[llvm-branch-commits] [llvm] AMDGPU: MC support for v_cvt_scalef32_pk32_f32_[fp|bf]6 of gfx950 (PR #117590)

[Shilei Tian via llvm-branch-commits]

================
@@ -1552,7 +1558,9 @@ def FeatureISAVersion9_5_Common : FeatureSet<
    FeatureBitOp3Insts,
    FeatureFP8ConversionScaleInsts,
    FeatureBF8ConversionScaleInsts,
-   FeatureFP4ConversionScaleInsts
+   FeatureFP4ConversionScaleInsts,
+   FeatureFP6BF6ConversionScaleInsts,
+   FeatureFP8Insts
----------------
shiltian wrote:

why `FeatureFP8Insts` is added here?

https://github.com/llvm/llvm-project/pull/117590