a724f1ebb7
Add ring simple chunk size tuning ( #1180 )
...
* Add ring simple chunk size tuning
* modifying the tuning table to improve the performance of broadcast for 8MB to 32MB for single-node MI300X after ring simple chunk size tuning
* modifying the tuning table to improve the performance of reduce for 1MB to 4MB for single-node MI300X after ring simple chunk size tuning
---------
Co-authored-by: PedramAlizadeh <pmohamma@amd.com >
[ROCm/rccl commit: 73221b4230
2024-05-29 07:59:47 -07:00
73221b4230
Add ring simple chunk size tuning ( #1180 )
...
* Add ring simple chunk size tuning
* modifying the tuning table to improve the performance of broadcast for 8MB to 32MB for single-node MI300X after ring simple chunk size tuning
* modifying the tuning table to improve the performance of reduce for 1MB to 4MB for single-node MI300X after ring simple chunk size tuning
---------
Co-authored-by: PedramAlizadeh <pmohamma@amd.com >
2024-05-29 07:59:47 -07:00
d1a5031722
adding keyword scan ( #874 )
...
* adding keyword scan
* update
* update
* update
* checking on fix
* check
* check
* check
* check
* update
[ROCm/rocprofiler-sdk commit: ba14e748ca
2024-05-29 09:41:59 -05:00
ba14e748ca
adding keyword scan ( #874 )
...
* adding keyword scan
* update
* update
* update
* checking on fix
* check
* check
* check
* check
* update
2024-05-29 09:41:59 -05:00
b1cd519cc9
SWDEV-462635 - 256 byte image memory alignment
...
Change-Id: I1d21368ff460477d3238d71e4e2a0a7d6b9167ac
[ROCm/clr commit: 80011685b2
2024-05-29 10:37:27 -04:00
80011685b2
SWDEV-462635 - 256 byte image memory alignment
...
Change-Id: I1d21368ff460477d3238d71e4e2a0a7d6b9167ac
2024-05-29 10:37:27 -04:00
c160884b44
Moving ATT to amd_detail ( #885 )
...
* Moving ATT to amd_detail
* Formatting
[ROCm/rocprofiler-sdk commit: 385980e279
2024-05-29 11:28:01 -03:00
385980e279
Moving ATT to amd_detail ( #885 )
...
* Moving ATT to amd_detail
* Formatting
2024-05-29 11:28:01 -03:00
76107fa745
Adjust cmake target to work with different build tools
...
This change allows to build smaples repo with different build tools like ninja
Signed-off-by: Sebastian Luzynski <Sebastian.Luzynski@amd.com >
Change-Id: I232efc3f19895e84b9de0d410ea43ec55b913ab4
[ROCm/hip-tests commit: 65512f5872
2024-05-29 10:26:20 -04:00
65512f5872
Adjust cmake target to work with different build tools
...
This change allows to build smaples repo with different build tools like ninja
Signed-off-by: Sebastian Luzynski <Sebastian.Luzynski@amd.com >
Change-Id: I232efc3f19895e84b9de0d410ea43ec55b913ab4
2024-05-29 10:26:20 -04:00
86af9da51e
Update RTD config to Python 3.10 and latest rocm-docs-core ( #357 )
...
[ROCm/rocdecode commit: 188f7de64f
2024-05-29 09:08:16 -04:00
188f7de64f
Update RTD config to Python 3.10 and latest rocm-docs-core ( #357 )
2024-05-29 09:08:16 -04:00
4bde9b2152
Updates to compilation without HSA PC sampling support ( #887 )
...
- move ROCPROFILER_SDK_HSA_PC_SAMPLING define from lib/rocprofiler-sdk/hsa/hsa.hpp to lib/rocprofiler-sdk/pc_sampling/defines.hpp
- Update lib/rocprofiler-sdk/pc_sampling/CMakeLists.txt to return if HSA version is < 1.14.0
- update various includes for "lib/rocprofiler-sdk/pc_sampling/defines.hpp"
[ROCm/rocprofiler-sdk commit: fbf0b49e22
2024-05-29 13:40:26 +02:00
fbf0b49e22
Updates to compilation without HSA PC sampling support ( #887 )
...
