[llvm] [RISCV] SPLAT_VECTOR of bf16 should not require Zvfhmin. (PR #95357)

[Kito Cheng via llvm-commits]

================
@@ -0,0 +1,117 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=riscv32 -mattr=+d,+v,+m,+experimental-zfbfmin,+experimental-zvfbfmin -target-abi=ilp32d \
+; RUN:   -verify-machineinstrs < %s | FileCheck %s
+; RUN: llc -mtriple=riscv64 -mattr=+d,+v,+m,+experimental-zfbfmin,+experimental-zvfbfmin -target-abi=lp64d \
+; RUN:   -verify-machineinstrs < %s | FileCheck %s
+
+declare <2 x bfloat> @llvm.vp.merge.v2bf16(<2 x i1>, <2 x bfloat>, <2 x bfloat>, i32)
+
+define <2 x bfloat> @vpmerge_vv_v2bf16(<2 x bfloat> %va, <2 x bfloat> %vb, <2 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: vpmerge_vv_v2bf16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, tu, ma
+; CHECK-NEXT:    vmerge.vvm v9, v9, v8, v0
+; CHECK-NEXT:    vmv1r.v v8, v9
+; CHECK-NEXT:    ret
+  %v = call <2 x bfloat> @llvm.vp.merge.v2bf16(<2 x i1> %m, <2 x bfloat> %va, <2 x bfloat> %vb, i32 %evl)
+  ret <2 x bfloat> %v
+}
+
+define <2 x bfloat> @vpmerge_vf_v2bf16(bfloat %a, <2 x bfloat> %vb, <2 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: vpmerge_vf_v2bf16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    fcvt.s.bf16 fa5, fa0
+; CHECK-NEXT:    vsetvli a1, zero, e32, mf2, ta, ma
+; CHECK-NEXT:    vfmv.v.f v9, fa5
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, tu, mu
+; CHECK-NEXT:    vfncvtbf16.f.f.w v8, v9, v0.t
----------------
kito-cheng wrote:

Random idea to improving the splat of bf16 with zvfbfmin only:
```
fmv.x.w t0, fa0
vsetvli zero, a0, e16, mf4, tu, mu
vmv.v.x v9, t0, v0.t
```

https://github.com/llvm/llvm-project/pull/95357