Commits · 4f31669fecf5129dff94da5e47c67e03103532ec · gaoqiong / composable_kernel

05 Mar, 2021 1 commit
- add workaround for SWDEV-275126 · 4f31669f
  Chao Liu authored Mar 05, 2021
  
  4f31669f
03 Mar, 2021 3 commits
- Merge branch 'dynamic_tensor_descriptor' of... · 129cc2e3
  Chao Liu authored Mar 02, 2021
```
Merge branch 'dynamic_tensor_descriptor' of github.com:asroy/modular_convolution into dynamic_tensor_descriptor
```
  129cc2e3
- add a script · 245723a3
  Chao Liu authored Mar 02, 2021
  
  245723a3
- update buffer load · a34d310c
  Chao Liu authored Mar 02, 2021
  
  a34d310c
02 Mar, 2021 3 commits
- fix bug · 1762eb16
  Chao Liu authored Mar 02, 2021
  
  1762eb16
- bug fix · ac87ed7c
  Chao Liu authored Mar 01, 2021
  
  ac87ed7c
- refactor buffer resource · 899df971
  Chao Liu authored Mar 01, 2021
  
  899df971
26 Feb, 2021 5 commits
- testing navi · a915f574
  Chao Liu authored Feb 26, 2021
  
  a915f574
- testing · 12225618
  Chao Liu authored Feb 26, 2021
  
  12225618
- fix · 6559076e
  Chao Liu authored Feb 25, 2021
  
  6559076e
- refactor · ca8ba252
  Chao Liu authored Feb 25, 2021
  
  ca8ba252
- static kernel use raw buffer load/store · edc08fe6
  Chao Liu authored Feb 25, 2021
  
  edc08fe6
25 Feb, 2021 1 commit
- test · ecad4061
  Chao Liu authored Feb 25, 2021
  
  ecad4061
24 Feb, 2021 3 commits
- add non-padded · c31867bd
  Chao Liu authored Feb 24, 2021
  
  c31867bd
- refactor vector_type · 5f0c56d0
  Chao Liu authored Feb 23, 2021
  
  5f0c56d0
- add fwd-v4r4-nhwc, change vector_type · 20fa988f
  Chao Liu authored Feb 23, 2021
  
  20fa988f
23 Feb, 2021 2 commits
- clean up · 1c62b47b
  Chao Liu authored Feb 22, 2021
  
  1c62b47b
- threadwise copy v1r3 take (compile-time) SrcSliceOriginIdx as argument · c9b52bce
  Chao Liu authored Feb 22, 2021
  
  c9b52bce
22 Feb, 2021 5 commits
- added IsKnownAtCompileTime() in multi-index transform and tensor descriptor · dea22d0e
  Chao Liu authored Feb 22, 2021
  
  dea22d0e
- refactor · 55599afd
  Chao Liu authored Feb 22, 2021
  
  55599afd
- clean up · 4cf69087
  Chao Liu authored Feb 22, 2021
  
  4cf69087
- made multi-index transform support compile-time and run-time info · 4687ef88
  Chao Liu authored Feb 22, 2021
  
  4687ef88
- making dynamic multi-index transform support compile-time info · 2558d019
  Chao Liu authored Feb 21, 2021
  
  2558d019
21 Feb, 2021 4 commits
- add v_fmac inline asm · 1e55a3b1
  Chao Liu authored Feb 20, 2021
  
  1e55a3b1
- use raw buffer intrinsic · 2a87a973
  Chao Liu authored Feb 20, 2021
  
  2a87a973
- refactor buffer load/store · 079b745d
  Chao Liu authored Feb 20, 2021
  
  079b745d
- changed blockwise and threadwise gemm to use new tensor descriptor · f6ec737c
  Chao Liu authored Feb 20, 2021
  
  f6ec737c
19 Feb, 2021 1 commit

overhauling DynamicTensorDescriptor and dynamic multi-index transform in... · a7c587ee

Chao Liu authored Feb 19, 2021

overhauling DynamicTensorDescriptor and dynamic multi-index transform in preparation for partially compile-time and partially run-time tensor descriptor

a7c587ee

18 Feb, 2021 1 commit

overhauling DynamicTensorDescriptor and dynamic multi-index transform in... · cb7ed650

Chao Liu authored Feb 18, 2021

overhauling DynamicTensorDescriptor and dynamic multi-index transform in preparation for partially compile-time and partially run-time tensor descriptor

cb7ed650

17 Feb, 2021 1 commit

overhauling DynamicTensorDescriptor and dynamic multi-index transform in... · 3990522d

Chao Liu authored Feb 17, 2021

overhauling DynamicTensorDescriptor and dynamic multi-index transform in preparation for partially compile-time and partially run-time tensor descriptor

3990522d

14 Feb, 2021 1 commit
- fixed GetSrcCoordinateResetStep and GetDstCoordinateResetStep in v1r3 and v3 · 2dea900b
  Chao Liu authored Feb 14, 2021
  
  2dea900b
12 Feb, 2021 2 commits
- move iterator hack to host · 6fe9682a
  Chao Liu authored Feb 12, 2021
  
  6fe9682a
- refactor · 0d475c27
  Chao Liu authored Feb 11, 2021
  
  0d475c27
10 Feb, 2021 1 commit
- clean up threadwise copy · 1c704471
  Chao Liu authored Feb 09, 2021
  
  1c704471
08 Feb, 2021 1 commit
- pass tensor descriptor from host to device by reference, pointer and void* · 8ce8f734
  Chao Liu authored Feb 07, 2021
  
  8ce8f734
07 Feb, 2021 3 commits
- changing class to POD · e1eea81a
  Chao Liu authored Feb 07, 2021
  
  e1eea81a
- changing class to POD: remove explicit keyword · 43d5e05f
  Chao Liu authored Feb 07, 2021
  
  43d5e05f
- changing class to POD · e00de11e
  Chao Liu authored Feb 07, 2021
  
  e00de11e
03 Feb, 2021 1 commit
- adding n-D RunWrite for threadwise copy v3 · f16356d4
  Chao Liu authored Feb 02, 2021
  
  f16356d4
01 Feb, 2021 1 commit
- N-D copy for threadwise copy v3 · 1e347018
  Chao Liu authored Jan 31, 2021
  
  1e347018