[llvm] [LoongArch] Implement COPY instruction between CFRs (PR #69300)

[Xi Ruoyao via llvm-commits]

================
@@ -513,15 +515,134 @@ bool LoongArchPreRAExpandPseudo::expandFunctionCALL(
   return true;
 }
 
+class LoongArchExpandPseudo : public MachineFunctionPass {
+public:
+  const LoongArchInstrInfo *TII;
+  static char ID;
+
+  LoongArchExpandPseudo() : MachineFunctionPass(ID) {
+    initializeLoongArchExpandPseudoPass(*PassRegistry::getPassRegistry());
+  }
+
+  bool runOnMachineFunction(MachineFunction &MF) override;
+
+  StringRef getPassName() const override {
+    return LOONGARCH_EXPAND_PSEUDO_NAME;
+  }
+
+private:
+  bool expandMBB(MachineBasicBlock &MBB);
+  bool expandMI(MachineBasicBlock &MBB, MachineBasicBlock::iterator MBBI,
+                MachineBasicBlock::iterator &NextMBBI);
+  bool expandCopyCFR(MachineBasicBlock &MBB, MachineBasicBlock::iterator MBBI,
+                     MachineBasicBlock::iterator &NextMBBI);
+};
+
+char LoongArchExpandPseudo::ID = 0;
+
+bool LoongArchExpandPseudo::runOnMachineFunction(MachineFunction &MF) {
+  TII =
+      static_cast<const LoongArchInstrInfo *>(MF.getSubtarget().getInstrInfo());
+
+  bool Modified = false;
+  for (auto &MBB : MF)
+    Modified |= expandMBB(MBB);
+
+  return Modified;
+}
+
+bool LoongArchExpandPseudo::expandMBB(MachineBasicBlock &MBB) {
+  bool Modified = false;
+
+  MachineBasicBlock::iterator MBBI = MBB.begin(), E = MBB.end();
+  while (MBBI != E) {
+    MachineBasicBlock::iterator NMBBI = std::next(MBBI);
+    Modified |= expandMI(MBB, MBBI, NMBBI);
+    MBBI = NMBBI;
+  }
+
+  return Modified;
+}
+
+bool LoongArchExpandPseudo::expandMI(MachineBasicBlock &MBB,
+                                     MachineBasicBlock::iterator MBBI,
+                                     MachineBasicBlock::iterator &NextMBBI) {
+  switch (MBBI->getOpcode()) {
+  case LoongArch::PseudoCopyCFR:
+    return expandCopyCFR(MBB, MBBI, NextMBBI);
+  }
+
+  return false;
+}
+
+bool LoongArchExpandPseudo::expandCopyCFR(
+    MachineBasicBlock &MBB, MachineBasicBlock::iterator MBBI,
+    MachineBasicBlock::iterator &NextMBBI) {
+  MachineFunction *MF = MBB.getParent();
+  MachineInstr &MI = *MBBI;
+  DebugLoc DL = MI.getDebugLoc();
+
+  // Expand:
+  // MBB:
+  //    fcmp.caf.s  $dst, $fa0, $fa0 # set $dst 0(false)
----------------
xry111 wrote:

Phew:

```
$ cat t.S
.globl main
main:
  li.w		$a0, 1000000
.L0:
.rept 100
#if USE_MOVGR2CF
  movgr2cf	$fcc0, $r0
#else
  fcmp.caf.s	$fcc0, $f0, $f0
#endif
.endr
  addi.w	$a0, $a0, -1
  bnez		$a0, .L0
  li.w		$a0, 0
  jr		$ra
$ gcc t.S -DUSE_MOVGR2CF
$ time ./a.out

real	0m0.688s
user	0m0.687s
sys	0m0.001s
$ gcc t.S
$ time ./a.out

real	0m0.024s
user	0m0.023s
sys	0m0.000s
```

So `fcmp.caf.s` is indeed better...

https://github.com/llvm/llvm-project/pull/69300