AI/rocm-systems
2
0 Форкнуть 0
Код Задачи Запросы на слияние Действия Пакеты Проекты Релизы Вики Активность
76 333 коммитов 3 Ветки 0 Теги
develop
Граф коммитов
76333 Коммитов
This Branch
This Branch
Все ветки
Автор SHA1 Сообщение Дата
Kiumars Sabeti cec4cb2538 SWDEV-322312: RPM packages are generated while build roctracer for UBUNTU 
replaced -DCPACK_GENERATOR=DEB

Change-Id: I9f6d4d652e7cad510343731948675f0cd4398ef4
 2022-02-11 08:33:17 +00:00
Hao Zhou 0098b0e5d9 Merge amd-staging into amd-master 20220211 
Signed-off-by: Hao Zhou <Hao.Zhou@amd.com>
Change-Id: I95fd0cafb212a3e0f64b58ba6a009a4cd37ae0a6


[ROCm/rocm_smi_lib commit: 19c569146c]
 2022-02-11 10:20:57 +08:00
Hao Zhou 19c569146c Merge amd-staging into amd-master 20220211 
Signed-off-by: Hao Zhou <Hao.Zhou@amd.com>
Change-Id: I95fd0cafb212a3e0f64b58ba6a009a4cd37ae0a6
 2022-02-11 10:20:57 +08:00
Sean Keely b9a0c1d313 Do not discard fragment allocator blocks multiple times. 
discardBlock may be called multiple times on the same block.
We must not discard the block multiple times or we will corrupt
in-use memory accounting.

Change-Id: Ife9f3162785965a795dcf81887d4d447cc096e62
 2022-02-10 18:39:46 -06:00
Sean Keely 523e6e883a Do not discard fragment allocator blocks multiple times. 
discardBlock may be called multiple times on the same block.
We must not discard the block multiple times or we will corrupt
in-use memory accounting.

Change-Id: Ife9f3162785965a795dcf81887d4d447cc096e62


[ROCm/ROCR-Runtime commit: b9a0c1d313]
 2022-02-10 18:39:46 -06:00
Sean Keely 266cd68524 Add fallback case for cache line size. 
KFD sometimes returns 0 for cache line sizes.

Change-Id: If82de0068318bbc138f0d1d4692ff908359174ad
 2022-02-10 18:39:46 -06:00
Sean Keely 305b7394b3 Add fallback case for cache line size. 
KFD sometimes returns 0 for cache line sizes.

Change-Id: If82de0068318bbc138f0d1d4692ff908359174ad


[ROCm/ROCR-Runtime commit: 266cd68524]
 2022-02-10 18:39:46 -06:00
haoyuan2 73130808d8 SWDEV-316128 - HIP surface API support (#2468) 
[ROCm/hip commit: 09583b0183]
 2022-02-10 11:00:25 -08:00
haoyuan2 09583b0183 SWDEV-316128 - HIP surface API support (#2468) 2022-02-10 11:00:25 -08:00
Konstantin Zhuravlyov 3ef52cee16 SWDEV-314372 - Refactor hipcc and hipconfig scripts (#2476) 
* SWDEV-314372 - Refactor hipcc and hipconfig scripts

- Rename original hipcc to hipcc.pl
- Rename original hipconfig to hipconfig.pl
- New hipcc to invoke either hipcc.pl or hipcc.bin based on env var
- New hipconfig to invoke either hipconfig.pl or hipconfig.bin based on env var

* SWDEV-314372 - Add executable permissions to hipcc and hipconfig

[ROCm/hip commit: c447b392d7]
 2022-02-10 09:33:01 -08:00
Konstantin Zhuravlyov c447b392d7 SWDEV-314372 - Refactor hipcc and hipconfig scripts (#2476) 
* SWDEV-314372 - Refactor hipcc and hipconfig scripts

- Rename original hipcc to hipcc.pl
- Rename original hipconfig to hipconfig.pl
- New hipcc to invoke either hipcc.pl or hipcc.bin based on env var
- New hipconfig to invoke either hipconfig.pl or hipconfig.bin based on env var

* SWDEV-314372 - Add executable permissions to hipcc and hipconfig
 2022-02-10 09:33:01 -08:00
agunashe 7429fd2d30 SWDEV-1 - hip change for Windows applications hipInfo (#2471) 
BLDSPPT-3818

