Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Implement Cumulative reduction (max, min, sum, prod) forward with small last dim #3182

Open
wants to merge 52 commits into
base: develop
Choose a base branch
from
+2,337 −2
Open

Implement Cumulative reduction (max, min, sum, prod) forward with small last dim #3182

Show file tree
Hide file tree
Changes from 38 commits
Commits
Show all changes
52 commits
Select commit Hold shift + click to select a range
af02031
impl cumulative reduction forward (without GTest and Driver)
long10024070 Jun 19, 2024
b290533
impl CumMax, CumMin
long10024070 Jun 28, 2024
702ffd5
impl cumulative reduction forward with GTest
long10024070 Jul 3, 2024
822b133
update doxygen
long10024070 Jul 7, 2024
c197d6d
added error check in problem_description
long10024070 Jul 7, 2024
895d0ba
fixed bug and added Driver
long10024070 Jul 9, 2024
ec0c441
added improvement over ROCM constraint and removed unused code
long10024070 Jul 10, 2024
15c27cf
removed unused lines of code
long10024070 Jul 10, 2024
d431f14
used dynamic Local_size
long10024070 Jul 11, 2024
6b4c5bd
update doxygen comments
long10024070 Jul 11, 2024
b4331ac
changed Tensor Length input format
long10024070 Jul 11, 2024
005af5b
updated test invoke condition
long10024070 Jul 12, 2024
409ca2d
reduce number of GTest testcases
long10024070 Jul 12, 2024
b7c9f2f
fixed for make analyze
long10024070 Jul 15, 2024
2c6e4b1
remove unused constraint
long10024070 Jul 15, 2024
b4050b4
removed GetWorkspaceSize
long10024070 Jul 15, 2024
e4dcc47
added working dim value check in ProblemDescription
long10024070 Jul 15, 2024
fa89c6d
Compile error fixed: packed MIOPEN_THROW message into a string
long10024070 Jul 15, 2024
bd9ba30
bug fixed: checking output or indices tensor is empty or unused in Is…
long10024070 Jul 15, 2024
ac39e2e
more detail in the api descriptor
long10024070 Jul 15, 2024
6dfe5cb
updated network config and added IsAllDimStride1 check
long10024070 Jul 15, 2024
cd62a72
removed excessive assert statement
long10024070 Jul 15, 2024
0e6159f
added more detail to NetworkConfig
long10024070 Jul 17, 2024
b70e17d
fixed: IsAllPacked return false instead of Throw as this is a filter …
long10024070 Jul 19, 2024
51b82cc
packed problem decription checks
long10024070 Jul 19, 2024
c7ad580
removed excessive log
long10024070 Jul 19, 2024
27d66aa
removed excessive log
long10024070 Jul 19, 2024
49b83eb
Merge branch 'develop' into impl_cumulative_reduction_improvedOverROCM
long10024070 Jul 24, 2024
dfd5b31
debug: ndims from auto into int, and reduce number of testcase in GTest
long10024070 Jul 24, 2024
3cca721
Merge remote-tracking branch 'rocm/develop' into impl_cumulative_redu…
long10024070 Jul 24, 2024
7f53a94
format code
long10024070 Jul 24, 2024
634224b
add MIOPEN_INTERNALS_EXPORT
long10024070 Jul 24, 2024
93c57ec
undo unnecessary changed when merging with rocm/MIOpen
long10024070 Jul 24, 2024
6f591c3
undo unnecessary changed when merging with rocm/MIOpen
long10024070 Jul 24, 2024
2ac8e11
Merge remote-tracking branch 'rocm/develop' into impl_cumulative_redu…
long10024070 Aug 6, 2024
c9ebf28
Merge remote-tracking branch 'rocm/develop' into impl_cumulative_redu…
long10024070 Aug 6, 2024
68035ff
update GTest code structure
long10024070 Aug 6, 2024
4fb6c3c
using warpSize from context
long10024070 Aug 6, 2024
47610b6
Merge remote-tracking branch 'rocm/develop' into impl_cumulative_redu…
long10024070 Aug 26, 2024
e9f00f6
Merge branch 'develop' into impl_cumulative_reduction_improvedOverROCM
long10024070 Aug 26, 2024
af0f320
updated cumulative_reduction driver code
long10024070 Aug 27, 2024
215d13a
Merge remote-tracking branch 'rocm/impl_cumulative_reduction_improved…
long10024070 Aug 27, 2024
3b940c2
updated: use CRTP instead of virtual functions
long10024070 Aug 27, 2024
b866eaa
Added more comments
long10024070 Aug 30, 2024
0feeb17
Merge branch 'develop' into impl_cumulative_reduction_improvedOverROCM
long10024070 Sep 23, 2024
71a0008
Merge branch 'develop' into impl_cumulative_reduction_improvedOverROCM
long10024070 Sep 24, 2024
81ee6b1
Merge branch 'develop' into impl_cumulative_reduction_improvedOverROCM
long10024070 Sep 26, 2024
b3fc0ea
Fixed: undefined AlignUp
long10024070 Sep 26, 2024
59445dd
Merge remote-tracking branch 'rocm/impl_cumulative_reduction_improved…
long10024070 Sep 26, 2024
c7b3675
Merge branch 'develop' into impl_cumulative_reduction_improvedOverROCM
long10024070 Sep 27, 2024
8f353b3
Merge branch 'develop' into impl_cumulative_reduction_improvedOverROCM
long10024070 Sep 29, 2024
e8e8dfa
Merge remote-tracking branch 'rocm/impl_cumulative_reduction_improved…
long10024070 Sep 29, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions docs/reference/index.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -35,3 +35,4 @@ The MIOpen API library is structured as follows:
* :doc:`ReduceExtreme <../doxygen/html/group__ReduceExtreme>` (experimental)
* :doc:`Getitem <../doxygen/html/group__getitem>` (experimental)
* :doc:`ReduceCalculation <../doxygen/html/group__ReduceCalculation>` (experimental)
* :doc:`Cumulative Reduction <./group___cumulative_reduction>` (experimental)
1 change: 1 addition & 0 deletions driver/CMakeLists.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -40,6 +40,7 @@ add_executable(MIOpenDriver
dm_convfp16.cpp
dm_convfp8.cpp
dm_convint8.cpp
dm_cumulative_reduction.cpp
dm_dropout.cpp
dm_fusion.cpp
dm_gemm.cpp
Expand Down
Loading