[Mlir-commits] [mlir] [mlir][ROCDL] adds wmma scaled intrinsics for gfx1250 (PR #165915)

[Jakub Kuderski]

================
@@ -627,6 +627,8 @@ def ROCDL_wmma_f16_16x16x128_fp8_bf8 : ROCDL_Wmma_IntrOp<"wmma.f16.16x16x128.fp8
 def ROCDL_wmma_f16_16x16x128_bf8_fp8 : ROCDL_Wmma_IntrOp<"wmma.f16.16x16x128.bf8_fp8", [0]>;
 def ROCDL_wmma_f16_16x16x128_bf8_bf8 : ROCDL_Wmma_IntrOp<"wmma.f16.16x16x128.bf8_bf8", [0]>;
 def ROCDL_wmma_i32_16x16x64_iu8 : ROCDL_Wmma_IntrOp<"wmma.i32.16x16x64.iu8", [1]>;
+def ROCDL_wmma_scale_f32_16x16x128_f8f6f4   : ROCDL_Wmma_IntrOp<"wmma.scale.f32.16x16x128.f8f6f4", [1,3]>;
+def ROCDL_wmma_scale16_f32_16x16x128_f8f6f4   : ROCDL_Wmma_IntrOp<"wmma.scale16.f32.16x16x128.f8f6f4", [1,3]>;
----------------
kuhar wrote:

What about the variants with M=32?

https://github.com/llvm/llvm-project/pull/165915