Haicheng WuandHaicheng Wu 497b499d9d Add residual support for shmem staging iterator used in back-to-back GEMM fusion. This allows support of problem_size_0_n that is not multiple of 32. (#590) ...

Co-authored-by: Haicheng Wu <haichengw@nvidia.com>

2022-08-15 11:19:24 -04:00

..

b2b_gemm.h

Add residual support for shmem staging iterator used in back-to-back GEMM fusion. This allows support of problem_size_0_n that is not multiple of 32. (#590)

2022-08-15 11:19:24 -04:00

b2b_implicit_gemm_convolution.h

CUTLASS 2.9 (#468)

2022-04-23 15:02:38 -04:00

default_b2b_conv2d_fprop_sm75.h

CUTLASS 2.9 (#468)

2022-04-23 15:02:38 -04:00

default_b2b_conv2d_fprop_sm80.h

CUTLASS 2.9 (#468)

2022-04-23 15:02:38 -04:00

default_b2b_conv2d_fprop_smem_accumulator_sm75.h

CUTLASS 2.9 (#468)

2022-04-23 15:02:38 -04:00

default_b2b_conv2d_fprop_smem_accumulator_sm80.h

b2b bias vector support (#482)

2022-04-30 04:16:15 -07:00

default_b2b_conv2d_fprop.h

CUTLASS 2.9 (#468)

2022-04-23 15:02:38 -04:00

default_b2b_gemm_smem_accumulator.h

CUTLASS 2.9 (#468)

2022-04-23 15:02:38 -04:00

default_b2b_gemm.h

CUTLASS 2.9 (#468)

2022-04-23 15:02:38 -04:00