RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-18 18:42:46 +02:00
Code Issues Projects Releases Wiki Activity

AMDGPU: Add option to run the load/store vectorizer

Browse Source 
llvm-svn: 274329
This commit is contained in:
Matt Arsenault 2016-07-01 03:33:52 +00:00
parent e4bc120062
commit f430ee2504
1 changed files with 16 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
View File

@ -39,6 +39,7 @@
#include "llvm/Transforms/IPO.h"
#include "llvm/Transforms/Scalar.h"
#include "llvm/Transforms/Scalar/GVN.h"
#include "llvm/Transforms/Vectorize.h"
using namespace llvm;
@ -59,6 +60,13 @@ static cl::opt<bool> EnableR600IfConvert(
cl::ReallyHidden,
cl::init(true));
// Option to disable vectorizer for tests.
static cl::opt<bool> EnableLoadStoreVectorizer(
"amdgpu-load-store-vectorizer",
cl::desc("Enable load store vectorizer"),
cl::init(false),
cl::Hidden);
extern "C" void LLVMInitializeAMDGPUTarget() {
// Register the target
RegisterTargetMachine<R600TargetMachine> X(TheAMDGPUTarget);
@ -267,6 +275,7 @@ public:
void addEarlyCSEOrGVNPass();
void addStraightLineScalarOptimizationPasses();
void addIRPasses() override;
void addCodeGenPrepare() override;
bool addPreISel() override;
bool addInstSelector() override;
bool addGCPasses() override;
@ -392,6 +401,13 @@ void AMDGPUPassConfig::addIRPasses() {
addEarlyCSEOrGVNPass();
}
void AMDGPUPassConfig::addCodeGenPrepare() {
TargetPassConfig::addCodeGenPrepare();
if (EnableLoadStoreVectorizer)
addPass(createLoadStoreVectorizerPass());
}
bool AMDGPUPassConfig::addPreISel() {
addPass(createFlattenCFGPass());
return false;