================
@@ -2696,6 +2696,25 @@ def int_amdgcn_udot8 :
ImmArg<ArgIndex<0>>, ImmArg<ArgIndex<2>>, ImmArg<ArgIndex<5>>]
>;
+// f32 %r = llvm.amdgcn.dot4.f32.type_a.type_b (v4type_a (as i32) %a, v4type_b
(as i32) %b, f32 %c)
+// %r = %a[0] * %b[0] + %a[1] * %b[1] + %a[2] * %b[2] + %a[3] * %b[3] + %c
+class AMDGPU8bitFloatDot4Intrinsic :
+ ClangBuiltin<!subst("int", "__builtin", NAME)>,
+ DefaultAttrsIntrinsic<
+ [llvm_float_ty], // %r
+ [
+ llvm_i32_ty, // %a
+ llvm_i32_ty, // %b
+ llvm_float_ty, // %c
+ ],
+ [IntrNoMem, IntrSpeculatable]
+ >;
+
+def int_amdgcn_fdot4_f32_fp8_bf8 : AMDGPU8bitFloatDot4Intrinsic;
+def int_amdgcn_fdot4_f32_bf8_fp8 : AMDGPU8bitFloatDot4Intrinsic;
----------------
mariusz-sikora-at-amd wrote:
Done, renamed fdot4 to dot4
https://github.com/llvm/llvm-project/pull/77892
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
