AMDGPU/SI: Emit HSA kernels with symbol type STT_AMDGPU_HSA_KERNEL

[arsenm]

LGTM

lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.h

34

Why does this need to be virtual?

[• tstellarAMD]

lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.h

34

This is the parent class.

lib/Target/AMDGPU/AMDGPUAsmPrinter.h

public:
 
   /// Implemented in AMDGPUMCInstLower.cpp
   void EmitInstruction(const MachineInstr *MI) override;
 
   void EmitFunctionBodyStart() override;
 
   void EmitEndOfAsmFile(Module &M) override;
 
+  void EmitFunctionEntryLabel() override;
+
   bool PrintAsmOperand(const MachineInstr *MI, unsigned OpNo,
                        unsigned AsmVariant, const char *ExtraCode,
                        raw_ostream &O) override;
 
 protected:
   std::vector<std::string> DisasmLines, HexLines;
   size_t DisasmLineMaxLen;
 };
 
 } // End anonymous llvm
 
 #endif

lib/Target/AMDGPU/AMDGPUAsmPrinter.cpp

void AMDGPUAsmPrinter::EmitEndOfAsmFile(Module &M) {
   // This label is used to mark the end of the .text section.
   const TargetLoweringObjectFile &TLOF = getObjFileLowering();
   OutStreamer->SwitchSection(TLOF.getTextSection());
   MCSymbol *EndOfTextLabel =
       OutContext.getOrCreateSymbol(StringRef(END_OF_TEXT_LABEL_NAME));
   OutStreamer->EmitLabel(EndOfTextLabel);
 }
 
+void AMDGPUAsmPrinter::EmitFunctionEntryLabel() {
+  const SIMachineFunctionInfo *MFI = MF->getInfo<SIMachineFunctionInfo>();
+  const AMDGPUSubtarget &STM = MF->getSubtarget<AMDGPUSubtarget>();
+  if (MFI->isKernel() && STM.isAmdHsaOS()) {
+    AMDGPUTargetStreamer *TS =
+        static_cast<AMDGPUTargetStreamer *>(OutStreamer->getTargetStreamer());
+    TS->EmitAMDGPUSymbolType(CurrentFnSym->getName(),
+                             ELF::STT_AMDGPU_HSA_KERNEL);
+  }
+
+  AsmPrinter::EmitFunctionEntryLabel();
+}
+
 bool AMDGPUAsmPrinter::runOnMachineFunction(MachineFunction &MF) {
 
   // The starting address of all shader programs must be 256 bytes aligned.
   MF.setAlignment(8);
 
   SetupMachineFunction(MF);
 
   MCContext &Context = getObjFileLowering().getContext();

lib/Target/AMDGPU/AMDGPUMachineFunction.h

public:
 
   /// Start of implicit kernel args
   unsigned ABIArgOffset;
 
   unsigned getShaderType() const {
     return ShaderType;
   }
 
+  bool isKernel() const {
+    // FIXME: Assume everything is a kernel until function calls are supported.
+    return true;
+  }
+
   unsigned ScratchSize;
   bool IsKernel;
 };
 
 }
 #endif

lib/Target/AMDGPU/AsmParser/AMDGPUAsmParser.cpp

 #include "llvm/MC/MCInst.h"
 #include "llvm/MC/MCInstrInfo.h"
 #include "llvm/MC/MCParser/MCAsmLexer.h"
 #include "llvm/MC/MCParser/MCAsmParser.h"
 #include "llvm/MC/MCParser/MCParsedAsmOperand.h"
 #include "llvm/MC/MCRegisterInfo.h"
 #include "llvm/MC/MCStreamer.h"
 #include "llvm/MC/MCSubtargetInfo.h"
+#include "llvm/MC/MCSymbolELF.h"
 #include "llvm/MC/MCTargetAsmParser.h"
+#include "llvm/Support/ELF.h"
 #include "llvm/Support/SourceMgr.h"
 #include "llvm/Support/TargetRegistry.h"
 #include "llvm/Support/raw_ostream.h"
 #include "llvm/Support/Debug.h"
 
 using namespace llvm;
 
 namespace {

 
 private:
   bool ParseDirectiveMajorMinor(uint32_t &Major, uint32_t &Minor);
   bool ParseDirectiveHSACodeObjectVersion();
   bool ParseDirectiveHSACodeObjectISA();
   bool ParseAMDKernelCodeTValue(StringRef ID, amd_kernel_code_t &Header);
   bool ParseDirectiveAMDKernelCodeT();
   bool ParseSectionDirectiveHSAText();
+  bool ParseDirectiveAMDGPUHsaKernel();
 
 public:
 public:
   enum AMDGPUMatchResultTy {
     Match_PreferE32 = FIRST_TARGET_MATCH_RESULT_TY
   };
 