- move ROCPROFILER_SDK_HSA_PC_SAMPLING define from lib/rocprofiler-sdk/hsa/hsa.hpp to lib/rocprofiler-sdk/pc_sampling/defines.hpp
- Update lib/rocprofiler-sdk/pc_sampling/CMakeLists.txt to return if HSA version is < 1.14.0
- update various includes for "lib/rocprofiler-sdk/pc_sampling/defines.hpp"
2024-05-29 13:40:26 +02:00
86b6063aad
PC Sampling - blit kernels handling ( #878 )
...
* correlation id 0 for blit kernels' samples
* rocprofiler_pc_sampling_snapshot_v1_t docs update (for future use)
* ROCPROFILER_CORRELATION_ID_VALUE_NONE introduced
* Simplifying ROCPROFILER_CORRELATION_ID_VALUE_NONE
* Apply suggestions from code review
Co-authored-by: Vladimir Indic <139573562+vlaindic@users.noreply.github.com >
---------
Co-authored-by: Jonathan R. Madsen <jrmadsen@users.noreply.github.com >
[ROCm/rocprofiler-sdk commit: c45bf712d1
2024-05-29 12:55:47 +02:00
c45bf712d1
PC Sampling - blit kernels handling ( #878 )
...
* correlation id 0 for blit kernels' samples
* rocprofiler_pc_sampling_snapshot_v1_t docs update (for future use)
* ROCPROFILER_CORRELATION_ID_VALUE_NONE introduced
* Simplifying ROCPROFILER_CORRELATION_ID_VALUE_NONE
* Apply suggestions from code review
Co-authored-by: Vladimir Indic <139573562+vlaindic@users.noreply.github.com >
---------
Co-authored-by: Jonathan R. Madsen <jrmadsen@users.noreply.github.com >
2024-05-29 12:55:47 +02:00
e1261f20d8
Adding python script for rocprofv3 ( #849 )
...
* Adding python script for rocprofv3
* script update
* updating script
* Fixing script for counter collection tests
* Fixing Sanitizer issues
* Adding YAML input file support
* Fixing counter validation tests
* script modifications
* Adding missing LD_PRELOAD
* doc updates
* Adding test for yaml input
* updated yaml extension support in doc
* backward compatibility
* updating scripts
* Fixing git history rocprofv3- part1
* Fixing git history rocprofv3- part2
* Fixing rocprofv3 history final
* Rebasing PR 860 for json support
* Review comments: Parser updates
* Removed color encoding and rebasing again
* Addressing review comments
* removing globals
* Update rocprofv3.py
- update tests to conform to new argparse requirements
- added support for JSON
* Slight tweak to update_env for ROCP_OUTPUT_FORMAT
* Update rocprofv3.py
- Handle ROCPROF_PRELOAD
- Add --preload option
- Add --kernel-names option
* Update rocprofv3.py
- Fix update_env handling of prepend/append
- Tweak --preload argument
---------
Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com >
[ROCm/rocprofiler-sdk commit: dc054eea76
2024-05-29 05:05:10 -05:00
dc054eea76
Adding python script for rocprofv3 ( #849 )
...
* Adding python script for rocprofv3
* script update
* updating script
* Fixing script for counter collection tests
* Fixing Sanitizer issues
* Adding YAML input file support
* Fixing counter validation tests
* script modifications
* Adding missing LD_PRELOAD
* doc updates
* Adding test for yaml input
* updated yaml extension support in doc
* backward compatibility
* updating scripts
* Fixing git history rocprofv3- part1
* Fixing git history rocprofv3- part2
* Fixing rocprofv3 history final
* Rebasing PR 860 for json support
* Review comments: Parser updates
* Removed color encoding and rebasing again
* Addressing review comments
* removing globals
* Update rocprofv3.py
- update tests to conform to new argparse requirements
- added support for JSON
* Slight tweak to update_env for ROCP_OUTPUT_FORMAT
* Update rocprofv3.py
- Handle ROCPROF_PRELOAD
- Add --preload option
- Add --kernel-names option
* Update rocprofv3.py
- Fix update_env handling of prepend/append
- Tweak --preload argument
---------
Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com >
2024-05-29 05:05:10 -05:00
e94fb36b0b
Bump version to 0.4.0 for AFAR release ( #879 )
...
[ROCm/rocprofiler-sdk commit: 69c381246f
2024-05-29 03:38:38 -05:00
69c381246f
Bump version to 0.4.0 for AFAR release ( #879 )
2024-05-29 03:38:38 -05:00
92a9ba163e
SWDEV-394940 Enabling basic testcases with HIPRTC apis for supported compiler options & also with combination of compiler options
...
