[AMDGPU][Scheduler] Refactor ArchVGPR rematerialization during scheduling

llvm/include/llvm/CodeGen/MachineRegisterInfo.h

@@ -23,6 +23,7 @@
 #include "llvm/ADT/iterator_range.h"
 #include "llvm/CodeGen/MachineBasicBlock.h"
 #include "llvm/CodeGen/MachineFunction.h"
+#include "llvm/CodeGen/MachineInstr.h"
 #include "llvm/CodeGen/MachineInstrBundle.h"
 #include "llvm/CodeGen/MachineOperand.h"
 #include "llvm/CodeGen/RegisterBank.h"
@@ -592,6 +593,9 @@ class MachineRegisterInfo {
   /// multiple uses.
   bool hasOneNonDBGUser(Register RegNo) const;
 
+  /// If the register has a single non-Debug instruction using the specified
+  /// register, returns it; otherwise returns nullptr.
+  MachineInstr *getOneNonDBGUser(Register RegNo) const;
 
   /// hasAtMostUses - Return true if the given register has at most \p MaxUsers
   /// non-debug user instructions.

llvm/lib/CodeGen/MachineRegisterInfo.cpp

@@ -432,6 +432,11 @@ bool MachineRegisterInfo::hasOneNonDBGUser(Register RegNo) const {
   return hasSingleElement(use_nodbg_instructions(RegNo));
 }
 
+MachineInstr *MachineRegisterInfo::getOneNonDBGUser(Register RegNo) const {
+  auto RegNoDbgUsers = use_nodbg_instructions(RegNo);
+  return hasSingleElement(RegNoDbgUsers) ? &*RegNoDbgUsers.begin() : nullptr;
+}
+
 bool MachineRegisterInfo::hasAtMostUserInstrs(Register Reg,
                                               unsigned MaxUsers) const {
   return hasNItemsOrLess(use_instr_nodbg_begin(Reg), use_instr_nodbg_end(),

llvm/lib/Target/AMDGPU/GCNRegPressure.h

@@ -53,11 +53,20 @@ struct GCNRegPressure {
   /// UnifiedVGPRFile
   unsigned getVGPRNum(bool UnifiedVGPRFile) const {
     if (UnifiedVGPRFile) {
-      return Value[AGPR32] ? alignTo(Value[VGPR32], 4) + Value[AGPR32]
+      return Value[AGPR32] ? getUnifiedVGPRNum(Value[VGPR32], Value[AGPR32])
                            : Value[VGPR32] + Value[AGPR32];
     }
     return std::max(Value[VGPR32], Value[AGPR32]);
   }
+
+  /// Returns the aggregated VGPR pressure, assuming \p NumArchVGPRs ArchVGPRs
+  /// and \p NumAGPRs AGPRS, for a target with a unified VGPR file.
+  inline static unsigned getUnifiedVGPRNum(unsigned NumArchVGPRs,
+                                           unsigned NumAGPRs) {
+    return alignTo(NumArchVGPRs, AMDGPU::IsaInfo::getArchVGPRAllocGranule()) +
+           NumAGPRs;
+  }
+
   /// \returns the ArchVGPR32 pressure
   unsigned getArchVGPRNum() const { return Value[VGPR32]; }
   /// \returns the AccVGPR32 pressure