R600/SI: Add comments for number of used registers.

llvm-svn: 196467

llvm/lib/Target/R600/AMDGPUAsmPrinter.cpp

@@ -46,8 +46,7 @@ extern "C" void LLVMInitializeR600AsmPrinter() {
 }
 
 AMDGPUAsmPrinter::AMDGPUAsmPrinter(TargetMachine &TM, MCStreamer &Streamer)
-    : AsmPrinter(TM, Streamer)
+    : AsmPrinter(TM, Streamer) {
-{
   DisasmEnabled = TM.getSubtarget<AMDGPUSubtarget>().dumpCode() &&
                   ! Streamer.hasRawTextSupport();
 }
@@ -56,6 +55,7 @@ AMDGPUAsmPrinter::AMDGPUAsmPrinter(TargetMachine &TM, MCStreamer &Streamer)
 /// the call to EmitFunctionHeader(), which the MCPureStreamer can't handle.
 bool AMDGPUAsmPrinter::runOnMachineFunction(MachineFunction &MF) {
   SetupMachineFunction(MF);
+
   if (OutStreamer.hasRawTextSupport()) {
     OutStreamer.EmitRawText("@" + MF.getName() + ":");
   }
@@ -65,9 +65,12 @@ bool AMDGPUAsmPrinter::runOnMachineFunction(MachineFunction &MF) {
                                               ELF::SHT_PROGBITS, 0,
                                               SectionKind::getReadOnly());
   OutStreamer.SwitchSection(ConfigSection);
+
   const AMDGPUSubtarget &STM = TM.getSubtarget<AMDGPUSubtarget>();
+  SIProgramInfo KernelInfo;
   if (STM.getGeneration() > AMDGPUSubtarget::NORTHERN_ISLANDS) {
-    EmitProgramInfoSI(MF);
+    findNumUsedRegistersSI(MF, KernelInfo.NumSGPR, KernelInfo.NumVGPR);
+    EmitProgramInfoSI(MF, KernelInfo);
   } else {
     EmitProgramInfoR600(MF);
   }
@@ -79,6 +82,19 @@ bool AMDGPUAsmPrinter::runOnMachineFunction(MachineFunction &MF) {
   OutStreamer.SwitchSection(getObjFileLowering().getTextSection());
   EmitFunctionBody();
 
+  if (isVerbose() && OutStreamer.hasRawTextSupport()) {
+    const MCSectionELF *CommentSection
+      = Context.getELFSection(".AMDGPU.csdata",
+                              ELF::SHT_PROGBITS, 0,
+                              SectionKind::getReadOnly());
+    OutStreamer.SwitchSection(CommentSection);
+
+    OutStreamer.EmitRawText(
+      Twine("; Kernel info:\n") +
+      "; NumSgprs: " + Twine(KernelInfo.NumSGPR) + "\n" +
+      "; NumVgprs: " + Twine(KernelInfo.NumVGPR) + "\n");
+  }
+
   if (STM.dumpCode()) {
 #if !defined(NDEBUG) || defined(LLVM_ENABLE_DUMP)
     MF.dump();
@@ -166,8 +182,9 @@ void AMDGPUAsmPrinter::EmitProgramInfoR600(MachineFunction &MF) {
   }
 }
 
-void AMDGPUAsmPrinter::EmitProgramInfoSI(MachineFunction &MF) {
+void AMDGPUAsmPrinter::findNumUsedRegistersSI(MachineFunction &MF,
-  const AMDGPUSubtarget &STM = TM.getSubtarget<AMDGPUSubtarget>();
+                                              unsigned &NumSGPR,
+                                              unsigned &NumVGPR) const {
   unsigned MaxSGPR = 0;
   unsigned MaxVGPR = 0;
   bool VCCUsed = false;
@@ -252,10 +269,24 @@ void AMDGPUAsmPrinter::EmitProgramInfoSI(MachineFunction &MF) {
       }
     }
   }
-  if (VCCUsed) {
+
+  if (VCCUsed)
     MaxSGPR += 2;
-  }
+
-  SIMachineFunctionInfo * MFI = MF.getInfo<SIMachineFunctionInfo>();
+  NumSGPR = MaxSGPR;
+  NumVGPR = MaxVGPR;
+}
+
+void AMDGPUAsmPrinter::getSIProgramInfo(SIProgramInfo &Out,
+                                        MachineFunction &MF) const {
+  findNumUsedRegistersSI(MF, Out.NumSGPR, Out.NumVGPR);
+}
+
+void AMDGPUAsmPrinter::EmitProgramInfoSI(MachineFunction &MF,
+                                         const SIProgramInfo &KernelInfo) {
+  const AMDGPUSubtarget &STM = TM.getSubtarget<AMDGPUSubtarget>();
+
+  SIMachineFunctionInfo *MFI = MF.getInfo<SIMachineFunctionInfo>();
   unsigned RsrcReg;
   switch (MFI->ShaderType) {
   default: // Fall through
@@ -266,7 +297,8 @@ void AMDGPUAsmPrinter::EmitProgramInfoSI(MachineFunction &MF) {
   }
 