Change-Id: If762335c9258fa6b0a49d53c54c0508fb7987056
[ROCm/hip-tests commit: 72f2f3187b
2024-05-29 02:44:17 -04:00
72f2f3187b
SWDEV-394940 Enabling basic testcases with HIPRTC apis for supported compiler options & also with combination of compiler options
...
Change-Id: If762335c9258fa6b0a49d53c54c0508fb7987056
2024-05-29 02:44:17 -04:00
48374bf453
Fixes multiple issues with tool
...
Change-Id: Ib465caa9029edc737df2c419d2ef763ec24165e1
2024-05-29 01:30:09 -04:00
8f765d2a1e
Fixes multiple issues with tool
...
Change-Id: Ib465caa9029edc737df2c419d2ef763ec24165e1
[ROCm/rocprofiler commit: 48374bf453
2024-05-29 01:30:09 -04:00
b8726a6225
Adding JSON & Major fixes
...
Adding Chrome Tracing JSON for V2
Some fixes for the Kernel Dispatch tracing
Changes related to the HIP Runtime Destruction fix
Change-Id: I2fe1f1ef66b415df17c503a4a9fadcfa107d8c49
2024-05-29 01:21:52 -04:00
d0dfb4f3e2
Adding JSON & Major fixes
...
Adding Chrome Tracing JSON for V2
Some fixes for the Kernel Dispatch tracing
Changes related to the HIP Runtime Destruction fix
Change-Id: I2fe1f1ef66b415df17c503a4a9fadcfa107d8c49
[ROCm/rocprofiler commit: b8726a6225
2024-05-29 01:21:52 -04:00
6dad9b159c
Removing code object static library ( #865 )
...
* Removing static library build for codeobj library
* Moving codeobj library to amd_detail
* Formatting
* Formatting
* Adding findDW
* Adding libdw to common samples cmake
[ROCm/rocprofiler-sdk commit: a84c9fa7d4
2024-05-28 23:15:11 -03:00
a84c9fa7d4
Removing code object static library ( #865 )
...
* Removing static library build for codeobj library
* Moving codeobj library to amd_detail
* Formatting
* Formatting
* Adding findDW
* Adding libdw to common samples cmake
2024-05-28 23:15:11 -03:00
176d812103
(IMPORTANT: AFAR V ) Hide PC sampling if HSA does not support it. ( #881 )
...
* Hide PC sampling if HSA does not support it.
* missing hsa.hpp include
[ROCm/rocprofiler-sdk commit: 7201aa321e
2024-05-29 03:02:14 +02:00
7201aa321e
(IMPORTANT: AFAR V ) Hide PC sampling if HSA does not support it. ( #881 )
...
* Hide PC sampling if HSA does not support it.
* missing hsa.hpp include
2024-05-29 03:02:14 +02:00
ae6c372406
Make WSL detection thread safe ( #1178 )
...
* Make WSL detection thread safe
* Change static to beginning
* Switch to use atomics
[ROCm/rccl commit: 8f099b1adb
2024-05-28 17:23:50 -07:00
8f099b1adb
Make WSL detection thread safe ( #1178 )
...
* Make WSL detection thread safe
* Change static to beginning
* Switch to use atomics
2024-05-28 17:23:50 -07:00
f0e8d11ed0
Build fixes for clang-18 ( #880 )
...
Fixes unnecessary inline and ambiguous conditional return.
[ROCm/rocprofiler-sdk commit: 00f31e593c
2024-05-28 17:01:50 -07:00
00f31e593c
Build fixes for clang-18 ( #880 )
...
Fixes unnecessary inline and ambiguous conditional return.
2024-05-28 17:01:50 -07:00
ff977139eb
Added static construct to topology ( #868 )
...
* Added static construct to topology
[ROCm/rocprofiler-sdk commit: 705a791553
2024-05-28 15:06:54 -07:00
705a791553
Added static construct to topology ( #868 )
...
