Add accelerator code generation pass skeleton

Add a new pass to serve as basis for automatic accelerator mapping in Polly.
The pass structure and the analyses preserved are copied from
CodeGeneration.cpp, as we will rely on IslNodeBuilder and IslExprBuilder for
LLVM-IR code generation.

Polly's accelerator code generation is enabled with -polly-target=gpu

I would like to use this commit as opportunity to thank Yabin Hu for his work in
the context of two Google summer of code projects during which he implemented
initial prototypes of the Polly accelerator code generation -- in parts this
code is already available in todays Polly (e.g., tools/GPURuntime). More will
come as part of the upcoming Polly ACC changes.

Reviewers: Meinersbur

Subscribers: pollydev, llvm-commits

Differential Revision: http://reviews.llvm.org/D22036

llvm-svn: 275275
This commit is contained in:
Tobias Grosser 2016-07-13 15:54:58 +00:00
parent a041239bb7
commit 9dfe4e7c05
4 changed files with 117 additions and 13 deletions

View File

@ -42,6 +42,7 @@ llvm::Pass *createScopInfoRegionPassPass();
llvm::Pass *createScopInfoWrapperPassPass();
llvm::Pass *createIslAstInfoPass();
llvm::Pass *createCodeGenerationPass();
llvm::Pass *createPPCGCodeGenerationPass();
llvm::Pass *createIslScheduleOptimizerPass();
extern char &CodePreparationID;
@ -71,6 +72,7 @@ struct PollyForcePassLinking {
polly::createPollyCanonicalizePass();
polly::createIslAstInfoPass();
polly::createCodeGenerationPass();
polly::createPPCGCodeGenerationPass();
polly::createIslScheduleOptimizerPass();
}
} PollyForcePassLinking; // Force link by creating a global definition.
@ -84,6 +86,7 @@ void initializeJSONExporterPass(llvm::PassRegistry &);
void initializeJSONImporterPass(llvm::PassRegistry &);
void initializeIslAstInfoPass(llvm::PassRegistry &);
void initializeCodeGenerationPass(llvm::PassRegistry &);
void initializePPCGCodeGenerationPass(llvm::PassRegistry &);
void initializeIslScheduleOptimizerPass(llvm::PassRegistry &);
void initializePollyCanonicalizePass(llvm::PassRegistry &);
} // namespace llvm

View File

@ -13,7 +13,9 @@ set(ISL_CODEGEN_FILES
CodeGen/CodeGeneration.cpp)
if (GPU_CODEGEN)
set (GPGPU_CODEGEN_FILES)
set (GPGPU_CODEGEN_FILES
CodeGen/PPCGCodeGeneration.cpp
)
endif (GPU_CODEGEN)
# Compile ISL into a separate library.