   OutStreamer.EmitIntValue(RsrcReg, 4);
-  OutStreamer.EmitIntValue(S_00B028_VGPRS(MaxVGPR / 4) | S_00B028_SGPRS(MaxSGPR / 8), 4);
+  OutStreamer.EmitIntValue(S_00B028_VGPRS(KernelInfo.NumVGPR / 4) |
+                           S_00B028_SGPRS(KernelInfo.NumSGPR / 8), 4);
 
   unsigned LDSAlignShift;
   if (STM.getGeneration() < AMDGPUSubtarget::SEA_ISLANDS) {

llvm/lib/Target/R600/AMDGPUAsmPrinter.h

@@ -22,6 +22,21 @@
 namespace llvm {
 
 class AMDGPUAsmPrinter : public AsmPrinter {
+private:
+  struct SIProgramInfo {
+    unsigned NumSGPR;
+    unsigned NumVGPR;
+  };
+
+  void getSIProgramInfo(SIProgramInfo &Out, MachineFunction &MF) const;
+  void findNumUsedRegistersSI(MachineFunction &MF,
+                              unsigned &NumSGPR,
+                              unsigned &NumVGPR) const;
+
+  /// \brief Emit register usage information so that the GPU driver
+  /// can correctly setup the GPU state.
+  void EmitProgramInfoR600(MachineFunction &MF);
+  void EmitProgramInfoSI(MachineFunction &MF, const SIProgramInfo &KernelInfo);
 
 public:
   explicit AMDGPUAsmPrinter(TargetMachine &TM, MCStreamer &Streamer);
@@ -32,11 +47,6 @@ public:
     return "AMDGPU Assembly Printer";
   }
 
-  /// \brief Emit register usage information so that the GPU driver
-  /// can correctly setup the GPU state.
-  void EmitProgramInfoR600(MachineFunction &MF);
-  void EmitProgramInfoSI(MachineFunction &MF);
-
   /// Implemented in AMDGPUMCInstLower.cpp
   virtual void EmitInstruction(const MachineInstr *MI);
 

llvm/test/CodeGen/R600/register-count-comments.ll

@@ -0,0 +1,20 @@
+; RUN: llc -march=r600 -mcpu=SI < %s | FileCheck -check-prefix=SI %s
+
+declare i32 @llvm.SI.tid() nounwind readnone
+
+; SI-LABEL: @foo:
+; SI: .section	.AMDGPU.csdata
+; SI: ; Kernel info:
+; SI: ; NumSgprs: {{[0-9]+}}
+; SI: ; NumVgprs: {{[0-9]+}}
+define void @foo(i32 addrspace(1)* noalias %out, i32 addrspace(1)* %abase, i32 addrspace(1)* %bbase) nounwind {
+  %tid = call i32 @llvm.SI.tid() nounwind readnone
+  %aptr = getelementptr i32 addrspace(1)* %abase, i32 %tid
+  %bptr = getelementptr i32 addrspace(1)* %bbase, i32 %tid
+  %outptr = getelementptr i32 addrspace(1)* %out, i32 %tid
+  %a = load i32 addrspace(1)* %aptr, align 4
+  %b = load i32 addrspace(1)* %bptr, align 4
+  %result = add i32 %a, %b
+  store i32 %result, i32 addrspace(1)* %outptr, align 4
+  ret void
+}