forked from OSchip/llvm-project
463 lines
14 KiB
C++
463 lines
14 KiB
C++
//===-- AMDGPUBaseInfo.cpp - AMDGPU Base encoding information--------------===//
|
|
//
|
|
// The LLVM Compiler Infrastructure
|
|
//
|
|
// This file is distributed under the University of Illinois Open Source
|
|
// License. See LICENSE.TXT for details.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
#include "AMDGPUBaseInfo.h"
|
|
#include "AMDGPU.h"
|
|
#include "SIDefines.h"
|
|
#include "llvm/IR/LLVMContext.h"
|
|
#include "llvm/IR/Function.h"
|
|
#include "llvm/IR/GlobalValue.h"
|
|
#include "llvm/MC/MCContext.h"
|
|
#include "llvm/MC/MCInstrInfo.h"
|
|
#include "llvm/MC/MCRegisterInfo.h"
|
|
#include "llvm/MC/MCSectionELF.h"
|
|
#include "llvm/MC/MCSubtargetInfo.h"
|
|
#include "llvm/MC/SubtargetFeature.h"
|
|
|
|
#define GET_SUBTARGETINFO_ENUM
|
|
#include "AMDGPUGenSubtargetInfo.inc"
|
|
#undef GET_SUBTARGETINFO_ENUM
|
|
|
|
#define GET_REGINFO_ENUM
|
|
#include "AMDGPUGenRegisterInfo.inc"
|
|
#undef GET_REGINFO_ENUM
|
|
|
|
#define GET_INSTRINFO_NAMED_OPS
|
|
#define GET_INSTRINFO_ENUM
|
|
#include "AMDGPUGenInstrInfo.inc"
|
|
#undef GET_INSTRINFO_NAMED_OPS
|
|
#undef GET_INSTRINFO_ENUM
|
|
|
|
namespace {
|
|
|
|
/// \returns Bit mask for given bit \p Shift and bit \p Width.
|
|
unsigned getBitMask(unsigned Shift, unsigned Width) {
|
|
return ((1 << Width) - 1) << Shift;
|
|
}
|
|
|
|
/// \brief Packs \p Src into \p Dst for given bit \p Shift and bit \p Width.
|
|
///
|
|
/// \returns Packed \p Dst.
|
|
unsigned packBits(unsigned Src, unsigned Dst, unsigned Shift, unsigned Width) {
|
|
Dst &= ~(1 << Shift) & ~getBitMask(Shift, Width);
|
|
Dst |= (Src << Shift) & getBitMask(Shift, Width);
|
|
return Dst;
|
|
}
|
|
|
|
/// \brief Unpacks bits from \p Src for given bit \p Shift and bit \p Width.
|
|
///
|
|
/// \returns Unpacked bits.
|
|
unsigned unpackBits(unsigned Src, unsigned Shift, unsigned Width) {
|
|
return (Src & getBitMask(Shift, Width)) >> Shift;
|
|
}
|
|
|
|
/// \returns Vmcnt bit shift.
|
|
unsigned getVmcntBitShift() { return 0; }
|
|
|
|
/// \returns Vmcnt bit width.
|
|
unsigned getVmcntBitWidth() { return 4; }
|
|
|
|
/// \returns Expcnt bit shift.
|
|
unsigned getExpcntBitShift() { return 4; }
|
|
|
|
/// \returns Expcnt bit width.
|
|
unsigned getExpcntBitWidth() { return 3; }
|
|
|
|
/// \returns Lgkmcnt bit shift.
|
|
unsigned getLgkmcntBitShift() { return 8; }
|
|
|
|
/// \returns Lgkmcnt bit width.
