Andrew Kerr fd7e058d0c Added examples to enable the unity build (#102) ... * Updated documentation of fused GEMM example and removed UNITY BUILD batch size. The default batch size when unity build is enabled tends to be favorable.		2020-06-17 07:09:18 -07:00
..
00_basic_gemm	CUTLASS 2.2 (#96)	2020-06-08 16:17:35 -07:00
01_cutlass_utilities	CUTLASS 2.2 (#96)	2020-06-08 16:17:35 -07:00
02_dump_reg_shmem	CUTLASS 2.2 (#96)	2020-06-08 16:17:35 -07:00
03_visualize_layout	Updated mma_sm80.h to avoid perf penalty due to reinterpret_cast<>. (#100)	2020-06-15 10:47:01 -07:00
04_tile_iterator	CUTLASS 2.2 (#96)	2020-06-08 16:17:35 -07:00
05_batched_gemm	CUTLASS 2.2 (#96)	2020-06-08 16:17:35 -07:00
06_splitK_gemm	Updated mma_sm80.h to avoid perf penalty due to reinterpret_cast<>. (#100)	2020-06-15 10:47:01 -07:00
07_volta_tensorop_gemm	Updated mma_sm80.h to avoid perf penalty due to reinterpret_cast<>. (#100)	2020-06-15 10:47:01 -07:00
08_turing_tensorop_gemm	Updated mma_sm80.h to avoid perf penalty due to reinterpret_cast<>. (#100)	2020-06-15 10:47:01 -07:00
10_planar_complex	CUTLASS 2.2 (#96)	2020-06-08 16:17:35 -07:00
11_planar_complex_array	CUTLASS 2.2 (#96)	2020-06-08 16:17:35 -07:00
12_gemm_bias_relu	CUTLASS 2.2 (#96)	2020-06-08 16:17:35 -07:00
13_fused_two_gemms	Added examples to enable the unity build (#102)	2020-06-17 07:09:18 -07:00
common	CUTLASS 2.0 (#62)	2019-11-19 16:55:34 -08:00
CMakeLists.txt	Updated mma_sm80.h to avoid perf penalty due to reinterpret_cast<>. (#100)	2020-06-15 10:47:01 -07:00