Change-Id: I624786a0d79678fbd850f0b8bedc7314731a77f4

[ROCm/hip-tests commit: 835bde481b]
 2022-02-10 08:27:05 -08:00
agunashe 835bde481b SWDEV-1 - hip change for Windows applications hipInfo (#2471) 
BLDSPPT-3818

Change-Id: I624786a0d79678fbd850f0b8bedc7314731a77f4
 2022-02-10 08:27:05 -08:00
agunashe 8d2e226266 SWDEV-1 - hip change for Windows applications hipInfo (#2471) 
BLDSPPT-3818

Change-Id: I624786a0d79678fbd850f0b8bedc7314731a77f4

[ROCm/hip commit: 0284dfb3bd]
 2022-02-10 08:27:05 -08:00
agunashe 0284dfb3bd SWDEV-1 - hip change for Windows applications hipInfo (#2471) 
BLDSPPT-3818

Change-Id: I624786a0d79678fbd850f0b8bedc7314731a77f4
 2022-02-10 08:27:05 -08:00
Payam 0d02019353 SWDEV-316901 - Adding nullptr checks to Graph 
Change-Id: I3ed2ba60875b800133c7f9e692b61f4d57da7aee


[ROCm/clr commit: 4c4acd9fa0]
 2022-02-09 18:36:26 -05:00
Payam 4c4acd9fa0 SWDEV-316901 - Adding nullptr checks to Graph 
Change-Id: I3ed2ba60875b800133c7f9e692b61f4d57da7aee
 2022-02-09 18:36:26 -05:00
German Andryeyev 3c4f97f66c SWDEV-286150 - Remove GSL backend 
Change-Id: Iba9a997ee7d5ff6ac00d5888ff189a4514958fe9


[ROCm/clr commit: 525a1bbf1a]
 2022-02-09 17:16:39 -05:00
German Andryeyev 525a1bbf1a SWDEV-286150 - Remove GSL backend 
Change-Id: Iba9a997ee7d5ff6ac00d5888ff189a4514958fe9
 2022-02-09 17:16:39 -05:00
Jeremy Newton 87809a0387 SWDEV-1 - Fix cmake build 
CPACK_PACKAGING_INSTALL_PREFIX is defined in the wrong location.

Signed-off-by: Jeremy Newton <Jeremy.Newton@amd.com>
Change-Id: Id8ce6beb1d18878c9132cab335cb372a53cc0ee8


[ROCm/clr commit: 9c1f2da1a2]
 2022-02-09 16:09:25 -05:00
Jeremy Newton 9c1f2da1a2 SWDEV-1 - Fix cmake build 
CPACK_PACKAGING_INSTALL_PREFIX is defined in the wrong location.

Signed-off-by: Jeremy Newton <Jeremy.Newton@amd.com>
Change-Id: Id8ce6beb1d18878c9132cab335cb372a53cc0ee8
 2022-02-09 16:09:25 -05:00
Ori Messinger 9d6285f6c8 ROCm SMI CLI: Hide Failed Command Warning 
The purpose of this patch is to hide 'One or more commands failed.'
from showing up, unless an appropriate log level has been set.

You can set the loglevel in the CLI with:
--loglevel <debug/info/warning/error/critical>

Signed-off-by: Ori Messinger <Ori.Messinger@amd.com>
Change-Id: Ifa309cd62596491a6ea5892e0752251f037fc0e9


[ROCm/rocm_smi_lib commit: 007f326c34]
 2022-02-09 11:52:33 -05:00
Ori Messinger 007f326c34 ROCm SMI CLI: Hide Failed Command Warning 
The purpose of this patch is to hide 'One or more commands failed.'
from showing up, unless an appropriate log level has been set.

You can set the loglevel in the CLI with:
--loglevel <debug/info/warning/error/critical>

Signed-off-by: Ori Messinger <Ori.Messinger@amd.com>
Change-Id: Ifa309cd62596491a6ea5892e0752251f037fc0e9
 2022-02-09 11:52:33 -05:00
Ori Messinger e9afb27da3 ROCm SMI CLI: Hide Failed Command Warning 
The purpose of this patch is to hide 'One or more commands failed.'
from showing up, unless an appropriate log level has been set.

