package info (click to toggle)
nvidia-cutlass 3.4.1%2Bds-2
  • links: PTS, VCS
  • area: contrib
  • in suites: forky, sid, trixie
  • size: 48,488 kB
  • sloc: cpp: 206,571; ansic: 69,215; python: 25,487; sh: 16; makefile: 15

Folder: device

d .. (parent)
- - rw-r--r-- 8,967 CMakeLists.txt
- - rw-r--r-- 5,344 conv2d_dgrad_implicit_gemm_cf32nhwc_cf32nhwc_cf32nhwc_simt_f32_sm50.cu
- - rw-r--r-- 5,443 conv2d_dgrad_implicit_gemm_cf32nhwc_cf32nhwc_cf32nhwc_simt_f32_sm80.cu
- - rw-r--r-- 11,470 conv2d_dgrad_implicit_gemm_f16nhwc_f16nhwc_f16nhwc_tensor_op_f16_sm80.cu
- - rw-r--r-- 5,239 conv2d_dgrad_implicit_gemm_f16nhwc_f16nhwc_f32nhwc_tensor_op_f32_sm70.cu
- - rw-r--r-- 9,110 conv2d_dgrad_implicit_gemm_f16nhwc_f16nhwc_f32nhwc_tensor_op_f32_sm75.cu
- - rw-r--r-- 8,485 conv2d_dgrad_implicit_gemm_f16nhwc_f16nhwc_f32nhwc_tensor_op_f32_sm80.cu
- - rw-r--r-- 5,243 conv2d_dgrad_implicit_gemm_f32nhwc_f32nhwc_f32nhwc_simt_f32_sm80.cu
- - rw-r--r-- 5,378 conv2d_dgrad_implicit_gemm_tf32nhwc_tf32nhwc_f32nhwc_tensor_op_f32_sm80.cu
- - rw-r--r-- 12,054 conv2d_fprop_few_channels_f16nhwc_f16nhwc_f16nhwc_tensor_op_f32_sm80.cu
- - rw-r--r-- 9,603 conv2d_fprop_fixed_channels_f16nhwc_f16nhwc_f16nhwc_tensor_op_f32_sm80.cu
- - rw-r--r-- 5,267 conv2d_fprop_implicit_gemm_cf32nhwc_cf32nhwc_cf32nhwc_simt_f32_sm50.cu
- - rw-r--r-- 5,357 conv2d_fprop_implicit_gemm_cf32nhwc_cf32nhwc_cf32nhwc_simt_f32_sm80.cu
- - rw-r--r-- 5,089 conv2d_fprop_implicit_gemm_f16nhwc_f16nhwc_f16nhwc_simt_f16_sm60.cu
- - rw-r--r-- 13,690 conv2d_fprop_implicit_gemm_f16nhwc_f16nhwc_f16nhwc_tensor_op_f16_sm80.cu
- - rw-r--r-- 5,390 conv2d_fprop_implicit_gemm_f16nhwc_f16nhwc_f16nhwc_tensor_op_f32_sm80.cu
- - rw-r--r-- 5,191 conv2d_fprop_implicit_gemm_f16nhwc_f16nhwc_f32nhwc_tensor_op_f32_sm70.cu
- - rw-r--r-- 11,136 conv2d_fprop_implicit_gemm_f16nhwc_f16nhwc_f32nhwc_tensor_op_f32_sm75.cu
- - rw-r--r-- 5,291 conv2d_fprop_implicit_gemm_f16nhwc_f16nhwc_f32nhwc_tensor_op_f32_sm80.cu
- - rw-r--r-- 3,551 conv2d_fprop_implicit_gemm_f32nhwc_f32nhwc_f32nhwc_simt_f32_sm50.cu
- - rw-r--r-- 5,157 conv2d_fprop_implicit_gemm_f32nhwc_f32nhwc_f32nhwc_simt_f32_sm80.cu
- - rwxr-xr-x 8,278 conv2d_fprop_implicit_gemm_qf32nhwc_qf32nhwc_qf32nhwc_simt_f32_sm50.cu
- - rw-r--r-- 20,553 conv2d_fprop_implicit_gemm_s4ncxhwx_s4cxrskx_s4ncxhwx_tensor_op_s32_sm75.cu
- - rw-r--r-- 20,647 conv2d_fprop_implicit_gemm_s4ncxhwx_s4cxrskx_s4ncxhwx_tensor_op_s32_sm80.cu
- - rw-r--r-- 5,150 conv2d_fprop_implicit_gemm_s4nhwc_s4nhwc_s32nhwc_tensor_op_s32_sm75.cu
- - rw-r--r-- 5,239 conv2d_fprop_implicit_gemm_s4nhwc_s4nhwc_s32nhwc_tensor_op_s32_sm80.cu
- - rw-r--r-- 26,113 conv2d_fprop_implicit_gemm_s8ncxhwx_s8cxrskx_s8ncxhwx_tensor_op_s32_sm75.cu
- - rw-r--r-- 26,210 conv2d_fprop_implicit_gemm_s8ncxhwx_s8cxrskx_s8ncxhwx_tensor_op_s32_sm80.cu
- - rw-r--r-- 5,106 conv2d_fprop_implicit_gemm_s8nhwc_s8nhwc_s32nhwc_tensor_op_s32_sm75.cu
