AI/rocm-systems
2
0
Förgrening 0
Kod Ärenden Pull-förfrågningar Actions Packages Projekt Släpp Wiki Aktiviteter
64 512 Incheckningar 3 Grenar 0 Taggar
bb1295bcdfd72123700cd66e631326ab38e82db8
Commit-Graf

64512 Incheckningar

This Branch
This Branch
Alla brancher
Upphovsman SHA1 Meddelande Datum
Galantsev, Dmitrii 95e057c88d Simplify ModuleMgr 
Change-Id: I3a57876c73e50771fcedb7ca4c67d55ac406b34d
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>
 2024-01-09 11:37:11 -06:00
Galantsev, Dmitrii 61cf14d7cc Simplify ModuleMgr 
Change-Id: I3a57876c73e50771fcedb7ca4c67d55ac406b34d
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>


[ROCm/rdc commit: 95e057c88d]
 2024-01-09 11:37:11 -06:00
Jonathan R. Madsen 5e0a39e5d5 Async memory copy tracing (#317) 
* Update samples/api_buffered_tracing/client.cpp

- support ROCPROFILER_BUFFER_TRACING_MEMORY_COPY

* Update include/rocprofiler-sdk/{buffer_tracing,fwd}.h

- update rocprofiler_buffer_tracing_memory_copy_record_t
- add ROCPROFILER_BUFFER_TRACING_MEMORY_COPY_HOST_TO_HOST to rocprofiler_memory_copy_operation_t

* Update lib/rocprofiler-sdk/context/context.*

- get_registered_contexts functions (local copy)

* Update tests/apps/reproducible-runtime/reproducible-runtime.cpp

- include some memory allocations and memory copies for better testing

* Update tests/common/serialization.hpp

- update serialization save function for rocprofiler_buffer_tracing_memory_copy_record_t

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

- remove stale set_callback / activity_functor_t code
- forward decl hsa_api_meta
- template struct hsa_api_func for getting function return type and args

* Update tests/kernel-tracing/validate.py

- enforce memory_copies data size
- test timestamps in memory copies data
- improve internal and external correlation id validation

* Update lib/rocprofiler-sdk/hsa/defines.hpp

- HSA_API_META_DEFINITION macro

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

- HSA_API_META_DEFINITION specializations for async copy functions

* Add lib/rocprofiler-sdk/hsa/async_copy.{hpp,cpp}

- implements buffer memory tracing

* Update lib/rocprofiler-sdk/registration.cpp

- invoke rocprofiler::hsa::async_copy_init

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

- logging improvements
- improve hsa <-> rocp agent mapping

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

- load original signal in async signal handler before store_screlease

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

- use store_relaxed instead of store_screlease

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

- logging

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

- logging

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

- misc changes

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

- misc changes

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

- misc changes

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

- return function pointer instead of lambda

* Update reproducible-runtime.cpp

- device sync

* Update tests/apps/reproducible-runtime/reproducible-runtime.cpp

- use *Async variants of hipMalloc and hipMemcpy

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

- populate async data properly

* Update tests/kernel-tracing/validate.py

- verification of async copy direction

* Update tests/apps/reproducible-runtime/reproducible-runtime.cpp

- temporarily disable async memcpy functions

* Create tests/tools

- directory containing tool libraries used for collecting data in integration tests

* Update tests/kernel-tracing

- remove kernel-tracing-test-tool library (now rocprofiler-sdk-json-tool)
- update cmake, validate.py, conftest.py accordingly

* Add tests/async-copy-tracing

- integration test validating async copy tracing in transpose example

* Update tests/CMakeLists.txt

- updates for restructuring

* Revert tests/apps/reproducible-runtime

- restore code to semi-original state (no memory copying)

* Update tests/async-copy-tracing/validate.py

- fix comment in test_async_copy_direction

* Fix building tests against installation

[ROCm/rocprofiler-sdk commit: 936816f762]
 2024-01-09 11:34:46 -06:00
Jonathan R. Madsen 936816f762 Async memory copy tracing (#317) 
* Update samples/api_buffered_tracing/client.cpp

- support ROCPROFILER_BUFFER_TRACING_MEMORY_COPY

* Update include/rocprofiler-sdk/{buffer_tracing,fwd}.h

- update rocprofiler_buffer_tracing_memory_copy_record_t
- add ROCPROFILER_BUFFER_TRACING_MEMORY_COPY_HOST_TO_HOST to rocprofiler_memory_copy_operation_t

