WMMA support for GEMM reduce (#2823)

Added gemm + reduce instance library for RDNA4. This includes:

- New device implementation running GEMM and reduction kernel
- instances for wmma (xdl parity)
- examples for wmma (xdl parity)
- tests for existing xdl and wmma

[ROCm/composable_kernel commit: b25d4d684a]

include/ck/host_utility/device_prop.hpp

@@ -129,5 +129,10 @@ inline bool is_gfx103_supported()
            ck::get_device_name() == "gfx1035" || ck::get_device_name() == "gfx1036";
 }
 
+inline bool is_wmma_supported()
+{
+    return is_gfx103_supported() || is_gfx11_supported() || is_gfx12_supported();
+}
+
 } // namespace ck
 #endif