Граф коммитов
64512 Коммитов
Автор SHA1 Сообщение Дата
Jatin Chaudhary a9f5e0bd3d Add missing tests for hipHostMalloc (#2566)
[ROCm/hip-tests commit: 8b291f071a]
2022-06-10 21:16:23 +05:30
Jatin Chaudhary 8b291f071a Add missing tests for hipHostMalloc (#2566) 2022-06-10 21:16:23 +05:30
Jatin Chaudhary 781c99d9a9 Add missing tests for hipHostMalloc (#2566)
[ROCm/hip commit: fbdda38cf7]
2022-06-10 21:16:23 +05:30
Jatin Chaudhary fbdda38cf7 Add missing tests for hipHostMalloc (#2566) 2022-06-10 21:16:23 +05:30
Jonathan R. Madsen 04edcf33c3 Implements --label option for python profiler (#34)
* Implements --label option for python profiler

- removes '-a', '-f', and '-l' options in favor of '--label args file line' for consistency with omnitrace exe

* cmake formatting

* Bump version to 1.1.0

[ROCm/rocprofiler-systems commit: 017e794d63]
2022-06-10 10:07:15 -05:00
Jonathan R. Madsen 017e794d63 Implements --label option for python profiler (#34)
* Implements --label option for python profiler

- removes '-a', '-f', and '-l' options in favor of '--label args file line' for consistency with omnitrace exe

* cmake formatting

* Bump version to 1.1.0
2022-06-10 10:07:15 -05:00
Jonathan R. Madsen ac25b485e7 Fix sampling counter time scales (#33)
* Fix sampling counter time scales

- All perfetto trace events have "begin_ns" and "end_ns" debug fields
- data for thread start and end timestamp in pthread_create_gotcha
- discard samples outside of thread start and end timestamps
- rename "CPU User CPU Time" perfetto counter to "CPU User Time"
- rename "CPU Kernel CPU Time" perfetto counter to "CPU Kernel Time"
- ensure CPU system samples in perfetto are set to zero at end
- backtrace uses comp::wall_clock record() for timestamps (consistency)
- "Peak Memory Usage [Thread X] (S)" renamed to "Thread Peak Memory Usage [X] (S)"
- "Context Switches [Thread X] (S)" renamed to "Thread Context Switches Usage [X] (S)"
- "Page Faults [Thread X] (S)" renamed to "Thread Page Faults Usage [X] (S)"
- "<PAPI_DESC> [Thread X] (S)" renamed to "Thread <PAPI_DESC> [X] (S)"
- samples

* Fix includes

[ROCm/rocprofiler-systems commit: 90ab7a89fc]
2022-06-10 08:35:39 -05:00
Jonathan R. Madsen 90ab7a89fc Fix sampling counter time scales (#33)
* Fix sampling counter time scales

- All perfetto trace events have "begin_ns" and "end_ns" debug fields
- data for thread start and end timestamp in pthread_create_gotcha
- discard samples outside of thread start and end timestamps
- rename "CPU User CPU Time" perfetto counter to "CPU User Time"
- rename "CPU Kernel CPU Time" perfetto counter to "CPU Kernel Time"
- ensure CPU system samples in perfetto are set to zero at end
- backtrace uses comp::wall_clock record() for timestamps (consistency)
- "Peak Memory Usage [Thread X] (S)" renamed to "Thread Peak Memory Usage [X] (S)"
- "Context Switches [Thread X] (S)" renamed to "Thread Context Switches Usage [X] (S)"
- "Page Faults [Thread X] (S)" renamed to "Thread Page Faults Usage [X] (S)"
- "<PAPI_DESC> [Thread X] (S)" renamed to "Thread <PAPI_DESC> [X] (S)"
- samples

* Fix includes
2022-06-10 08:35:39 -05:00
Jonathan R. Madsen 2eb4b4981c Fix loop-level instrumentation + more (#32)
- fix loop-level instrumentation
- support loop instrumentation w/o debug symbols via loop number
- improve module_function messages
- serialize num_basic_blocks
- serialize num_outer_loops
- serialize is_num_instructions_constrained
- serialize is_loop_num_instructions_constrained
- updated transpose example to use uniform_int_distribution
- added transpose loop test
- added fail regexes for tests which enable loop instrumentation
- use module->getFullName in get_loop_file_line_info
- use module->getFullName in get_func_file_line_info
- use module->getFullName in get_basic_block_file_line_info

