resolved conflicts

library/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm/CMakeLists.txt

+# ONLY XDL_KERNELS
 add_instance_library(device_batched_gemm_softmax_gemm_instance
     device_batched_gemm_softmax_gemm_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gno_gmo_instance.cpp
 )

library/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm_permute/CMakeLists.txt

+# ONLY XDL_KERNELS
 set(DEVICE_BATCHED_GEMM_SOFTMAX_GEMM_PERMUTE_INSTANCES)
 list(APPEND DEVICE_BATCHED_GEMM_SOFTMAX_GEMM_PERMUTE_INSTANCES
     device_batched_gemm_softmax_gemm_permute_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gno_gmo_instance.cpp

library/src/tensor_operation_instance/gpu/contraction_bilinear/CMakeLists.txt

+# ONLY XDL_KERNELS
 set(DEVICE_CONTRACTION_BILINEAR_INSTANCES)
 
 # FP32

library/src/tensor_operation_instance/gpu/contraction_scale/CMakeLists.txt

+# ONLY XDL_KERNELS
 set(DEVICE_CONTRACTION_SCALE_INSTANCES)
 
 # FP32

library/src/tensor_operation_instance/gpu/conv1d_bwd_data/CMakeLists.txt

+# ONLY XDL_KERNELS
 add_instance_library(device_conv1d_bwd_data_instance
    device_conv1d_bwd_data_xdl_nwc_kxc_nwk_f16_instance.cpp
    device_conv1d_bwd_data_xdl_nwc_kxc_nwk_f32_instance.cpp

library/src/tensor_operation_instance/gpu/conv2d_bwd_data/CMakeLists.txt

+# ONLY XDL_AND_DL_KERNELS
 set(CONV2D_BWD_DATA_INSTANCES)
 list(APPEND CONV2D_BWD_DATA_INSTANCES device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk_f32_instance.cpp
                                       device_conv2d_bwd_data_dl_nhwc_kyxc_nhwk_f32_instance.cpp

library/src/tensor_operation_instance/gpu/conv2d_fwd/CMakeLists.txt

+# ONLY XDL_KERNELS
 set(DEVICE_CONV2D_FWD_INSTANCES)
 list(APPEND DEVICE_CONV2D_FWD_INSTANCES device_conv2d_fwd_xdl_nhwc_kyxc_nhwk_f32_instance.cpp
                                         device_conv2d_fwd_xdl_nhwc_kyxc_nhwk_f16_instance.cpp

library/src/tensor_operation_instance/gpu/conv2d_fwd_bias_relu/CMakeLists.txt

+# ONLY XDL_KERNELS
 add_instance_library(device_conv2d_fwd_bias_relu_instance
    device_conv2d_fwd_xdl_c_shuffle_bias_relu_nhwc_kyxc_nhwk_f16_instance.cpp
 )

library/src/tensor_operation_instance/gpu/conv2d_fwd_bias_relu_add/CMakeLists.txt

+# ONLY XDL_KERNELS
 add_instance_library(device_conv2d_fwd_bias_relu_add_instance
    device_conv2d_fwd_xdl_c_shuffle_bias_relu_add_nhwc_kyxc_nhwk_f16_instance.cpp
 )

library/src/tensor_operation_instance/gpu/conv3d_bwd_data/CMakeLists.txt

+# ONLY XDL_KERNELS
 add_instance_library(device_conv3d_bwd_data_instance
    device_conv3d_bwd_data_xdl_ndhwc_kzyxc_ndhwk_f16_instance.cpp
    device_conv3d_bwd_data_xdl_ndhwc_kzyxc_ndhwk_f32_instance.cpp

library/src/tensor_operation_instance/gpu/gemm_add/CMakeLists.txt

+# ONLY XDL_KERNELS
 add_instance_library(device_gemm_add_instance
    device_gemm_add_xdl_c_shuffle_f16_i8_f16_f16_mk_kn_mn_mn_instance.cpp
    device_gemm_add_xdl_c_shuffle_bf16_i8_bf16_bf16_mk_kn_mn_mn_instance.cpp