   AMDGPUAsmParser(MCSubtargetInfo &STI, MCAsmParser &_Parser,

 }
 
 bool AMDGPUAsmParser::ParseSectionDirectiveHSAText() {
   getParser().getStreamer().SwitchSection(
       AMDGPU::getHSATextSection(getContext()));
   return false;
 }
 
+bool AMDGPUAsmParser::ParseDirectiveAMDGPUHsaKernel() {
+  if (getLexer().isNot(AsmToken::Identifier))
+    return TokError("expected symbol name");
+
+  StringRef KernelName = Parser.getTok().getString();
+
+  getTargetStreamer().EmitAMDGPUSymbolType(KernelName,
+                                           ELF::STT_AMDGPU_HSA_KERNEL);
+  Lex(); 
+  return false;
+}
+
 bool AMDGPUAsmParser::ParseDirective(AsmToken DirectiveID) {
   StringRef IDVal = DirectiveID.getString();
 
   if (IDVal == ".hsa_code_object_version")
     return ParseDirectiveHSACodeObjectVersion();
 
   if (IDVal == ".hsa_code_object_isa")
     return ParseDirectiveHSACodeObjectISA();
 
   if (IDVal == ".amd_kernel_code_t")
     return ParseDirectiveAMDKernelCodeT();
 
   if (IDVal == ".hsatext" || IDVal == ".text")
     return ParseSectionDirectiveHSAText();
 
+  if (IDVal == ".amdgpu_hsa_kernel")
+    return ParseDirectiveAMDGPUHsaKernel();
+
   return true;
 }
 
 static bool operandsHaveModifiers(const OperandVector &Operands) {
 
   for (unsigned i = 0, e = Operands.size(); i != e; ++i) {
     const AMDGPUOperand &Op = ((AMDGPUOperand&)*Operands[i]);
     if (Op.isRegKind() && Op.hasModifiers())

lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.h

virtual void EmitDirectiveHSACodeObjectVersion(uint32_t Major,
                                                  uint32_t Minor) = 0;
 
   virtual void EmitDirectiveHSACodeObjectISA(uint32_t Major, uint32_t Minor,
                                              uint32_t Stepping,
                                              StringRef VendorName,
                                              StringRef ArchName) = 0;
 
   virtual void EmitAMDKernelCodeT(const amd_kernel_code_t &Header) = 0;
+
+  virtual void EmitAMDGPUSymbolType(StringRef SymbolName, unsigned Type) = 0;
 };
 
 class AMDGPUTargetAsmStreamer : public AMDGPUTargetStreamer {
   formatted_raw_ostream &OS;
 public:
   AMDGPUTargetAsmStreamer(MCStreamer &S, formatted_raw_ostream &OS);
   void EmitDirectiveHSACodeObjectVersion(uint32_t Major,
                                          uint32_t Minor) override;
 
   void EmitDirectiveHSACodeObjectISA(uint32_t Major, uint32_t Minor,
                                      uint32_t Stepping, StringRef VendorName,
                                      StringRef ArchName) override;
 
   void EmitAMDKernelCodeT(const amd_kernel_code_t &Header) override;
+
+  void EmitAMDGPUSymbolType(StringRef SymbolName, unsigned Type) override;
 };
 
 class AMDGPUTargetELFStreamer : public AMDGPUTargetStreamer {
 
   enum NoteType {
     NT_AMDGPU_HSA_CODE_OBJECT_VERSION = 1,
     NT_AMDGPU_HSA_HSAIL = 2,
     NT_AMDGPU_HSA_ISA = 3,
void EmitDirectiveHSACodeObjectVersion(uint32_t Major,
                                          uint32_t Minor) override;
 
   void EmitDirectiveHSACodeObjectISA(uint32_t Major, uint32_t Minor,
                                      uint32_t Stepping, StringRef VendorName,
                                      StringRef ArchName) override;
 
   void EmitAMDKernelCodeT(const amd_kernel_code_t &Header) override;
 
