mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-10-22 20:43:44 +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
100 lines
2.3 KiB
C++
100 lines
2.3 KiB
C++
//===-- AMDGPUMachineFunctionInfo.h -------------------------------*- C++ -*-=//
|
|
//
|
|
// The LLVM Compiler Infrastructure
|
|
//
|
|
// This file is distributed under the University of Illinois Open Source
|
|
// License. See LICENSE.TXT for details.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#ifndef LLVM_LIB_TARGET_AMDGPU_AMDGPUMACHINEFUNCTION_H
|
|
#define LLVM_LIB_TARGET_AMDGPU_AMDGPUMACHINEFUNCTION_H
|
|
|
|
#include "llvm/ADT/DenseMap.h"
|
|
#include "llvm/CodeGen/MachineFunction.h"
|
|
|
|
namespace llvm {
|
|
|
|
class AMDGPUMachineFunction : public MachineFunctionInfo {
|
|
/// A map to keep track of local memory objects and their offsets within the
|
|
/// local memory space.
|
|
SmallDenseMap<const GlobalValue *, unsigned, 4> LocalMemoryObjects;
|
|
|
|
uint64_t KernArgSize;
|
|
unsigned MaxKernArgAlign;
|
|
|
|
/// Number of bytes in the LDS that are being used.
|
|
unsigned LDSSize;
|
|
|
|
// FIXME: This should probably be removed.
|
|
/// Start of implicit kernel args
|
|
unsigned ABIArgOffset;
|
|
|
|
// Kernels + shaders. i.e. functions called by the driver and not called
|
|
// by other functions.
|
|
bool IsEntryFunction;
|
|
|
|
bool NoSignedZerosFPMath;
|
|
|
|
// Function may be memory bound.
|
|
bool MemoryBound;
|
|
|
|
// Kernel may need limited waves per EU for better performance.
|
|
bool WaveLimiter;
|
|
|
|
public:
|
|
AMDGPUMachineFunction(const MachineFunction &MF);
|
|
|
|
uint64_t allocateKernArg(uint64_t Size, unsigned Align) {
|
|
assert(isPowerOf2_32(Align));
|
|
KernArgSize = alignTo(KernArgSize, Align);
|
|
|
|
uint64_t Result = KernArgSize;
|
|
KernArgSize += Size;
|
|
|
|
MaxKernArgAlign = std::max(Align, MaxKernArgAlign);
|
|
return Result;
|
|
}
|
|
|
|
uint64_t getKernArgSize() const {
|
|
return KernArgSize;
|
|
}
|
|
|
|
unsigned getMaxKernArgAlign() const {
|
|
return MaxKernArgAlign;
|
|
}
|
|
|
|
void setABIArgOffset(unsigned NewOffset) {
|
|
ABIArgOffset = NewOffset;
|
|
}
|
|
|
|
unsigned getABIArgOffset() const {
|
|
return ABIArgOffset;
|
|
}
|
|
|
|
unsigned getLDSSize() const {
|
|
return LDSSize;
|
|
}
|
|
|
|
bool isEntryFunction() const {
|
|
return IsEntryFunction;
|
|
}
|
|
|
|
bool hasNoSignedZerosFPMath() const {
|
|
return NoSignedZerosFPMath;
|
|
}
|
|
|
|
bool isMemoryBound() const {
|
|
return MemoryBound;
|
|
}
|
|
|
|
bool needsWaveLimiter() const {
|
|
return WaveLimiter;
|
|
}
|
|
|
|
unsigned allocateLDSGlobal(const DataLayout &DL, const GlobalValue &GV);
|
|
};
|
|
|
|
}
|
|
#endif
|