13e49dcee4
[amdgpu] Implement lower function LDS pass Local variables are allocated at kernel launch. This pass collects global variables that are used from non-kernel functions, moves them into a new struct type, and allocates an instance of that type in every kernel. Uses are then replaced with a constantexpr offset. Prior to this pass, accesses from a function are compiled to trap. With this pass, most such accesses are removed before reaching codegen. The trap logic is left unchanged by this pass. It is still reachable for the cases this pass misses, notably the extern shared construct from hip and variables marked constant which survive the optimizer. This is of interest to the openmp project because the deviceRTL runtime library uses cuda shared variables from functions that cannot be inlined. Trunk llvm therefore cannot compile some openmp kernels for amdgpu. In addition to the unit tests attached, this patch applied to ROCm llvm with fixed-abi enabled and the function pointer hashing scheme deleted passes the openmp suite. This lowering will use more LDS than strictly necessary. It is intended to be a functionally correct fallback for cases that are difficult to target from future optimisation passes. Reviewed By: arsenm Differential Revision: https://reviews.llvm.org/D94648
91 lines
3.3 KiB
C++
91 lines
3.3 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 "AMDGPUPerfHintAnalysis.h"
|
|
#include "AMDGPUSubtarget.h"
|
|
#include "llvm/CodeGen/MachineModuleInfo.h"
|
|
#include "llvm/Target/TargetMachine.h"
|
|
|
|
using namespace llvm;
|
|
|
|
AMDGPUMachineFunction::AMDGPUMachineFunction(const MachineFunction &MF)
|
|
: MachineFunctionInfo(), Mode(MF.getFunction()),
|
|
IsEntryFunction(
|
|
AMDGPU::isEntryFunctionCC(MF.getFunction().getCallingConv())),
|
|
IsModuleEntryFunction(
|
|
AMDGPU::isModuleEntryFunctionCC(MF.getFunction().getCallingConv())),
|
|
NoSignedZerosFPMath(MF.getTarget().Options.NoSignedZerosFPMath) {
|
|
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 GlobalVariable &GV) {
|
|
auto Entry = LocalMemoryObjects.insert(std::make_pair(&GV, 0));
|
|
if (!Entry.second)
|
|
return Entry.first->second;
|
|
|
|
Align Alignment =
|
|
DL.getValueOrABITypeAlignment(GV.getAlign(), 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 = StaticLDSSize = alignTo(StaticLDSSize, Alignment);
|
|
|
|
Entry.first->second = Offset;
|
|
StaticLDSSize += DL.getTypeAllocSize(GV.getValueType());
|
|
|
|
// Update the LDS size considering the padding to align the dynamic shared
|
|
// memory.
|
|
LDSSize = alignTo(StaticLDSSize, DynLDSAlign);
|
|
|
|
return Offset;
|
|
}
|
|
|
|
void AMDGPUMachineFunction::allocateModuleLDSGlobal(const Module *M) {
|
|
if (isModuleEntryFunction()) {
|
|
GlobalVariable *GV = M->getGlobalVariable("llvm.amdgcn.module.lds");
|
|
if (GV) {
|
|
unsigned Offset = allocateLDSGlobal(M->getDataLayout(), *GV);
|
|
(void)Offset;
|
|
assert(Offset == 0 &&
|
|
"Module LDS expected to be allocated before other LDS");
|
|
}
|
|
}
|
|
}
|
|
|
|
void AMDGPUMachineFunction::setDynLDSAlign(const DataLayout &DL,
|
|
const GlobalVariable &GV) {
|
|
assert(DL.getTypeAllocSize(GV.getValueType()).isZero());
|
|
|
|
Align Alignment =
|
|
DL.getValueOrABITypeAlignment(GV.getAlign(), GV.getValueType());
|
|
if (Alignment <= DynLDSAlign)
|
|
return;
|
|
|
|
LDSSize = alignTo(StaticLDSSize, Alignment);
|
|
DynLDSAlign = Alignment;
|
|
}
|