mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-10-22 12:33:33 +02:00
c29c4efaa7
This is adoption of HSAIL perfhint pass. Two types of hints are produced: 1. Function is memory bound. 2. Kernel can use wave limiter. Currently these hints are used in the scheduler. If a function is suspected to be memory bound we allow occupancy to decrease to 4 waves in the course of scheduling. Differential Revision: https://reviews.llvm.org/D46992 llvm-svn: 333289
60 lines
2.0 KiB
C++
60 lines
2.0 KiB
C++
//===-- AMDGPUMachineFunctionInfo.cpp ---------------------------------------=//
|
|
//
|
|
// The LLVM Compiler Infrastructure
|
|
//
|
|
// This file is distributed under the University of Illinois Open Source
|
|
// License. See LICENSE.TXT for details.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#include "AMDGPUMachineFunction.h"
|
|
#include "AMDGPUSubtarget.h"
|
|
#include "AMDGPUPerfHintAnalysis.h"
|
|
#include "llvm/CodeGen/MachineModuleInfo.h"
|
|
|
|
using namespace llvm;
|
|
|
|
AMDGPUMachineFunction::AMDGPUMachineFunction(const MachineFunction &MF) :
|
|
MachineFunctionInfo(),
|
|
LocalMemoryObjects(),
|
|
KernArgSize(0),
|
|
MaxKernArgAlign(0),
|
|
LDSSize(0),
|
|
ABIArgOffset(0),
|
|
IsEntryFunction(AMDGPU::isEntryFunctionCC(MF.getFunction().getCallingConv())),
|
|
NoSignedZerosFPMath(MF.getTarget().Options.NoSignedZerosFPMath),
|
|
MemoryBound(false),
|
|
WaveLimiter(false) {
|
|
// FIXME: Should initialize KernArgSize based on ExplicitKernelArgOffset,
|
|
// except reserved size is not correctly aligned.
|
|
|
|
if (auto *Resolver = MF.getMMI().getResolver()) {
|
|
if (AMDGPUPerfHintAnalysis *PHA = static_cast<AMDGPUPerfHintAnalysis*>(
|
|
Resolver->getAnalysisIfAvailable(&AMDGPUPerfHintAnalysisID, true))) {
|
|
MemoryBound = PHA->isMemoryBound(&MF.getFunction());
|
|
WaveLimiter = PHA->needsWaveLimiter(&MF.getFunction());
|
|
}
|
|
}
|
|
}
|
|
|
|
unsigned AMDGPUMachineFunction::allocateLDSGlobal(const DataLayout &DL,
|
|
const GlobalValue &GV) {
|
|
auto Entry = LocalMemoryObjects.insert(std::make_pair(&GV, 0));
|
|
if (!Entry.second)
|
|
return Entry.first->second;
|
|
|
|
unsigned Align = GV.getAlignment();
|
|
if (Align == 0)
|
|
Align = DL.getABITypeAlignment(GV.getValueType());
|
|
|
|
/// TODO: We should sort these to minimize wasted space due to alignment
|
|
/// padding. Currently the padding is decided by the first encountered use
|
|
/// during lowering.
|
|
unsigned Offset = LDSSize = alignTo(LDSSize, Align);
|
|
|
|
Entry.first->second = Offset;
|
|
LDSSize += DL.getTypeAllocSize(GV.getValueType());
|
|
|
|
return Offset;
|
|
}
|