* Update lib/rocprofiler-sdk/context/context.*

- get_registered_contexts functions (local copy)

* Update tests/apps/reproducible-runtime/reproducible-runtime.cpp

- include some memory allocations and memory copies for better testing

* Update tests/common/serialization.hpp

- update serialization save function for rocprofiler_buffer_tracing_memory_copy_record_t

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

- remove stale set_callback / activity_functor_t code
- forward decl hsa_api_meta
- template struct hsa_api_func for getting function return type and args

* Update tests/kernel-tracing/validate.py

- enforce memory_copies data size
- test timestamps in memory copies data
- improve internal and external correlation id validation

* Update lib/rocprofiler-sdk/hsa/defines.hpp

- HSA_API_META_DEFINITION macro

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

- HSA_API_META_DEFINITION specializations for async copy functions

* Add lib/rocprofiler-sdk/hsa/async_copy.{hpp,cpp}

- implements buffer memory tracing

* Update lib/rocprofiler-sdk/registration.cpp

- invoke rocprofiler::hsa::async_copy_init

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

- logging improvements
- improve hsa <-> rocp agent mapping

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

- load original signal in async signal handler before store_screlease

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

- use store_relaxed instead of store_screlease

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

- logging

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

- logging

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

- misc changes

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

- misc changes

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

- misc changes

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

- return function pointer instead of lambda

* Update reproducible-runtime.cpp

- device sync

* Update tests/apps/reproducible-runtime/reproducible-runtime.cpp

- use *Async variants of hipMalloc and hipMemcpy

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

- populate async data properly

* Update tests/kernel-tracing/validate.py

- verification of async copy direction

* Update tests/apps/reproducible-runtime/reproducible-runtime.cpp

- temporarily disable async memcpy functions

* Create tests/tools

- directory containing tool libraries used for collecting data in integration tests

* Update tests/kernel-tracing

- remove kernel-tracing-test-tool library (now rocprofiler-sdk-json-tool)
- update cmake, validate.py, conftest.py accordingly

* Add tests/async-copy-tracing

- integration test validating async copy tracing in transpose example

* Update tests/CMakeLists.txt

- updates for restructuring

* Revert tests/apps/reproducible-runtime

- restore code to semi-original state (no memory copying)

* Update tests/async-copy-tracing/validate.py

- fix comment in test_async_copy_direction

* Fix building tests against installation
 2024-01-09 11:34:46 -06:00
Ben Richard e75c591baa Fix MPI test failures (#322) 
The CI test machines only have 2 MPI slots. MPI tests were failing
when requesting 4 CPUs. Update these tests to request 2 CPUs.

[ROCm/rocprofiler-systems commit: aeb346b6d6]
 2024-01-09 09:19:06 -06:00
Ben Richard aeb346b6d6 Fix MPI test failures (#322) 
The CI test machines only have 2 MPI slots. MPI tests were failing
when requesting 4 CPUs. Update these tests to request 2 CPUs.
 2024-01-09 09:19:06 -06:00
David Yat Sin 0412fdba60 Set -m64 flag only on x86-64 hosts 
-m64 only applies to x86-64, it's more reasonable to enable it only on x86_64 host.
It fixes build on some other platforms as well.

Provided by user r-value on github

https: //github.com/RadeonOpenCompute/rocminfo/pull/63
Change-Id: I9c1c40d3fa39b0a61d28041fe4998b5e1ad0cdcd


[ROCm/rocminfo commit: 17de0f9097]
 2024-01-09 09:49:04 -05:00
David Yat Sin 17de0f9097 Set -m64 flag only on x86-64 hosts 
-m64 only applies to x86-64, it's more reasonable to enable it only on x86_64 host.
It fixes build on some other platforms as well.

Provided by user r-value on github

https: //github.com/RadeonOpenCompute/rocminfo/pull/63
Change-Id: I9c1c40d3fa39b0a61d28041fe4998b5e1ad0cdcd
 2024-01-09 09:49:04 -05:00
German ba4a3cd9f4 SWDEV-439241 - Keep direct map for MGPU 
Single OCL context with multiple devices should use direct map
even with persistent memory, because cache coherency layer.

Change-Id: I02a48830440203a1dea176acd4dff4452b70f133


[ROCm/clr commit: 49037b9762]
 2024-01-08 18:14:15 -05:00
German 49037b9762 SWDEV-439241 - Keep direct map for MGPU 
Single OCL context with multiple devices should use direct map
even with persistent memory, because cache coherency layer.