You can set the loglevel in the CLI with:
--loglevel <debug/info/warning/error/critical>

Signed-off-by: Ori Messinger <Ori.Messinger@amd.com>
Change-Id: Ifa309cd62596491a6ea5892e0752251f037fc0e9


[ROCm/amdsmi commit: 007f326c34]
 2022-02-09 11:52:33 -05:00
agunashe 6fded87b97 SWDEV-273235 - hip change to build catch tests on Windows (#2472) 
* SWDEV-273235 - hip change to build catch tests on Windows

Change-Id: I96de305694609c669cb81480f3572d987ce87d98

* SWDEV-1 - skip failing hipStreamPerThread_DeviceReset_1 test on Linux

[ROCm/hip-tests commit: ec8d624959]
 2022-02-09 08:17:45 -08:00
agunashe ec8d624959 SWDEV-273235 - hip change to build catch tests on Windows (#2472) 
* SWDEV-273235 - hip change to build catch tests on Windows

Change-Id: I96de305694609c669cb81480f3572d987ce87d98

* SWDEV-1 - skip failing hipStreamPerThread_DeviceReset_1 test on Linux
 2022-02-09 08:17:45 -08:00
agunashe f8746b1982 SWDEV-273235 - hip change to build catch tests on Windows (#2472) 
* SWDEV-273235 - hip change to build catch tests on Windows

Change-Id: I96de305694609c669cb81480f3572d987ce87d98

* SWDEV-1 - skip failing hipStreamPerThread_DeviceReset_1 test on Linux

[ROCm/hip commit: ffe3f9cf81]
 2022-02-09 08:17:45 -08:00
agunashe ffe3f9cf81 SWDEV-273235 - hip change to build catch tests on Windows (#2472) 
* SWDEV-273235 - hip change to build catch tests on Windows

Change-Id: I96de305694609c669cb81480f3572d987ce87d98

* SWDEV-1 - skip failing hipStreamPerThread_DeviceReset_1 test on Linux
 2022-02-09 08:17:45 -08:00
Chauncey Hui 4767a9b231 SWDEV-2 - Change OpenCL version number from 3419 to 3420 
[ROCm/clr commit: c640b395c7]
 2022-02-09 03:00:06 -05:00
Chauncey Hui c640b395c7 SWDEV-2 - Change OpenCL version number from 3419 to 3420 2022-02-09 03:00:06 -05:00
Satyanvesh Dittakavi c128131a6e SWDEV-314661 - Add hipGraphInstantiateWithFlags API mapping in nvidia path 
Change-Id: Ibbf54ef18978448e92571f0535124844154726b6


[ROCm/hipother commit: d64b750aec]
 2022-02-09 00:02:55 -05:00
Satyanvesh Dittakavi d64b750aec SWDEV-314661 - Add hipGraphInstantiateWithFlags API mapping in nvidia path 
Change-Id: Ibbf54ef18978448e92571f0535124844154726b6
 2022-02-09 00:02:55 -05:00
Satyanvesh Dittakavi 556b1bbc69 SWDEV-314661 - Add hipGraphInstantiateWithFlags API mapping in nvidia path 
Change-Id: Ibbf54ef18978448e92571f0535124844154726b6


[ROCm/clr commit: 0759f4ff81]
 2022-02-09 00:02:55 -05:00
Satyanvesh Dittakavi 0759f4ff81 SWDEV-314661 - Add hipGraphInstantiateWithFlags API mapping in nvidia path 
Change-Id: Ibbf54ef18978448e92571f0535124844154726b6
 2022-02-09 00:02:55 -05:00
Hao Zhou a67543f63a Merge amd-staging into amd-master 20220209 
Signed-off-by: Hao Zhou <Hao.Zhou@amd.com>
Change-Id: Ibf40dc4d7c66f2d926d37f09d493d06fb52b183e


[ROCm/rocm_smi_lib commit: 1da93b3dd2]
 2022-02-09 10:19:19 +08:00
Hao Zhou 1da93b3dd2 Merge amd-staging into amd-master 20220209 
Signed-off-by: Hao Zhou <Hao.Zhou@amd.com>
Change-Id: Ibf40dc4d7c66f2d926d37f09d493d06fb52b183e
 2022-02-09 10:19:19 +08:00
Jonathan R. Madsen 4ae26e2d08 rocm-smi and KokkosTools support (#23) 
* renamed omnitrace_thread_data to thread_data