[ROCm/rocprofiler-systems commit: a640fbdb29]
2022-06-10 06:57:50 -05:00
Jonathan R. Madsen a640fbdb29 Fix loop-level instrumentation + more (#32)
- fix loop-level instrumentation
- support loop instrumentation w/o debug symbols via loop number
- improve module_function messages
- serialize num_basic_blocks
- serialize num_outer_loops
- serialize is_num_instructions_constrained
- serialize is_loop_num_instructions_constrained
- updated transpose example to use uniform_int_distribution
- added transpose loop test
- added fail regexes for tests which enable loop instrumentation
- use module->getFullName in get_loop_file_line_info
- use module->getFullName in get_func_file_line_info
- use module->getFullName in get_basic_block_file_line_info
2022-06-10 06:57:50 -05:00
Jenkins b8f111330a SWDEV-299127 - Merge 'develop' into 'amd-staging'
Change-Id: I9b17091d0113e2cceedec0c12390578b062ee55b


[ROCm/hip commit: 1dfaa6d463]
2022-06-10 07:10:43 -04:00
Jenkins 1dfaa6d463 SWDEV-299127 - Merge 'develop' into 'amd-staging'
Change-Id: I9b17091d0113e2cceedec0c12390578b062ee55b
2022-06-10 07:10:43 -04:00
Maneesh Gupta c52fae6f49 Update config_amd_windows.json
[ROCm/hip-tests commit: efcb5ad910]
2022-06-10 12:17:49 +05:30
Maneesh Gupta efcb5ad910 Update config_amd_windows.json 2022-06-10 12:17:49 +05:30
Maneesh Gupta 584e951a7a Update config_amd_windows.json
[ROCm/hip commit: 08b7053a37]
2022-06-10 12:17:49 +05:30
Maneesh Gupta 08b7053a37 Update config_amd_windows.json 2022-06-10 12:17:49 +05:30
Maneesh Gupta dcaed0054c Update config_amd_windows.json
Disable Unit_hiprtc_functional on windows

[ROCm/hip-tests commit: 8ae2844848]
2022-06-10 10:28:37 +05:30
Maneesh Gupta 8ae2844848 Update config_amd_windows.json
Disable Unit_hiprtc_functional on windows
2022-06-10 10:28:37 +05:30
Maneesh Gupta 422c422521 Update config_amd_windows.json
Disable Unit_hiprtc_functional on windows

[ROCm/hip commit: ad988ac01a]
2022-06-10 10:28:37 +05:30
Maneesh Gupta ad988ac01a Update config_amd_windows.json
Disable Unit_hiprtc_functional on windows
2022-06-10 10:28:37 +05:30
Hao Zhou 99f1744adc Merge amd-staging into amd-master 20220610
Signed-off-by: Hao Zhou <Hao.Zhou@amd.com>
Change-Id: Iaefd0a9180925d91d2e3ec03be84e5b04cf262b6


[ROCm/rocm_smi_lib commit: 90571416c1]
2022-06-10 09:08:16 +08:00
Hao Zhou 90571416c1 Merge amd-staging into amd-master 20220610
Signed-off-by: Hao Zhou <Hao.Zhou@amd.com>
Change-Id: Iaefd0a9180925d91d2e3ec03be84e5b04cf262b6
2022-06-10 09:08:16 +08:00
Ajay 70189c7e2e SWDEV-327563 - support hipStreamWrite32/64 and hipStreamWait32/64 funcs
Windows complains about undefined symbol for
hipStreamWrite32/64 and hipStreamWait32/64 -
commit hash 08435a972b

Change-Id: I48b9a6591cab3a05baaedbc26030914dd930fb68


[ROCm/clr commit: de026633c0]
2022-06-09 20:59:46 -04:00
Ajay de026633c0 SWDEV-327563 - support hipStreamWrite32/64 and hipStreamWait32/64 funcs
Windows complains about undefined symbol for
hipStreamWrite32/64 and hipStreamWait32/64 -
commit hash 08435a972b

Change-Id: I48b9a6591cab3a05baaedbc26030914dd930fb68
2022-06-09 20:59:46 -04:00
Laurent Morichetti c3e991dfb1 Remove EvtStats from the tracer_tool
The same information can be generated from the hcc_ops_trace.txt file,
so in a later commit, will add a stage to the tblextr.py script to
generate the .csv files when ROCP_STATS_OPT=1.

Change-Id: I3d1575e096bedf98c66068d9a4ca141421e5bb9d


[ROCm/roctracer commit: 836bab37d3]
2022-06-09 15:20:14 -07:00
Laurent Morichetti 836bab37d3 Remove EvtStats from the tracer_tool
The same information can be generated from the hcc_ops_trace.txt file,
so in a later commit, will add a stage to the tblextr.py script to
generate the .csv files when ROCP_STATS_OPT=1.