* Added static construct to topology
2024-05-28 15:06:54 -07:00
dd374ea0ef
remove use of distutils package entirely to avoid future deprecation
...
issues
Signed-off-by: Karl W. Schulz <karl.schulz@amd.com >
[ROCm/rocprofiler-compute commit: 7a01f499d7
2024-05-28 15:34:00 -05:00
7a01f499d7
remove use of distutils package entirely to avoid future deprecation
...
issues
Signed-off-by: Karl W. Schulz <karl.schulz@amd.com >
2024-05-28 15:34:00 -05:00
7288bf34f4
updated approach for runtime dependency check that does use "pkg_resources"
...
which will reportedly be deprecated at some point in the future.
Signed-off-by: Karl W. Schulz <karl.schulz@amd.com >
[ROCm/rocprofiler-compute commit: aca084f41c
2024-05-28 15:34:00 -05:00
aca084f41c
updated approach for runtime dependency check that does use "pkg_resources"
...
which will reportedly be deprecated at some point in the future.
Signed-off-by: Karl W. Schulz <karl.schulz@amd.com >
2024-05-28 15:34:00 -05:00
782ea3099b
Wrap text displayed in 'Top Dispatch' table for neatness
...
Signed-off-by: coleramos425 <colramos@amd.com >
[ROCm/rocprofiler-compute commit: c6cfa9cc26
2024-05-28 15:34:00 -05:00
c6cfa9cc26
Wrap text displayed in 'Top Dispatch' table for neatness
...
Signed-off-by: coleramos425 <colramos@amd.com >
2024-05-28 15:34:00 -05:00
8bd72673e8
Add fix for case where we pass a single 'nan' value to to_avg
...
This is triggered by doing e.g., analyze -p <whatever> -k <kernel> -n per_kernel -b 17 18
Manifests as e.g.:
```
ERROR [analysis] 'float' object has no attribute 'empty'
```
because of:
https://github.com/ROCm/omniperf/blob/f3a0360a5640e4539fac534f73876f51ddd268d0/src/utils/parser.py#L135
Instead, we first check whether numpy thinks the whole array is nan's, and bail early if so
Signed-off-by: Nicholas Curtis <nicurtis@amd.com >
[ROCm/rocprofiler-compute commit: 047d7771f3
2024-05-28 15:34:00 -05:00
047d7771f3
Add fix for case where we pass a single 'nan' value to to_avg
...
This is triggered by doing e.g., analyze -p <whatever> -k <kernel> -n per_kernel -b 17 18
Manifests as e.g.:
```
ERROR [analysis] 'float' object has no attribute 'empty'
```
because of:
https://github.com/ROCm/omniperf/blob/d1ee2ec8709b21f2e72536cc14dba8ac2f8621ab/src/utils/parser.py#L135
Instead, we first check whether numpy thinks the whole array is nan's, and bail early if so
Signed-off-by: Nicholas Curtis <nicurtis@amd.com >
2024-05-28 15:34:00 -05:00
f7da503e6f
handle unspecified case
...
Signed-off-by: Nicholas Curtis <nicurtis@amd.com >
[ROCm/rocprofiler-compute commit: 1f584c1612
2024-05-28 15:34:00 -05:00
1f584c1612
handle unspecified case
...
Signed-off-by: Nicholas Curtis <nicurtis@amd.com >
2024-05-28 15:34:00 -05:00
562e36a5c3
fix formatting
...
Signed-off-by: Nick Curtis <nicholas.curtis@amd.com >
[ROCm/rocprofiler-compute commit: 5579beeed5
2024-05-28 15:34:00 -05:00
5579beeed5
fix formatting
...
Signed-off-by: Nick Curtis <nicholas.curtis@amd.com >
2024-05-28 15:34:00 -05:00
fbb384bd2f
Add ability to overide arch when name missing in rocminfo
...
Signed-off-by: Nick Curtis <nicholas.curtis@amd.com >
[ROCm/rocprofiler-compute commit: 989dd3b7ae
2024-05-28 15:34:00 -05:00
989dd3b7ae
Add ability to overide arch when name missing in rocminfo
...
Signed-off-by: Nick Curtis <nicholas.curtis@amd.com >
2024-05-28 15:34:00 -05:00
Wenkai Du
Kiran Thumma
Alex Xie
Giovanni Lenzi Baraldi
Sebastian Luzynski
Sam Wu
Jonathan R. Madsen
Vladimir Indic
Gopesh Bhardwaj
poojajs
Ammar ELWazir
Benjamin Welton
Karl W. Schulz
coleramos425
Nicholas Curtis
Nick Curtis