[AMDGPU] Emit debugger prologue and emit the rest of the debugger fields in the kernel code header

Debugger prologue is emitted if -mattr=+amdgpu-debugger-emit-prologue.

Debugger prologue writes work group IDs and work item IDs to scratch memory at fixed location in the following format:
  - offset 0: work group ID x
  - offset 4: work group ID y
  - offset 8: work group ID z
  - offset 16: work item ID x
  - offset 20: work item ID y
  - offset 24: work item ID z

Set
  - amd_kernel_code_t::debug_wavefront_private_segment_offset_sgpr to scratch wave offset reg
  - amd_kernel_code_t::debug_private_segment_buffer_sgpr to scratch rsrc reg
  - amd_kernel_code_t::is_debug_supported to true if all debugger features are enabled

Differential Revision: http://reviews.llvm.org/D20335

llvm-svn: 273769

11 files changed, 207 insertions, 5 deletions

diff --git a/llvm/lib/Target/AMDGPU/AMDGPU.td b/llvm/lib/Target/AMDGPU/AMDGPU.td
index dfd65fadf64..7736fd6c4cf 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPU.td
+++ b/llvm/lib/Target/AMDGPU/AMDGPU.td
@@ -329,6 +329,13 @@ def FeatureDebuggerReserveRegs : SubtargetFeature<
   "Reserve registers for debugger usage"
 >;
 
+def FeatureDebuggerEmitPrologue : SubtargetFeature<
+  "amdgpu-debugger-emit-prologue",
+  "DebuggerEmitPrologue",
+  "true",
+  "Emit debugger prologue"
+>;
+
 //===----------------------------------------------------------------------===//
 
 def AMDGPUInstrInfo : InstrInfo {
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUAsmPrinter.cpp b/llvm/lib/Target/AMDGPU/AMDGPUAsmPrinter.cpp
index b18c97acd72..c7784d7a76c 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUAsmPrinter.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUAsmPrinter.cpp
@@ -200,6 +200,13 @@ bool AMDGPUAsmPrinter::runOnMachineFunction(MachineFunction &MF) {
       OutStreamer->emitRawComment(" ReservedVGPRCount: " + Twine(KernelInfo.ReservedVGPRCount),
                                   false);
 
+      if (MF.getSubtarget<SISubtarget>().debuggerEmitPrologue()) {
+        OutStreamer->emitRawComment(" DebuggerWavefrontPrivateSegmentOffsetSGPR: s" +
+                                    Twine(KernelInfo.DebuggerWavefrontPrivateSegmentOffsetSGPR), false);
+        OutStreamer->emitRawComment(" DebuggerPrivateSegmentBufferSGPR: s" +
+                                    Twine(KernelInfo.DebuggerPrivateSegmentBufferSGPR), false);
+      }
+
       OutStreamer->emitRawComment(" COMPUTE_PGM_RSRC2:USER_SGPR: " +
                                   Twine(G_00B84C_USER_SGPR(KernelInfo.ComputePGMRSrc2)),
                                   false);
@@ -444,6 +451,16 @@ void AMDGPUAsmPrinter::getSIProgramInfo(SIProgramInfo &ProgInfo,
     MaxVGPR += MFI->getDebuggerReservedVGPRCount();
   }
 
+  // Update DebuggerWavefrontPrivateSegmentOffsetSGPR and
+  // DebuggerPrivateSegmentBufferSGPR fields if "amdgpu-debugger-emit-prologue"
+  // attribute was specified.
+  if (STM.debuggerEmitPrologue()) {
+    ProgInfo.DebuggerWavefrontPrivateSegmentOffsetSGPR =
+      RI->getHWRegIndex(MFI->getScratchWaveOffsetReg());
+    ProgInfo.DebuggerPrivateSegmentBufferSGPR =
+      RI->getHWRegIndex(MFI->getScratchRSrcReg());
+  }
+
   // We found the maximum register index. They start at 0, so add one to get the
   // number of registers.
   ProgInfo.NumVGPR = MaxVGPR + 1;
@@ -670,6 +687,9 @@ void AMDGPUAsmPrinter::EmitAmdKernelCodeT(const MachineFunction &MF,
   if (MFI->hasDispatchPtr())
     header.code_properties |= AMD_CODE_PROPERTY_ENABLE_SGPR_DISPATCH_PTR;
 
