[AArch64] Do not split bfloat HFA args between regs and stack (#128909)

In AAPCS64, __fp16 and __bf16 share the same machine type, so they
should be treated the same way for argument passing. In particular,
arrays of them need to be treated as homogeneous aggregates, and not
split between registers and the stack.

Author: ostannard

llvm/lib/Target/AArch64/AArch64CallingConvention.cpp

@@ -142,7 +142,7 @@ static bool CC_AArch64_Custom_Block(unsigned &ValNo, MVT &ValVT, MVT &LocVT,
   ArrayRef<MCPhysReg> RegList;
   if (LocVT.SimpleTy == MVT::i64 || (IsDarwinILP32 && LocVT.SimpleTy == MVT::i32))
     RegList = XRegList;
-  else if (LocVT.SimpleTy == MVT::f16)
+  else if (LocVT.SimpleTy == MVT::f16 || LocVT.SimpleTy == MVT::bf16)
     RegList = HRegList;
   else if (LocVT.SimpleTy == MVT::f32 || LocVT.is32BitVector())
     RegList = SRegList;

llvm/test/CodeGen/AArch64/argument-blocks.ll

@@ -195,3 +195,10 @@ define half @test_f16_blocked([7 x double], [2 x half] %in) {
   %val = extractvalue [2 x half] %in, 0
   ret half %val
 }
+
+define bfloat @test_bf16_blocked([7 x double], [2 x bfloat] %in) {
+; CHECK-LABEL: test_bf16_blocked:
+; CHECK: ldr h0, [sp]
+  %val = extractvalue [2 x bfloat] %in, 0
+  ret bfloat %val
+}