ltqin bb66a0b0d6 Fix conv2d bwd data bug when filter is 1x1 and stride = 2 (#132) ...

* fix bwd data filter1strid2 bug

* fichangeshort to ck::bhalf_t

* reset input to zero

Co-authored-by: ltqin <letaoqin@amd.com>

[ROCm/composable_kernel commit: b51808d7a5]

2022-03-21 10:53:23 -05:00

..

profile_batched_gemm_impl.hpp

Batched GEMM for fp16 (#79)

2022-02-11 09:36:52 -06:00

profile_conv_bwd_data_impl.hpp

Fix conv2d bwd data bug when filter is 1x1 and stride = 2 (#132)

2022-03-21 10:53:23 -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_gemm_bias_2d_impl.hpp

Gemm alpha beta profiler (fp32 & fp16) (#91)

2022-02-21 11:35:21 -06:00

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

GEMM+Bias+ReLU+Add (#76)

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

profile_gemm_impl.hpp

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

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

profile_reduce_impl.hpp

Pr82 followup (#115)

2022-03-10 10:14:43 -06:00