|
|
unsigned getLgkmcntBitWidth() { return 4; }
|
|
|
|
} // anonymous namespace
|
|
|
|
namespace llvm {
|
|
namespace AMDGPU {
|
|
|
|
IsaVersion getIsaVersion(const FeatureBitset &Features) {
|
|
|
|
if (Features.test(FeatureISAVersion7_0_0))
|
|
return {7, 0, 0};
|
|
|
|
if (Features.test(FeatureISAVersion7_0_1))
|
|
return {7, 0, 1};
|
|
|
|
if (Features.test(FeatureISAVersion7_0_2))
|
|
return {7, 0, 2};
|
|
|
|
if (Features.test(FeatureISAVersion8_0_0))
|
|
return {8, 0, 0};
|
|
|
|
if (Features.test(FeatureISAVersion8_0_1))
|
|
return {8, 0, 1};
|
|
|
|
if (Features.test(FeatureISAVersion8_0_2))
|
|
return {8, 0, 2};
|
|
|
|
if (Features.test(FeatureISAVersion8_0_3))
|
|
return {8, 0, 3};
|
|
|
|
if (Features.test(FeatureISAVersion8_0_4))
|
|
return {8, 0, 4};
|
|
|
|
if (Features.test(FeatureISAVersion8_1_0))
|
|
return {8, 1, 0};
|
|
|
|
return {0, 0, 0};
|
|
}
|
|
|
|
void initDefaultAMDKernelCodeT(amd_kernel_code_t &Header,
|
|
const FeatureBitset &Features) {
|
|
|
|
IsaVersion ISA = getIsaVersion(Features);
|
|
|
|
memset(&Header, 0, sizeof(Header));
|
|
|
|
Header.amd_kernel_code_version_major = 1;
|
|
Header.amd_kernel_code_version_minor = 0;
|
|
Header.amd_machine_kind = 1; // AMD_MACHINE_KIND_AMDGPU
|
|
Header.amd_machine_version_major = ISA.Major;
|
|
Header.amd_machine_version_minor = ISA.Minor;
|
|
Header.amd_machine_version_stepping = ISA.Stepping;
|
|
Header.kernel_code_entry_byte_offset = sizeof(Header);
|
|
// wavefront_size is specified as a power of 2: 2^6 = 64 threads.
|
|
Header.wavefront_size = 6;
|
|
// These alignment values are specified in powers of two, so alignment =
|
|
// 2^n. The minimum alignment is 2^4 = 16.
|
|
Header.kernarg_segment_alignment = 4;
|
|
Header.group_segment_alignment = 4;
|
|
Header.private_segment_alignment = 4;
|
|
}
|
|
|
|
MCSection *getHSATextSection(MCContext &Ctx) {
|
|
return Ctx.getELFSection(".hsatext", ELF::SHT_PROGBITS,
|
|
ELF::SHF_ALLOC | ELF::SHF_WRITE |
|
|
ELF::SHF_EXECINSTR |
|
|
ELF::SHF_AMDGPU_HSA_AGENT |
|
|
ELF::SHF_AMDGPU_HSA_CODE);
|
|
}
|
|
|
|
MCSection *getHSADataGlobalAgentSection(MCContext &Ctx) {
|
|
return Ctx.getELFSection(".hsadata_global_agent", ELF::SHT_PROGBITS,
|
|
ELF::SHF_ALLOC | ELF::SHF_WRITE |
|
|
ELF::SHF_AMDGPU_HSA_GLOBAL |
|
|
ELF::SHF_AMDGPU_HSA_AGENT);
|
|
}
|
|
|
|
MCSection *getHSADataGlobalProgramSection(MCContext &Ctx) {
|
|
return Ctx.getELFSection(".hsadata_global_program", ELF::SHT_PROGBITS,
|
|
ELF::SHF_ALLOC | ELF::SHF_WRITE |
|
|
ELF::SHF_AMDGPU_HSA_GLOBAL);
|
|
}
|
|
|
|
MCSection *getHSARodataReadonlyAgentSection(MCContext &Ctx) {
|
|
return Ctx.getELFSection(".hsarodata_readonly_agent", ELF::SHT_PROGBITS,
|
|
ELF::SHF_ALLOC | ELF::SHF_AMDGPU_HSA_READONLY |
|
|
ELF::SHF_AMDGPU_HSA_AGENT);
|
|
}
|
|
|
|
bool isGroupSegment(const GlobalValue *GV) {
|
|
return GV->getType()->getAddressSpace() == AMDGPUAS::LOCAL_ADDRESS;
|
|
}
|
|
|
|
bool isGlobalSegment(const GlobalValue *GV) {
|
|
return GV->getType()->getAddressSpace() == AMDGPUAS::GLOBAL_ADDRESS;
|
|
}
|
|
|
|