library/src/tensor_operation_instance/gpu/gemm_add_add_fastgelu/CMakeLists.txt

+# ONLY XDL_KERNELS
 add_instance_library(device_gemm_add_add_fastgelu_instance
    device_gemm_add_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_f16_km_kn_mn_mn_mn_instance.cpp
    device_gemm_add_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_f16_km_nk_mn_mn_mn_instance.cpp

library/src/tensor_operation_instance/gpu/gemm_add_fastgelu/CMakeLists.txt

+# ONLY XDL_KERNELS
 add_instance_library(device_gemm_add_fastgelu_instance
    device_gemm_add_fastgelu_xdl_c_shuffle_bf16_i8_bf16_bf16_mk_kn_mn_mn_instance.cpp
    device_gemm_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_km_kn_mn_mn_instance.cpp

library/src/tensor_operation_instance/gpu/gemm_add_multiply/CMakeLists.txt

+# ONLY XDL_KERNELS
 add_instance_library(device_gemm_add_multiply_instance
    device_gemm_add_multiply_xdl_c_shuffle_f16_f16_f16_f16_f16_km_kn_mn_mn_mn_instance.cpp
    device_gemm_add_multiply_xdl_c_shuffle_f16_f16_f16_f16_f16_km_nk_mn_mn_mn_instance.cpp

library/src/tensor_operation_instance/gpu/gemm_add_relu/CMakeLists.txt

+# ONLY XDL_KERNELS
 add_instance_library(device_gemm_add_relu_instance
    device_gemm_add_relu_xdl_c_shuffle_f16_i8_f16_f16_mk_kn_mn_mn_instance.cpp
    device_gemm_add_relu_xdl_c_shuffle_bf16_i8_bf16_bf16_mk_kn_mn_mn_instance.cpp

library/src/tensor_operation_instance/gpu/gemm_add_relu_add_layernorm/CMakeLists.txt

+# ONLY XDL_KERNELS
 add_instance_library(device_gemm_add_relu_add_layernorm_instance
    device_gemm_add_relu_add_xdl_c_shuffle_layernorm_f16_km_kn_mn_mn_mn_instance.cpp
    device_gemm_add_relu_add_xdl_c_shuffle_layernorm_f16_km_nk_mn_mn_mn_instance.cpp

library/src/tensor_operation_instance/gpu/gemm_add_silu/CMakeLists.txt

+# ONLY XDL_KERNELS
 add_instance_library(device_gemm_add_silu_instance
    device_gemm_add_silu_xdl_c_shuffle_f16_i8_f16_f16_mk_kn_mn_mn_instance.cpp
    device_gemm_add_silu_xdl_c_shuffle_bf16_i8_bf16_bf16_mk_kn_mn_mn_instance.cpp

library/src/tensor_operation_instance/gpu/gemm_bias_add_reduce/CMakeLists.txt

+# ONLY XDL_KERNELS
 add_instance_library(device_gemm_bias_add_reduce_instance
     device_gemm_bias_add_mean_squaremean_xdl_cshuffle_f16_f16_f16_f32_f32_mk_kn_mn_instance.cpp
     device_gemm_bias_add_mean_squaremean_xdl_cshuffle_f16_f16_f16_f32_f32_mk_nk_mn_instance.cpp

library/src/tensor_operation_instance/gpu/gemm_bilinear/CMakeLists.txt

+# ONLY XDL_AND_WMMA_KERNELS
 add_instance_library(device_gemm_bilinear_instance
    device_gemm_bilinear_xdl_c_shuffle_f16_f16_f16_f16_km_kn_mn_mn_instance.cpp
    device_gemm_bilinear_xdl_c_shuffle_f16_f16_f16_f16_km_nk_mn_mn_instance.cpp

library/src/tensor_operation_instance/gpu/gemm_fastgelu/CMakeLists.txt

+# ONLY XDL_KERNELS
 add_instance_library(device_gemm_fastgelu_instance
    device_gemm_fastgelu_xdl_c_shuffle_f16_f16_f16_km_kn_mn_instance.cpp
    device_gemm_fastgelu_xdl_c_shuffle_f16_f16_f16_km_nk_mn_instance.cpp