+  void EmitAMDGPUSymbolType(StringRef SymbolName, unsigned Type) override;
 };
 
 }
 #endif

lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp

"\t\tcall_convention = " <<
         Header.call_convention << '\n' <<
     "\t\truntime_loader_kernel_symbol = " <<
         Header.runtime_loader_kernel_symbol << '\n' <<
     // TODO: control_directives
     "\t.end_amd_kernel_code_t\n";
 
 }
 
+void AMDGPUTargetAsmStreamer::EmitAMDGPUSymbolType(StringRef SymbolName,
+                                                   unsigned Type) {
+  switch (Type) {
+    default: llvm_unreachable("Invalid AMDGPU symbol type");
+    case ELF::STT_AMDGPU_HSA_KERNEL:
+      OS << "\t.amdgpu_hsa_kernel " << SymbolName << '\n' ;
+      break;
+  }
+}
+
 //===----------------------------------------------------------------------===//
 // AMDGPUTargetELFStreamer
 //===----------------------------------------------------------------------===//
 
 AMDGPUTargetELFStreamer::AMDGPUTargetELFStreamer(MCStreamer &S)
     : AMDGPUTargetStreamer(S), Streamer(S) { }
 
 MCELFStreamer &AMDGPUTargetELFStreamer::getStreamer() {
AMDGPUTargetELFStreamer::EmitAMDKernelCodeT(const amd_kernel_code_t &Header) {
   OS.PushSection();
   // The MCObjectFileInfo that is available to the assembler is a generic
   // implementation and not AMDGPUHSATargetObjectFile, so we can't use
   // MCObjectFileInfo::getTextSection() here for fetching the HSATextSection.
   OS.SwitchSection(AMDGPU::getHSATextSection(OS.getContext()));
   OS.EmitBytes(StringRef((const char*)&Header, sizeof(Header)));
   OS.PopSection();
 }
+
+void AMDGPUTargetELFStreamer::EmitAMDGPUSymbolType(StringRef SymbolName,
+                                                   unsigned Type) {
+  MCSymbolELF *Symbol = cast<MCSymbolELF>(
+      getStreamer().getContext().getOrCreateSymbol(SymbolName));
+  Symbol->setType(ELF::STT_AMDGPU_HSA_KERNEL);
+}

test/CodeGen/AMDGPU/hsa.ll

 ; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=kaveri | FileCheck --check-prefix=HSA-CI --check-prefix=HSA %s
 ; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=carrizo | FileCheck --check-prefix=HSA-VI --check-prefix=HSA %s
-; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=kaveri -filetype=obj  | llvm-readobj -s -sd | FileCheck --check-prefix=ELF %s
-; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=kaveri | llvm-mc -filetype=obj -triple amdgcn--amdhsa -mcpu=kaveri | llvm-readobj -s -sd | FileCheck %s --check-prefix=ELF
+; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=kaveri -filetype=obj  | llvm-readobj -symbols -s -sd | FileCheck --check-prefix=ELF %s
+; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=kaveri | llvm-mc -filetype=obj -triple amdgcn--amdhsa -mcpu=kaveri | llvm-readobj -symbols -s -sd | FileCheck %s --check-prefix=ELF
 
 ; The SHT_NOTE section contains the output from the .hsa_code_object_*
 ; directives.
 
 ; ELF: Section {
 ; ELF: Name: .hsatext
 ; ELF: Type: SHT_PROGBITS (0x1)
 ; ELF: Flags [ (0xC00007)
 ; ELF: SHF_ALLOC (0x2)
 ; ELF: SHF_AMDGPU_HSA_AGENT (0x800000)
 ; ELF: SHF_AMDGPU_HSA_CODE (0x400000)
 ; ELF: SHF_EXECINSTR (0x4)
 ; ELF: SHF_WRITE (0x1)
 ; ELF: }
 
