llvm-project/llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.cpp

299 lines
8.3 KiB
C++
Raw Normal View History

//===-- 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"
AMDGPU] Assembler: better support for immediate literals in assembler. Summary: Prevously assembler parsed all literals as either 32-bit integers or 32-bit floating-point values. Because of this we couldn't support f64 literals. E.g. in instruction "v_fract_f64 v[0:1], 0.5", literal 0.5 was encoded as 32-bit literal 0x3f000000, which is incorrect and will be interpreted as 3.0517578125E-5 instead of 0.5. Correct encoding is inline constant 240 (optimal) or 32-bit literal 0x3FE00000 at least. With this change the way immediate literals are parsed is changed. All literals are always parsed as 64-bit values either integer or floating-point. Then we convert parsed literals to correct form based on information about type of operand parsed (was literal floating or binary) and type of expected instruction operands (is this f32/64 or b32/64 instruction). Here are rules how we convert literals: - We parsed fp literal: - Instruction expects 64-bit operand: - If parsed literal is inlinable (e.g. v_fract_f64_e32 v[0:1], 0.5) - then we do nothing this literal - Else if literal is not-inlinable but instruction requires to inline it (e.g. this is e64 encoding, v_fract_f64_e64 v[0:1], 1.5) - report error - Else literal is not-inlinable but we can encode it as additional 32-bit literal constant - If instruction expect fp operand type (f64) - Check if low 32 bits of literal are zeroes (e.g. v_fract_f64 v[0:1], 1.5) - If so then do nothing - Else (e.g. v_fract_f64 v[0:1], 3.1415) - report warning that low 32 bits will be set to zeroes and precision will be lost - set low 32 bits of literal to zeroes - Instruction expects integer operand type (e.g. s_mov_b64_e32 s[0:1], 1.5) - report error as it is unclear how to encode this literal - Instruction expects 32-bit operand: - Convert parsed 64 bit fp literal to 32 bit fp. Allow lose of precision but not overflow or underflow - Is this literal inlinable and are we required to inline literal (e.g. v_trunc_f32_e64 v0, 0.5) - do nothing - Else report error - Do nothing. We can encode any other 32-bit fp literal (e.g. v_trunc_f32 v0, 10000000.0) - Parsed binary literal: - Is this literal inlinable (e.g. v_trunc_f32_e32 v0, 35) - do nothing - Else, are we required to inline this literal (e.g. v_trunc_f32_e64 v0, 35) - report error - Else, literal is not-inlinable and we are not required to inline it - Are high 32 bit of literal zeroes or same as sign bit (32 bit) - do nothing (e.g. v_trunc_f32 v0, 0xdeadbeef) - Else - report error (e.g. v_trunc_f32 v0, 0x123456789abcdef0) For this change it is required that we know operand types of instruction (are they f32/64 or b32/64). I added several new register operands (they extend previous register operands) and set operand types to corresponding types: ''' enum OperandType { OPERAND_REG_IMM32_INT, OPERAND_REG_IMM32_FP, OPERAND_REG_INLINE_C_INT, OPERAND_REG_INLINE_C_FP, } ''' This is not working yet: - Several tests are failing - Problems with predicate methods for inline immediates - LLVM generated assembler parts try to select e64 encoding before e32. More changes are required for several AsmOperands. Reviewers: vpykhtin, tstellarAMD Subscribers: arsenm, kzhuravl, artem.tamazov Differential Revision: https://reviews.llvm.org/D22922 llvm-svn: 281050
2016-09-09 22:44:04 +08:00
#include "SIDefines.h"
#include "llvm/IR/LLVMContext.h"
#include "llvm/IR/Function.h"
#include "llvm/IR/GlobalValue.h"
#include "llvm/MC/MCContext.h"
