Po Yen Chen 850144a0d3 Split GEMM instance library & enable pipeline v2 optimization (#783) ...

* Move source file into sub-directories

* Add missing include directive

* Split DeviceGemmXdl<> fp16 instances

* Fix format

* Remove unnecessary CMakeLists.txt

* Add macros to toggle new features

* Remove debug message

* Turn off GEMM v2 pipeline optimization by default

* Fix format

* Extract duplicated string as list

* Enlarge indent in CMakeLists.txt

2023-07-06 10:59:35 -05:00

..

batched_gemm

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

batched_gemm_add_relu_gemm_add

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

batched_gemm_bias_permute

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

batched_gemm_gemm

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

batched_gemm_multi_d

Fix copyrights for DeviceBatchedGemmMultipleD_Dl

2023-07-06 15:50:27 +02:00

batched_gemm_reduce

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

batched_gemm_softmax_gemm

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

batched_gemm_softmax_gemm_permute

Fix flash attn mask bug (#733)

2023-06-12 08:35:31 -05:00

batchnorm

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

contraction_bilinear

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

contraction_scale

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

conv1d_bwd_data

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

conv2d_bwd_data

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

conv2d_fwd

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

conv2d_fwd_bias_relu

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

conv2d_fwd_bias_relu_add

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

conv3d_bwd_data

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

elementwise

Padded Generic Kernel Instance (#730)

2023-06-16 23:43:11 -05:00

elementwise_normalization

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

gemm

Split GEMM instance library & enable pipeline v2 optimization (#783)

2023-07-06 10:59:35 -05:00

gemm_add_add_fastgelu

Add generic kernel instances for ck::tensor_operation::device::DeviceGemmMultipleD (#741)

2023-06-14 16:06:56 -05:00

gemm_add_fastgelu

Add generic kernel instances for ck::tensor_operation::device::DeviceGemmMultipleD (#741)

2023-06-14 16:06:56 -05:00

gemm_add_multiply

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

gemm_add_relu_add_layernorm

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

gemm_bias_add_reduce

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

gemm_bilinear

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

gemm_fastgelu

Add generic kernel instances for ck::tensor_operation::device::DeviceGemmMultipleD (#741)

2023-06-14 16:06:56 -05:00

gemm_reduce

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

gemm_splitk

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

grouped_conv1d_bwd_weight

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

grouped_conv1d_fwd

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

grouped_conv2d_bwd_data

Support bf16/f32/f16 and NHWGC conv2d_bwd_data (#757)

2023-06-21 08:20:31 -05:00

grouped_conv2d_bwd_weight

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

grouped_conv2d_fwd

Move Device Ops implementations into impl directory. (#777)

2023-07-06 16:15:51 +02:00

grouped_conv3d_bwd_weight

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

grouped_conv3d_fwd

Fixed Weight layout of grouped_conv 3d fwd (#743)

2023-06-15 10:19:33 -05:00

grouped_gemm

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

grouped_gemm_fastgelu

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

normalization

Padded Generic Kernel Instance (#730)

2023-06-16 23:43:11 -05:00

pool_fwd

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

quantization

Move Device Ops implementations into impl directory. (#777)

2023-07-06 16:15:51 +02:00

reduce

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

softmax

Padded Generic Kernel Instance (#730)

2023-06-16 23:43:11 -05:00

CMakeLists.txt

Input/output permutation for fused attention (#460)

2022-10-27 14:58:20 -06:00