+  if (STM.debuggerSupported())
+    header.code_properties |= AMD_CODE_PROPERTY_IS_DEBUG_SUPPORTED;
+
   if (STM.isXNACKEnabled())
     header.code_properties |= AMD_CODE_PROPERTY_IS_XNACK_SUPPORTED;
 
@@ -681,6 +701,13 @@ void AMDGPUAsmPrinter::EmitAmdKernelCodeT(const MachineFunction &MF,
   header.reserved_vgpr_first = KernelInfo.ReservedVGPRFirst;
   header.reserved_vgpr_count = KernelInfo.ReservedVGPRCount;
 
+  if (STM.debuggerEmitPrologue()) {
+    header.debug_wavefront_private_segment_offset_sgpr =
+      KernelInfo.DebuggerWavefrontPrivateSegmentOffsetSGPR;
+    header.debug_private_segment_buffer_sgpr =
+      KernelInfo.DebuggerPrivateSegmentBufferSGPR;
+  }
+
   AMDGPUTargetStreamer *TS =
       static_cast<AMDGPUTargetStreamer *>(OutStreamer->getTargetStreamer());
 
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUAsmPrinter.h b/llvm/lib/Target/AMDGPU/AMDGPUAsmPrinter.h
index 87f953fce27..2d44ffefd80 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUAsmPrinter.h
+++ b/llvm/lib/Target/AMDGPU/AMDGPUAsmPrinter.h
@@ -42,6 +42,8 @@ private:
       FlatUsed(false),
       ReservedVGPRFirst(0),
       ReservedVGPRCount(0),
+      DebuggerWavefrontPrivateSegmentOffsetSGPR((uint16_t)-1),
+      DebuggerPrivateSegmentBufferSGPR((uint16_t)-1),
       VCCUsed(false),
       CodeLen(0) {}
 
@@ -75,6 +77,14 @@ private:
     // The number of consecutive VGPRs reserved.
     uint16_t ReservedVGPRCount;
 
+    // Fixed SGPR number used to hold wave scratch offset for entire kernel
+    // execution, or uint16_t(-1) if the register is not used or not known.
+    uint16_t DebuggerWavefrontPrivateSegmentOffsetSGPR;
+    // Fixed SGPR number of the first 4 SGPRs used to hold scratch V# for entire
+    // kernel execution, or uint16_t(-1) if the register is not used or not
+    // known.
+    uint16_t DebuggerPrivateSegmentBufferSGPR;
+
     // Bonus information for debugging.
     bool VCCUsed;
     uint64_t CodeLen;
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUSubtarget.cpp b/llvm/lib/Target/AMDGPU/AMDGPUSubtarget.cpp
index c6ac84bd3a3..e973f8e4837 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUSubtarget.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUSubtarget.cpp
@@ -101,6 +101,7 @@ AMDGPUSubtarget::AMDGPUSubtarget(const Triple &TT, StringRef GPU, StringRef FS,
     EnableXNACK(false),
     DebuggerInsertNops(false),
     DebuggerReserveRegs(false),
+    DebuggerEmitPrologue(false),
 
     EnableVGPRSpilling(false),
     EnablePromoteAlloca(false),
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUSubtarget.h b/llvm/lib/Target/AMDGPU/AMDGPUSubtarget.h
index 3c1bb5c07f0..53117e3cb60 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUSubtarget.h
+++ b/llvm/lib/Target/AMDGPU/AMDGPUSubtarget.h
@@ -77,6 +77,7 @@ protected:
   bool EnableXNACK;
   bool DebuggerInsertNops;
   bool DebuggerReserveRegs;
+  bool DebuggerEmitPrologue;
 
   // Used as options.
   bool EnableVGPRSpilling;
@@ -402,6 +403,11 @@ public:
     return EnableSIScheduler;
   }
 
+  bool debuggerSupported() const {
+    return debuggerInsertNops() && debuggerReserveRegs() &&
+      debuggerEmitPrologue();
+  }
+
   bool debuggerInsertNops() const {
     return DebuggerInsertNops;
   }
@@ -410,6 +416,10 @@ public:
     return DebuggerReserveRegs;
   }
 