AMDGPU] Assembler: better support for immediate literals in assembler. Summary: Prevously assembler parsed all literals as either 32-bit integers or 32-bit floating-point values. Because of this we couldn't support f64 literals. E.g. in instruction "v_fract_f64 v[0:1], 0.5", literal 0.5 was encoded as 32-bit literal 0x3f000000, which is incorrect and will be interpreted as 3.0517578125E-5 instead of 0.5. Correct encoding is inline constant 240 (optimal) or 32-bit literal 0x3FE00000 at least. With this change the way immediate literals are parsed is changed. All literals are always parsed as 64-bit values either integer or floating-point. Then we convert parsed literals to correct form based on information about type of operand parsed (was literal floating or binary) and type of expected instruction operands (is this f32/64 or b32/64 instruction). Here are rules how we convert literals: - We parsed fp literal: - Instruction expects 64-bit operand: - If parsed literal is inlinable (e.g. v_fract_f64_e32 v[0:1], 0.5) - then we do nothing this literal - Else if literal is not-inlinable but instruction requires to inline it (e.g. this is e64 encoding, v_fract_f64_e64 v[0:1], 1.5) - report error - Else literal is not-inlinable but we can encode it as additional 32-bit literal constant - If instruction expect fp operand type (f64) - Check if low 32 bits of literal are zeroes (e.g. v_fract_f64 v[0:1], 1.5) - If so then do nothing - Else (e.g. v_fract_f64 v[0:1], 3.1415) - report warning that low 32 bits will be set to zeroes and precision will be lost - set low 32 bits of literal to zeroes - Instruction expects integer operand type (e.g. s_mov_b64_e32 s[0:1], 1.5) - report error as it is unclear how to encode this literal - Instruction expects 32-bit operand: - Convert parsed 64 bit fp literal to 32 bit fp. Allow lose of precision but not overflow or underflow - Is this literal inlinable and are we required to inline literal (e.g. v_trunc_f32_e64 v0, 0.5) - do nothing - Else report error - Do nothing. We can encode any other 32-bit fp literal (e.g. v_trunc_f32 v0, 10000000.0) - Parsed binary literal: - Is this literal inlinable (e.g. v_trunc_f32_e32 v0, 35) - do nothing - Else, are we required to inline this literal (e.g. v_trunc_f32_e64 v0, 35) - report error - Else, literal is not-inlinable and we are not required to inline it - Are high 32 bit of literal zeroes or same as sign bit (32 bit) - do nothing (e.g. v_trunc_f32 v0, 0xdeadbeef) - Else - report error (e.g. v_trunc_f32 v0, 0x123456789abcdef0) For this change it is required that we know operand types of instruction (are they f32/64 or b32/64). I added several new register operands (they extend previous register operands) and set operand types to corresponding types: ''' enum OperandType { OPERAND_REG_IMM32_INT, OPERAND_REG_IMM32_FP, OPERAND_REG_INLINE_C_INT, OPERAND_REG_INLINE_C_FP, } ''' This is not working yet: - Several tests are failing - Problems with predicate methods for inline immediates - LLVM generated assembler parts try to select e64 encoding before e32. More changes are required for several AsmOperands. Reviewers: vpykhtin, tstellarAMD Subscribers: arsenm, kzhuravl, artem.tamazov Differential Revision: https://reviews.llvm.org/D22922 llvm-svn: 281050
2016-09-09 22:44:04 +08:00
#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
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(FeatureISAVersion8_0_0))
return {8, 0, 0};
if (Features.test(FeatureISAVersion8_0_1))
return {8, 0, 1};
if (Features.test(FeatureISAVersion8_0_3))
return {8, 0, 3};
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;
}
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 getVmcntMask(IsaVersion Version) {
return 0xf;
}
unsigned getVmcntShift(IsaVersion Version) {
return 0;
}
unsigned getExpcntMask(IsaVersion Version) {
return 0x7;
}
unsigned getExpcntShift(IsaVersion Version) {
return 4;
}
unsigned getLgkmcntMask(IsaVersion Version) {
return 0xf;
}
unsigned getLgkmcntShift(IsaVersion Version) {
return 8;
}
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;
}
AMDGPU] Assembler: better support for immediate literals in assembler. Summary: Prevously assembler parsed all literals as either 32-bit integers or 32-bit floating-point values. Because of this we couldn't support f64 literals. E.g. in instruction "v_fract_f64 v[0:1], 0.5", literal 0.5 was encoded as 32-bit literal 0x3f000000, which is incorrect and will be interpreted as 3.0517578125E-5 instead of 0.5. Correct encoding is inline constant 240 (optimal) or 32-bit literal 0x3FE00000 at least. With this change the way immediate literals are parsed is changed. All literals are always parsed as 64-bit values either integer or floating-point. Then we convert parsed literals to correct form based on