Index: lib/Target/AMDGPU/Utils/AMDKernelCodeTInfo.h =================================================================== --- /dev/null +++ lib/Target/AMDGPU/Utils/AMDKernelCodeTInfo.h @@ -0,0 +1,165 @@ +//===--------------------- AMDKernelCodeTInfo.h ---------------------------===// +// +// The LLVM Compiler Infrastructure +// +// This file is distributed under the University of Illinois Open Source +// License. See LICENSE.TXT for details. +// +//===----------------------------------------------------------------------===// +// +//===----------------------------------------------------------------------===// +// +/// \file - specifies tables for amd_kernel_code_t structure parsing/printing +// +//===----------------------------------------------------------------------===// + +#define QNAME(name) amd_kernel_code_t::name +#define FLD_T(name) decltype(QNAME(name)), &QNAME(name) + +#define FIELD2(sname, name) \ + RECORD(sname, printField, parseField) + +#define FIELD(name) FIELD2(name, name) + + +#define PRINTCODEPROP(name) \ + printBitField + +#define PARSECODEPROP(name) \ + parseBitField + +#define CODEPROP(name, shift) \ + RECORD(name, PRINTCODEPROP(shift), PARSECODEPROP(shift)) + +// have to define these lambdas because of Set/GetMacro +#define PRINTCOMP(GetMacro, Shift) \ +[](StringRef Name, const amd_kernel_code_t& C, raw_ostream& OS) { \ + printName(OS, Name) << \ + (int)GetMacro(C.compute_pgm_resource_registers >> Shift); \ +} +#define PARSECOMP(SetMacro, Shift) \ +[](amd_kernel_code_t& C, MCAsmLexer& Lexer, raw_ostream& Err) { \ + if (!expectEqualInt(Lexer, Err)) \ + return false; \ + const uint64_t Value = Lexer.getTok().getIntVal(); \ + C.compute_pgm_resource_registers |= SetMacro(Value) << Shift; \ + return true; \ +} + +#define COMPPGM(name, GetMacro, SetMacro, Shift) \ + RECORD(name, PRINTCOMP(GetMacro, Shift), PARSECOMP(SetMacro, Shift)) + +#define COMPPGM1(name, AccMacro) \ + COMPPGM(compute_pgm_rsrc1_##name, \ + G_00B848_##AccMacro, S_00B848_##AccMacro, 0) + +#define COMPPGM2(name, AccMacro) \ + COMPPGM(compute_pgm_rsrc2_##name, \ + G_00B84C_##AccMacro, S_00B84C_##AccMacro, 32) + +/////////////////////////////////////////////////////////////////////////////// +// Begin of the table +// Define RECORD(name, print, parse) in your code to get field definitions +// and include this file + +FIELD2(kernel_code_version_major, amd_kernel_code_version_major), +FIELD2(kernel_code_version_minor, amd_kernel_code_version_minor), +FIELD2(machine_kind, amd_machine_kind), +FIELD2(machine_version_major, amd_machine_version_major), +FIELD2(machine_version_minor, amd_machine_version_minor), +FIELD2(machine_version_stepping, amd_machine_version_stepping), +FIELD(kernel_code_entry_byte_offset), +FIELD(kernel_code_prefetch_byte_size), +FIELD(max_scratch_backing_memory_byte_size), +FIELD(compute_pgm_resource_registers), +FIELD(workitem_private_segment_byte_size), +FIELD(workgroup_group_segment_byte_size), +FIELD(gds_segment_byte_size), +FIELD(kernarg_segment_byte_size), +FIELD(workgroup_fbarrier_count), +FIELD(wavefront_sgpr_count), +FIELD(workitem_vgpr_count), +FIELD(reserved_vgpr_first), +FIELD(reserved_vgpr_count), +FIELD(reserved_sgpr_first), +FIELD(reserved_sgpr_count), +FIELD(debug_wavefront_private_segment_offset_sgpr), +FIELD(debug_private_segment_buffer_sgpr), +FIELD(kernarg_segment_alignment), +FIELD(group_segment_alignment), +FIELD(private_segment_alignment), +FIELD(wavefront_size), +FIELD(call_convention), +FIELD(runtime_loader_kernel_symbol), + +COMPPGM1(vgprs, VGPRS), +COMPPGM1(sgprs, SGPRS), +COMPPGM1(priority, PRIORITY), +COMPPGM1(float_mode, FLOAT_MODE), +COMPPGM1(priv, PRIV), +COMPPGM1(dx10_clamp, DX10_CLAMP), +COMPPGM1(debug_mode, DEBUG_MODE), +COMPPGM1(ieee_mode, IEEE_MODE), +COMPPGM2(scratch_en, SCRATCH_EN), +COMPPGM2(user_sgpr, USER_SGPR), +COMPPGM2(tgid_x_en, TGID_X_EN), +COMPPGM2(tgid_y_en, TGID_Y_EN), +COMPPGM2(tgid_z_en, TGID_Z_EN), +COMPPGM2(tg_size_en, TG_SIZE_EN), +COMPPGM2(tidig_comp_cnt, TIDIG_COMP_CNT), +COMPPGM2(excp_en_msb, EXCP_EN_MSB), +COMPPGM2(lds_size, LDS_SIZE), +COMPPGM2(excp_en, EXCP_EN), + +CODEPROP(enable_sgpr_private_segment_buffer, + ENABLE_SGPR_PRIVATE_SEGMENT_BUFFER), +CODEPROP(enable_sgpr_dispatch_ptr, + ENABLE_SGPR_DISPATCH_PTR), +CODEPROP(enable_sgpr_queue_ptr, + ENABLE_SGPR_QUEUE_PTR), +CODEPROP(enable_sgpr_kernarg_segment_ptr, + ENABLE_SGPR_KERNARG_SEGMENT_PTR), +CODEPROP(enable_sgpr_dispatch_id, + ENABLE_SGPR_DISPATCH_ID), +CODEPROP(enable_sgpr_flat_scratch_init, + ENABLE_SGPR_FLAT_SCRATCH_INIT), +CODEPROP(enable_sgpr_private_segment_size, + ENABLE_SGPR_PRIVATE_SEGMENT_SIZE), +CODEPROP(enable_sgpr_grid_workgroup_count_x, + ENABLE_SGPR_GRID_WORKGROUP_COUNT_X), +CODEPROP(enable_sgpr_grid_workgroup_count_y, + ENABLE_SGPR_GRID_WORKGROUP_COUNT_Y), +CODEPROP(enable_sgpr_grid_workgroup_count_z, + ENABLE_SGPR_GRID_WORKGROUP_COUNT_Z), +CODEPROP(enable_ordered_append_gds, + ENABLE_ORDERED_APPEND_GDS), +CODEPROP(private_element_size, + PRIVATE_ELEMENT_SIZE), +CODEPROP(is_ptr64, + IS_PTR64), +CODEPROP(is_dynamic_callstack, + IS_DYNAMIC_CALLSTACK), +CODEPROP(is_debug_enabled, + IS_DEBUG_SUPPORTED), +CODEPROP(is_xnack_enabled, + IS_XNACK_SUPPORTED) + +// end of the table +/////////////////////////////////////////////////////////////////////////////// + +#undef QNAME +#undef FLD_T +#undef FIELD2 +#undef FIELD +#undef PRINTCODEPROP +#undef PARSECODEPROP +#undef CODEPROP +#undef PRINTCOMP +#undef PAPSECOMP +#undef COMPPGM +#undef COMPPGM1 +#undef COMPPGM2 Index: lib/Target/AMDGPU/Utils/AMDKernelCodeTUtils.h =================================================================== --- /dev/null +++ lib/Target/AMDGPU/Utils/AMDKernelCodeTUtils.h @@ -0,0 +1,38 @@ +//===- AMDGPUKernelCodeTUtils.h - helpers for amd_kernel_code_t *- C++ -*-===// +// +// The LLVM Compiler Infrastructure +// +// This file is distributed under the University of Illinois Open Source +// License. See LICENSE.TXT for details. +// +//===----------------------------------------------------------------------===// +/// \file AMDKernelCodeTUtils.h +//===----------------------------------------------------------------------===// + +#ifndef AMDKERNELCODETUTILS_H +#define AMDKERNELCODETUTILS_H + +#include "AMDKernelCodeT.h" + +namespace llvm { + +class MCAsmLexer; +class raw_ostream; +class StringRef; + +void printAmdKernelCodeField(const amd_kernel_code_t& C, + int FldIndex, + raw_ostream& OS); + +void dumpAmdKernelCode(const amd_kernel_code_t* C, + raw_ostream& OS, + const char* tab); + +bool parseAmdKernelCodeField(StringRef ID, + MCAsmLexer& Lexer, + amd_kernel_code_t& C, + raw_ostream& Err); + +} + +#endif // AMDKERNELCODETUTILS_H Index: lib/Target/AMDGPU/Utils/AMDKernelCodeTUtils.cpp =================================================================== --- /dev/null +++ lib/Target/AMDGPU/Utils/AMDKernelCodeTUtils.cpp @@ -0,0 +1,165 @@ +//===--------------------AMDKernelCodeTUtils.cpp --------------------------===// +// +// The LLVM Compiler Infrastructure +// +// This file is distributed under the University of Illinois Open Source +// License. See LICENSE.TXT for details. +// +//===----------------------------------------------------------------------===// +// +//===----------------------------------------------------------------------===// +// +/// \file - utility functions to parse/print amd_kernel_code_t structure +// +//===----------------------------------------------------------------------===// + +#include "AMDKernelCodeTUtils.h" +#include "SIDefines.h" +#include +#include + +using namespace llvm; + +static ArrayRef get_amd_kernel_code_t_FldNames() { + static StringRef const table[] = { + "", // not found placeholder +#define RECORD(name, print, parse) #name +#include "AMDKernelCodeTInfo.h" +#undef RECORD + }; + return table; +} + +static StringMap createIndexMap(const ArrayRef& a) { + StringMap map; + for (auto Name : a) + map.insert(std::make_pair(Name, map.size())); + return std::move(map); +} + +static int get_amd_kernel_code_t_FieldIndex(StringRef name) { + static const auto map = createIndexMap(get_amd_kernel_code_t_FldNames()); + return map.lookup(name) - 1; // returns -1 if not found +} + +static StringRef get_amd_kernel_code_t_FieldName(int index) { + return get_amd_kernel_code_t_FldNames()[index + 1]; +} + + +// Field printing + +raw_ostream& printName(raw_ostream& OS, StringRef Name) { + return OS << Name << " = "; +} + +template +void printField(StringRef Name, + const amd_kernel_code_t& C, + raw_ostream& OS) { + printName(OS, Name) << (int)(C.*ptr); +} + +template +void printBitField(StringRef Name, + const amd_kernel_code_t& c, + raw_ostream& OS) { + const auto Mask = (static_cast(1) << width) - 1; + printName(OS, Name) << (int)((c.*ptr >> shift) & Mask); +} + +typedef void(*PrintFx)(StringRef, + const amd_kernel_code_t&, + raw_ostream&); + +static ArrayRef getPrinterTable() { + static const PrintFx table[] = { +#define RECORD(name, print, parse) print +#include "AMDKernelCodeTInfo.h" +#undef RECORD + }; + return table; +} + +void llvm::printAmdKernelCodeField(const amd_kernel_code_t& C, + int FldIndex, + raw_ostream& OS) { + auto Printer = getPrinterTable()[FldIndex]; + if (Printer) + Printer(get_amd_kernel_code_t_FieldName(FldIndex), C, OS); +} + +void llvm::dumpAmdKernelCode(const amd_kernel_code_t* C, + raw_ostream& OS, + const char* tab) { + const int Size = getPrinterTable().size(); + for (int i = 0; i < Size; ++i) { + OS << tab; + printAmdKernelCodeField(*C, i, OS); + OS << '\n'; + } +} + + +// Field parsing + +static bool expectEqualInt(MCAsmLexer& Lexer, raw_ostream& Err) { + if (Lexer.isNot(AsmToken::Equal)) { + Err << "expected '='"; + return false; + } + Lexer.Lex(); + if (Lexer.isNot(AsmToken::Integer)) { + Err << "integer literal expected"; + return false; + } + return true; +} + +template +bool parseField(amd_kernel_code_t& C, + MCAsmLexer& Lexer, + raw_ostream& Err) { + if (!expectEqualInt(Lexer, Err)) + return false; + C.*ptr = (T)Lexer.getTok().getIntVal(); + return true; +} + +template +bool parseBitField(amd_kernel_code_t& C, + MCAsmLexer& Lexer, + raw_ostream& Err) { + if (!expectEqualInt(Lexer, Err)) + return false; + const uint64_t Mask = ((1ull << width) - 1) << shift; + C.*ptr &= (T)~Mask; + C.*ptr |= (T)((Lexer.getTok().getIntVal() << shift) & Mask); + return true; +} + +typedef bool(*ParseFx)(amd_kernel_code_t&, + MCAsmLexer& Lexer, + raw_ostream& Err); + +static ArrayRef getParserTable() { + static const ParseFx table[] = { +#define RECORD(name, print, parse) parse +#include "AMDKernelCodeTInfo.h" +#undef RECORD + }; + return table; +} + +bool llvm::parseAmdKernelCodeField(StringRef ID, + MCAsmLexer& Lexer, + amd_kernel_code_t& C, + raw_ostream& Err) { + const int Idx = get_amd_kernel_code_t_FieldIndex(ID); + if (Idx < 0) { + Err << "unexpected amd_kernel_code_t field name " << ID; + return false; + } + auto Parser = getParserTable()[Idx]; + return Parser ? Parser(C, Lexer, Err) : false; +} Index: lib/Target/AMDGPU/Utils/CMakeLists.txt =================================================================== --- lib/Target/AMDGPU/Utils/CMakeLists.txt +++ lib/Target/AMDGPU/Utils/CMakeLists.txt @@ -1,3 +1,4 @@ add_llvm_library(LLVMAMDGPUUtils AMDGPUBaseInfo.cpp + AMDKernelCodeTUtils.cpp )