* initial implementation

* Numerous fixes and updates

- Updated timemory submodule
- Updated perfetto submodule (pulls in fixes for TRACE_EVENT)
- pthread_gotcha only after omnitrace_init_tooling
- omnitrace banner
- config settings for rocm-smi freq and devices
- critical_trace::get_entries
- OMNITRACE_BASIC_PRINT
- rocm_smi perfetto category
- redirect roctracer warnings for ROCm 4.5.0
- property specializations for rocm-smi components
- units fixes data_tracker types
- roctracer entries for pthread_create and start_thread
- omnitrace-avail defaults to settings, not components
- settings have conforming names
- settings warn about duplicates
- ptl named threads
- decreased max freq for sampler SIGALRM
- rocm-smi names thread
- rocm-smi avoids call to hipGetDeviceCount
- name roctracer activity callback threads
- fixed binary rewrite test output names

* Update lulesh example

- supports non-UVM GPU

* Lulesh tweaks + formatting

* KokkosP + Mode + Roctracer sampling deadlock fix

- kokkosp support
- omnitrace_init_library
- config::print_settings()
- config::get_mode()
- omnitrace::Mode
- omnitrace-avail improvements (removes settings)
- handle get_verbose() < 0
- disable dyninst InstrStackFrames by default
- handle perf_event_paranoid > 1 by disabling PAPI
- SIGALRM max freq to 5.0
- Name threads
- rocm-smi handles get_use_perfetto() and get_use_timemory()
- HSA_ENABLE_INTERRUPT=0 when roctracer + sampling (fixes deadlock)

* Tests, API renaming, roctracer

- disable renaming of thread 0
- verbprintf_bare
- enable dyninst merge tramp
- tweaked some omnitrace exe verbose levels
- reworked roctracer::setup and roctracer::shutdown
- rocm_smi::data::poll checks get_state()
- omnitrace_trace_finalize -> omnitrace_finalize
- omnitrace_trace_init -> omnitrace_init
- omnitrace_trace_set_env -> omnitrace_set_env
- omnitrace_trace_set_mpi -> omnitrace_set_mpi
- sampling mode does not disable timemory
- disable roctracer before shutting down rocm-smi
- lulesh tests w/ and w/o kokkosp
- lulesh tests for perfetto only
    - with --dynamic-callsites --traps --allow-overlapping
- lulesh tests for timemory only
    - with --stdlib --dynamic-callsites --traps --allow-overlapping

* Update timemory submodule

- fix for TIMEMORY_PROPERTY_SPECIALIZATION

* get_verbose() handling + timemory submodule update

- Findroctracer.cmake uses find_package(hsakmt)

* Stability fixes + rework roctracer + perfetto

- reworked roctracer start up
- critical_trace perfetto basic values
- perfetto sampling category
- sampler checks signals
- peak_rss in sampling
- pthread_gotcha::shutdown()
- rocm_smi::device_count()
- HSA_TOOLS_LIB is set
- HSA_ENABLE_INTERRUPT in omnitrace exe
- omnitrace exe verbosity level changes
- Avoid instrumenting Impl ns in Kokkos
- gpu::device_count prefers rocm_smi instead of hip
- ptl blocks signals
- fixed pthread_gotcha roctracer_data values
- removed runtime-instrument-sampling tests
- timemory submodule update

* cmake formatting

* timemory + roctracer updates

- fix timemory issue with papi_common
- fix timemory issue with units
- define roctracer::is_setup()

* Miscellaneous tweaks

- Disable sampling during runtime instrument
- Fixed warnings about dynamic callsites
- Fixed backtrace output when timemory disabled
- Test tweaks

* cmake-format

* omnitrace_target_compile_definitions

* timemory submodule update

* config, omnitrace, State, mpi_gotcha updates

- use OMNITRACE_THROW instead of direct throw
- is_attached()
- is_binary_rewrite()
- get_is_continuous_integration()
- get_debug_init()
- get_debug_finalize()
- max_thread_bookmarks default to 1
- State::Init
- app_thread oneTimeCode
- runtime instrumentation uses waitpid
- fixed init_names
- include main in MPI runs
- fixed sampling setup when disabled
- reworked mpi_gotcha
- disabled critical trace in transpose test