+  bool debuggerEmitPrologue() const {
+    return DebuggerEmitPrologue;
+  }
+
   bool loadStoreOptEnabled() const {
     return EnableLoadStoreOpt;
   }
diff --git a/llvm/lib/Target/AMDGPU/SIFrameLowering.cpp b/llvm/lib/Target/AMDGPU/SIFrameLowering.cpp
index 1f3b361175e..03b11f0fd38 100644
--- a/llvm/lib/Target/AMDGPU/SIFrameLowering.cpp
+++ b/llvm/lib/Target/AMDGPU/SIFrameLowering.cpp
@@ -39,6 +39,12 @@ static ArrayRef<MCPhysReg> getAllSGPRs() {
 
 void SIFrameLowering::emitPrologue(MachineFunction &MF,
                                    MachineBasicBlock &MBB) const {
+  // Emit debugger prologue if "amdgpu-debugger-emit-prologue" attribute was
+  // specified.
+  const SISubtarget &ST = MF.getSubtarget<SISubtarget>();
+  if (ST.debuggerEmitPrologue())
+    emitDebuggerPrologue(MF, MBB);
+
   if (!MF.getFrameInfo()->hasStackObjects())
     return;
 
@@ -54,7 +60,6 @@ void SIFrameLowering::emitPrologue(MachineFunction &MF,
   if (hasOnlySGPRSpills(MFI, MF.getFrameInfo()))
     return;
 
-  const SISubtarget &ST = MF.getSubtarget<SISubtarget>();
   const SIInstrInfo *TII = ST.getInstrInfo();
   const SIRegisterInfo *TRI = &TII->getRegisterInfo();
   MachineRegisterInfo &MRI = MF.getRegInfo();
@@ -87,6 +92,8 @@ void SIFrameLowering::emitPrologue(MachineFunction &MF,
     // pointer. Because we only detect if flat instructions are used at all,
     // this will be used more often than necessary on VI.
 
+    // Debug location must be unknown since the first debug location is used to
+    // determine the end of the prologue.
     DebugLoc DL;
 
     unsigned FlatScratchInitReg
@@ -289,3 +296,44 @@ void SIFrameLowering::processFunctionBeforeFrameFinalized(
     RS->addScavengingFrameIndex(ScavengeFI);
   }
 }
+
+void SIFrameLowering::emitDebuggerPrologue(MachineFunction &MF,
+                                           MachineBasicBlock &MBB) const {
+  const SISubtarget &ST = MF.getSubtarget<SISubtarget>();
+  const SIInstrInfo *TII = ST.getInstrInfo();
+  const SIRegisterInfo *TRI = &TII->getRegisterInfo();
+  const SIMachineFunctionInfo *MFI = MF.getInfo<SIMachineFunctionInfo>();
+
+  MachineBasicBlock::iterator I = MBB.begin();
+  DebugLoc DL;
+
+  // For each dimension:
+  for (unsigned i = 0; i < 3; ++i) {
+    // Get work group ID SGPR, and make it live-in again.
+    unsigned WorkGroupIDSGPR = MFI->getWorkGroupIDSGPR(i);
+    MF.getRegInfo().addLiveIn(WorkGroupIDSGPR);
+    MBB.addLiveIn(WorkGroupIDSGPR);
+
+    // Since SGPRs are spilled into VGPRs, copy work group ID SGPR to VGPR in
+    // order to spill it to scratch.
+    unsigned WorkGroupIDVGPR =
+      MF.getRegInfo().createVirtualRegister(&AMDGPU::VGPR_32RegClass);
+    BuildMI(MBB, I, DL, TII->get(AMDGPU::V_MOV_B32_e32), WorkGroupIDVGPR)
+      .addReg(WorkGroupIDSGPR);
+
+    // Spill work group ID.
+    int WorkGroupIDObjectIdx = MFI->getDebuggerWorkGroupIDStackObjectIndex(i);
+    TII->storeRegToStackSlot(MBB, I, WorkGroupIDVGPR, false,
+      WorkGroupIDObjectIdx, &AMDGPU::VGPR_32RegClass, TRI);
+
+    // Get work item ID VGPR, and make it live-in again.
+    unsigned WorkItemIDVGPR = MFI->getWorkItemIDVGPR(i);
+    MF.getRegInfo().addLiveIn(WorkItemIDVGPR);
+    MBB.addLiveIn(WorkItemIDVGPR);
+
+    // Spill work item ID.
+    int WorkItemIDObjectIdx = MFI->getDebuggerWorkItemIDStackObjectIndex(i);
+    TII->storeRegToStackSlot(MBB, I, WorkItemIDVGPR, false,
+      WorkItemIDObjectIdx, &AMDGPU::VGPR_32RegClass, TRI);
+  }
+}
diff --git a/llvm/lib/Target/AMDGPU/SIFrameLowering.h b/llvm/lib/Target/AMDGPU/SIFrameLowering.h
index c2e7a710817..37417d098f3 100644
--- a/llvm/lib/Target/AMDGPU/SIFrameLowering.h
+++ b/llvm/lib/Target/AMDGPU/SIFrameLowering.h
@@ -29,6 +29,10 @@ public:
   void processFunctionBeforeFrameFinalized(
     MachineFunction &MF,
     RegScavenger *RS = nullptr) const override;
+
+private:
+  /// \brief Emits debugger prologue.
+  void emitDebuggerPrologue(MachineFunction &MF, MachineBasicBlock &MBB) const;
 };
 
