Merge branch 'develop' into barkocot/col2img

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

@@ -8,13 +8,13 @@ list(APPEND GEMM_SPLITK_INSTANCES device_gemm_xdl_splitk_f32_f32_f32_mk_kn_mn_in
                                   device_gemm_xdl_splitk_f16_f16_f16_mk_nk_mn_instance.cpp
                                   device_gemm_xdl_splitk_f16_f16_f16_km_kn_mn_instance.cpp
                                   device_gemm_xdl_splitk_f16_f16_f16_km_nk_mn_instance.cpp
-                                  device_gemm_xdl_splitk_f8_f16_f16_mk_kn_mn_instance.cpp
-                                  device_gemm_xdl_splitk_f8_f16_f16_mk_nk_mn_instance.cpp
-                                  device_gemm_xdl_splitk_f8_f16_f16_km_kn_mn_instance.cpp
-                                  device_gemm_xdl_splitk_f8_f16_f16_km_nk_mn_instance.cpp
-                                  device_gemm_xdl_splitk_f16_f8_f16_mk_kn_mn_instance.cpp
-                                  device_gemm_xdl_splitk_f16_f8_f16_mk_nk_mn_instance.cpp
-                                  device_gemm_xdl_splitk_f16_f8_f16_km_kn_mn_instance.cpp
-                                  device_gemm_xdl_splitk_f16_f8_f16_km_nk_mn_instance.cpp)
+                                  device_gemm_xdl_splitk_fp8_f16_f16_mk_kn_mn_instance.cpp
+                                  device_gemm_xdl_splitk_fp8_f16_f16_mk_nk_mn_instance.cpp
+                                  device_gemm_xdl_splitk_fp8_f16_f16_km_kn_mn_instance.cpp
+                                  device_gemm_xdl_splitk_fp8_f16_f16_km_nk_mn_instance.cpp
+                                  device_gemm_xdl_splitk_f16_fp8_f16_mk_kn_mn_instance.cpp
+                                  device_gemm_xdl_splitk_f16_fp8_f16_mk_nk_mn_instance.cpp
+                                  device_gemm_xdl_splitk_f16_fp8_f16_km_kn_mn_instance.cpp
+                                  device_gemm_xdl_splitk_f16_fp8_f16_km_nk_mn_instance.cpp)
 
 add_instance_library(device_gemm_splitk_instance ${GEMM_SPLITK_INSTANCES})

library/src/tensor_operation_instance/gpu/grouped_conv1d_fwd/CMakeLists.txt

 add_instance_library(device_grouped_conv1d_fwd_instance
-   device_grouped_conv1d_fwd_xdl_gnwc_gkxc_gnwk_bf16_instance.cpp
-   device_grouped_conv1d_fwd_xdl_gnwc_gkxc_gnwk_f16_instance.cpp
-   device_grouped_conv1d_fwd_xdl_gnwc_gkxc_gnwk_f32_instance.cpp
-   device_grouped_conv1d_fwd_xdl_gnwc_gkxc_gnwk_int8_instance.cpp
+   xdl/device_grouped_conv1d_fwd_xdl_gnwc_gkxc_gnwk_bf16_instance.cpp
+   xdl/device_grouped_conv1d_fwd_xdl_gnwc_gkxc_gnwk_f16_instance.cpp
+   xdl/device_grouped_conv1d_fwd_xdl_gnwc_gkxc_gnwk_f32_instance.cpp
+   xdl/device_grouped_conv1d_fwd_xdl_gnwc_gkxc_gnwk_int8_instance.cpp
 )

library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/CMakeLists.txt

 add_instance_library(device_grouped_conv2d_fwd_instance
    #xdl
    # GNHWC, GKYXC, GNHWK
-   device_grouped_conv2d_fwd_xdl_gnhwc_gkyxc_gnhwk_bf16_instance.cpp
-   device_grouped_conv2d_fwd_xdl_gnhwc_gkyxc_gnhwk_f16_instance.cpp
-   device_grouped_conv2d_fwd_xdl_gnhwc_gkyxc_gnhwk_f32_instance.cpp
+   xdl/device_grouped_conv2d_fwd_xdl_gnhwc_gkyxc_gnhwk_bf16_instance.cpp
+   xdl/device_grouped_conv2d_fwd_xdl_gnhwc_gkyxc_gnhwk_f16_instance.cpp
+   xdl/device_grouped_conv2d_fwd_xdl_gnhwc_gkyxc_gnhwk_f32_instance.cpp
    # NHWGC, GKYXC, NHWGK
-   device_grouped_conv2d_fwd_xdl_nhwgc_gkyxc_nhwgk_bf16_instance.cpp
-   device_grouped_conv2d_fwd_xdl_nhwgc_gkyxc_nhwgk_f16_instance.cpp
-   device_grouped_conv2d_fwd_xdl_nhwgc_gkyxc_nhwgk_f32_instance.cpp
+   xdl/device_grouped_conv2d_fwd_xdl_nhwgc_gkyxc_nhwgk_bf16_instance.cpp
+   xdl/device_grouped_conv2d_fwd_xdl_nhwgc_gkyxc_nhwgk_f16_instance.cpp
+   xdl/device_grouped_conv2d_fwd_xdl_nhwgc_gkyxc_nhwgk_f32_instance.cpp
    #dl
    # GNHWC, GKYXC, GNHWK
-   device_grouped_conv2d_fwd_dl_gnhwc_gkyxc_gnhwk_f16_instance.cpp
-   device_grouped_conv2d_fwd_dl_gnhwc_gkyxc_gnhwk_f32_instance.cpp
+   dl/device_grouped_conv2d_fwd_dl_gnhwc_gkyxc_gnhwk_f16_instance.cpp
+   dl/device_grouped_conv2d_fwd_dl_gnhwc_gkyxc_gnhwk_f32_instance.cpp
+   # NHWGC, GKYXC, NHWGK
+   dl/device_grouped_conv2d_fwd_dl_nhwgc_gkyxc_nhwgk_f16_instance.cpp
+   dl/device_grouped_conv2d_fwd_dl_nhwgc_gkyxc_nhwgk_f32_instance.cpp
    # WMMA
-   device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_f16_instance.cpp
-   device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_i8_instance.cpp
+   # GNHWC, GKYXC, GNHWK
+   wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_f16_instance.cpp
+   wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_i8_instance.cpp
+   wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_f16_1x1p0_instance.cpp
+   wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_i8_1x1p0_instance.cpp
+   wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_f16_1x1s1p0_instance.cpp
+   wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_i8_1x1s1p0_instance.cpp
+   wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_f16_oddc_instance.cpp
+   wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_i8_oddc_instance.cpp
    # NHWGC, GKYXC, NHWGK
-   device_grouped_conv2d_fwd_dl_nhwgc_gkyxc_nhwgk_f16_instance.cpp
-   device_grouped_conv2d_fwd_dl_nhwgc_gkyxc_nhwgk_f32_instance.cpp
+   wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_f16_instance.cpp
+   wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_i8_instance.cpp
+   wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_f16_1x1p0_instance.cpp
+   wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_i8_1x1p0_instance.cpp
+   wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_f16_1x1s1p0_instance.cpp
+   wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_i8_1x1s1p0_instance.cpp
+   wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_f16_oddc_instance.cpp
+   wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_i8_oddc_instance.cpp
 )