b65fa48305
Summary: This is patch is part of a series to introduce an Alignment type. See this thread for context: http://lists.llvm.org/pipermail/llvm-dev/2019-July/133851.html See this patch for the introduction of the type: https://reviews.llvm.org/D64790 Reviewers: courbet, jdoerfert Reviewed By: courbet Subscribers: arsenm, jvesely, nhaehnle, hiraditya, cfe-commits, llvm-commits Tags: #clang, #llvm Differential Revision: https://reviews.llvm.org/D68792 llvm-svn: 374884
64 lines
2.3 KiB
C++
64 lines
2.3 KiB
C++
//===-- AMDGPUMachineFunctionInfo.cpp ---------------------------------------=//
|
|
//
|
|
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
|
|
// See https://llvm.org/LICENSE.txt for license information.
|
|
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#include "AMDGPUMachineFunction.h"
|
|
#include "AMDGPUSubtarget.h"
|
|
#include "AMDGPUPerfHintAnalysis.h"
|
|
#include "llvm/CodeGen/MachineModuleInfo.h"
|
|
|
|
using namespace llvm;
|
|
|
|
AMDGPUMachineFunction::AMDGPUMachineFunction(const MachineFunction &MF) :
|
|
MachineFunctionInfo(),
|
|
LocalMemoryObjects(),
|
|
ExplicitKernArgSize(0),
|
|
LDSSize(0),
|
|
IsEntryFunction(AMDGPU::isEntryFunctionCC(MF.getFunction().getCallingConv())),
|
|
NoSignedZerosFPMath(MF.getTarget().Options.NoSignedZerosFPMath),
|
|
MemoryBound(false),
|
|
WaveLimiter(false) {
|
|
const AMDGPUSubtarget &ST = AMDGPUSubtarget::get(MF);
|
|
|
|
// FIXME: Should initialize KernArgSize based on ExplicitKernelArgOffset,
|
|
// except reserved size is not correctly aligned.
|
|
const Function &F = MF.getFunction();
|
|
|
|
Attribute MemBoundAttr = F.getFnAttribute("amdgpu-memory-bound");
|
|
MemoryBound = MemBoundAttr.isStringAttribute() &&
|
|
MemBoundAttr.getValueAsString() == "true";
|
|
|
|
Attribute WaveLimitAttr = F.getFnAttribute("amdgpu-wave-limiter");
|
|
WaveLimiter = WaveLimitAttr.isStringAttribute() &&
|
|
WaveLimitAttr.getValueAsString() == "true";
|
|
|
|
CallingConv::ID CC = F.getCallingConv();
|
|
if (CC == CallingConv::AMDGPU_KERNEL || CC == CallingConv::SPIR_KERNEL)
|
|
ExplicitKernArgSize = ST.getExplicitKernArgSize(F, MaxKernArgAlign);
|
|
}
|
|
|
|
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;
|
|
}
|