 }
diff --git a/llvm/lib/Target/AMDGPU/SIISelLowering.cpp b/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
index 3142e4c8f42..ad02c4113ca 100644
--- a/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
+++ b/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
@@ -596,6 +596,11 @@ SDValue SITargetLowering::LowerFormalArguments(
     return DAG.getEntryNode();
   }
 
+  // Create stack objects that are used for emitting debugger prologue if
+  // "amdgpu-debugger-emit-prologue" attribute was specified.
+  if (ST.debuggerEmitPrologue())
+    createDebuggerPrologueStackObjects(MF);
+
   SmallVector<ISD::InputArg, 16> Splits;
   BitVector Skipped(Ins.size());
 
@@ -1258,6 +1263,32 @@ bool SITargetLowering::isCFIntrinsic(const SDNode *Intr) const {
   }
 }
 
+void SITargetLowering::createDebuggerPrologueStackObjects(
+    MachineFunction &MF) const {
+  // Create stack objects that are used for emitting debugger prologue.
+  //
+  // Debugger prologue writes work group IDs and work item IDs to scratch memory
+  // at fixed location in the following format:
+  //   offset 0:  work group ID x
+  //   offset 4:  work group ID y
+  //   offset 8:  work group ID z
+  //   offset 16: work item ID x
+  //   offset 20: work item ID y
+  //   offset 24: work item ID z
+  SIMachineFunctionInfo *Info = MF.getInfo<SIMachineFunctionInfo>();
+  int ObjectIdx = 0;
+
+  // For each dimension:
+  for (unsigned i = 0; i < 3; ++i) {
+    // Create fixed stack object for work group ID.
+    ObjectIdx = MF.getFrameInfo()->CreateFixedObject(4, i * 4, true);
+    Info->setDebuggerWorkGroupIDStackObjectIndex(i, ObjectIdx);
+    // Create fixed stack object for work item ID.
+    ObjectIdx = MF.getFrameInfo()->CreateFixedObject(4, i * 4 + 16, true);
+    Info->setDebuggerWorkItemIDStackObjectIndex(i, ObjectIdx);
+  }
+}
+
 /// This transforms the control flow intrinsics to get the branch destination as
 /// last parameter, also switches branch target with BR if the need arise
 SDValue SITargetLowering::LowerBRCOND(SDValue BRCOND,
diff --git a/llvm/lib/Target/AMDGPU/SIISelLowering.h b/llvm/lib/Target/AMDGPU/SIISelLowering.h
index 032372b7b17..3806e95dff3 100644
--- a/llvm/lib/Target/AMDGPU/SIISelLowering.h
+++ b/llvm/lib/Target/AMDGPU/SIISelLowering.h
@@ -70,6 +70,8 @@ class SITargetLowering final : public AMDGPUTargetLowering {
   bool isLegalMUBUFAddressingMode(const AddrMode &AM) const;
 
   bool isCFIntrinsic(const SDNode *Intr) const;
+
+  void createDebuggerPrologueStackObjects(MachineFunction &MF) const;
 public:
   SITargetLowering(const TargetMachine &tm, const SISubtarget &STI);
 
diff --git a/llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.cpp b/llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.cpp
index 6daebbaa0e4..0904d7dc8ab 100644
--- a/llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.cpp
@@ -54,6 +54,8 @@ SIMachineFunctionInfo::SIMachineFunctionInfo(const MachineFunction &MF)
     ReturnsVoid(true),
     MaximumWorkGroupSize(0),
     DebuggerReservedVGPRCount(0),
+    DebuggerWorkGroupIDStackObjectIndices{0, 0, 0},
+    DebuggerWorkItemIDStackObjectIndices{0, 0, 0},
     LDSWaveSpillSize(0),
     PSInputEna(0),
     NumUserSGPRs(0),
@@ -92,16 +94,16 @@ SIMachineFunctionInfo::SIMachineFunctionInfo(const MachineFunction &MF)
     WorkItemIDX = true;
   }
 
