mirror of
https://github.com/RPCSX/llvm.git
synced 2025-01-06 03:38:24 +00:00
03d317688d
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 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@281050 91177308-0d34-0410-b5e6-96231b3b80d8
275 lines
7.9 KiB
C++
275 lines
7.9 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
|
|
|
|
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 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_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
|