[AMDGPU] Distinguish between S/VGPR allocation and encoding granularities

[kzhuravl]

Summary

Tested in D28760.

[arsenm]

LGTM, though I'm not sure how these could be different

llvm/trunk/lib/Target/AMDGPU/AMDGPUAsmPrinter.cpp

if (MFI->getLDSSize() > static_cast<unsigned>(STM.getLocalMemorySize())) {
     LLVMContext &Ctx = MF.getFunction()->getContext();
     DiagnosticInfoResourceLimit Diag(*MF.getFunction(), "local memory",
                                      MFI->getLDSSize(), DS_Error);
     Ctx.diagnose(Diag);
   }
 
   // SGPRBlocks is actual number of SGPR blocks minus 1.
   ProgInfo.SGPRBlocks = alignTo(ProgInfo.NumSGPRsForWavesPerEU,
-                                STM.getSGPRAllocGranule());
-  ProgInfo.SGPRBlocks = ProgInfo.SGPRBlocks / STM.getSGPRAllocGranule() - 1;
+                                STM.getSGPREncodingGranule());
+  ProgInfo.SGPRBlocks = ProgInfo.SGPRBlocks / STM.getSGPREncodingGranule() - 1;
 
   // VGPRBlocks is actual number of VGPR blocks minus 1.
   ProgInfo.VGPRBlocks = alignTo(ProgInfo.NumVGPRsForWavesPerEU,
-                                STM.getVGPRAllocGranule());
-  ProgInfo.VGPRBlocks = ProgInfo.VGPRBlocks / STM.getVGPRAllocGranule() - 1;
+                                STM.getVGPREncodingGranule());
+  ProgInfo.VGPRBlocks = ProgInfo.VGPRBlocks / STM.getVGPREncodingGranule() - 1;
 
   // Record first reserved register and reserved register count fields, and
   // update max register counts if "amdgpu-debugger-reserve-regs" attribute was
   // requested.
   ProgInfo.ReservedVGPRFirst = STM.debuggerReserveRegs() ? MaxVGPR + 1 : 0;
   ProgInfo.ReservedVGPRCount = STM.getReservedNumVGPRs(MF);
 
   // Update DebuggerWavefrontPrivateSegmentOffsetSGPR and

llvm/trunk/lib/Target/AMDGPU/AMDGPUSubtarget.h

public:
   /// \returns True if waitcnt instruction is needed before barrier instruction,
   /// false otherwise.
   bool needWaitcntBeforeBarrier() const {
     return true;
   }
 
   /// \returns SGPR allocation granularity supported by the subtarget.
   unsigned getSGPRAllocGranule() const {
+    if (getGeneration() >= AMDGPUSubtarget::VOLCANIC_ISLANDS)
+      return 16;
+    return 8;
+  }
+
+  /// \returns SGPR encoding granularity supported by the subtarget.
+  unsigned getSGPREncodingGranule() const {
     return 8;
   }
 
   /// \returns Total number of SGPRs supported by the subtarget.
   unsigned getTotalNumSGPRs() const {
     if (getGeneration() >= AMDGPUSubtarget::VOLCANIC_ISLANDS)
       return 800;
     return 512;
public:
   /// unit requirement.
   unsigned getMaxNumSGPRs(const MachineFunction &MF) const;
 
   /// \returns VGPR allocation granularity supported by the subtarget.
   unsigned getVGPRAllocGranule() const {
     return 4;
   }
 
+  /// \returns VGPR encoding granularity supported by the subtarget.
+  unsigned getVGPREncodingGranule() const {
+    return getVGPRAllocGranule();
+  }
+
   /// \returns Total number of VGPRs supported by the subtarget.
   unsigned getTotalNumVGPRs() const {
     return 256;
   }
 
   /// \returns Addressable number of VGPRs supported by the subtarget.
   unsigned getAddressableNumVGPRs() const {
     return getTotalNumVGPRs();