View File

@ -0,0 +1,82 @@
//===------ PPCGCodeGeneration.cpp - Polly Accelerator Code Generation. ---===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// Take a scop created by ScopInfo and map it to GPU code using the ppcg
// GPU mapping strategy.
//
//===----------------------------------------------------------------------===//
#include "polly/CodeGen/IslNodeBuilder.h"
#include "polly/DependenceInfo.h"
#include "polly/LinkAllPasses.h"
#include "polly/ScopInfo.h"
#include "llvm/Analysis/AliasAnalysis.h"
#include "llvm/Analysis/BasicAliasAnalysis.h"
#include "llvm/Analysis/GlobalsModRef.h"
#include "llvm/Analysis/PostDominators.h"
#include "llvm/Analysis/ScalarEvolutionAliasAnalysis.h"
#include "llvm/Support/Debug.h"
using namespace polly;
using namespace llvm;
#define DEBUG_TYPE "polly-codegen-ppcg"
namespace {
class PPCGCodeGeneration : public ScopPass {
public:
static char ID;
PPCGCodeGeneration() : ScopPass(ID) {}
bool runOnScop(Scop &S) override { return true; }
void printScop(raw_ostream &, Scop &) const override {}
void getAnalysisUsage(AnalysisUsage &AU) const override {
AU.addRequired<DominatorTreeWrapperPass>();
AU.addRequired<RegionInfoPass>();
AU.addRequired<ScalarEvolutionWrapperPass>();
AU.addRequired<ScopDetection>();
AU.addRequired<ScopInfoRegionPass>();
AU.addRequired<LoopInfoWrapperPass>();
AU.addPreserved<AAResultsWrapperPass>();
AU.addPreserved<BasicAAWrapperPass>();
AU.addPreserved<LoopInfoWrapperPass>();
AU.addPreserved<DominatorTreeWrapperPass>();
AU.addPreserved<GlobalsAAWrapperPass>();
AU.addPreserved<PostDominatorTreeWrapperPass>();
AU.addPreserved<ScopDetection>();
AU.addPreserved<ScalarEvolutionWrapperPass>();
AU.addPreserved<SCEVAAWrapperPass>();
// FIXME: We do not yet add regions for the newly generated code to the
// region tree.
AU.addPreserved<RegionInfoPass>();
AU.addPreserved<ScopInfoRegionPass>();
}
};
}
char PPCGCodeGeneration::ID = 1;
Pass *polly::createPPCGCodeGenerationPass() { return new PPCGCodeGeneration(); }
INITIALIZE_PASS_BEGIN(PPCGCodeGeneration, "polly-codegen-ppcg",
"Polly - Apply PPCG translation to SCOP", false, false)
INITIALIZE_PASS_DEPENDENCY(DependenceInfo);
INITIALIZE_PASS_DEPENDENCY(DominatorTreeWrapperPass);
INITIALIZE_PASS_DEPENDENCY(LoopInfoWrapperPass);
INITIALIZE_PASS_DEPENDENCY(RegionInfoPass);
INITIALIZE_PASS_DEPENDENCY(ScalarEvolutionWrapperPass);
INITIALIZE_PASS_DEPENDENCY(ScopDetection);
INITIALIZE_PASS_END(PPCGCodeGeneration, "polly-codegen-ppcg",
"Polly - Apply PPCG translation to SCOP", false, false)

View File

@ -86,6 +86,14 @@ static cl::opt<CodeGenChoice> CodeGenerator(
clEnumValEnd),
cl::Hidden, cl::init(CODEGEN_ISL), cl::ZeroOrMore, cl::cat(PollyCategory));
enum TargetChoice { TARGET_CPU, TARGET_GPU };
static cl::opt<TargetChoice>
Target("polly-target", cl::desc("The hardware to target"),
cl::values(clEnumValN(TARGET_CPU, "cpu", "generate CPU code"),
clEnumValN(TARGET_GPU, "gpu", "generate GPU code"),
clEnumValEnd),
cl::init(TARGET_CPU), cl::ZeroOrMore, cl::cat(PollyCategory));
VectorizerChoice polly::PollyVectorizerChoice;
static cl::opt<polly::VectorizerChoice, true> Vectorizer(
"polly-vectorizer", cl::desc("Select the vectorization strategy"),
@ -145,6 +153,7 @@ static cl::opt<bool>
namespace polly {
void initializePollyPasses(PassRegistry &Registry) {
initializeCodeGenerationPass(Registry);
initializePPCGCodeGenerationPass(Registry);
initializeCodePreparationPass(Registry);
initializeDeadCodeElimPass(Registry);
initializeDependenceInfoPass(Registry);
@ -209,24 +218,32 @@ void registerPollyPasses(llvm::legacy::PassManagerBase &PM) {
if (DeadCodeElim)
PM.add(polly::createDeadCodeElimPass());
switch (Optimizer) {
case OPTIMIZER_NONE:
break; /* Do nothing */
if (Target == TARGET_GPU) {
// GPU generation provides its own scheduling optimization strategy.
} else {
switch (Optimizer) {
case OPTIMIZER_NONE:
break; /* Do nothing */
case OPTIMIZER_ISL:
PM.add(polly::createIslScheduleOptimizerPass());
break;
case OPTIMIZER_ISL:
PM.add(polly::createIslScheduleOptimizerPass());
break;
}
}
if (ExportJScop)
PM.add(polly::createJSONExporterPass());
switch (CodeGenerator) {
case CODEGEN_ISL:
PM.add(polly::createCodeGenerationPass());
break;
case CODEGEN_NONE:
break;
if (Target == TARGET_GPU) {
PM.add(polly::createPPCGCodeGenerationPass());
} else {
switch (CodeGenerator) {
case CODEGEN_ISL:
PM.add(polly::createCodeGenerationPass());
break;
case CODEGEN_NONE:
break;
}
}
// FIXME: This dummy ModulePass keeps some programs from miscompiling,