llvm-project/llvm/lib/Target/AMDGPU/AMDGPU.h

193 lines
6.3 KiB
C
Raw Normal View History

//===-- AMDGPU.h - MachineFunction passes hw codegen --------------*- C++ -*-=//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
/// \file
//===----------------------------------------------------------------------===//
#ifndef LLVM_LIB_TARGET_AMDGPU_AMDGPU_H
#define LLVM_LIB_TARGET_AMDGPU_AMDGPU_H
#include "llvm/Target/TargetMachine.h"
namespace llvm {
class AMDGPUTargetMachine;
class FunctionPass;
class GCNTargetMachine;
class ModulePass;
class Pass;
class Target;
class TargetMachine;
class PassRegistry;
// R600 Passes
FunctionPass *createR600VectorRegMerger(TargetMachine &tm);
FunctionPass *createR600ExpandSpecialInstrsPass(TargetMachine &tm);
FunctionPass *createR600EmitClauseMarkers();
FunctionPass *createR600ClauseMergePass(TargetMachine &tm);
FunctionPass *createR600Packetizer(TargetMachine &tm);
FunctionPass *createR600ControlFlowFinalizer(TargetMachine &tm);
FunctionPass *createAMDGPUCFGStructurizerPass();
// SI Passes
FunctionPass *createSITypeRewriter();
FunctionPass *createSIAnnotateControlFlowPass();
FunctionPass *createSIFoldOperandsPass();
[ADMGPU] SDWA peephole optimization pass. Summary: First iteration of SDWA peephole. This pass tries to combine several instruction into one SDWA instruction. E.g. it converts: ''' V_LSHRREV_B32_e32 %vreg0, 16, %vreg1 V_ADD_I32_e32 %vreg2, %vreg0, %vreg3 V_LSHLREV_B32_e32 %vreg4, 16, %vreg2 ''' Into: ''' V_ADD_I32_sdwa %vreg4, %vreg1, %vreg3 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:DWORD ''' Pass structure: 1. Iterate over machine instruction in basic block and try to apply "SDWA patterns" to each of them. SDWA patterns match machine instruction into either source or destination SDWA operand. E.g. ''' V_LSHRREV_B32_e32 %vreg0, 16, %vreg1''' is matched to source SDWA operand '''%vreg1 src_sel:WORD_1'''. 2. Iterate over found SDWA operands and find instruction that could be potentially coverted into SDWA. E.g. for source SDWA operand potential instruction are all instruction in this basic block that uses '''%vreg0''' 3. Iterate over all potential instructions and check if they can be converted into SDWA. 4. Convert instructions to SDWA. This review contains basic implementation of SDWA peephole pass. This pass requires additional testing fot both correctness and performance (no performance testing done). There are several ways this pass can be improved: 1. Make this pass work on whole function not only basic block. As I can see this can be done right now without changes to pass. 2. Introduce more SDWA patterns 3. Introduce mnemonics to limit when SDWA patterns should apply Reviewers: vpykhtin, alex-t, arsenm, rampitec Subscribers: wdng, nhaehnle, mgorny Differential Revision: https://reviews.llvm.org/D30038 llvm-svn: 298365
2017-03-21 20:51:34 +08:00
FunctionPass *createSIPeepholeSDWAPass();
FunctionPass *createSILowerI1CopiesPass();
FunctionPass *createSIShrinkInstructionsPass();
FunctionPass *createSILoadStoreOptimizerPass(TargetMachine &tm);
FunctionPass *createSIWholeQuadModePass();
FunctionPass *createSIFixControlFlowLiveIntervalsPass();
FunctionPass *createSIFixSGPRCopiesPass();
