | FileCheck %s --check-prefix=CHECK-O3-SLP
; RUN: llvm-dis %t.o.4.opt.bc -o - | FileCheck %s --check-prefix=CHECK-O3-LPV
; CHECK-O0-SLP-NOT: Running pass: SLPVectorizerPass
; CHECK-O1-SLP-NOT: Running pass: SLPVectorizerPass
; CHECK-O2-SLP: Running pass: SLPVectorizerPass
; CHECK-O3-SLP: Running pass: SLPVectorizerPass
; CHECK-O0-LPV-NOT: = !{!"llvm.loop.isvectorized", i32 1}
; CHECK-O1-LPV-NOT: = !{!"llvm.loop.isvectorized", i32 1}
; CHECK-O2-LPV: = !{!"llvm.loop.isvectorized", i32 1}
; CHECK-O3-LPV: = !{!"llvm.loop.isvectorized", i32 1}
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"
define i32 @foo(i32* %a) {
entry:
br label %for.body
for.body:
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
%red.05 = phi i32 [ 0, %entry ], [ %add, %for.body ]
%arrayidx = getelementptr inbounds i32, i32* %a, i64 %indvars.iv
%0 = load i32, i32* %arrayidx, align 4
%add = add nsw i32 %0, %red.05
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond = icmp eq i64 %indvars.iv.next, 255
br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !0
for.end:
ret i32 %add
}
!0 = distinct !{!0, !1}
!1 = !{!"llvm.loop.unroll.disable", i1 true}

51
test/tools/llvm-lto2/X86/slp-vectorize-pm.ll Normal file
View File

@ -0,0 +1,51 @@
; RUN: opt -module-summary %s -o %t1.bc
; Test SLP and Loop Vectorization are enabled by default at O2 and O3.
; RUN: llvm-lto2 run %t1.bc -o %t2.o -O0 -r %t1.bc,foo,plx -debug-pass-manager \
; RUN: -use-new-pm -save-temps 2>&1 | FileCheck %s --check-prefix=CHECK-O0-SLP
; RUN: llvm-dis %t2.o.1.4.opt.bc -o - | FileCheck %s --check-prefix=CHECK-O0-LPV
; RUN: llvm-lto2 run %t1.bc -o %t3.o -O1 -r %t1.bc,foo,plx -debug-pass-manager \
; RUN: -use-new-pm -save-temps 2>&1 | FileCheck %s --check-prefix=CHECK-O1-SLP
; RUN: llvm-dis %t3.o.1.4.opt.bc -o - | FileCheck %s --check-prefix=CHECK-O1-LPV
; RUN: llvm-lto2 run %t1.bc -o %t4.o -O2 -r %t1.bc,foo,plx -debug-pass-manager \
; RUN: -use-new-pm -save-temps 2>&1 | FileCheck %s --check-prefix=CHECK-O2-SLP
; RUN: llvm-dis %t4.o.1.4.opt.bc -o - | FileCheck %s --check-prefix=CHECK-O2-LPV
; RUN: llvm-lto2 run %t1.bc -o %t5.o -O3 -r %t1.bc,foo,plx -debug-pass-manager \
; RUN: -use-new-pm -save-temps 2>&1 | FileCheck %s --check-prefix=CHECK-O3-SLP
; RUN: llvm-dis %t5.o.1.4.opt.bc -o - | FileCheck %s --check-prefix=CHECK-O3-LPV
; CHECK-O0-SLP-NOT: Running pass: SLPVectorizerPass
; CHECK-O1-SLP-NOT: Running pass: SLPVectorizerPass
; CHECK-O2-SLP: Running pass: SLPVectorizerPass
; CHECK-O3-SLP: Running pass: SLPVectorizerPass
; CHECK-O0-LPV-NOT: = !{!"llvm.loop.isvectorized", i32 1}
; CHECK-O1-LPV-NOT: = !{!"llvm.loop.isvectorized", i32 1}
; CHECK-O2-LPV: = !{!"llvm.loop.isvectorized", i32 1}
; CHECK-O3-LPV: = !{!"llvm.loop.isvectorized", i32 1}
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"
define i32 @foo(i32* %a) {
entry:
br label %for.body
for.body:
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
%red.05 = phi i32 [ 0, %entry ], [ %add, %for.body ]
%arrayidx = getelementptr inbounds i32, i32* %a, i64 %indvars.iv
%0 = load i32, i32* %arrayidx, align 4
%add = add nsw i32 %0, %red.05
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond = icmp eq i64 %indvars.iv.next, 255
br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !0
for.end:
ret i32 %add
}
!0 = distinct !{!0, !1}
!1 = !{!"llvm.loop.unroll.disable", i1 true}

3
tools/gold/gold-plugin.cpp
View File

@ -860,6 +860,9 @@ static std::unique_ptr<LTO> createLTO(IndexWriteCallback OnIndexWrite,
Conf.CGOptLevel = getCGOptLevel();
Conf.DisableVerify = options::DisableVerify;
Conf.OptLevel = options::OptLevel;
Conf.PTO.LoopVectorization = options::OptLevel > 1;
Conf.PTO.SLPVectorization = options::OptLevel > 1;
if (options::Parallelism)
Backend = createInProcessThinBackend(options::Parallelism);
if (options::thinlto_index_only) {

1
tools/llvm-lto2/CMakeLists.txt
View File

@ -9,6 +9,7 @@ set(LLVM_LINK_COMPONENTS
LTO
MC
Object
Passes
Support
Target
)

2
tools/llvm-lto2/llvm-lto2.cpp
View File

@ -270,6 +270,8 @@ static int run(int argc, char **argv) {
Conf.OverrideTriple = OverrideTriple;
Conf.DefaultTriple = DefaultTriple;
Conf.StatsFile = StatsFile;
Conf.PTO.LoopVectorization = Conf.OptLevel > 1;
Conf.PTO.SLPVectorization = Conf.OptLevel > 1;
ThinBackend Backend;
if (ThinLTODistributedIndexes)