[llvm] Co-issue packed instructions by unpacking (PR #151704)

[Jeffrey Byrnes via llvm-commits]

================
@@ -225,6 +254,712 @@ bool GCNPreRAOptimizationsImpl::processReg(Register Reg) {
   return true;
 }
 
+bool GCNPreRAOptimizationsImpl::isUnpackingSupportedInstr(
+    MachineInstr &MI) const {
+  unsigned Opcode = MI.getOpcode();
+  switch (Opcode) {
+  case AMDGPU::V_PK_ADD_F32:
+  case AMDGPU::V_PK_MUL_F32:
+  case AMDGPU::V_PK_MUL_F16:
+  case AMDGPU::V_PK_ADD_F16:
+  case AMDGPU::V_PK_FMA_F32:
+    return true;
+
+  default:
+    return false;
+  }
+}
+
+uint16_t GCNPreRAOptimizationsImpl::mapToUnpackedOpcode(MachineInstr &I) {
+  unsigned Opcode = I.getOpcode();
+  // use 64 bit encoding to allow use of VOP3 instructions.
+  // VOP3 instructions allow VOP3P source modifiers to be translated to VOP3
+  // e32 instructions are VOP2 and don't allow source modifiers
+  switch (Opcode) {
+  case AMDGPU::V_PK_ADD_F32:
+    return AMDGPU::V_ADD_F32_e64;
+  case AMDGPU::V_PK_MUL_F32:
+    return AMDGPU::V_MUL_F32_e64;
+  case AMDGPU::V_PK_ADD_F16:
+    return AMDGPU::V_ADD_F16_e64;
+  case AMDGPU::V_PK_MUL_F16:
+    return AMDGPU::V_MUL_F16_e64;
+  case AMDGPU::V_PK_FMA_F32:
+    return AMDGPU::V_FMA_F32_e64;
+  default:
+    return std::numeric_limits<uint16_t>::max();
+  }
+}
+
+bool GCNPreRAOptimizationsImpl::createListOfPackedInstr(
+    MachineInstr &BeginMI, SetVector<MachineInstr *> &InstrsToUnpack,
+    uint16_t NumMFMACycles) {
+  auto *BB = BeginMI.getParent();
+  auto *MF = BB->getParent();
+  int NumInst = 0;
----------------
jrbyrnes wrote:

unused?

https://github.com/llvm/llvm-project/pull/151704