8c752900dd
Use a local pointer type to represent the named barrier in builtin and intrinsic. This makes the definitions more user friendly bacause they do not need to worry about the hardware ID assignment. Also this approach is more like the other popular GPU programming language. Named barriers should be represented as global variables of addrspace(3) in LLVM-IR. Compiler assigns the special LDS offsets for those variables during AMDGPULowerModuleLDS pass. Those addresses are converted to hw barrier ID during instruction selection. The rest of the instruction-selection changes are primarily due to the intrinsic-definition changes.
79 lines
2.4 KiB
C++
79 lines
2.4 KiB
C++
//===- AMDGPUMemoryUtils.h - Memory related helper functions -*- 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_UTILS_AMDGPUMEMORYUTILS_H
|
|
#define LLVM_LIB_TARGET_AMDGPU_UTILS_AMDGPUMEMORYUTILS_H
|
|
|
|
#include "llvm/ADT/ArrayRef.h"
|
|
#include "llvm/ADT/DenseMap.h"
|
|
#include "llvm/ADT/DenseSet.h"
|
|
|
|
namespace llvm {
|
|
|
|
struct Align;
|
|
class AAResults;
|
|
class DataLayout;
|
|
class GlobalVariable;
|
|
class LoadInst;
|
|
class MemoryDef;
|
|
class MemorySSA;
|
|
class Value;
|
|
class Function;
|
|
class CallGraph;
|
|
class Module;
|
|
class TargetExtType;
|
|
|
|
namespace AMDGPU {
|
|
|
|
using FunctionVariableMap = DenseMap<Function *, DenseSet<GlobalVariable *>>;
|
|
using VariableFunctionMap = DenseMap<GlobalVariable *, DenseSet<Function *>>;
|
|
|
|
Align getAlign(const DataLayout &DL, const GlobalVariable *GV);
|
|
|
|
// If GV is a named-barrier return its type. Otherwise return nullptr.
|
|
TargetExtType *isNamedBarrier(const GlobalVariable &GV);
|
|
|
|
bool isDynamicLDS(const GlobalVariable &GV);
|
|
bool isLDSVariableToLower(const GlobalVariable &GV);
|
|
|
|
struct LDSUsesInfoTy {
|
|
FunctionVariableMap direct_access;
|
|
FunctionVariableMap indirect_access;
|
|
bool HasSpecialGVs = false;
|
|
};
|
|
|
|
bool eliminateConstantExprUsesOfLDSFromAllInstructions(Module &M);
|
|
|
|
void getUsesOfLDSByFunction(const CallGraph &CG, Module &M,
|
|
FunctionVariableMap &kernels,
|
|
FunctionVariableMap &functions);
|
|
|
|
bool isKernelLDS(const Function *F);
|
|
|
|
LDSUsesInfoTy getTransitiveUsesOfLDS(const CallGraph &CG, Module &M);
|
|
|
|
/// Strip FnAttr attribute from any functions where we may have
|
|
/// introduced its use.
|
|
void removeFnAttrFromReachable(CallGraph &CG, Function *KernelRoot,
|
|
ArrayRef<StringRef> FnAttrs);
|
|
|
|
/// Given a \p Def clobbering a load from \p Ptr according to the MSSA check
|
|
/// if this is actually a memory update or an artificial clobber to facilitate
|
|
/// ordering constraints.
|
|
bool isReallyAClobber(const Value *Ptr, MemoryDef *Def, AAResults *AA);
|
|
|
|
/// Check is a \p Load is clobbered in its function.
|
|
bool isClobberedInFunction(const LoadInst *Load, MemorySSA *MSSA,
|
|
AAResults *AA);
|
|
|
|
} // end namespace AMDGPU
|
|
|
|
} // end namespace llvm
|
|
|
|
#endif // LLVM_LIB_TARGET_AMDGPU_UTILS_AMDGPUMEMORYUTILS_H
|