-  if (F->hasFnAttribute("amdgpu-work-group-id-y"))
+  if (F->hasFnAttribute("amdgpu-work-group-id-y") || ST.debuggerEmitPrologue())
     WorkGroupIDY = true;
 
-  if (F->hasFnAttribute("amdgpu-work-group-id-z"))
+  if (F->hasFnAttribute("amdgpu-work-group-id-z") || ST.debuggerEmitPrologue())
     WorkGroupIDZ = true;
 
-  if (F->hasFnAttribute("amdgpu-work-item-id-y"))
+  if (F->hasFnAttribute("amdgpu-work-item-id-y") || ST.debuggerEmitPrologue())
     WorkItemIDY = true;
 
-  if (F->hasFnAttribute("amdgpu-work-item-id-z"))
+  if (F->hasFnAttribute("amdgpu-work-item-id-z") || ST.debuggerEmitPrologue())
     WorkItemIDZ = true;
 
   // X, XY, and XYZ are the only supported combinations, so make sure Y is
diff --git a/llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.h b/llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.h
index ee2f722aba5..0ad25f0cae4 100644
--- a/llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.h
+++ b/llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.h
@@ -64,6 +64,10 @@ class SIMachineFunctionInfo final : public AMDGPUMachineFunction {
 
   // Number of reserved VGPRs for debugger usage.
   unsigned DebuggerReservedVGPRCount;
+  // Stack object indices for work group IDs.
+  int DebuggerWorkGroupIDStackObjectIndices[3];
+  // Stack object indices for work item IDs.
+  int DebuggerWorkItemIDStackObjectIndices[3];
 
 public:
   // FIXME: Make private
@@ -334,6 +338,62 @@ public:
     return DebuggerReservedVGPRCount;
   }
 
+  /// \returns Stack object index for \p Dim's work group ID.
+  int getDebuggerWorkGroupIDStackObjectIndex(unsigned Dim) const {
+    assert(Dim < 3);
+    return DebuggerWorkGroupIDStackObjectIndices[Dim];
+  }
+
+  /// \brief Sets stack object index for \p Dim's work group ID to \p ObjectIdx.
+  void setDebuggerWorkGroupIDStackObjectIndex(unsigned Dim, int ObjectIdx) {
+    assert(Dim < 3);
+    DebuggerWorkGroupIDStackObjectIndices[Dim] = ObjectIdx;
+  }
+
+  /// \returns Stack object index for \p Dim's work item ID.
+  int getDebuggerWorkItemIDStackObjectIndex(unsigned Dim) const {
+    assert(Dim < 3);
+    return DebuggerWorkItemIDStackObjectIndices[Dim];
+  }
+
+  /// \brief Sets stack object index for \p Dim's work item ID to \p ObjectIdx.
+  void setDebuggerWorkItemIDStackObjectIndex(unsigned Dim, int ObjectIdx) {
+    assert(Dim < 3);
+    DebuggerWorkItemIDStackObjectIndices[Dim] = ObjectIdx;
+  }
+
+  /// \returns SGPR used for \p Dim's work group ID.
+  unsigned getWorkGroupIDSGPR(unsigned Dim) const {
+    switch (Dim) {
+    case 0:
+      assert(hasWorkGroupIDX());
+      return WorkGroupIDXSystemSGPR;
+    case 1:
+      assert(hasWorkGroupIDY());
+      return WorkGroupIDYSystemSGPR;
+    case 2:
+      assert(hasWorkGroupIDZ());
+      return WorkGroupIDZSystemSGPR;
+    }
+    llvm_unreachable("unexpected dimension");
+  }
+
+  /// \returns VGPR used for \p Dim' work item ID.
+  unsigned getWorkItemIDVGPR(unsigned Dim) const {
+    switch (Dim) {
+    case 0:
+      assert(hasWorkItemIDX());
+      return AMDGPU::VGPR0;
+    case 1:
+      assert(hasWorkItemIDY());
+      return AMDGPU::VGPR1;
+    case 2:
+      assert(hasWorkItemIDZ());
+      return AMDGPU::VGPR2;
+    }
+    llvm_unreachable("unexpected dimension");
+  }
+
   unsigned getMaximumWorkGroupSize(const MachineFunction &MF) const;
 };