Change-Id: I3d1575e096bedf98c66068d9a4ca141421e5bb9d
2022-06-09 15:20:14 -07:00
Jonathan R. Madsen 5c1e6ea127 Rework sampling trace counter names + new trace counters (#30)
* Rework sampling trace counter names + new trace counters

- reformulate trace counter names for easier comparison (thread sampling)
- new process-level trace counters for context switches (thread sampling)
- new process-level trace counters for page faults (thread sampling)
- new process-level trace counters for CPU time (thread sampling)
- new thread-level trace counters for context switches (sampling)
- new thread-level trace counters for page faults (sampling)

* tweak header include in backtrace.cpp

[ROCm/rocprofiler-systems commit: 1db3934f85]
2022-06-09 13:43:07 -05:00
Jonathan R. Madsen 1db3934f85 Rework sampling trace counter names + new trace counters (#30)
* Rework sampling trace counter names + new trace counters

- reformulate trace counter names for easier comparison (thread sampling)
- new process-level trace counters for context switches (thread sampling)
- new process-level trace counters for page faults (thread sampling)
- new process-level trace counters for CPU time (thread sampling)
- new thread-level trace counters for context switches (sampling)
- new thread-level trace counters for page faults (sampling)

* tweak header include in backtrace.cpp
2022-06-09 13:43:07 -05:00
Ajay 65d3357dbc SWDEV-337331 - graph feature on Windows
Fixes for hipGraphInstantiate OutofMemory issue and
soft hang of hipStreamSynchronize.
Change-Id: Ic2bb97582c5978ef2e4eb3a1b124483aa412838e


[ROCm/clr commit: c06bfa6bef]
2022-06-09 12:04:51 -04:00
Ajay c06bfa6bef SWDEV-337331 - graph feature on Windows
Fixes for hipGraphInstantiate OutofMemory issue and
soft hang of hipStreamSynchronize.
Change-Id: Ic2bb97582c5978ef2e4eb3a1b124483aa412838e
2022-06-09 12:04:51 -04:00
sdashmiz b0d323fe42 SWDEV-318833 - Get and Set attribute for kernel nodes
Signed-off-by: sdashmiz <shadi.dashmiz@amd.com>
Change-Id: Ie51aa4b56661cbb8c5b4eb1dbaad327377084ffb
Signed-off-by: sdashmiz <shadi.dashmiz@amd.com>


[ROCm/hipother commit: f874762659]
2022-06-09 09:47:05 -04:00
sdashmiz f874762659 SWDEV-318833 - Get and Set attribute for kernel nodes
Signed-off-by: sdashmiz <shadi.dashmiz@amd.com>
Change-Id: Ie51aa4b56661cbb8c5b4eb1dbaad327377084ffb
Signed-off-by: sdashmiz <shadi.dashmiz@amd.com>
2022-06-09 09:47:05 -04:00
sdashmiz 3f588bf604 SWDEV-318833 - Get and Set attribute for kernel nodes
Signed-off-by: sdashmiz <shadi.dashmiz@amd.com>
Change-Id: Ie51aa4b56661cbb8c5b4eb1dbaad327377084ffb
Signed-off-by: sdashmiz <shadi.dashmiz@amd.com>


[ROCm/clr commit: efd2d55e9d]
2022-06-09 09:47:05 -04:00
sdashmiz efd2d55e9d SWDEV-318833 - Get and Set attribute for kernel nodes
Signed-off-by: sdashmiz <shadi.dashmiz@amd.com>
Change-Id: Ie51aa4b56661cbb8c5b4eb1dbaad327377084ffb
Signed-off-by: sdashmiz <shadi.dashmiz@amd.com>
2022-06-09 09:47:05 -04:00
Bill(Shuzhou) Liu c8fbb50d8e Remove python pyc file when uninstall rpm
Remove python pyc file when uninstall rpm.

Change-Id: I6520b51aac34060b5b90f94a016cec1827a4973f


[ROCm/rocm_smi_lib commit: 42f11bdd63]
2022-06-09 09:00:38 -04:00
Bill(Shuzhou) Liu 42f11bdd63 Remove python pyc file when uninstall rpm
Remove python pyc file when uninstall rpm.

Change-Id: I6520b51aac34060b5b90f94a016cec1827a4973f
2022-06-09 09:00:38 -04:00
Laurent Morichetti 4af9cdc409 Add a data region to the memory pool
Some records may need to point to data with the same lifetime as the
records themselves. One solution is to store the data at the end of
the memory pool buffer. Records in the buffer grow up, and the data
grows down. When the buffer is flushed both records and data are
recycled.

