0507448d82
The premise here is to allow non-kernel functions to locate external LDS variables without using LDS or extra magic SGPRs to do so. 1/ First it crawls the callgraph to work out which external LDS variables are reachable from a given kernel 2/ Then it creates a new `extern char[0]` variable for each kernel, which will alias all the other extern LDS variables because that's the documented behaviour of these variables 3/ The address of that variable is written to a lookup table. The global variable is tagged with metadata to track what address it was allocated at by codegen 4/ The assembler builds the lookup table using the metadata 5/ Any non-kernel functions use the same magic intrinsic used by table lookups of non-dynamic LDS variables to find the address to use Heavy overlap with the code paths taken for other lowering, in particular the same intrinsic is used to pass the dynamic scope information through the same sgpr as for table lookups of static LDS. Reviewed By: arsenm Differential Revision: https://reviews.llvm.org/D144233
119 lines
3.4 KiB
C++
119 lines
3.4 KiB
C++
//===-- AMDGPUMachineFunctionInfo.h -------------------------------*- C++ -*-=//
|
|
//
|
|
// 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
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#ifndef LLVM_LIB_TARGET_AMDGPU_AMDGPUMACHINEFUNCTION_H
|
|
#define LLVM_LIB_TARGET_AMDGPU_AMDGPUMACHINEFUNCTION_H
|
|
|
|
#include "Utils/AMDGPUBaseInfo.h"
|
|
#include "llvm/ADT/DenseMap.h"
|
|
#include "llvm/CodeGen/MachineFunction.h"
|
|
#include "llvm/IR/DataLayout.h"
|
|
#include "llvm/IR/Function.h"
|
|
#include "llvm/IR/GlobalValue.h"
|
|
#include "llvm/IR/GlobalVariable.h"
|
|
|
|
namespace llvm {
|
|
|
|
class AMDGPUSubtarget;
|
|
class GCNSubtarget;
|
|
|
|
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;
|
|
|
|
protected:
|
|
uint64_t ExplicitKernArgSize = 0; // Cache for this.
|
|
Align MaxKernArgAlign; // Cache for this.
|
|
|
|
/// Number of bytes in the LDS that are being used.
|
|
uint32_t LDSSize = 0;
|
|
uint32_t GDSSize = 0;
|
|
|
|
/// Number of bytes in the LDS allocated statically. This field is only used
|
|
/// in the instruction selector and not part of the machine function info.
|
|
uint32_t StaticLDSSize = 0;
|
|
uint32_t StaticGDSSize = 0;
|
|
|
|
/// Align for dynamic shared memory if any. Dynamic shared memory is
|
|
/// allocated directly after the static one, i.e., LDSSize. Need to pad
|
|
/// LDSSize to ensure that dynamic one is aligned accordingly.
|
|
/// The maximal alignment is updated during IR translation or lowering
|
|
/// stages.
|
|
Align DynLDSAlign;
|
|
|
|
// Kernels + shaders. i.e. functions called by the hardware and not called
|
|
// by other functions.
|
|
bool IsEntryFunction = false;
|
|
|
|
// Entry points called by other functions instead of directly by the hardware.
|
|
bool IsModuleEntryFunction = false;
|
|
|
|
bool NoSignedZerosFPMath = false;
|
|
|
|
// Function may be memory bound.
|
|
bool MemoryBound = false;
|
|
|
|
// Kernel may need limited waves per EU for better performance.
|
|
bool WaveLimiter = false;
|
|
|
|
public:
|
|
AMDGPUMachineFunction(const Function &F, const AMDGPUSubtarget &ST);
|
|
|
|
uint64_t getExplicitKernArgSize() const {
|
|
return ExplicitKernArgSize;
|
|
}
|
|
|
|
Align getMaxKernArgAlign() const { return MaxKernArgAlign; }
|
|
|
|
uint32_t getLDSSize() const {
|
|
return LDSSize;
|
|
}
|
|
|
|
uint32_t getGDSSize() const {
|
|
return GDSSize;
|
|
}
|
|
|
|
bool isEntryFunction() const {
|
|
return IsEntryFunction;
|
|
}
|
|
|
|
bool isModuleEntryFunction() const { return IsModuleEntryFunction; }
|
|
|
|
bool hasNoSignedZerosFPMath() const {
|
|
return NoSignedZerosFPMath;
|
|
}
|
|
|
|
bool isMemoryBound() const {
|
|
return MemoryBound;
|
|
}
|
|
|
|
bool needsWaveLimiter() const {
|
|
return WaveLimiter;
|
|
}
|
|
|
|
unsigned allocateLDSGlobal(const DataLayout &DL, const GlobalVariable &GV) {
|
|
return allocateLDSGlobal(DL, GV, DynLDSAlign);
|
|
}
|
|
|
|
unsigned allocateLDSGlobal(const DataLayout &DL, const GlobalVariable &GV,
|
|
Align Trailing);
|
|
|
|
void allocateKnownAddressLDSGlobal(const Function &F);
|
|
|
|
static std::optional<uint32_t> getLDSKernelIdMetadata(const Function &F);
|
|
static std::optional<uint32_t> getLDSAbsoluteAddress(const GlobalValue &GV);
|
|
|
|
Align getDynLDSAlign() const { return DynLDSAlign; }
|
|
|
|
void setDynLDSAlign(const Function &F, const GlobalVariable &GV);
|
|
};
|
|
|
|
}
|
|
#endif
|