FunctionPass *createSIDebuggerInsertNopsPass();
FunctionPass *createSIInsertWaitsPass();
FunctionPass *createAMDGPUCodeGenPreparePass(const GCNTargetMachine *TM = nullptr);
ModulePass *createAMDGPUAnnotateKernelFeaturesPass(const TargetMachine *TM = nullptr);
void initializeAMDGPUAnnotateKernelFeaturesPass(PassRegistry &);
extern char &AMDGPUAnnotateKernelFeaturesID;
ModulePass *createAMDGPULowerIntrinsicsPass();
void initializeAMDGPULowerIntrinsicsPass(PassRegistry &);
extern char &AMDGPULowerIntrinsicsID;
void initializeSIFoldOperandsPass(PassRegistry &);
extern char &SIFoldOperandsID;
[ADMGPU] SDWA peephole optimization pass. Summary: First iteration of SDWA peephole. This pass tries to combine several instruction into one SDWA instruction. E.g. it converts: ''' V_LSHRREV_B32_e32 %vreg0, 16, %vreg1 V_ADD_I32_e32 %vreg2, %vreg0, %vreg3 V_LSHLREV_B32_e32 %vreg4, 16, %vreg2 ''' Into: ''' V_ADD_I32_sdwa %vreg4, %vreg1, %vreg3 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:DWORD ''' Pass structure: 1. Iterate over machine instruction in basic block and try to apply "SDWA patterns" to each of them. SDWA patterns match machine instruction into either source or destination SDWA operand. E.g. ''' V_LSHRREV_B32_e32 %vreg0, 16, %vreg1''' is matched to source SDWA operand '''%vreg1 src_sel:WORD_1'''. 2. Iterate over found SDWA operands and find instruction that could be potentially coverted into SDWA. E.g. for source SDWA operand potential instruction are all instruction in this basic block that uses '''%vreg0''' 3. Iterate over all potential instructions and check if they can be converted into SDWA. 4. Convert instructions to SDWA. This review contains basic implementation of SDWA peephole pass. This pass requires additional testing fot both correctness and performance (no performance testing done). There are several ways this pass can be improved: 1. Make this pass work on whole function not only basic block. As I can see this can be done right now without changes to pass. 2. Introduce more SDWA patterns 3. Introduce mnemonics to limit when SDWA patterns should apply Reviewers: vpykhtin, alex-t, arsenm, rampitec Subscribers: wdng, nhaehnle, mgorny Differential Revision: https://reviews.llvm.org/D30038 llvm-svn: 298365
2017-03-21 20:51:34 +08:00
void initializeSIPeepholeSDWAPass(PassRegistry &);
extern char &SIPeepholeSDWAID;
void initializeSIShrinkInstructionsPass(PassRegistry&);
extern char &SIShrinkInstructionsID;
void initializeSIFixSGPRCopiesPass(PassRegistry &);
extern char &SIFixSGPRCopiesID;
void initializeSIFixVGPRCopiesPass(PassRegistry &);
extern char &SIFixVGPRCopiesID;
void initializeSILowerI1CopiesPass(PassRegistry &);
extern char &SILowerI1CopiesID;
void initializeSILoadStoreOptimizerPass(PassRegistry &);
extern char &SILoadStoreOptimizerID;
void initializeSIWholeQuadModePass(PassRegistry &);
extern char &SIWholeQuadModeID;
void initializeSILowerControlFlowPass(PassRegistry &);
extern char &SILowerControlFlowID;
void initializeSIInsertSkipsPass(PassRegistry &);
extern char &SIInsertSkipsPassID;
void initializeSIOptimizeExecMaskingPass(PassRegistry &);
extern char &SIOptimizeExecMaskingID;
// Passes common to R600 and SI
