ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-13 01:36:06 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
54b68eb343e9b29af024f4a5c4ac57e4e225c8fc
composable_kernel/include/ck/tensor_operation/gpu/device/impl
History
Bartłomiej Kocot fc9f97568f Add DeviceBatchedGemmMultipleD_Dl (#732) 
* Add DeviceBatchedGemmMultipleD_Dl

* Fix batched_gemm tests

* Fix comments

* test_batched_gemm_multi_d fixes

* Fix args for isSupported batchedGemmMultipleDDl

* Disable tests for gfx90a
2023-06-12 08:37:15 -05:00
..
device_batched_contraction_multiple_d_wmma_cshuffle.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_batched_contraction_multiple_d_xdl_cshuffle.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_batched_gemm_e_permute_xdl.hpp
Syncing up from internal repo to enable MI300. (#690)
2023-04-28 18:22:59 -05:00
device_batched_gemm_gemm_xdl_cshuffle.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_batched_gemm_multi_d_xdl.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_batched_gemm_multiple_d_dl.hpp
Add DeviceBatchedGemmMultipleD_Dl (#732)
2023-06-12 08:37:15 -05:00
device_batched_gemm_multiple_d_gemm_multiple_d_xdl_cshuffle.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_batched_gemm_reduce_xdl_cshuffle.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_batched_gemm_softmax_gemm_permute_xdl_cshuffle.hpp
Fix flash attn mask bug (#733)
2023-06-12 08:35:31 -05:00
device_batched_gemm_softmax_gemm_xdl_cshuffle.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_batched_gemm_xdl.hpp
Simplify kernel argument of device operator Device(Batched)GemmXdl<> (#723)
2023-06-01 16:23:02 -05:00
device_batchnorm_backward_impl.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_batchnorm_forward_impl.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_cgemm_4gemm_xdl_cshuffle.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_contraction_multiple_d_xdl_cshuffle.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_conv2d_backward_weight_xdl_c_shuffle_nhwc_kyxc_nhwk.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk.hpp
Simplify kernel argument of device operator Device(Batched)GemmXdl<> (#723)
2023-06-01 16:23:02 -05:00
device_conv2d_fwd_xdl_c_shuffle_bias_activation_add_nhwc_kyxc_nhwk.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_conv2d_fwd_xdl_c_shuffle_bias_activation_nhwc_kyxc_nhwk.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_conv2d_fwd_xdl_c_shuffle_nhwc_kyxc_nhwk.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_conv2d_fwd_xdl_nhwc_kyxc_nhwk.hpp
Simplify kernel argument of device operator Device(Batched)GemmXdl<> (#723)
2023-06-01 16:23:02 -05:00
device_conv3d_fwd_naive_ndhwc_kzyxc_ndhwk.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_conv3d_fwd_xdl_ndhwc_kzyxc_ndhwk.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_convnd_bwd_data_nwc_kxc_nwk_dl.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_convnd_bwd_data_nwc_kxc_nwk_xdl.hpp
Simplify kernel argument of device operator Device(Batched)GemmXdl<> (#723)
2023-06-01 16:23:02 -05:00
device_elementwise_2d_impl.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_elementwise_impl.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_elementwise_normalization_impl.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_gemm_bias_add_reduce_xdl_cshuffle.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_gemm_dl.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_gemm_multiple_d_dl.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_gemm_multiple_d_layernorm_xdl_cshuffle.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_gemm_multiple_d_multiple_r_xdl_cshuffle.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_gemm_multiple_d_wmma_cshuffle.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_gemm_multiple_d_xdl_cshuffle.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_gemm_reduce_xdl_cshuffle.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_gemm_wmma.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_gemm_xdl_cshuffle.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_gemm_xdl_layernorm_cshuffle.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_gemm_xdl_skip_b_lds.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_gemm_xdl_splitk_c_shuffle.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_gemm_xdl.hpp
Simplify kernel argument of device operator Device(Batched)GemmXdl<> (#723)
2023-06-01 16:23:02 -05:00
device_grouped_contraction_multiple_d_xdl_cshuffle.hpp
fix clang format (#740)
2023-06-02 14:10:02 -07:00
device_grouped_conv_bwd_data_multiple_d_xdl_cshuffle_v1.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_grouped_conv_bwd_weight_gnwc_gkxc_gnwk_dl.hpp
Enable gemm_dl and other kernels on Navi3x. (#714)
2023-05-23 11:23:16 -05:00
device_grouped_conv_bwd_weight_gnwc_gkxc_gnwk_xdl_cshuffle.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_grouped_conv_fwd_multiple_d_multiple_r_xdl_cshuffle.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_grouped_conv_fwd_multiple_d_multiple_r.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_grouped_conv_fwd_multiple_d_wmma_cshuffle.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_grouped_conv_fwd_multiple_d_xdl_cshuffle.hpp
Syncing up from internal repo to enable MI300. (#690)
2023-04-28 18:22:59 -05:00
device_grouped_gemm_multiple_d_dl.hpp
fix clang format (#740)
2023-06-02 14:10:02 -07:00
device_grouped_gemm_xdl_splitk_cshuffle.hpp
fix clang format (#740)
2023-06-02 14:10:02 -07:00
device_grouped_gemm_xdl.hpp
fix clang format (#740)
2023-06-02 14:10:02 -07:00
device_multiple_reduce_multiblock.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_multiple_reduce_threadwise.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_normalization_impl.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_normalization_splitk_impl.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_permute_impl.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_pool2d_fwd_nhwc_nhwc.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_pool3d_fwd_ndhwc_ndhwc.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_reduce_common.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_reduce_multiblock.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_reduce_threadwise.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_softmax_impl.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
device_sparse_embeddings_forward_layernorm.hpp
update copyright headers (#726)
2023-05-31 18:46:57 -05:00