ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-14 02:02:46 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
4e27eae99d11caab824feecb7e94149779139a96
composable_kernel/library/src/tensor_operation_instance/gpu
History
Bartlomiej Wroblewski 4d9c41c7f5 Add basic support for direct loads from global to LDS (#999) 
* Add basic support for direct loads from global to LDS

* Clean the code and comments

* Add support for fp16

* Add comments

* Add check for thread cluster lengths

* Align non-direct-load fp16 example

* Small fixes

* Extend IsSupported to check for supported GPU gens

* Build examples only on the supported HW

* Do not throw when instance not supported in 04 example

* Review: Apply review suggestions

* Review: small fix

* Review: small fix

[ROCm/composable_kernel commit: 627054b941]
2023-11-25 13:35:22 +01:00
..
avg_pool3d_bwd
Refactoring cmake files to build data types separately. (#932)
2023-09-20 22:15:56 -07:00
batched_gemm
Refactoring cmake files to build data types separately. (#932)
2023-09-20 22:15:56 -07:00
batched_gemm_add_relu_gemm_add
Refactoring cmake files to build data types separately. (#932)
2023-09-20 22:15:56 -07:00
batched_gemm_bias_permute
Refactoring cmake files to build data types separately. (#932)
2023-09-20 22:15:56 -07:00
batched_gemm_gemm
Refactoring cmake files to build data types separately. (#932)
2023-09-20 22:15:56 -07:00
batched_gemm_multi_d
Refactoring cmake files to build data types separately. (#932)
2023-09-20 22:15:56 -07:00
batched_gemm_reduce
Refactoring cmake files to build data types separately. (#932)
2023-09-20 22:15:56 -07:00
batched_gemm_softmax_gemm
Refactoring cmake files to build data types separately. (#932)
2023-09-20 22:15:56 -07:00
batched_gemm_softmax_gemm_permute
Refactoring cmake files to build data types separately. (#932)
2023-09-20 22:15:56 -07:00
batchnorm
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
column_to_image
Add support for groups in Img2Col/Col2Img (#1007)
2023-10-31 10:46:32 +01:00
contraction_bilinear
Add support for mixed precision in contraction scale and bilinear (#973)
2023-11-02 14:26:33 -07:00
contraction_scale
Add support for mixed precision in contraction scale and bilinear (#973)
2023-11-02 14:26:33 -07:00
conv1d_bwd_data
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
conv2d_bwd_data
Refactoring cmake files to build data types separately. (#932)
2023-09-20 22:15:56 -07:00
conv2d_fwd
Refactoring cmake files to build data types separately. (#932)
2023-09-20 22:15:56 -07:00
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
Refactoring cmake files to build data types separately. (#932)
2023-09-20 22:15:56 -07:00
gemm
Add basic support for direct loads from global to LDS (#999)
2023-11-25 13:35:22 +01:00
gemm_add_add_fastgelu
Refactoring cmake files to build data types separately. (#932)
2023-09-20 22:15:56 -07:00
gemm_add_fastgelu
Refactoring cmake files to build data types separately. (#932)
2023-09-20 22:15:56 -07:00
gemm_add_multiply
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
gemm_add_relu_add_layernorm
Refactoring cmake files to build data types separately. (#932)
2023-09-20 22:15:56 -07:00
gemm_bias_add_reduce
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
gemm_bilinear
Refactoring cmake files to build data types separately. (#932)
2023-09-20 22:15:56 -07:00
gemm_fastgelu
Refactoring cmake files to build data types separately. (#932)
2023-09-20 22:15:56 -07:00
gemm_multiply_add
Refactoring cmake files to build data types separately. (#932)
2023-09-20 22:15:56 -07:00
gemm_reduce
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
gemm_splitk
Add Gemm instances for performance improvement (#1018)
2023-11-07 09:09:58 -06:00
gemm_streamk
Refactoring cmake files to build data types separately. (#932)
2023-09-20 22:15:56 -07:00
grouped_conv1d_bwd_weight
Add grouped conv bwd weight wmma (#985)
2023-10-17 10:32:26 +02:00
grouped_conv1d_fwd
Introduce multiABD api and deprecate multiD (#1035)
2023-11-14 17:00:40 +01:00
grouped_conv2d_bwd_data
Add grouped conv bwd data wmma (#950)
2023-09-28 23:10:18 +02:00
grouped_conv2d_bwd_weight
Add grouped conv bwd weight wmma (#985)
2023-10-17 10:32:26 +02:00
grouped_conv2d_fwd
Introduce multiABD api and deprecate multiD (#1035)
2023-11-14 17:00:40 +01:00
grouped_conv3d_bwd_data
Clean DTYPES conditions in CMake (#974)
2023-10-18 11:14:14 -05:00
grouped_conv3d_bwd_weight
Fix cmake dtype check (#989)
2023-10-21 22:19:43 +02:00
grouped_conv3d_fwd
Introduce multiABD api and deprecate multiD (#1035)
2023-11-14 17:00:40 +01:00
grouped_conv3d_fwd_scaleadd_ab
Introduce multiABD api and deprecate multiD (#1035)
2023-11-14 17:00:40 +01:00
grouped_conv3d_fwd_scaleadd_scaleadd_relu
Introduce multiABD api and deprecate multiD (#1035)
2023-11-14 17:00:40 +01:00
grouped_gemm
Add Gemm instances for performance improvement (#1018)
2023-11-07 09:09:58 -06:00
grouped_gemm_bias
Grouped Gemm with Fixed K and N with SplitK (#818)
2023-08-31 09:22:12 -05:00
grouped_gemm_fastgelu
Refactoring cmake files to build data types separately. (#932)
2023-09-20 22:15:56 -07:00
grouped_gemm_fixed_nk
Clean DTYPES conditions in CMake (#974)
2023-10-18 11:14:14 -05:00
image_to_column
Add support for groups in Img2Col/Col2Img (#1007)
2023-10-31 10:46:32 +01:00
max_pool_bwd
Refactoring cmake files to build data types separately. (#932)
2023-09-20 22:15:56 -07:00
normalization_fwd
Layernorm4d (#1022)
2023-11-09 08:34:51 +08:00
pool3d_fwd
Refactoring cmake files to build data types separately. (#932)
2023-09-20 22:15:56 -07:00
quantization
Introduce multiABD api and deprecate multiD (#1035)
2023-11-14 17:00:40 +01:00
reduce
update copyright headers (#726)
2023-05-31 18:46:57 -05:00
softmax
Refactoring cmake files to build data types separately. (#932)
2023-09-20 22:15:56 -07:00
transpose
Transpose 3d (#984)
2023-11-08 19:45:07 -06:00
CMakeLists.txt
Fix cmake dtype check (#989)
2023-10-21 22:19:43 +02:00