[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

llvm-svn: 294518

2 files changed, 37 insertions, 0 deletions

diff --git a/llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp b/llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp
index fb468223230..492a92a4d8a 100644
--- a/llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp
+++ b/llvm/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/llvm/lib/Target/AMDGPU/SIRegisterInfo.h b/llvm/lib/Target/AMDGPU/SIRegisterInfo.h
index c75a4526857..4330e610681 100644
--- a/llvm/lib/Target/AMDGPU/SIRegisterInfo.h
+++ b/llvm/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,