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
ad541ad6b9de9b0579d5254f82e9d5b86103d309
composable_kernel/library/src/tensor_operation_instance/gpu
History
rocking5566 ad541ad6b9 gemm, conv perchannel quantization (#503) 
* Use gemm_multiple_D instead

* Add gemm bias relu quantization example

* Add pure gemm quantization example

* Add quantization of perchannel conv + bias + relu example

* Refine the code

* Rename multiplier to requant_scale

* Rename the folder

* Remove redundant comment

* Rename the file. Prepare to add perchannel

* Add conv perchannel instance

* Move to quantization folder

* Add conv perchannel client example

* Apply Rangify constructor of HostTensorDescriptor & Tensor<>

* Fix merge error
2022-11-30 14:13:04 -06:00
..
batched_gemm
Add pipeline v1/v2 selector, add more instances (#381)
2022-11-02 16:50:48 -06:00
batched_gemm_add_relu_gemm_add
Refactor device op implementations into impl subdirectory. (#420)
2022-10-13 09:05:08 -05:00
batched_gemm_gemm
Input/output permutation for fused attention (#460)
2022-10-27 14:58:20 -06:00
batched_gemm_reduce
Refactor device op implementations into impl subdirectory. (#420)
2022-10-13 09:05:08 -05:00
batched_gemm_softmax_gemm
remove atten kernel workarounds as we move over to rocm 5.3 (#496)
2022-11-02 16:56:07 -06:00
batched_gemm_softmax_gemm_permute
Add BF16 tests for batched_gemm_softmax_gemm_permute (#504)
2022-11-15 16:30:23 -06:00
batchnorm
BatchNorm backward instance/external API/profiler/tests (#519)
2022-11-30 13:32:20 -06:00
contraction_bilinear
Refactor device op implementations into impl subdirectory. (#420)
2022-10-13 09:05:08 -05:00
contraction_scale
Refactor device op implementations into impl subdirectory. (#420)
2022-10-13 09:05:08 -05:00
conv1d_bwd_data
Refactor device op implementations into impl subdirectory. (#420)
2022-10-13 09:05:08 -05:00
conv2d_bwd_data
Add Conv Backward Data on Navi21 for ResNet50 (#499)
2022-11-15 16:22:20 -06:00
conv2d_fwd
Refactor device op implementations into impl subdirectory. (#420)
2022-10-13 09:05:08 -05:00
conv2d_fwd_bias_relu
Refactor device op implementations into impl subdirectory. (#420)
2022-10-13 09:05:08 -05:00
conv2d_fwd_bias_relu_add
Refactor device op implementations into impl subdirectory. (#420)
2022-10-13 09:05:08 -05:00
conv3d_bwd_data
Refactor device op implementations into impl subdirectory. (#420)
2022-10-13 09:05:08 -05:00
elementwise
Refactor device op implementations into impl subdirectory. (#420)
2022-10-13 09:05:08 -05:00
elementwise_normalization
Fused elementwise normalization (#492)
2022-11-03 12:01:58 -06:00
gemm
Add pipeline v1/v2 selector, add more instances (#381)
2022-11-02 16:50:48 -06:00
gemm_add_add_fastgelu
Add pipeline v1/v2 selector, add more instances (#381)
2022-11-02 16:50:48 -06:00
gemm_add_fastgelu
Client examples AddFastGelu and FastGelu + instances. (#509)
2022-11-19 22:08:26 -06:00
gemm_bias_add_reduce
Refactor device op implementations into impl subdirectory. (#420)
2022-10-13 09:05:08 -05:00
gemm_bilinear
Refactor device op implementations into impl subdirectory. (#420)
2022-10-13 09:05:08 -05:00
gemm_fastgelu
Client examples AddFastGelu and FastGelu + instances. (#509)
2022-11-19 22:08:26 -06:00
gemm_reduce
Refactor device op implementations into impl subdirectory. (#420)
2022-10-13 09:05:08 -05:00
gemm_splitk
Refactor device op implementations into impl subdirectory. (#420)
2022-10-13 09:05:08 -05:00
grouped_conv1d_bwd_weight
Add client example of grouped conv2d backward weight (data type: fp16) (#498)
2022-11-09 18:50:03 -06:00
grouped_conv1d_fwd
Refactor device op implementations into impl subdirectory. (#420)
2022-10-13 09:05:08 -05:00
grouped_conv2d_bwd_data
Remove interface 'DeviceGroupedConvBwdData' (#500)
2022-11-09 18:32:17 -06:00
grouped_conv2d_bwd_weight
Add client example of grouped conv2d backward weight (data type: fp16) (#498)
2022-11-09 18:50:03 -06:00
grouped_conv2d_fwd
Add Conv Forward on Navi21 for ResNet50 (#490)
2022-10-31 10:24:25 -06:00
grouped_conv3d_bwd_weight
Add client example of grouped conv2d backward weight (data type: fp16) (#498)
2022-11-09 18:50:03 -06:00
grouped_conv3d_fwd
fix missing -fPIC flag for conv3d_fwd instance lib (#473)
2022-10-27 15:32:46 -06:00
grouped_gemm
Refactor device op implementations into impl subdirectory. (#420)
2022-10-13 09:05:08 -05:00
normalization
Refactor device op implementations into impl subdirectory. (#420)
2022-10-13 09:05:08 -05:00
quantization
gemm, conv perchannel quantization (#503)
2022-11-30 14:13:04 -06:00
reduce
Update to the Reduction API and instances (#476)
2022-10-25 09:39:11 -06:00
softmax
Softmax unit-test reduction across all and non innermost dims cases. (#406)
2022-11-02 16:46:08 -06:00
CMakeLists.txt
Input/output permutation for fused attention (#460)
2022-10-27 14:58:20 -06:00