bool isReadOnlySegment(const GlobalValue *GV) {
|
|
return GV->getType()->getAddressSpace() == AMDGPUAS::CONSTANT_ADDRESS;
|
|
}
|
|
|
|
bool shouldEmitConstantsToTextSection(const Triple &TT) {
|
|
return TT.getOS() != Triple::AMDHSA;
|
|
}
|
|
|
|
int getIntegerAttribute(const Function &F, StringRef Name, int Default) {
|
|
Attribute A = F.getFnAttribute(Name);
|
|
int Result = Default;
|
|
|
|
if (A.isStringAttribute()) {
|
|
StringRef Str = A.getValueAsString();
|
|
if (Str.getAsInteger(0, Result)) {
|
|
LLVMContext &Ctx = F.getContext();
|
|
Ctx.emitError("can't parse integer attribute " + Name);
|
|
}
|
|
}
|
|
|
|
return Result;
|
|
}
|
|
|
|
std::pair<int, int> getIntegerPairAttribute(const Function &F,
|
|
StringRef Name,
|
|
std::pair<int, int> Default,
|
|
bool OnlyFirstRequired) {
|
|
Attribute A = F.getFnAttribute(Name);
|
|
if (!A.isStringAttribute())
|
|
return Default;
|
|
|
|
LLVMContext &Ctx = F.getContext();
|
|
std::pair<int, int> Ints = Default;
|
|
std::pair<StringRef, StringRef> Strs = A.getValueAsString().split(',');
|
|
if (Strs.first.trim().getAsInteger(0, Ints.first)) {
|
|
Ctx.emitError("can't parse first integer attribute " + Name);
|
|
return Default;
|
|
}
|
|
if (Strs.second.trim().getAsInteger(0, Ints.second)) {
|
|
if (!OnlyFirstRequired || Strs.second.trim().size()) {
|
|
Ctx.emitError("can't parse second integer attribute " + Name);
|
|
return Default;
|
|
}
|
|
}
|
|
|
|
return Ints;
|
|
}
|
|
|
|
unsigned getWaitcntBitMask(IsaVersion Version) {
|
|
unsigned Vmcnt = getBitMask(getVmcntBitShift(), getVmcntBitWidth());
|
|
unsigned Expcnt = getBitMask(getExpcntBitShift(), getExpcntBitWidth());
|
|
unsigned Lgkmcnt = getBitMask(getLgkmcntBitShift(), getLgkmcntBitWidth());
|
|
return Vmcnt | Expcnt | Lgkmcnt;
|
|
}
|
|
|
|
unsigned getVmcntBitMask(IsaVersion Version) {
|
|
return (1 << getVmcntBitWidth()) - 1;
|
|
}
|
|
|
|
unsigned getExpcntBitMask(IsaVersion Version) {
|
|
return (1 << getExpcntBitWidth()) - 1;
|
|
}
|
|
|
|
unsigned getLgkmcntBitMask(IsaVersion Version) {
|
|
return (1 << getLgkmcntBitWidth()) - 1;
|
|
}
|
|
|
|
unsigned decodeVmcnt(IsaVersion Version, unsigned Waitcnt) {
|
|
return unpackBits(Waitcnt, getVmcntBitShift(), getVmcntBitWidth());
|
|
}
|
|
|
|
unsigned decodeExpcnt(IsaVersion Version, unsigned Waitcnt) {
|
|
return unpackBits(Waitcnt, getExpcntBitShift(), getExpcntBitWidth());
|
|
}
|
|
|
|
unsigned decodeLgkmcnt(IsaVersion Version, unsigned Waitcnt) {
|
|
return unpackBits(Waitcnt, getLgkmcntBitShift(), getLgkmcntBitWidth());
|
|
}
|
|
|
|
void decodeWaitcnt(IsaVersion Version, unsigned Waitcnt,
|
|
unsigned &Vmcnt, unsigned &Expcnt, unsigned &Lgkmcnt) {
|
|
Vmcnt = decodeVmcnt(Version, Waitcnt);
|
|
Expcnt = decodeExpcnt(Version, Waitcnt);
|
|
Lgkmcnt = decodeLgkmcnt(Version, Waitcnt);
|
|
}
|
|
|
|
unsigned encodeVmcnt(IsaVersion Version, unsigned Waitcnt, unsigned Vmcnt) {
|
|
return packBits(Vmcnt, Waitcnt, getVmcntBitShift(), getVmcntBitWidth());
|
|
}
|
|
|
|
unsigned encodeExpcnt(IsaVersion Version, unsigned Waitcnt, unsigned Expcnt) {
