unpack packed instructions overlapped by MFMAs post-RA scheduling

Author: akadutta

llvm/lib/Target/AMDGPU/SIInstrInfo.cpp

@@ -6359,6 +6359,66 @@ bool SIInstrInfo::isOperandLegal(const MachineInstr &MI, unsigned OpIdx,
   return isImmOperandLegal(MI, OpIdx, *MO);
 }
 
+bool SIInstrInfo::isNeverCoissue(MachineInstr &MI) const {
+  bool IsGFX950Only = ST.hasGFX950Insts();
+  bool IsGFX940Only = ST.hasGFX940Insts();
+
+  if (!IsGFX950Only && !IsGFX940Only)
+    return false;
+
+  if (!isVALU(MI))
+    return false;
+
+  // V_COS, V_EXP, V_RCP, etc.
+  if (isTRANS(MI))
+    return true;
+
+  // DOT2, DOT2C, DOT4, etc.
+  if (isDOT(MI))
+    return true;
+
+  // MFMA, SMFMA
+  if (isMFMA(MI))
+    return true;
+
+  unsigned Opcode = MI.getOpcode();
+  switch (Opcode) {
+    case AMDGPU::V_CVT_PK_BF8_F32_e64:
+    case AMDGPU::V_CVT_PK_FP8_F32_e64:
+    case AMDGPU::V_MQSAD_PK_U16_U8_e64:
+    case AMDGPU::V_MQSAD_U32_U8_e64:
+    case AMDGPU::V_PK_ADD_F16:
+    case AMDGPU::V_PK_ADD_F32:
+    case AMDGPU::V_PK_ADD_I16:
+    case AMDGPU::V_PK_ADD_U16:
+    case AMDGPU::V_PK_ASHRREV_I16:
+    case AMDGPU::V_PK_FMA_F16:
+    case AMDGPU::V_PK_FMA_F32:
+    case AMDGPU::V_PK_FMAC_F16_e32:
+    case AMDGPU::V_PK_FMAC_F16_e64:
+    case AMDGPU::V_PK_LSHLREV_B16:
+    case AMDGPU::V_PK_LSHRREV_B16:
+    case AMDGPU::V_PK_MAD_I16:
+    case AMDGPU::V_PK_MAD_U16:
+    case AMDGPU::V_PK_MAX_F16:
+    case AMDGPU::V_PK_MAX_I16:
+    case AMDGPU::V_PK_MAX_U16:
+    case AMDGPU::V_PK_MIN_F16:
+    case AMDGPU::V_PK_MIN_I16:
+    case AMDGPU::V_PK_MIN_U16:
+    case AMDGPU::V_PK_MOV_B32:
+    case AMDGPU::V_PK_MUL_F16:
+    case AMDGPU::V_PK_MUL_F32:
+    case AMDGPU::V_PK_MUL_LO_U16:
+    case AMDGPU::V_PK_SUB_I16:
+    case AMDGPU::V_PK_SUB_U16:
+    case AMDGPU::V_QSAD_PK_U16_U8_e64:
+      return true;
+    default:
+      return false;
+    }
+}
+
 void SIInstrInfo::legalizeOperandsVOP2(MachineRegisterInfo &MRI,
                                        MachineInstr &MI) const {
   unsigned Opc = MI.getOpcode();

llvm/lib/Target/AMDGPU/SIInstrInfo.h

@@ -1200,6 +1200,8 @@ class SIInstrInfo final : public AMDGPUGenInstrInfo {
     return isImmOperandLegal(MI.getDesc(), OpNo, MO);
   }
 
+  bool isNeverCoissue(MachineInstr &MI) const;
+  
   /// Check if this immediate value can be used for AV_MOV_B64_IMM_PSEUDO.
   bool isLegalAV64PseudoImm(uint64_t Imm) const;