[Mlir-commits] [mlir] Adds Arm Neon SMMLA, UMMLA, and USMMLA Intrinsics (PR #80511)

[Diego Caballero]

================
@@ -39,3 +39,45 @@ llvm.func @arm_neon_sdot_16_i8i8(%a: vector<4xi32>, %b: vector<16xi8>, %c: vecto
   %0 = arm_neon.intr.sdot %a, %b, %c : vector<16xi8>, vector<16xi8> to vector<4xi32>
   llvm.return %0 : vector<4xi32>
 }
+
+// -----
+
+// CHECK-LABEL: define <4 x i32> @arm_neon_smmla
+llvm.func @arm_neon_smmla(%arg0: vector<16xi8>,
+                         %arg1: vector<16xi8>,
----------------
dcaballe wrote:

nit: alignment? here and below

https://github.com/llvm/llvm-project/pull/80511