|
|
return packBits(Expcnt, Waitcnt, getExpcntBitShift(), getExpcntBitWidth());
|
|
}
|
|
|
|
unsigned encodeLgkmcnt(IsaVersion Version, unsigned Waitcnt, unsigned Lgkmcnt) {
|
|
return packBits(Lgkmcnt, Waitcnt, getLgkmcntBitShift(), getLgkmcntBitWidth());
|
|
}
|
|
|
|
unsigned encodeWaitcnt(IsaVersion Version,
|
|
unsigned Vmcnt, unsigned Expcnt, unsigned Lgkmcnt) {
|
|
unsigned Waitcnt = getWaitcntBitMask(Version);
|
|
Waitcnt = encodeVmcnt(Version, Waitcnt, Vmcnt);
|
|
Waitcnt = encodeExpcnt(Version, Waitcnt, Expcnt);
|
|
Waitcnt = encodeLgkmcnt(Version, Waitcnt, Lgkmcnt);
|
|
return Waitcnt;
|
|
}
|
|
|
|
unsigned getInitialPSInputAddr(const Function &F) {
|
|
return getIntegerAttribute(F, "InitialPSInputAddr", 0);
|
|
}
|
|
|
|
bool isShader(CallingConv::ID cc) {
|
|
switch(cc) {
|
|
case CallingConv::AMDGPU_VS:
|
|
case CallingConv::AMDGPU_GS:
|
|
case CallingConv::AMDGPU_PS:
|
|
case CallingConv::AMDGPU_CS:
|
|
return true;
|
|
default:
|
|
return false;
|
|
}
|
|
}
|
|
|
|
bool isCompute(CallingConv::ID cc) {
|
|
return !isShader(cc) || cc == CallingConv::AMDGPU_CS;
|
|
}
|
|
|
|
bool isSI(const MCSubtargetInfo &STI) {
|
|
return STI.getFeatureBits()[AMDGPU::FeatureSouthernIslands];
|
|
}
|
|
|
|
bool isCI(const MCSubtargetInfo &STI) {
|
|
return STI.getFeatureBits()[AMDGPU::FeatureSeaIslands];
|
|
}
|
|
|
|
bool isVI(const MCSubtargetInfo &STI) {
|
|
return STI.getFeatureBits()[AMDGPU::FeatureVolcanicIslands];
|
|
}
|
|
|
|
unsigned getMCReg(unsigned Reg, const MCSubtargetInfo &STI) {
|
|
|
|
switch(Reg) {
|
|
default: break;
|
|
case AMDGPU::FLAT_SCR:
|
|
assert(!isSI(STI));
|
|
return isCI(STI) ? AMDGPU::FLAT_SCR_ci : AMDGPU::FLAT_SCR_vi;
|
|
|
|
case AMDGPU::FLAT_SCR_LO:
|
|
assert(!isSI(STI));
|
|
return isCI(STI) ? AMDGPU::FLAT_SCR_LO_ci : AMDGPU::FLAT_SCR_LO_vi;
|
|
|
|
case AMDGPU::FLAT_SCR_HI:
|
|
assert(!isSI(STI));
|
|
return isCI(STI) ? AMDGPU::FLAT_SCR_HI_ci : AMDGPU::FLAT_SCR_HI_vi;
|
|
}
|
|
return Reg;
|
|
}
|
|
|
|
bool isSISrcOperand(const MCInstrDesc &Desc, unsigned OpNo) {
|
|
unsigned OpType = Desc.OpInfo[OpNo].OperandType;
|
|
return OpType >= AMDGPU::OPERAND_SRC_FIRST &&
|
|
OpType <= AMDGPU::OPERAND_SRC_LAST;
|
|
}
|
|
|
|
bool isSISrcFPOperand(const MCInstrDesc &Desc, unsigned OpNo) {
|
|
unsigned OpType = Desc.OpInfo[OpNo].OperandType;
|
|
switch (OpType) {
|
|
case AMDGPU::OPERAND_REG_IMM_FP32:
|
|
case AMDGPU::OPERAND_REG_IMM_FP64:
|
|
case AMDGPU::OPERAND_REG_IMM_FP16:
|
|
case AMDGPU::OPERAND_REG_INLINE_C_FP32:
|
|
case AMDGPU::OPERAND_REG_INLINE_C_FP64:
|
|
case AMDGPU::OPERAND_REG_INLINE_C_FP16:
|
|
return true;
|
|
default:
|
|
return false;
|
|
}
|
|
}
|
|
|
|
bool isSISrcInlinableOperand(const MCInstrDesc &Desc, unsigned OpNo) {
|
|
unsigned OpType = Desc.OpInfo[OpNo].OperandType;
|
|
return OpType >= AMDGPU::OPERAND_REG_INLINE_C_FIRST &&
|
|
OpType <= AMDGPU::OPERAND_REG_INLINE_C_LAST;
|
|
}
|
|
|
|
// Avoid using MCRegisterClass::getSize, since that function will go away
|
|
// (move from MC* level to Target* level). Return size in bits.
