[AArch64] Don't emit Neon in streaming[-compatible] functions with -fzero-call-used-regs (llvm#116995)

Previously, with `-fzero-call-used-regs` clang/LLVM would incorrectly
emit Neon instructions in streaming functions, and streaming-compatible
functions without SVE.

With this change:

* In streaming functions, Z/p registers will be zeroed
* In streaming compatible functions w/o SVE, D registers will be zeroed
  - (As Neon vector instructions are illegal including `movi v..`)

Author: MacDue

llvm/lib/Target/AArch64/AArch64FrameLowering.cpp

@@ -1010,7 +1010,7 @@ void AArch64FrameLowering::emitZeroCallUsedRegs(BitVector RegsToZero,
 
   BitVector GPRsToZero(TRI.getNumRegs());
   BitVector FPRsToZero(TRI.getNumRegs());
-  bool HasSVE = STI.hasSVE();
+  bool HasSVE = STI.isSVEorStreamingSVEAvailable();
   for (MCRegister Reg : RegsToZero.set_bits()) {
     if (TRI.isGeneralPurposeRegister(MF, Reg)) {
       // For GPRs, we only care to clear out the 64-bit register.

llvm/lib/Target/AArch64/AArch64InstrInfo.cpp

@@ -9700,13 +9700,20 @@ void AArch64InstrInfo::buildClearRegister(Register Reg, MachineBasicBlock &MBB,
 
   if (TRI.isGeneralPurposeRegister(MF, Reg)) {
     BuildMI(MBB, Iter, DL, get(AArch64::MOVZXi), Reg).addImm(0).addImm(0);
-  } else if (STI.hasSVE()) {
+  } else if (STI.isSVEorStreamingSVEAvailable()) {
     BuildMI(MBB, Iter, DL, get(AArch64::DUP_ZI_D), Reg)
       .addImm(0)
       .addImm(0);
-  } else {
+  } else if (STI.isNeonAvailable()) {
     BuildMI(MBB, Iter, DL, get(AArch64::MOVIv2d_ns), Reg)
       .addImm(0);
+  } else {
+    // This is a streaming-compatible function without SVE. We don't have full
+    // Neon (just FPRs), so we can at most use the first 64-bit sub-register.
+    // So given `movi v..` would be illegal use `fmov d..` instead.
+    assert(STI.hasNEON() && "Expected to have NEON.");
+    Register Reg64 = TRI.getSubReg(Reg, AArch64::dsub);
+    BuildMI(MBB, Iter, DL, get(AArch64::FMOVD0), Reg64);
   }
 }