Commit Graph

13501 Commits

Author SHA1 Message Date
Karl W Schulz b8b5409d4f updating version file for RC1
Signed-off-by: Karl W Schulz <karl.schulz@amd.com>


[ROCm/rocprofiler-compute commit: 04c0c8ad46]
2024-03-14 14:46:41 -05:00
Karl W Schulz 04c0c8ad46 updating version file for RC1
Signed-off-by: Karl W Schulz <karl.schulz@amd.com>
2024-03-14 14:46:41 -05:00
David Yat Sin 9d842dd1d8 Fix uninialized variables
Change-Id: Ie5da4547fa764e55162aff287cbb338ed4324093
2024-03-14 15:20:56 -04:00
Karl W Schulz f442662aa2 update analyze_commands tests to demarcate a subset of tests which
should be run serially; needed to avoid file output race conditions in
a common directory

Signed-off-by: Karl W Schulz <karl.schulz@amd.com>


[ROCm/rocprofiler-compute commit: b38dcfd2c9]
2024-03-14 13:39:10 -05:00
Karl W Schulz b38dcfd2c9 update analyze_commands tests to demarcate a subset of tests which
should be run serially; needed to avoid file output race conditions in
a common directory

Signed-off-by: Karl W Schulz <karl.schulz@amd.com>
2024-03-14 13:39:10 -05:00
Nick Curtis c5408fb22b fixup MI300 MFMA rate disagreement between SOL and pipeline (#315)
Signed-off-by: Nicholas Curtis <nicurtis@amd.com>
Co-authored-by: Nicholas Curtis <nicurtis@amd.com>

[ROCm/rocprofiler-compute commit: b610e1c27b]
2024-03-14 10:41:35 -05:00
Nick Curtis b610e1c27b fixup MI300 MFMA rate disagreement between SOL and pipeline (#315)
Signed-off-by: Nicholas Curtis <nicurtis@amd.com>
Co-authored-by: Nicholas Curtis <nicurtis@amd.com>
2024-03-14 10:41:35 -05:00
Jonathan R. Madsen 3712738692 Context Updates (#624)
* Improve error checks related to context create/start/stop/is_valid

* Bump version to 0.2.1

* Track number of kernels associated with correlation id

- add atomic kernel counter variable to context::correlation_id

* Update lib/rocprofiler-sdk/hsa/queue.cpp

- apply the +/- kernel count

[ROCm/rocprofiler-sdk commit: 0fdb21c050]
2024-03-14 04:40:58 -05:00
Jonathan R. Madsen 0fdb21c050 Context Updates (#624)
* Improve error checks related to context create/start/stop/is_valid

* Bump version to 0.2.1

* Track number of kernels associated with correlation id

- add atomic kernel counter variable to context::correlation_id

* Update lib/rocprofiler-sdk/hsa/queue.cpp

- apply the +/- kernel count
2024-03-14 04:40:58 -05:00
Jonathan R. Madsen 72fdb3e8ed Fix tracing context domain logic for operations (#621)
* Fix tracing context domain logic for operations

- logic error: domain enabled (all operations all implicitly enabled) + domain enabled for subset of operations resulted in only explicitly enabled operations being treated as enabled
- domain_context: split single bitset for operations in all domains into array of bitsets for each domain

* Update lib/common/mpl.hpp

- assert_false for static_asserts in if constexpr expressions

* Update lib/rocprofiler-sdk/tests/contexts.cpp

- Tests for validating logic regarding domain and operations for callback and buffer tracing

[ROCm/rocprofiler-sdk commit: 7ab1a8015f]
2024-03-14 01:25:43 -05:00
Jonathan R. Madsen 7ab1a8015f Fix tracing context domain logic for operations (#621)
* Fix tracing context domain logic for operations

- logic error: domain enabled (all operations all implicitly enabled) + domain enabled for subset of operations resulted in only explicitly enabled operations being treated as enabled
- domain_context: split single bitset for operations in all domains into array of bitsets for each domain

* Update lib/common/mpl.hpp

- assert_false for static_asserts in if constexpr expressions

* Update lib/rocprofiler-sdk/tests/contexts.cpp

- Tests for validating logic regarding domain and operations for callback and buffer tracing
2024-03-14 01:25:43 -05:00
guanyu12 ab8ebd4dea Merge amd-staging into amd-master 20240314
Signed-off-by: guanyu12 <guanyu12@amd.com>
Change-Id: I1d79ce09196cf101c2a885fd6be8f1094e8d5f9f
2024-03-14 11:15:44 +08:00
colramos-amd 4be73b88c6 Trying patch for test_device_filter(). HIP_VISABLE_DEVICES should not dictate expected device
Signed-off-by: colramos-amd <colramos@amd.com>