* cmake-format

* handle rocm_smi::device_count() exception

* CI timeouts

* Re-enable runtime-instrument + sampling

[ROCm/rocprofiler-systems commit: 39f17ae8b8]
 2022-02-08 17:42:17 -06:00
Jonathan R. Madsen 39f17ae8b8 rocm-smi and KokkosTools support (#23) 
* renamed omnitrace_thread_data to thread_data

* initial implementation

* Numerous fixes and updates

- Updated timemory submodule
- Updated perfetto submodule (pulls in fixes for TRACE_EVENT)
- pthread_gotcha only after omnitrace_init_tooling
- omnitrace banner
- config settings for rocm-smi freq and devices
- critical_trace::get_entries
- OMNITRACE_BASIC_PRINT
- rocm_smi perfetto category
- redirect roctracer warnings for ROCm 4.5.0
- property specializations for rocm-smi components
- units fixes data_tracker types
- roctracer entries for pthread_create and start_thread
- omnitrace-avail defaults to settings, not components
- settings have conforming names
- settings warn about duplicates
- ptl named threads
- decreased max freq for sampler SIGALRM
- rocm-smi names thread
- rocm-smi avoids call to hipGetDeviceCount
- name roctracer activity callback threads
- fixed binary rewrite test output names

* Update lulesh example

- supports non-UVM GPU

* Lulesh tweaks + formatting

* KokkosP + Mode + Roctracer sampling deadlock fix

- kokkosp support
- omnitrace_init_library
- config::print_settings()
- config::get_mode()
- omnitrace::Mode
- omnitrace-avail improvements (removes settings)
- handle get_verbose() < 0
- disable dyninst InstrStackFrames by default
- handle perf_event_paranoid > 1 by disabling PAPI
- SIGALRM max freq to 5.0
- Name threads
- rocm-smi handles get_use_perfetto() and get_use_timemory()
- HSA_ENABLE_INTERRUPT=0 when roctracer + sampling (fixes deadlock)

* Tests, API renaming, roctracer

- disable renaming of thread 0
- verbprintf_bare
- enable dyninst merge tramp
- tweaked some omnitrace exe verbose levels
- reworked roctracer::setup and roctracer::shutdown
- rocm_smi::data::poll checks get_state()
- omnitrace_trace_finalize -> omnitrace_finalize
- omnitrace_trace_init -> omnitrace_init
- omnitrace_trace_set_env -> omnitrace_set_env
- omnitrace_trace_set_mpi -> omnitrace_set_mpi
- sampling mode does not disable timemory
- disable roctracer before shutting down rocm-smi
- lulesh tests w/ and w/o kokkosp
- lulesh tests for perfetto only
    - with --dynamic-callsites --traps --allow-overlapping
- lulesh tests for timemory only
    - with --stdlib --dynamic-callsites --traps --allow-overlapping

* Update timemory submodule

- fix for TIMEMORY_PROPERTY_SPECIALIZATION

* get_verbose() handling + timemory submodule update

- Findroctracer.cmake uses find_package(hsakmt)

* Stability fixes + rework roctracer + perfetto

- reworked roctracer start up
- critical_trace perfetto basic values
- perfetto sampling category
- sampler checks signals
- peak_rss in sampling
- pthread_gotcha::shutdown()
- rocm_smi::device_count()
- HSA_TOOLS_LIB is set
- HSA_ENABLE_INTERRUPT in omnitrace exe
- omnitrace exe verbosity level changes
- Avoid instrumenting Impl ns in Kokkos
- gpu::device_count prefers rocm_smi instead of hip
- ptl blocks signals
- fixed pthread_gotcha roctracer_data values
- removed runtime-instrument-sampling tests
- timemory submodule update

* cmake formatting

* timemory + roctracer updates

- fix timemory issue with papi_common
- fix timemory issue with units
- define roctracer::is_setup()

* Miscellaneous tweaks

- Disable sampling during runtime instrument
- Fixed warnings about dynamic callsites
- Fixed backtrace output when timemory disabled
- Test tweaks

