[clang] [llvm] [RFC][AMDGPU] Use `bf16` instead of `i16` for bfloat (PR #80908)

[Shilei Tian via llvm-commits]

================
@@ -79,17 +79,17 @@ define amdgpu_ps void @test_llvm_amdgcn_fdot2_bf16_bf16_sis(
 ; GFX11:       ; %bb.0: ; %entry
 ; GFX11-NEXT:    v_mov_b32_e32 v2, s1
 ; GFX11-NEXT:    s_delay_alu instid0(VALU_DEP_1)
-; GFX11-NEXT:    v_dot2_bf16_bf16 v2, s0, 0x10001, v2
+; GFX11-NEXT:    v_dot2_bf16_bf16 v2, s0, 0x3f803f80, v2
----------------
shiltian wrote:

Yeah, but I tested the FP16 version `llvm.amdgcn.fdot2.f16.f16` (w/ trunk w/o my patch), it generates `v_dot2_f16_f16 v2, s0, 0x3c003c00, v2`. I think we generally have issues with showing inline literals.

https://github.com/llvm/llvm-project/pull/80908