Bing Xu d0d941efc7 [hardswish] correct implmentation (#403) ...

* [hardswish] correct implmentation

* seems working

* hardswish fp32/fp16x2 optimization

* [relu] half2 support

* add relu0; add multiply_add_relu0;

* cleanup

Co-authored-by: Bing Xu <bingxu@fb.com>
Co-authored-by: Haicheng Wu <haichengw@nvidia.com>

2022-02-09 14:28:53 -05:00

..

00_basic_gemm

Cutlass 2.6 Update 1 (#301)

2021-07-27 17:58:30 -07:00

01_cutlass_utilities

Cutlass 2.6 Update 1 (#301)

2021-07-27 17:58:30 -07:00

02_dump_reg_shmem

Cutlass 2.6 Update 1 (#301)

2021-07-27 17:58:30 -07:00

03_visualize_layout

CUTLASS 2.7 (#318)

2021-09-20 11:02:22 -07:00

04_tile_iterator

Cutlass 2.6 Update 1 (#301)

2021-07-27 17:58:30 -07:00

05_batched_gemm

Cutlass 2.6 Update 1 (#301)

2021-07-27 17:58:30 -07:00

06_splitK_gemm

Cutlass 2.6 Update 1 (#301)

2021-07-27 17:58:30 -07:00

07_volta_tensorop_gemm

Cutlass 2.6 Update 1 (#301)

2021-07-27 17:58:30 -07:00

08_turing_tensorop_gemm

Cutlass 2.6 Update 1 (#301)

2021-07-27 17:58:30 -07:00

09_turing_tensorop_conv2dfprop

Cutlass 2.6 Update 1 (#301)

2021-07-27 17:58:30 -07:00

10_planar_complex

Cutlass 2.6 Update 1 (#301)

2021-07-27 17:58:30 -07:00

11_planar_complex_array

Cutlass 2.6 Update 1 (#301)

2021-07-27 17:58:30 -07:00

12_gemm_bias_relu

Cutlass 2.6 Update 1 (#301)

2021-07-27 17:58:30 -07:00

13_two_tensor_op_fusion

CUTLASS 2.8 (#363)

2021-11-19 13:26:35 -08:00

14_ampere_tf32_tensorop_gemm

Cutlass 2.6 Update 1 (#301)

2021-07-27 17:58:30 -07:00

15_ampere_sparse_tensorop_gemm

Updates to fused epilogue (#383)

2021-12-17 16:04:43 -05:00

16_ampere_tensorop_conv2dfprop

[hardswish] correct implmentation (#403)

2022-02-09 14:28:53 -05:00

17_fprop_per_channel_bias

Updates to fused epilogue (#383)

2021-12-17 16:04:43 -05:00

18_ampere_fp64_tensorop_affine2_gemm

Cutlass 2.6 Update 1 (#301)

2021-07-27 17:58:30 -07:00

19_tensorop_canonical

Cutlass 2.6 Update 1 (#301)

2021-07-27 17:58:30 -07:00

20_simt_canonical

Cutlass 2.6 Update 1 (#301)

2021-07-27 17:58:30 -07:00

21_quaternion_gemm

Cutlass 2.6 Update 1 (#301)

2021-07-27 17:58:30 -07:00

22_quaternion_conv

Cutlass 2.6 Update 1 (#301)

2021-07-27 17:58:30 -07:00

23_ampere_gemm_operand_reduction_fusion

example 23 gemm operand reduction fusion (#325)

2021-09-20 13:34:47 -07:00

24_gemm_grouped

CUTLASS 2.8 (#363)

2021-11-19 13:26:35 -08:00

25_ampere_fprop_mainloop_fusion

CUTLASS 2.8 (#363)

2021-11-19 13:26:35 -08:00

26_ampere_wgrad_mainloop_fusion

CUTLASS 2.8 (#363)

2021-11-19 13:26:35 -08:00

27_ampere_3xtf32_fast_accurate_tensorop_gemm

CUTLASS 2.8 (#363)

2021-11-19 13:26:35 -08:00

28_ampere_3xtf32_fast_accurate_tensorop_fprop

CUTLASS 2.8 (#363)

2021-11-19 13:26:35 -08:00

29_ampere_3xtf32_fast_accurate_tensorop_complex_gemm

CUTLASS 2.8 (#363)

2021-11-19 13:26:35 -08:00

common

CUTLASS 2.0 (#62)

2019-11-19 16:55:34 -08:00

CMakeLists.txt

Updates to fused epilogue (#383)

2021-12-17 16:04:43 -05:00