Change-Id: I278fa84478236bf895f7c2d152d47d4256987392


[ROCm/roctracer commit: ef3b2a8aa8]
2022-06-08 18:34:23 -04:00
Laurent Morichetti ef3b2a8aa8 Add a data region to the memory pool
Some records may need to point to data with the same lifetime as the
records themselves. One solution is to store the data at the end of
the memory pool buffer. Records in the buffer grow up, and the data
grows down. When the buffer is flushed both records and data are
recycled.

Change-Id: I278fa84478236bf895f7c2d152d47d4256987392
2022-06-08 18:34:23 -04:00
Jonathan R. Madsen c6207d2336 Support strict settings option in timemory + expanded config syntax (#31)
Support strict settings option in timemory

- timemory settings updates
  - strict config option
  - improved variable support
    - $env: lvalues
    - support for ${VARIABLE} syntax
    - support for variable expansion in substring
  - chained config files

[ROCm/rocprofiler-systems commit: 3ca81fd8c0]
2022-06-08 16:58:06 -05:00
Jonathan R. Madsen 3ca81fd8c0 Support strict settings option in timemory + expanded config syntax (#31)
Support strict settings option in timemory

- timemory settings updates
  - strict config option
  - improved variable support
    - $env: lvalues
    - support for ${VARIABLE} syntax
    - support for variable expansion in substring
  - chained config files
2022-06-08 16:58:06 -05:00
Ranjith Ramakrishnan 23ac479cbd SWDEV-321112 - Use GNUInstallDirs
Use GNUInstallDirs variables to determine the location of DOCDIR

Change-Id: I12b016bc1fe66afd92478c3a940093a4b35de0dc
2022-06-08 09:05:17 -07:00
Ranjith Ramakrishnan d8f996d16d SWDEV-321112 - Use GNUInstallDirs
Use GNUInstallDirs variables to determine the location of DOCDIR

Change-Id: I12b016bc1fe66afd92478c3a940093a4b35de0dc


[ROCm/rdc commit: 23ac479cbd]
2022-06-08 09:05:17 -07:00
arjun-raj-kuppala 4128667481 Add sleep time after tests are run (#2717)
*Add sleep after tests are run on AMD backend nodes
* Disable Unit_hipPtrGetAttribute_Simple test for now

[ROCm/hip commit: 3cb957d3b7]
2022-06-08 15:07:48 +05:30
arjun-raj-kuppala 3cb957d3b7 Add sleep time after tests are run (#2717)
*Add sleep after tests are run on AMD backend nodes
* Disable Unit_hipPtrGetAttribute_Simple test for now
2022-06-08 15:07:48 +05:30
Aakash Sudhanwa d23814bc40 Revert "SWDEV-335990 - Use GNUInstallDirs"
This reverts commit a5b6de5037.

Reason for revert: <Breaking all the staging builds. this is breaking components which are using find_package(HIP)>

Change-Id: Ic7340fb461a5efdd170a0988731e0885538a11d6


[ROCm/clr commit: 43c650cf48]
2022-06-07 18:18:06 -04:00
Aakash Sudhanwa 43c650cf48 Revert "SWDEV-335990 - Use GNUInstallDirs"
This reverts commit bf4df229c9.

Reason for revert: <Breaking all the staging builds. this is breaking components which are using find_package(HIP)>

Change-Id: Ic7340fb461a5efdd170a0988731e0885538a11d6
2022-06-07 18:18:06 -04:00
David Yat Sin 4ac840269c Add API for available GPU memory
Add support for AMD Agent to return amount of memory available

Change-Id: I5c32e2cebbaa2993b044250aefe434e4cc02d8c2
Signed-off-by: David Yat Sin <david.yatsin@amd.com>
2022-06-07 10:33:18 -04:00
David Yat Sin a3f395eacb Add API for available GPU memory
Add support for AMD Agent to return amount of memory available

Change-Id: I5c32e2cebbaa2993b044250aefe434e4cc02d8c2
Signed-off-by: David Yat Sin <david.yatsin@amd.com>


[ROCm/ROCR-Runtime commit: 4ac840269c]
2022-06-07 10:33:18 -04:00
Satyanvesh Dittakavi 9d8d473134 SWDEV-327030 - Fix incorrect checks to find components in CMake
Change-Id: Ib7b9bd82255af897a0f82bba8049c7d41379ae96


[ROCm/clr commit: 3bdc72d6ca]
2022-06-07 04:41:52 -04:00
Satyanvesh Dittakavi 3bdc72d6ca SWDEV-327030 - Fix incorrect checks to find components in CMake
Change-Id: Ib7b9bd82255af897a0f82bba8049c7d41379ae96
2022-06-07 04:41:52 -04:00