[llvm] [X86][BF16] Do not combine FP_TRUNC + FP_EXTEND if they come from user (PR #91420)

[Krzysztof Drewniak via llvm-commits]

================
@@ -2420,3 +2420,47 @@ define <16 x bfloat> @concat_dup_v8bf16(<8 x bfloat> %x, <8 x bfloat> %y) {
   %a = shufflevector <8 x bfloat> %x, <8 x bfloat> %y, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
   ret <16 x bfloat> %a
 }
+
+define float @trunc_ext(float %a) nounwind {
+; X86-LABEL: trunc_ext:
+; X86:       # %bb.0:
+; X86-NEXT:    pushl %eax
+; X86-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
+; X86-NEXT:    vcvtneps2bf16 %xmm0, %xmm0
+; X86-NEXT:    vmovw %xmm0, %eax
+; X86-NEXT:    shll $16, %eax
+; X86-NEXT:    vmovd %eax, %xmm0
+; X86-NEXT:    vmovd %xmm0, (%esp)
+; X86-NEXT:    flds (%esp)
+; X86-NEXT:    popl %eax
+; X86-NEXT:    retl
+;
+; SSE2-LABEL: trunc_ext:
+; SSE2:       # %bb.0:
+; SSE2-NEXT:    pushq %rax
+; SSE2-NEXT:    callq __truncsfbf2 at PLT
----------------
krzysz00 wrote:

__truncsfbf2 is usually defined as RNE in the implementations I've seen of it

https://github.com/llvm/llvm-project/pull/91420