1 files changed, 106 insertions, 3 deletions
diff --git a/contrib/llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.cpp b/contrib/llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.cpp
index 587ea63..935aad4 100644
--- a/contrib/llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.cpp
+++ b/contrib/llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.cpp
@@ -29,10 +29,114 @@ void SIMachineFunctionInfo::anchor() {}
 SIMachineFunctionInfo::SIMachineFunctionInfo(const MachineFunction &MF)
   : AMDGPUMachineFunction(MF),
     TIDReg(AMDGPU::NoRegister),
-    HasSpilledVGPRs(false),
+    ScratchRSrcReg(AMDGPU::NoRegister),
+    ScratchWaveOffsetReg(AMDGPU::NoRegister),
+    PrivateSegmentBufferUserSGPR(AMDGPU::NoRegister),
+    DispatchPtrUserSGPR(AMDGPU::NoRegister),
+    QueuePtrUserSGPR(AMDGPU::NoRegister),
+    KernargSegmentPtrUserSGPR(AMDGPU::NoRegister),
+    DispatchIDUserSGPR(AMDGPU::NoRegister),
+    FlatScratchInitUserSGPR(AMDGPU::NoRegister),
+    PrivateSegmentSizeUserSGPR(AMDGPU::NoRegister),
+    GridWorkGroupCountXUserSGPR(AMDGPU::NoRegister),
+    GridWorkGroupCountYUserSGPR(AMDGPU::NoRegister),
+    GridWorkGroupCountZUserSGPR(AMDGPU::NoRegister),
+    WorkGroupIDXSystemSGPR(AMDGPU::NoRegister),
+    WorkGroupIDYSystemSGPR(AMDGPU::NoRegister),
+    WorkGroupIDZSystemSGPR(AMDGPU::NoRegister),
+    WorkGroupInfoSystemSGPR(AMDGPU::NoRegister),
+    PrivateSegmentWaveByteOffsetSystemSGPR(AMDGPU::NoRegister),
+    LDSWaveSpillSize(0),
     PSInputAddr(0),
     NumUserSGPRs(0),
-    LDSWaveSpillSize(0) { }
+    NumSystemSGPRs(0),
+    HasSpilledSGPRs(false),
+    HasSpilledVGPRs(false),
+    PrivateSegmentBuffer(false),
+    DispatchPtr(false),
+    QueuePtr(false),
+    DispatchID(false),
+    KernargSegmentPtr(false),
+    FlatScratchInit(false),
+    GridWorkgroupCountX(false),
+    GridWorkgroupCountY(false),
+    GridWorkgroupCountZ(false),
+    WorkGroupIDX(true),
+    WorkGroupIDY(false),
+    WorkGroupIDZ(false),
+    WorkGroupInfo(false),
+    PrivateSegmentWaveByteOffset(false),
+    WorkItemIDX(true),
+    WorkItemIDY(false),
+    WorkItemIDZ(false) {
+  const AMDGPUSubtarget &ST = MF.getSubtarget<AMDGPUSubtarget>();
+  const Function *F = MF.getFunction();
+
+  const MachineFrameInfo *FrameInfo = MF.getFrameInfo();
+
+  if (getShaderType() == ShaderType::COMPUTE)
+    KernargSegmentPtr = true;
+
+  if (F->hasFnAttribute("amdgpu-work-group-id-y"))
+    WorkGroupIDY = true;
+
+  if (F->hasFnAttribute("amdgpu-work-group-id-z"))
+    WorkGroupIDZ = true;
+
+  if (F->hasFnAttribute("amdgpu-work-item-id-y"))
+    WorkItemIDY = true;
+
+  if (F->hasFnAttribute("amdgpu-work-item-id-z"))
+    WorkItemIDZ = true;
+
+  bool MaySpill = ST.isVGPRSpillingEnabled(this);
+  bool HasStackObjects = FrameInfo->hasStackObjects();
+
+  if (HasStackObjects || MaySpill)
+    PrivateSegmentWaveByteOffset = true;
+
+  if (ST.isAmdHsaOS()) {
+    if (HasStackObjects || MaySpill)
+      PrivateSegmentBuffer = true;
+
+    if (F->hasFnAttribute("amdgpu-dispatch-ptr"))
+      DispatchPtr = true;
+  }
+
+  // X, XY, and XYZ are the only supported combinations, so make sure Y is
+  // enabled if Z is.
+  if (WorkItemIDZ)
+    WorkItemIDY = true;
+}
+
+unsigned SIMachineFunctionInfo::addPrivateSegmentBuffer(
+  const SIRegisterInfo &TRI) {
+  PrivateSegmentBufferUserSGPR = TRI.getMatchingSuperReg(
+    getNextUserSGPR(), AMDGPU::sub0, &AMDGPU::SReg_128RegClass);
+  NumUserSGPRs += 4;
+  return PrivateSegmentBufferUserSGPR;
+}
+
+unsigned SIMachineFunctionInfo::addDispatchPtr(const SIRegisterInfo &TRI) {
+  DispatchPtrUserSGPR = TRI.getMatchingSuperReg(
+    getNextUserSGPR(), AMDGPU::sub0, &AMDGPU::SReg_64RegClass);
+  NumUserSGPRs += 2;
+  return DispatchPtrUserSGPR;
+}
+
+unsigned SIMachineFunctionInfo::addQueuePtr(const SIRegisterInfo &TRI) {
+  QueuePtrUserSGPR = TRI.getMatchingSuperReg(
+    getNextUserSGPR(), AMDGPU::sub0, &AMDGPU::SReg_64RegClass);
+  NumUserSGPRs += 2;
+  return QueuePtrUserSGPR;
+}
+
+unsigned SIMachineFunctionInfo::addKernargSegmentPtr(const SIRegisterInfo &TRI) {
+  KernargSegmentPtrUserSGPR = TRI.getMatchingSuperReg(
+    getNextUserSGPR(), AMDGPU::sub0, &AMDGPU::SReg_64RegClass);
+  NumUserSGPRs += 2;
+  return KernargSegmentPtrUserSGPR;
+}
 
 SIMachineFunctionInfo::SpilledReg SIMachineFunctionInfo::getSpilledReg(
                                                        MachineFunction *MF,
@@ -53,7 +157,6 @@ SIMachineFunctionInfo::SpilledReg SIMachineFunctionInfo::getSpilledReg(
   if (!LaneVGPRs.count(LaneVGPRIdx)) {
     unsigned LaneVGPR = TRI->findUnusedRegister(MRI, &AMDGPU::VGPR_32RegClass);
     LaneVGPRs[LaneVGPRIdx] = LaneVGPR;
-    MRI.setPhysRegUsed(LaneVGPR);
 
     // Add this register as live-in to all blocks to avoid machine verifer
     // complaining about use of an undefined physical register.