[ROCm/rocprofiler-compute commit: b3d63ea24e]
2024-03-13 16:30:52 -05:00
colramos-amd b3d63ea24e Trying patch for test_device_filter(). HIP_VISABLE_DEVICES should not dictate expected device
Signed-off-by: colramos-amd <colramos@amd.com>
2024-03-13 16:30:52 -05:00
Ammar ELWazir 0f7a5c7033 Temporary move CI to hip staging (#615)
* Update continuous_integration.yml

* Update ostream.hpp

[ROCm/rocprofiler-sdk commit: 2bfce8b86d]
2024-03-13 12:34:29 -05:00
Ammar ELWazir 2bfce8b86d Temporary move CI to hip staging (#615)
* Update continuous_integration.yml

* Update ostream.hpp
2024-03-13 12:34:29 -05:00
JoseSantosAMD ead7537cba Pytest remove kernel verbose (#314)
* Remove kernel-verbose from pytests

Signed-off-by: Jose Santos <josantos@amd.com>

* remove kernel-vebose from profile in cmake

Signed-off-by: Jose Santos <josantos@amd.com>

* update expected csvs for test_block_TCC

Signed-off-by: Jose Santos <josantos@amd.com>

* Remove stubbed binary

Signed-off-by: Jose Santos <josantos@amd.com>

* always clean workload_dir
Signed-off-by: Jose Santos <josantos@amd.com>

---------

Signed-off-by: Jose Santos <josantos@amd.com>

[ROCm/rocprofiler-compute commit: 4a86e39a25]
2024-03-13 11:30:28 -05:00
JoseSantosAMD 4a86e39a25 Pytest remove kernel verbose (#314)
* Remove kernel-verbose from pytests

Signed-off-by: Jose Santos <josantos@amd.com>

* remove kernel-vebose from profile in cmake

Signed-off-by: Jose Santos <josantos@amd.com>

* update expected csvs for test_block_TCC

Signed-off-by: Jose Santos <josantos@amd.com>

* Remove stubbed binary

Signed-off-by: Jose Santos <josantos@amd.com>

* always clean workload_dir
Signed-off-by: Jose Santos <josantos@amd.com>

---------

Signed-off-by: Jose Santos <josantos@amd.com>
2024-03-13 11:30:28 -05:00
Benjamin Welton da708a2651 Use static_object for dimension map (#616)
[ROCm/rocprofiler-sdk commit: a06eef3488]
2024-03-13 09:28:33 -05:00
Benjamin Welton a06eef3488 Use static_object for dimension map (#616) 2024-03-13 09:28:33 -05:00
Xinmudotmoe 0c06bec272 Update doorbell->size to support large default PAGE_SIZE kernels
Change-Id: I6fbe10ae3309f2f935d6782366cedb56dc1438c3
Signed-off-by: Xinmudotmoe <xinmu@xinmu.moe>
Signed-off-by: Kent Russell <kent.russell@amd.com>
2024-03-13 09:18:42 -04:00
Stella Laurenzo 7c10e1e4f5 Link CMAKE_DL_LIBS.
Was failing to link on AlmaLinux8.

Change-Id: Id7df245f1063c2bebd0f07efc352f1b9017eda0e
Signed-off-by: Stella Laurenzo <stellaraccident@gmail.com>
Signed-off-by: Kent Russell <kent.russell@amd.com>
2024-03-13 09:18:03 -04:00
Jonathan R. Madsen 043db3b3a4 Use small_vector for API iterate_args (#597)
* Use small_vector for API iterate_args

- replace dim3 value arguments with rocprofiler_dim3_t
  - dim3 has a non-trivial destructor
- common::mpl::unqualified_type
- common::stringified_argument_array_t<N> alias
- assert_public_data_type_properties()
- common::container::small_vector<T>::at function
- stringize returns small_vector<stringified_argument>
  - stack allocated vector
- remove has_pc_sampling condition (HSA, HIP)
  - this will be handled in queue interception

