[Mlir-commits] [mlir] [MLIR][AMDGPU] Add OCP FP8 support for new hardware (PR #106160)

[Paul C Fuqua]

================
@@ -454,6 +454,20 @@ static void wmmaPushOutputOperand(ConversionPatternRewriter &rewriter,
   }
 }
 
+/// Return true if `type` is the E5M2 variant of an 8-bit float that is
+/// supported by the `_bf8` instructions on the given `chipset`.
+static bool isNativeBf8(Chipset chipset, Type type) {
----------------
pcf000 wrote:

Previous job would have called it "typeIsNativelySupportedBf8ForChipset(Type,Chipset)" -- we liked naming the parameters in the function name -- or "typeIsExpectedBf8ForChipset(Type,Chipset)".  As I wrote those out, I think I like "expected" better than "native" or "supported," but I could be persuaded.

https://github.com/llvm/llvm-project/pull/106160