[AMDGPU] Implement register pressure callbacks

Implement getRegPressureLimit and getRegPressureSetLimit callbacks in
SIRegisterInfo.

This makes standard converge scheduler to behave almost the same as
GCNScheduler, sometime slightly better sometimes a bit worse.
In gerenal that is also possible to switch GCNScheduler to use these
callbacks instead of getMaxWaves(), which also makes GCNScheduler
slightly better on some tests and slightly worse on another. A big
win is behavior with converge scheduler.

Note, these are used not only by scheduling, but in places like
MachineLICM.

Differential Revision: https://reviews.llvm.org/D29700

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@294518 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/AMDGPU/SIRegisterInfo.cpp b/lib/Target/AMDGPU/SIRegisterInfo.cpp
index fb4682232303bd36b4998dd3fdf167a248bff5b8..492a92a4d8a33f93cf1d26ea377abbe3099f47e3 100644 (file)
--- a/lib/Target/AMDGPU/SIRegisterInfo.cpp
+++ b/lib/Target/AMDGPU/SIRegisterInfo.cpp
@@ -1298,3 +1298,34 @@ bool SIRegisterInfo::shouldCoalesce(MachineInstr *MI,
 
   return NewSize <= DstSize || NewSize <= SrcSize;
 }
+
+unsigned SIRegisterInfo::getRegPressureLimit(const TargetRegisterClass *RC,
+                                             MachineFunction &MF) const {
+
+  const SISubtarget &ST = MF.getSubtarget<SISubtarget>();
+  const SIMachineFunctionInfo *MFI = MF.getInfo<SIMachineFunctionInfo>();
+
+  unsigned Occupancy = ST.getOccupancyWithLocalMemSize(MFI->getLDSSize(),
+                                                       *MF.getFunction());
+  switch (RC->getID()) {
+  default:
+    return AMDGPURegisterInfo::getRegPressureLimit(RC, MF);
+  case AMDGPU::VGPR_32RegClassID:
+    return std::min(ST.getMaxNumVGPRs(Occupancy), ST.getMaxNumVGPRs(MF));
+  case AMDGPU::SGPR_32RegClassID:
+    return std::min(ST.getMaxNumSGPRs(Occupancy, true), ST.getMaxNumSGPRs(MF));
+  }
+}
+
+unsigned SIRegisterInfo::getRegPressureSetLimit(const MachineFunction &MF,
+                                                unsigned Idx) const {
+  if (Idx == getVGPRPressureSet())
+    return getRegPressureLimit(&AMDGPU::VGPR_32RegClass,
+                               const_cast<MachineFunction &>(MF));
+
+  if (Idx == getSGPRPressureSet())
+    return getRegPressureLimit(&AMDGPU::SGPR_32RegClass,
+                               const_cast<MachineFunction &>(MF));
+
+  return AMDGPURegisterInfo::getRegPressureSetLimit(MF, Idx);
+}

diff --git a/lib/Target/AMDGPU/SIRegisterInfo.h b/lib/Target/AMDGPU/SIRegisterInfo.h
index c75a4526857328c5d4a0bf1f41cec834cbb09611..4330e6106815a2fce58b7b5da81e2647ce814927 100644 (file)
--- a/lib/Target/AMDGPU/SIRegisterInfo.h
+++ b/lib/Target/AMDGPU/SIRegisterInfo.h
@@ -205,6 +205,12 @@ public:
                       unsigned DstSubReg,
                       const TargetRegisterClass *NewRC) const override;
 
+  unsigned getRegPressureLimit(const TargetRegisterClass *RC,
+                               MachineFunction &MF) const override;
+
+  unsigned getRegPressureSetLimit(const MachineFunction &MF,
+                                  unsigned Idx) const override;
+
 private:
   void buildSpillLoadStore(MachineBasicBlock::iterator MI,
                            unsigned LoadStoreOp,