* Misc tweaks

[ROCm/rocprofiler-sdk commit: 8591ed1c96]
2024-03-13 07:36:55 -05:00
Jonathan R. Madsen 8591ed1c96 Use small_vector for API iterate_args (#597)
* Use small_vector for API iterate_args

- replace dim3 value arguments with rocprofiler_dim3_t
  - dim3 has a non-trivial destructor
- common::mpl::unqualified_type
- common::stringified_argument_array_t<N> alias
- assert_public_data_type_properties()
- common::container::small_vector<T>::at function
- stringize returns small_vector<stringified_argument>
  - stack allocated vector
- remove has_pc_sampling condition (HSA, HIP)
  - this will be handled in queue interception

* Misc tweaks
2024-03-13 07:36:55 -05:00
Benjamin Welton fa90ca8669 Disable test that checks dims (need AQL fake data support) (#612)
* Disable test that checks dims (need AQL fake data support

* source formatting (clang-format v11) (#613)

Co-authored-by: bwelton <1683479+bwelton@users.noreply.github.com>

---------

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: bwelton <1683479+bwelton@users.noreply.github.com>

[ROCm/rocprofiler-sdk commit: 2a262235db]
2024-03-12 23:20:14 -05:00
Benjamin Welton 2a262235db Disable test that checks dims (need AQL fake data support) (#612)
* Disable test that checks dims (need AQL fake data support

* source formatting (clang-format v11) (#613)

Co-authored-by: bwelton <1683479+bwelton@users.noreply.github.com>

---------

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: bwelton <1683479+bwelton@users.noreply.github.com>
2024-03-12 23:20:14 -05:00
colramos-amd 0b4ee818ba Update doc samples for new logging output
Signed-off-by: colramos-amd <colramos@amd.com>


[ROCm/rocprofiler-compute commit: bfef420099]
2024-03-12 20:17:46 -05:00
colramos-amd bfef420099 Update doc samples for new logging output
Signed-off-by: colramos-amd <colramos@amd.com>
2024-03-12 20:17:46 -05:00
colramos-amd b2c4c8a8cc Found a bug in kernel filtering and fixed
Signed-off-by: colramos-amd <colramos@amd.com>


[ROCm/rocprofiler-compute commit: 2acc8e98c1]
2024-03-12 18:21:35 -05:00
colramos-amd 2acc8e98c1 Found a bug in kernel filtering and fixed
Signed-off-by: colramos-amd <colramos@amd.com>
2024-03-12 18:21:35 -05:00
colramos-amd 8cb9e5e959 Update expected pytest value for same workload case
Signed-off-by: colramos-amd <colramos@amd.com>


[ROCm/rocprofiler-compute commit: 945da7d83c]
2024-03-12 16:49:41 -05:00
colramos-amd 945da7d83c Update expected pytest value for same workload case
Signed-off-by: colramos-amd <colramos@amd.com>
2024-03-12 16:49:41 -05:00
colramos-amd 63d52b2e4c Python format
Signed-off-by: colramos-amd <colramos@amd.com>


[ROCm/rocprofiler-compute commit: cac4b1aff5]
2024-03-12 16:47:18 -05:00
colramos-amd cac4b1aff5 Python format
Signed-off-by: colramos-amd <colramos@amd.com>
2024-03-12 16:47:18 -05:00
colramos-amd 1a27707a4d Throw error if user analyzes two of same path (#260, #67)
Signed-off-by: colramos-amd <colramos@amd.com>


[ROCm/rocprofiler-compute commit: fa7c82de75]
2024-03-12 16:46:36 -05:00
colramos-amd fa7c82de75 Throw error if user analyzes two of same path (#260, #67)
Signed-off-by: colramos-amd <colramos@amd.com>
2024-03-12 16:46:36 -05:00
colramos-amd ff7751724b Fix missing argv in console_warning()
Signed-off-by: colramos-amd <colramos@amd.com>


[ROCm/rocprofiler-compute commit: e7cc326d5a]
2024-03-12 16:44:02 -05:00
colramos-amd e7cc326d5a Fix missing argv in console_warning()
Signed-off-by: colramos-amd <colramos@amd.com>
2024-03-12 16:44:02 -05:00
colramos-amd 31b3bff4de Update dashboard globals to reflect new (v2) sysinfo keys
Signed-off-by: colramos-amd <colramos@amd.com>