- - rw-r--r-- 5,194 conv2d_fprop_implicit_gemm_s8nhwc_s8nhwc_s32nhwc_tensor_op_s32_sm80.cu
- - rw-r--r-- 5,738 conv2d_fprop_implicit_gemm_tf32nhwc_tf32nhwc_f32nhwc_tensor_op_f32_sm80.cu
- - rw-r--r-- 5,439 conv2d_fprop_with_broadcast_sm70.cu
- - rw-r--r-- 7,363 conv2d_fprop_with_broadcast_sm75.cu
- - rw-r--r-- 3,984 conv2d_fprop_with_reduction_sm75.cu
- - rw-r--r-- 39,407 conv2d_problems.h
- - rw-r--r-- 14,471 conv2d_strided_dgrad_implicit_gemm_f16nhwc_f16nhwc_f32nhwc_tensor_op_f32_sm80.cu
- - rw-r--r-- 4,173 conv2d_strided_dgrad_implicit_gemm_swizzling4_sm80.cu
- - rw-r--r-- 4,662 conv2d_strided_dgrad_implicit_gemm_tf32nhwc_tf32nhwc_f32nhwc_tensor_op_f32_sm80.cu
- - rw-r--r-- 26,218 conv2d_testbed.h
- - rw-r--r-- 22,110 conv2d_testbed_interleaved.h
- - rw-r--r-- 5,179 conv2d_wgrad_implicit_gemm_cf32nhwc_cf32nhwc_cf32nhwc_simt_f32_sm50.cu
- - rw-r--r-- 5,358 conv2d_wgrad_implicit_gemm_cf32nhwc_cf32nhwc_cf32nhwc_simt_f32_sm80.cu
- - rw-r--r-- 5,264 conv2d_wgrad_implicit_gemm_f16nhwc_f16nhwc_f16nhwc_tensor_op_f16_sm80.cu
- - rw-r--r-- 3,615 conv2d_wgrad_implicit_gemm_f16nhwc_f16nhwc_f32nhwc_tensor_op_f32_sm70.cu
- - rw-r--r-- 7,591 conv2d_wgrad_implicit_gemm_f16nhwc_f16nhwc_f32nhwc_tensor_op_f32_sm75.cu
- - rw-r--r-- 10,514 conv2d_wgrad_implicit_gemm_f16nhwc_f16nhwc_f32nhwc_tensor_op_f32_sm80.cu
- - rw-r--r-- 5,157 conv2d_wgrad_implicit_gemm_f32nhwc_f32nhwc_f32nhwc_simt_f32_sm80.cu
- - rw-r--r-- 5,772 conv2d_wgrad_implicit_gemm_tf32nhwc_tf32nhwc_f32nhwc_tensor_op_f32_sm80.cu
- - rw-r--r-- 23,528 conv2d_with_broadcast_testbed.h
- - rw-r--r-- 21,514 conv2d_with_reduction_testbed.h
- - rw-r--r-- 5,135 conv3d_dgrad_implicit_gemm_f16ndhwc_f16ndhwc_f32ndhwc_tensor_op_f32_sm80.cu
- - rw-r--r-- 5,347 conv3d_dgrad_implicit_gemm_tf32ndhwc_tf32ndhwc_f32ndhwc_tensor_op_f32_sm80.cu
- - rw-r--r-- 3,736 conv3d_fprop_implicit_gemm_f16ndhwc_f16ndhwc_f32ndhwc_tensor_op_f32_sm75.cu
- - rw-r--r-- 6,560 conv3d_fprop_implicit_gemm_f16ndhwc_f16ndhwc_f32ndhwc_tensor_op_f32_sm80.cu
- - rw-r--r-- 5,257 conv3d_fprop_implicit_gemm_tf32ndhwc_tf32ndhwc_f32ndhwc_tensor_op_f32_sm80.cu
- - rw-r--r-- 12,276 conv3d_problems.h
- - rw-r--r-- 21,645 conv3d_testbed.h
- - rw-r--r-- 3,622 conv3d_wgrad_implicit_gemm_f16ndhwc_f16ndhwc_f32ndhwc_tensor_op_f32_sm75.cu
- - rw-r--r-- 6,560 conv3d_wgrad_implicit_gemm_f16ndhwc_f16ndhwc_f32ndhwc_tensor_op_f32_sm80.cu
- - rw-r--r-- 5,256 conv3d_wgrad_implicit_gemm_tf32ndhwc_tf32ndhwc_f32ndhwc_tensor_op_f32_sm80.cu
- - rw-r--r-- 17,700 depthwise_conv2d_direct_conv_testbed.h
- - rw-r--r-- 18,451 depthwise_conv2d_fprop_direct_conv_f16nhwc_f16nhwc_f16nhwc_simt_f16_sm60.cu
- - rw-r--r-- 22,194 depthwise_conv2d_fprop_direct_conv_fixed_stride_dilation_f16nhwc_f16nhwc_f16nhwc_simt_f16_sm60.cu
- - rw-r--r-- 9,383 depthwise_conv2d_fprop_implicit_gemm_f16nhwc_f16nhwc_f16nhwc_simt_f16_sm60.cu
- - rw-r--r-- 20,090 group_conv2d_fprop_implicit_gemm_f16nhwc_f16nhwc_f16nhwc_tensor_op_f32_sm80.cu