FunctionPass *createAMDGPUPromoteAlloca(const TargetMachine *TM = nullptr);
void initializeAMDGPUPromoteAllocaPass(PassRegistry&);
extern char &AMDGPUPromoteAllocaID;
Pass *createAMDGPUStructurizeCFGPass();
FunctionPass *createAMDGPUISelDag(TargetMachine &TM,
CodeGenOpt::Level OptLevel);
ModulePass *createAMDGPUAlwaysInlinePass();
ModulePass *createAMDGPUOpenCLImageTypeLoweringPass();
FunctionPass *createAMDGPUAnnotateUniformValues();
ModulePass* createAMDGPUUnifyMetadataPass();
void initializeAMDGPUUnifyMetadataPass(PassRegistry&);
extern char &AMDGPUUnifyMetadataID;
void initializeSIFixControlFlowLiveIntervalsPass(PassRegistry&);
extern char &SIFixControlFlowLiveIntervalsID;
void initializeAMDGPUAnnotateUniformValuesPass(PassRegistry&);
extern char &AMDGPUAnnotateUniformValuesPassID;
void initializeAMDGPUCodeGenPreparePass(PassRegistry&);
extern char &AMDGPUCodeGenPrepareID;
void initializeSIAnnotateControlFlowPass(PassRegistry&);
extern char &SIAnnotateControlFlowPassID;
void initializeSIDebuggerInsertNopsPass(PassRegistry&);
extern char &SIDebuggerInsertNopsID;
void initializeSIInsertWaitsPass(PassRegistry&);
extern char &SIInsertWaitsID;
void initializeAMDGPUUnifyDivergentExitNodesPass(PassRegistry&);
extern char &AMDGPUUnifyDivergentExitNodesID;
ImmutablePass *createAMDGPUAAWrapperPass();
void initializeAMDGPUAAWrapperPassPass(PassRegistry&);
Target &getTheAMDGPUTarget();
Target &getTheGCNTarget();
namespace AMDGPU {
enum TargetIndex {
TI_CONSTDATA_START,
TI_SCRATCH_RSRC_DWORD0,
TI_SCRATCH_RSRC_DWORD1,
TI_SCRATCH_RSRC_DWORD2,
TI_SCRATCH_RSRC_DWORD3
};
}
} // End namespace llvm
/// OpenCL uses address spaces to differentiate between
/// various memory regions on the hardware. On the CPU
/// all of the address spaces point to the same memory,
/// however on the GPU, each address space points to
/// a separate piece of memory that is unique from other
/// memory locations.
namespace AMDGPUAS {
enum AddressSpaces : unsigned {
PRIVATE_ADDRESS = 0, ///< Address space for private memory.
GLOBAL_ADDRESS = 1, ///< Address space for global memory (RAT0, VTX0).
CONSTANT_ADDRESS = 2, ///< Address space for constant memory (VTX2)
LOCAL_ADDRESS = 3, ///< Address space for local memory.
FLAT_ADDRESS = 4, ///< Address space for flat memory.
REGION_ADDRESS = 5, ///< Address space for region memory.
PARAM_D_ADDRESS = 6, ///< Address space for direct addressible parameter memory (CONST0)
PARAM_I_ADDRESS = 7, ///< Address space for indirect addressible parameter memory (VTX1)
// Do not re-order the CONSTANT_BUFFER_* enums. Several places depend on this
// order to be able to dynamically index a constant buffer, for example:
//
// ConstantBufferAS = CONSTANT_BUFFER_0 + CBIdx
CONSTANT_BUFFER_0 = 8,
CONSTANT_BUFFER_1 = 9,
CONSTANT_BUFFER_2 = 10,
CONSTANT_BUFFER_3 = 11,
CONSTANT_BUFFER_4 = 12,
CONSTANT_BUFFER_5 = 13,
CONSTANT_BUFFER_6 = 14,
CONSTANT_BUFFER_7 = 15,
CONSTANT_BUFFER_8 = 16,
CONSTANT_BUFFER_9 = 17,
CONSTANT_BUFFER_10 = 18,
CONSTANT_BUFFER_11 = 19,
CONSTANT_BUFFER_12 = 20,
CONSTANT_BUFFER_13 = 21,
CONSTANT_BUFFER_14 = 22,
CONSTANT_BUFFER_15 = 23,
// Some places use this if the address space can't be determined.
UNKNOWN_ADDRESS_SPACE = ~0u
};
} // namespace AMDGPUAS
#endif