[ROCm/rocprofiler-compute commit: 17262172a8]
2024-03-12 16:23:12 -05:00
colramos-amd 17262172a8 Update dashboard globals to reflect new (v2) sysinfo keys
Signed-off-by: colramos-amd <colramos@amd.com>
2024-03-12 16:23:12 -05:00
JoseSantosAMD bd4bc51cd4 change stubbed values to hbm bw (#302)
* change stubbed values to hbm bw

Signed-off-by: Jose Santos <josantos@amd.com>

* Reformat

Signed-off-by: Jose Santos <josantos@amd.com>

* Update analysis_webui.py

remove print statements

Signed-off-by: JoseSantosAMD <87447437+JoseSantosAMD@users.noreply.github.com>

* Update src/omniperf_analyze/analysis_webui.py

Co-authored-by: Cole Ramos <colramos@amd.com>
Signed-off-by: JoseSantosAMD <87447437+JoseSantosAMD@users.noreply.github.com>

* Update src/omniperf_analyze/analysis_webui.py

Co-authored-by: Cole Ramos <colramos@amd.com>
Signed-off-by: JoseSantosAMD <87447437+JoseSantosAMD@users.noreply.github.com>

---------

Signed-off-by: Jose Santos <josantos@amd.com>
Signed-off-by: JoseSantosAMD <87447437+JoseSantosAMD@users.noreply.github.com>
Co-authored-by: Cole Ramos <colramos@amd.com>

[ROCm/rocprofiler-compute commit: efb8f131ec]
2024-03-12 16:08:30 -05:00
JoseSantosAMD efb8f131ec change stubbed values to hbm bw (#302)
* change stubbed values to hbm bw

Signed-off-by: Jose Santos <josantos@amd.com>

* Reformat

Signed-off-by: Jose Santos <josantos@amd.com>

* Update analysis_webui.py

remove print statements

Signed-off-by: JoseSantosAMD <87447437+JoseSantosAMD@users.noreply.github.com>

* Update src/omniperf_analyze/analysis_webui.py

Co-authored-by: Cole Ramos <colramos@amd.com>
Signed-off-by: JoseSantosAMD <87447437+JoseSantosAMD@users.noreply.github.com>

* Update src/omniperf_analyze/analysis_webui.py

Co-authored-by: Cole Ramos <colramos@amd.com>
Signed-off-by: JoseSantosAMD <87447437+JoseSantosAMD@users.noreply.github.com>

---------

Signed-off-by: Jose Santos <josantos@amd.com>
Signed-off-by: JoseSantosAMD <87447437+JoseSantosAMD@users.noreply.github.com>
Co-authored-by: Cole Ramos <colramos@amd.com>
2024-03-12 16:08:30 -05:00
JoseSantosAMD 513ba356ae Kernel no overwrite (#303)
* Removing kernel name shortener from profile

-  Kernel name shortener now in analyze
-  db import uses pymongo to import

Signed-off-by: Jose Santos <josantos@amd.com>

* collections now added using pymongo

Signed-off-by: JoseSantosAMD <Jose.Santos@amd.com>

* kernel_name_shortener shortens dataframes and not a workload

-  argparser: --kernel-verbose to connection group
-  analysis_cli, profiler_rocprof_v2: remove kernel_name_shortener, so that it doesnt overwrite workload
-  db_import: demangle kernel_name dfs

Signed-off-by: JoseSantosAMD <Jose.Santos@amd.com>

* fix db name in pymongo command

Signed-off-by: JoseSantosAMD <Jose.Santos@amd.com>

* reformat

Signed-off-by: JoseSantosAMD <Jose.Santos@amd.com>

* fix typo

Signed-off-by: JoseSantosAMD <Jose.Santos@amd.com>

* remove checker for verbose in profiler_base

Signed-off-by: Jose Santos <josantos@amd.com>

* kernel_name_shortener now called in create_df_kerenel_top_stats and
create_df_pmc

Signed-off-by: Jose Santos <josantos@amd.com>

* add kernel_verbose to analysis_webui, remove stubbed values

Signed-off-by: JoseSantosAMD <Jose.Santos@amd.com>

* Update src/utils/kernel_name_shortener.py

keep console_debug

Co-authored-by: Cole Ramos <colramos@amd.com>
Signed-off-by: JoseSantosAMD <87447437+JoseSantosAMD@users.noreply.github.com>