* cmake-format

* omnitrace_target_compile_definitions

* timemory submodule update

* config, omnitrace, State, mpi_gotcha updates

- use OMNITRACE_THROW instead of direct throw
- is_attached()
- is_binary_rewrite()
- get_is_continuous_integration()
- get_debug_init()
- get_debug_finalize()
- max_thread_bookmarks default to 1
- State::Init
- app_thread oneTimeCode
- runtime instrumentation uses waitpid
- fixed init_names
- include main in MPI runs
- fixed sampling setup when disabled
- reworked mpi_gotcha
- disabled critical trace in transpose test

* cmake-format

* handle rocm_smi::device_count() exception

* CI timeouts

* Re-enable runtime-instrument + sampling
 2022-02-08 17:42:17 -06:00
Ke Wen 92d6888bdc Split IB parameter sanity check into two parts 
First part on collective mismatch, second part on internal errors


[ROCm/rccl commit: fbfb6ac5d7]
 2022-02-08 15:21:22 -08:00
Ke Wen fbfb6ac5d7 Split IB parameter sanity check into two parts 
First part on collective mismatch, second part on internal errors
 2022-02-08 15:21:22 -08:00
Ashutosh Mishra 1f10c39e2a SWDEV-306262 - Fix RUNPATH 
RUNPATH was not changed to correct ROCM_RPATH
Packaged proper binaries after RUNPATH correction

Signed-off-by: Ashutosh Mishra <Ashutosh.Mishra@amd.com>

Change-Id: I97443cc0d6cb1ecf7352e3c83ae0fe38a8f339bf


[ROCm/clr commit: e3fe3a6109]
 2022-02-08 15:14:05 -08:00
Ashutosh Mishra e3fe3a6109 SWDEV-306262 - Fix RUNPATH 
RUNPATH was not changed to correct ROCM_RPATH
Packaged proper binaries after RUNPATH correction

Signed-off-by: Ashutosh Mishra <Ashutosh.Mishra@amd.com>

Change-Id: I97443cc0d6cb1ecf7352e3c83ae0fe38a8f339bf
 2022-02-08 15:14:05 -08:00
Payam 316c83dd84 SWDEV-321079 - Blender GL interop Linux fix 
Change-Id: I920d30c575627c443a1d2e93c02abf8658bc3978


[ROCm/clr commit: 9faac0fe8d]
 2022-02-08 14:17:38 -05:00
Payam 9faac0fe8d SWDEV-321079 - Blender GL interop Linux fix 
Change-Id: I920d30c575627c443a1d2e93c02abf8658bc3978
 2022-02-08 14:17:38 -05:00
Payam 05a9c3057a SWDEV-315880 - adding Graph nullptr checks 
Change-Id: I84a70f9c2606cb480b32953631878df40d71a675


[ROCm/clr commit: 1f8c42deee]
 2022-02-07 22:35:24 -05:00
Payam 1f8c42deee SWDEV-315880 - adding Graph nullptr checks 
Change-Id: I84a70f9c2606cb480b32953631878df40d71a675
 2022-02-07 22:35:24 -05:00
German Andryeyev 0bfb898038 SWDEV-286150 - Don't report OCL2.2 support 
OCL2.2 requires SPIR-V and runtime doesn't support it.
Make sure PAL backend doesn't report any SPIR-V support.

Change-Id: I8d179069674205b54f7d20d149bcb675bee5cdb0


[ROCm/clr commit: 0bf395af39]
 2022-02-07 17:34:39 -05:00
German Andryeyev 0bf395af39 SWDEV-286150 - Don't report OCL2.2 support 
OCL2.2 requires SPIR-V and runtime doesn't support it.
Make sure PAL backend doesn't report any SPIR-V support.

Change-Id: I8d179069674205b54f7d20d149bcb675bee5cdb0
 2022-02-07 17:34:39 -05:00
Payam 80026db2b3 SWDEV-321160 - Checking if GL-Context is initialized 
Change-Id: I5482fa33bcf9a1587ee68ed37f2058b7ed7e706a


[ROCm/clr commit: f501317b5b]
 2022-02-07 15:05:55 -05:00
Payam f501317b5b SWDEV-321160 - Checking if GL-Context is initialized 
Change-Id: I5482fa33bcf9a1587ee68ed37f2058b7ed7e706a
 2022-02-07 15:05:55 -05:00