 ; ELF: SHT_NOTE
 ; ELF: 0000: 04000000 08000000 01000000 414D4400
 ; ELF: 0010: 01000000 00000000 04000000 1B000000
 ; ELF: 0020: 03000000 414D4400 04000700 07000000
 ; ELF: 0030: 00000000 00000000 414D4400 414D4447
 ; ELF: 0040: 50550000
 
+; ELF: Symbol {
+; ELF: Name: simple
+; ELF: Type: AMDGPU_HSA_KERNEL (0xA)
+; ELF: }
+
 ; HSA: .hsa_code_object_version 1,0
 ; HSA-CI: .hsa_code_object_isa 7,0,0,"AMD","AMDGPU"
 ; HSA-VI: .hsa_code_object_isa 8,0,1,"AMD","AMDGPU"
 
 ; HSA: .hsatext
 
+; HSA: .amdgpu_hsa_kernel simple
 ; HSA: {{^}}simple:
 ; HSA: .amd_kernel_code_t
 ; HSA: .end_amd_kernel_code_t
 ; HSA: s_load_dwordx2 s[{{[0-9]+:[0-9]+}}], s[0:1], 0x0
 
 ; Make sure we are setting the ATC bit:
 ; HSA-CI: s_mov_b32 s[[HI:[0-9]]], 0x100f000
 ; On VI+ we also need to set MTYPE = 2
 ; HSA-VI: s_mov_b32 s[[HI:[0-9]]], 0x1100f000
 ; HSA: buffer_store_dword v{{[0-9]+}}, s[0:[[HI]]], 0
 
 define void @simple(i32 addrspace(1)* %out) {
 entry:
   store i32 0, i32 addrspace(1)* %out
   ret void
 }

test/MC/AMDGPU/hsa.s

 // RUN: llvm-mc -triple amdgcn--amdhsa -mcpu=kaveri -show-encoding %s | FileCheck %s --check-prefix=ASM
-// RUN: llvm-mc -filetype=obj -triple amdgcn--amdhsa -mcpu=kaveri -show-encoding %s | llvm-readobj -s -sd | FileCheck %s --check-prefix=ELF
+// RUN: llvm-mc -filetype=obj -triple amdgcn--amdhsa -mcpu=kaveri -show-encoding %s | llvm-readobj -symbols -s -sd | FileCheck %s --check-prefix=ELF
 
 // ELF: Section {
 // ELF: Name: .hsatext
 // ELF: Type: SHT_PROGBITS (0x1)
 // ELF: Flags [ (0xC00007)
 // ELF: SHF_ALLOC (0x2)
 // ELF: SHF_AMDGPU_HSA_AGENT (0x800000)
 // ELF: SHF_AMDGPU_HSA_CODE (0x400000)
 // ELF: SHF_EXECINSTR (0x4)
 // ELF: SHF_WRITE (0x1)
-// ELF: }
 
 // ELF: SHT_NOTE
 // ELF: 0000: 04000000 08000000 01000000 414D4400
 // ELF: 0010: 01000000 00000000 04000000 1B000000
 // ELF: 0020: 03000000 414D4400 04000700 07000000
 // ELF: 0030: 00000000 00000000 414D4400 414D4447
 // ELF: 0040: 50550000
 
+// ELF: Symbol {
+// ELF: Name: amd_kernel_code_t_minimal
+// ELF: Type: AMDGPU_HSA_KERNEL (0xA)
+// ELF: Section: .hsatext
+// ELF: }
+// ELF: Symbol {
+// ELF: Name: amd_kernel_code_t_test_all
+// ELF: Type: AMDGPU_HSA_KERNEL (0xA)
+// ELF: Section: .hsatext
+// ELF: }
+
+
 .hsa_code_object_version 1,0
 // ASM: .hsa_code_object_version 1,0
 
 .hsa_code_object_isa 7,0,0,"AMD","AMDGPU"
 // ASM: .hsa_code_object_isa 7,0,0,"AMD","AMDGPU"
 
+.amdgpu_hsa_kernel amd_kernel_code_t_test_all
+.amdgpu_hsa_kernel amd_kernel_code_t_minimal
+
 .hsatext
 // ASM: .hsatext
 
 amd_kernel_code_t_test_all:
 ; Test all amd_kernel_code_t members with non-default values.
 .amd_kernel_code_t
   kernel_code_version_major = 100
   kernel_code_version_minor = 100