* Update src/utils/kernel_name_shortener.py

Co-authored-by: Cole Ramos <colramos@amd.com>
Signed-off-by: JoseSantosAMD <87447437+JoseSantosAMD@users.noreply.github.com>

---------

Signed-off-by: Jose Santos <josantos@amd.com>
Signed-off-by: JoseSantosAMD <Jose.Santos@amd.com>
Signed-off-by: JoseSantosAMD <87447437+JoseSantosAMD@users.noreply.github.com>
Co-authored-by: Cole Ramos <colramos@amd.com>

[ROCm/rocprofiler-compute commit: 4424f320ad]
2024-03-12 15:54:52 -05:00
JoseSantosAMD 4424f320ad Kernel no overwrite (#303)
* Removing kernel name shortener from profile

-  Kernel name shortener now in analyze
-  db import uses pymongo to import

Signed-off-by: Jose Santos <josantos@amd.com>

* collections now added using pymongo

Signed-off-by: JoseSantosAMD <Jose.Santos@amd.com>

* kernel_name_shortener shortens dataframes and not a workload

-  argparser: --kernel-verbose to connection group
-  analysis_cli, profiler_rocprof_v2: remove kernel_name_shortener, so that it doesnt overwrite workload
-  db_import: demangle kernel_name dfs

Signed-off-by: JoseSantosAMD <Jose.Santos@amd.com>

* fix db name in pymongo command

Signed-off-by: JoseSantosAMD <Jose.Santos@amd.com>

* reformat

Signed-off-by: JoseSantosAMD <Jose.Santos@amd.com>

* fix typo

Signed-off-by: JoseSantosAMD <Jose.Santos@amd.com>

* remove checker for verbose in profiler_base

Signed-off-by: Jose Santos <josantos@amd.com>

* kernel_name_shortener now called in create_df_kerenel_top_stats and
create_df_pmc

Signed-off-by: Jose Santos <josantos@amd.com>

* add kernel_verbose to analysis_webui, remove stubbed values

Signed-off-by: JoseSantosAMD <Jose.Santos@amd.com>

* Update src/utils/kernel_name_shortener.py

keep console_debug

Co-authored-by: Cole Ramos <colramos@amd.com>
Signed-off-by: JoseSantosAMD <87447437+JoseSantosAMD@users.noreply.github.com>

* Update src/utils/kernel_name_shortener.py

Co-authored-by: Cole Ramos <colramos@amd.com>
Signed-off-by: JoseSantosAMD <87447437+JoseSantosAMD@users.noreply.github.com>

---------

Signed-off-by: Jose Santos <josantos@amd.com>
Signed-off-by: JoseSantosAMD <Jose.Santos@amd.com>
Signed-off-by: JoseSantosAMD <87447437+JoseSantosAMD@users.noreply.github.com>
Co-authored-by: Cole Ramos <colramos@amd.com>
2024-03-12 15:54:52 -05:00
Ranjith Ramakrishnan b09eede016 Start rdc.service after installing the rdc package
The starting of rdc.service was done in preinstall scripts. It should be started after installing rdc package.
Moved the functionality to postinstall scripts

Change-Id: I9a8c733beea43f95474b990a35a431db287b9a8e
2024-03-12 13:30:27 -07:00
Jose Santos 5b53f2a28c remove binaries from tests directory
Signed-off-by: Jose Santos <josantos@amd.com>


[ROCm/rocprofiler-compute commit: 43bc78c1dd]
2024-03-12 13:06:11 -05:00
Jose Santos 43bc78c1dd remove binaries from tests directory
Signed-off-by: Jose Santos <josantos@amd.com>
2024-03-12 13:06:11 -05:00
Jose Santos ea4dd893a1 Check for CI_VISIBLE_DEVICES num_devices
-  add vcopy_MI200

Signed-off-by: Jose Santos <josantos@amd.com>


[ROCm/rocprofiler-compute commit: c4bd700a2d]
2024-03-12 13:06:11 -05:00
Jose Santos c4bd700a2d Check for CI_VISIBLE_DEVICES num_devices
-  add vcopy_MI200

Signed-off-by: Jose Santos <josantos@amd.com>
2024-03-12 13:06:11 -05:00
colramos-amd 4fb2f6e2b4 Update DB module for new sysinfo keys
Signed-off-by: colramos-amd <colramos@amd.com>


[ROCm/rocprofiler-compute commit: 706d3bb9f0]
2024-03-12 12:24:49 -05:00