|
|
unsigned getRegBitWidth(unsigned RCID) {
|
|
switch (RCID) {
|
|
case AMDGPU::SGPR_32RegClassID:
|
|
case AMDGPU::VGPR_32RegClassID:
|
|
case AMDGPU::VS_32RegClassID:
|
|
case AMDGPU::SReg_32RegClassID:
|
|
case AMDGPU::SReg_32_XM0RegClassID:
|
|
return 32;
|
|
case AMDGPU::SGPR_64RegClassID:
|
|
case AMDGPU::VS_64RegClassID:
|
|
case AMDGPU::SReg_64RegClassID:
|
|
case AMDGPU::VReg_64RegClassID:
|
|
return 64;
|
|
case AMDGPU::VReg_96RegClassID:
|
|
return 96;
|
|
case AMDGPU::SGPR_128RegClassID:
|
|
case AMDGPU::SReg_128RegClassID:
|
|
case AMDGPU::VReg_128RegClassID:
|
|
return 128;
|
|
case AMDGPU::SReg_256RegClassID:
|
|
case AMDGPU::VReg_256RegClassID:
|
|
return 256;
|
|
case AMDGPU::SReg_512RegClassID:
|
|
case AMDGPU::VReg_512RegClassID:
|
|
return 512;
|
|
default:
|
|
llvm_unreachable("Unexpected register class");
|
|
}
|
|
}
|
|
|
|
unsigned getRegBitWidth(const MCRegisterClass &RC) {
|
|
return getRegBitWidth(RC.getID());
|
|
}
|
|
|
|
unsigned getRegOperandSize(const MCRegisterInfo *MRI, const MCInstrDesc &Desc,
|
|
unsigned OpNo) {
|
|
unsigned RCID = Desc.OpInfo[OpNo].RegClass;
|
|
return getRegBitWidth(MRI->getRegClass(RCID)) / 8;
|
|
}
|
|
|
|
bool isInlinableLiteral64(int64_t Literal, bool HasInv2Pi) {
|
|
if (Literal >= -16 && Literal <= 64)
|
|
return true;
|
|
|
|
uint64_t Val = static_cast<uint64_t>(Literal);
|
|
return (Val == DoubleToBits(0.0)) ||
|
|
(Val == DoubleToBits(1.0)) ||
|
|
(Val == DoubleToBits(-1.0)) ||
|
|
(Val == DoubleToBits(0.5)) ||
|
|
(Val == DoubleToBits(-0.5)) ||
|
|
(Val == DoubleToBits(2.0)) ||
|
|
(Val == DoubleToBits(-2.0)) ||
|
|
(Val == DoubleToBits(4.0)) ||
|
|
(Val == DoubleToBits(-4.0)) ||
|
|
(Val == 0x3fc45f306dc9c882 && HasInv2Pi);
|
|
}
|
|
|
|
bool isInlinableLiteral32(int32_t Literal, bool HasInv2Pi) {
|
|
if (Literal >= -16 && Literal <= 64)
|
|
return true;
|
|
|
|
// The actual type of the operand does not seem to matter as long
|
|
// as the bits match one of the inline immediate values. For example:
|
|
//
|
|
// -nan has the hexadecimal encoding of 0xfffffffe which is -2 in decimal,
|
|
// so it is a legal inline immediate.
|
|
//
|
|
// 1065353216 has the hexadecimal encoding 0x3f800000 which is 1.0f in
|
|
// floating-point, so it is a legal inline immediate.
|
|
|
|
uint32_t Val = static_cast<uint32_t>(Literal);
|
|
return (Val == FloatToBits(0.0f)) ||
|
|
(Val == FloatToBits(1.0f)) ||
|
|
(Val == FloatToBits(-1.0f)) ||
|
|
(Val == FloatToBits(0.5f)) ||
|
|
(Val == FloatToBits(-0.5f)) ||
|
|
(Val == FloatToBits(2.0f)) ||
|
|
(Val == FloatToBits(-2.0f)) ||
|
|
(Val == FloatToBits(4.0f)) ||
|
|
(Val == FloatToBits(-4.0f)) ||
|
|
(Val == 0x3e22f983 && HasInv2Pi);
|
|
}
|
|
|
|
bool isInlinableLiteral16(int16_t Literal, bool HasInv2Pi) {
|
|
if (!HasInv2Pi)
|
|
return false;
|
|
|
|
if (Literal >= -16 && Literal <= 64)
|
|
return true;
|
|
|
|
uint16_t Val = static_cast<uint16_t>(Literal);
|
|
return Val == 0x3C00 || // 1.0
|
|
Val == 0xBC00 || // -1.0
|
|
Val == 0x3800 || // 0.5
|
|
Val == 0xB800 || // -0.5
|
|
Val == 0x4000 || // 2.0
|
|
Val == 0xC000 || // -2.0
|
|
Val == 0x4400 || // 4.0
|
|
Val == 0xC400 || // -4.0
|
|
Val == 0x3118; // 1/2pi
|
|
}
|
|
|
|
} // End namespace AMDGPU
|
|
} // End namespace llvm
|