information about type of operand parsed (was literal floating or binary) and type of expected instruction operands (is this f32/64 or b32/64 instruction). Here are rules how we convert literals: - We parsed fp literal: - Instruction expects 64-bit operand: - If parsed literal is inlinable (e.g. v_fract_f64_e32 v[0:1], 0.5) - then we do nothing this literal - Else if literal is not-inlinable but instruction requires to inline it (e.g. this is e64 encoding, v_fract_f64_e64 v[0:1], 1.5) - report error - Else literal is not-inlinable but we can encode it as additional 32-bit literal constant - If instruction expect fp operand type (f64) - Check if low 32 bits of literal are zeroes (e.g. v_fract_f64 v[0:1], 1.5) - If so then do nothing - Else (e.g. v_fract_f64 v[0:1], 3.1415) - report warning that low 32 bits will be set to zeroes and precision will be lost - set low 32 bits of literal to zeroes - Instruction expects integer operand type (e.g. s_mov_b64_e32 s[0:1], 1.5) - report error as it is unclear how to encode this literal - Instruction expects 32-bit operand: - Convert parsed 64 bit fp literal to 32 bit fp. Allow lose of precision but not overflow or underflow - Is this literal inlinable and are we required to inline literal (e.g. v_trunc_f32_e64 v0, 0.5) - do nothing - Else report error - Do nothing. We can encode any other 32-bit fp literal (e.g. v_trunc_f32 v0, 10000000.0) - Parsed binary literal: - Is this literal inlinable (e.g. v_trunc_f32_e32 v0, 35) - do nothing - Else, are we required to inline this literal (e.g. v_trunc_f32_e64 v0, 35) - report error - Else, literal is not-inlinable and we are not required to inline it - Are high 32 bit of literal zeroes or same as sign bit (32 bit) - do nothing (e.g. v_trunc_f32 v0, 0xdeadbeef) - Else - report error (e.g. v_trunc_f32 v0, 0x123456789abcdef0) For this change it is required that we know operand types of instruction (are they f32/64 or b32/64). I added several new register operands (they extend previous register operands) and set operand types to corresponding types: ''' enum OperandType { OPERAND_REG_IMM32_INT, OPERAND_REG_IMM32_FP, OPERAND_REG_INLINE_C_INT, OPERAND_REG_INLINE_C_FP, } ''' This is not working yet: - Several tests are failing - Problems with predicate methods for inline immediates - LLVM generated assembler parts try to select e64 encoding before e32. More changes are required for several AsmOperands. Reviewers: vpykhtin, tstellarAMD Subscribers: arsenm, kzhuravl, artem.tamazov Differential Revision: https://reviews.llvm.org/D22922 llvm-svn: 281050
2016-09-09 22:44:04 +08:00
bool isSISrcOperand(const MCInstrDesc &Desc, unsigned OpNo) {
unsigned OpType = Desc.OpInfo[OpNo].OperandType;
return OpType == AMDGPU::OPERAND_REG_IMM32_INT ||
OpType == AMDGPU::OPERAND_REG_IMM32_FP ||
OpType == AMDGPU::OPERAND_REG_INLINE_C_INT ||
OpType == AMDGPU::OPERAND_REG_INLINE_C_FP;
}
bool isSISrcFPOperand(const MCInstrDesc &Desc, unsigned OpNo) {
unsigned OpType = Desc.OpInfo[OpNo].OperandType;
return OpType == AMDGPU::OPERAND_REG_IMM32_FP ||
OpType == AMDGPU::OPERAND_REG_INLINE_C_FP;
}
bool isSISrcInlinableOperand(const MCInstrDesc &Desc, unsigned OpNo) {
unsigned OpType = Desc.OpInfo[OpNo].OperandType;
return OpType == AMDGPU::OPERAND_REG_INLINE_C_INT ||
OpType == AMDGPU::OPERAND_REG_INLINE_C_FP;
}
unsigned getRegOperandSize(const MCRegisterInfo *MRI, const MCInstrDesc &Desc,
unsigned OpNo) {
int RCID = Desc.OpInfo[OpNo].RegClass;
const MCRegisterClass &RC = MRI->getRegClass(RCID);
return RC.getSize();
}
bool isInlinableLiteral64(int64_t Literal, bool IsVI) {
if (Literal >= -16 && Literal <= 64)
return true;
double D = BitsToDouble(Literal);
if (D == 0.5 || D == -0.5 ||
D == 1.0 || D == -1.0 ||
D == 2.0 || D == -2.0 ||
D == 4.0 || D == -4.0)
return true;
if (IsVI && Literal == 0x3fc45f306dc9c882)
return true;
return false;
}
bool isInlinableLiteral32(int32_t Literal, bool IsVI) {
if (Literal >= -16 && Literal <= 64)
return true;
float F = BitsToFloat(Literal);
if (F == 0.5 || F == -0.5 ||
F == 1.0 || F == -1.0 ||
F == 2.0 || F == -2.0 ||
F == 4.0 || F == -4.0)
return true;
if (IsVI && Literal == 0x3e22f983)
return true;
return false;
}
} // End namespace AMDGPU
} // End namespace llvm