[llvm] [AMDGPU] Fix performFMACombine FDOT2 fold ignores denormal-fp-math-f32 (PR #205101)

[Wooseok Lee via llvm-commits]

================
@@ -411,3 +412,27 @@ entry:
   store float %acc2, ptr addrspace(1) %dst, align 4
   ret void
 }
+
+; GCN-LABEL: {{^}}dotproduct_f16_f32_contract_ieee_denorm
+; GFX950-DENORM:     v_fma_mix_f32
+; GFX950-DENORM:     v_fma_mix_f32
+; GFX950-DENORM-NOT: v_dot2c_f32_f16
+; GFX950-DENORM-NOT: v_dot2_f32_f16
+define amdgpu_kernel void @dotproduct_f16_f32_contract_ieee_denorm(<2 x half> %a, <2 x half> %b, float %z, ptr addrspace(1) %out) #0 {
+  %ax = extractelement <2 x half> %a, i32 0
+  %axf = fpext half %ax to float
+  %ay = extractelement <2 x half> %a, i32 1
+  %ayf = fpext half %ay to float
+
+  %bx = extractelement <2 x half> %b, i32 0
+  %bxf = fpext half %bx to float
+  %by = extractelement <2 x half> %b, i32 1
+  %byf = fpext half %by to float
+
+  %inner = call contract float @llvm.fma.f32(float %ayf, float %byf, float %z)
+  %outer = call contract float @llvm.fma.f32(float %axf, float %bxf, float %inner)
+  store float %outer, ptr addrspace(1) %out
+  ret void
+}
+
+attributes #0 = { "denormal-fp-math-f32"="ieee,ieee" }
----------------
wooseoklee wrote:

Thanks. I will update the test as you guided.

https://github.com/llvm/llvm-project/pull/205101