[llvm] AMDGPU: Fix incorrectly selecting fp8/bf8 conversion intrinsics (PR #107291)

[Stanislav Mekhanoshin via llvm-commits]

================
@@ -599,8 +599,8 @@ class Cvt_F32_F8_Pat<SDPatternOperator node, int index,
     (inst_sdwa 0, $src, 0, 0, index)
 >;
 
-let SubtargetPredicate = isGFX9Only in {
-let OtherPredicates = [HasCvtFP8VOP1Bug] in {
+let SubtargetPredicate = HasFP8ConversionInsts in {
----------------
rampitec wrote:

This will be true on gfx12, but it does not have these instructions. It uses opsel versions in the patterns below.

https://github.com/llvm/llvm-project/pull/107291