enable dlop gemm and conv on gfx1100

include/ck/tensor_operation/gpu/device/device_grouped_conv_fwd_dl_multiple_d_nhwc_kyxc_nhwk.hpp

@@ -709,7 +709,7 @@ struct DeviceGroupedConvFwdDlMultipleD_NHWC_KYXC_NHWK
         namespace ctc = tensor_layout::convolution;
 
         // check device
-        if(!(ck::get_device_name() == "gfx906" || ck::get_device_name() == "gfx1030"))
+        if(!(ck::get_device_name() == "gfx906" || ck::get_device_name() == "gfx1030" || ck::get_device_name() == "gfx1100"))
         {
             return false;
         }

include/ck/tensor_operation/gpu/device/impl/device_gemm_dl.hpp

@@ -485,7 +485,7 @@ struct DeviceGemmDl : public DeviceGemm<ALayout,
 
     static bool IsSupportedArgument(const Argument& arg)
     {
-        if(ck::get_device_name() == "gfx906" || ck::get_device_name() == "gfx1030")
+        if(ck::get_device_name() == "gfx906" || ck::get_device_name() == "gfx1030" || ck::get_device_name() == "gfx1100")
         {
             return GridwiseGemm::CheckValidity(
                 arg.a_grid_desc_k0_m_k1_, arg.b_grid_desc_k0_n_k1_, arg.c_grid_desc_m_n_);