ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-12 09:16:52 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
fbdf4332c79a18454a553105ae5373911b2ba4ce
composable_kernel/driver/include
History
zjing14 fbdf4332c7 Add xdlops v4r4r4 into online compilation (#48) 
* init for v4r4 xdlops olc

* refactor wrap

* init impl of v4r4 nchw xdlops olc

* tuning

* test perf

* fixed v4r4 nhwc

* tuned v4r4 nhwc

* use gridwise_gemm_xdlops_v2r3

* swap a/b

* add pointer support into offline v2r3

* debugging v4r4r4 transform for olc

* change timer of olc

* refactor v4r4 xdlops nchw olc

* remove transform fun in v4r4 xdlops nhwc olc

Co-authored-by: Chao Liu <chao.liu2@amd.com>
2021-07-16 23:27:08 -05:00
..
conv_common.hpp
Deprecate static kernel (#42)
2021-07-08 10:40:00 -05:00
conv_tunables.hpp
Add xdlops v4r4r4 into online compilation (#48)
2021-07-16 23:27:08 -05:00
device_dynamic_convolution_backward_data_implicit_gemm_v4r1_xdlops_nhwc_kyxc_nhwk.hpp
Add xdlops v4r4r4 into online compilation (#48)
2021-07-16 23:27:08 -05:00
device_dynamic_convolution_backward_data_implicit_gemm_v4r1r2_xdlops_nhwc_kyxc_nhwk.hpp
Add xdlops v4r4r4 into online compilation (#48)
2021-07-16 23:27:08 -05:00
device_dynamic_convolution_forward_implicit_gemm_v4r4_nchw_kcyx_nkhw.hpp
Tweak (#44)
2021-07-08 12:17:43 -05:00
device_dynamic_convolution_forward_implicit_gemm_v4r4_nhwc_kyxc_nhwk.hpp
Restructure gridwise and blockwise GEMM, add tensor contraction and FWD-v4r5 (#36)
2021-06-09 23:53:08 -05:00
device_dynamic_convolution_forward_implicit_gemm_v4r4r2_nhwc_kyxc_nhwk.hpp
DL GEMM fp32/fp16/int8 (#41)
2021-07-04 22:50:29 -05:00
device_dynamic_convolution_forward_implicit_gemm_v4r4r2_xdlops_nchw_kcyx_nkhw.hpp
Add xdlops v4r4r4 into online compilation (#48)
2021-07-16 23:27:08 -05:00
device_dynamic_convolution_forward_implicit_gemm_v4r4r4_xdlops_nhwc_kyxc_nhwk.hpp
Add xdlops v4r4r4 into online compilation (#48)
2021-07-16 23:27:08 -05:00
device_dynamic_convolution_forward_implicit_gemm_v4r5_nchw_kcyx_nkhw.hpp
Restructure gridwise and blockwise GEMM, add tensor contraction and FWD-v4r5 (#36)
2021-06-09 23:53:08 -05:00
device_dynamic_convolution_forward_implicit_gemm_v4r5r2_nchw_kcyx_nkhw.hpp
Deprecate static kernel (#42)
2021-07-08 10:40:00 -05:00
device_dynamic_convolution_forward_implicit_gemm_v5r1_nchw_kcyx_nkhw.hpp
Restructure gridwise and blockwise GEMM, add tensor contraction and FWD-v4r5 (#36)
2021-06-09 23:53:08 -05:00
device_tensor.hpp
Deprecate static kernel (#42)
2021-07-08 10:40:00 -05:00
device.hpp
DL GEMM fp32/fp16/int8 (#41)
2021-07-04 22:50:29 -05:00
host_conv_bwd_data.hpp
xdlops_v4r4_fwd fp32/fp16 (#34)
2021-07-01 14:33:00 -05:00
host_conv.hpp
xdlops_v4r4_fwd fp32/fp16 (#34)
2021-07-01 14:33:00 -05:00
host_tensor_generator.hpp
Change initialization method of tensor for iGEMM (#49)
2021-07-16 22:55:01 -05:00
host_tensor.hpp
xdlops_v4r4_fwd fp32/fp16 (#34)
2021-07-01 14:33:00 -05:00
olc_device_dynamic_convolution_forward_implicit_gemm_v4r4_nchw_kcyx_nkhw.hpp
Add online compilation for dynamic kernels (#37)
2021-06-24 08:34:19 -05:00
olc_device_dynamic_convolution_forward_implicit_gemm_v4r4_xdlops_nchw_kcyx_nkhw.hpp
Add xdlops v4r4r4 into online compilation (#48)
2021-07-16 23:27:08 -05:00
olc_device_dynamic_convolution_forward_implicit_gemm_v4r4_xdlops_nhwc_kyxc_nhwk.hpp
Add xdlops v4r4r4 into online compilation (#48)
2021-07-16 23:27:08 -05:00
olc_device_dynamic_convolution_forward_implicit_gemm_v4r5_nchw_kcyx_nkhw.hpp
Add online compilation for dynamic kernels (#37)
2021-06-24 08:34:19 -05:00
olc_driver_common.hpp
Add online compilation for dynamic kernels (#37)
2021-06-24 08:34:19 -05:00