ltqin fbc03c595d Patch for bwd data comments (#174) ...

* change function name and way to set input zero

* change enable if

[ROCm/composable_kernel commit: 6717168c18]

2022-04-04 20:33:53 -05:00

..

profile_batched_gemm_impl.hpp

use single threaded tensor generator (#161)

2022-03-30 22:28:30 -05:00

profile_batched_gemm_reduce_impl.hpp

Batched gemm and reduction (#156)

2022-03-30 11:21:18 -05:00

profile_conv_bwd_data_impl.hpp

Unified implementation of 1d/2d/3d conv bwd-data. fp32/fp16/bfp16/int8 (#134)

2022-03-29 10:52:25 -05:00

profile_conv_bwd_weight_impl.hpp

NHWC Conv2d Bwd weight fp16 ckprofiler and test (#166)

2022-04-04 20:32:00 -05:00

profile_conv_fwd_bias_relu_add_impl.hpp

GEMM+Bias+ReLU+Add (#76)

2022-02-06 22:32:47 -06:00

profile_conv_fwd_bias_relu_atomic_add_impl.hpp

Fusion Conv+Bias+ReLU(+Add) (#62)

2021-12-26 07:43:42 -07:00

profile_conv_fwd_bias_relu_impl.hpp

GEMM+Bias+ReLU+Add (#76)

2022-02-06 22:32:47 -06:00

profile_conv_fwd_impl.hpp

[Bf16 & int8] [example & ckprofiler] (#100)

2022-03-04 15:56:44 -06:00

profile_convnd_bwd_data_impl.hpp

Patch for bwd data comments (#174)

2022-04-04 20:33:53 -05:00

profile_gemm_bias_2d_impl.hpp

use single threaded tensor generator (#161)

2022-03-30 22:28:30 -05:00

profile_gemm_bias_relu_add_impl.hpp

GEMM+Bias+ReLU+Add (#76)

2022-02-06 22:32:47 -06:00

profile_gemm_bias_relu_impl.hpp

use single threaded tensor generator (#161)

2022-03-30 22:28:30 -05:00

profile_gemm_impl.hpp

use single threaded tensor generator (#161)

2022-03-30 22:28:30 -05:00

profile_gemm_reduce_impl.hpp

use single threaded tensor generator (#161)

2022-03-30 22:28:30 -05:00

profile_grouped_gemm_impl.hpp

use single threaded tensor generator (#161)

2022-03-30 22:28:30 -05:00

profile_reduce_impl.hpp

Compile for gfx908 and gfx90a (#130)

2022-03-31 12:33:34 -05:00