Change-Id: I02a48830440203a1dea176acd4dff4452b70f133
 2024-01-08 18:14:15 -05:00
sdashmiz 2860ef8a1c SWDEV-421027 - Add more hip Graph APIs 
Signed-off-by: sdashmiz <shadi.dashmiz@amd.com>
Change-Id: I1dfe86fd59373e83e09ffa861808a0ef5faeca68


[ROCm/hip commit: e74f60952a]
 2024-01-08 11:05:14 -05:00
sdashmiz e74f60952a SWDEV-421027 - Add more hip Graph APIs 
Signed-off-by: sdashmiz <shadi.dashmiz@amd.com>
Change-Id: I1dfe86fd59373e83e09ffa861808a0ef5faeca68
 2024-01-08 11:05:14 -05:00
German 5718f13901 SWDEV-438958 - Calculate persistent memory stored in the cache 
- Make sure persistent memory from resource cache is properly adjusted
in free memory calculation.

Change-Id: I74ef68975ccde4694fb1cb904617c418e85dfc9f


[ROCm/clr commit: 85c15d720d]
 2024-01-08 10:11:52 -05:00
German 85c15d720d SWDEV-438958 - Calculate persistent memory stored in the cache 
- Make sure persistent memory from resource cache is properly adjusted
in free memory calculation.

Change-Id: I74ef68975ccde4694fb1cb904617c418e85dfc9f
 2024-01-08 10:11:52 -05:00
Jatin Chaudhary f09b9af969 SWDEV-398975 - re-enable Unit_hipMemcpyWithStream_MultiThread test 
use correct macro inside the test

Change-Id: I7034a97efe91d6c9e2d9b4e6026ec770714a01ac


[ROCm/hip-tests commit: 9704c269d0]
 2024-01-08 06:07:14 -05:00
Jatin Chaudhary 9704c269d0 SWDEV-398975 - re-enable Unit_hipMemcpyWithStream_MultiThread test 
use correct macro inside the test

Change-Id: I7034a97efe91d6c9e2d9b4e6026ec770714a01ac
 2024-01-08 06:07:14 -05:00
Giovanni LB 4cda8f831a SWDEV-439965: Added some comments for att scripts 
Change-Id: I79e13f7b8446a7675732eb4118b5f1e95769d76a
 2024-01-08 07:44:37 -03:00
Giovanni LB 207815802b SWDEV-439965: Added some comments for att scripts 
Change-Id: I79e13f7b8446a7675732eb4118b5f1e95769d76a


[ROCm/rocprofiler commit: 4cda8f831a]
 2024-01-08 07:44:37 -03:00
Jatin Chaudhary e473199c50 SWDEV-430619 - fix Unit_hipDeviceGetUuid_From_RocmInfo test 
Ignore the iGPU when iterating rocminfo and correct the bounds check
when matching results with HIP API. Also do not compare bytes directly,
use string to do a string compare as it can go out of bounds.
Disabling this test on windows till I get hold of a working windows
machine.

Change-Id: Icf811e0310776567afecea92e1d54e8438b39235


[ROCm/hip-tests commit: af3ac29c40]
 2024-01-08 04:21:52 -05:00
Jatin Chaudhary af3ac29c40 SWDEV-430619 - fix Unit_hipDeviceGetUuid_From_RocmInfo test 
Ignore the iGPU when iterating rocminfo and correct the bounds check
when matching results with HIP API. Also do not compare bytes directly,
use string to do a string compare as it can go out of bounds.
Disabling this test on windows till I get hold of a working windows
machine.

Change-Id: Icf811e0310776567afecea92e1d54e8438b39235
 2024-01-08 04:21:52 -05:00
Rahul Garg 0589a9f7dd SWDEV-439426 - Update HIP patch version reported through CMake 
Change-Id: I2b32edfa18d85d49a4b96ff80ea8f60e1df5d517


[ROCm/clr commit: 956cc463bf]
 2024-01-08 03:43:01 -05:00
Rahul Garg 956cc463bf SWDEV-439426 - Update HIP patch version reported through CMake 
Change-Id: I2b32edfa18d85d49a4b96ff80ea8f60e1df5d517
 2024-01-08 03:43:01 -05:00
Jatin Chaudhary 3e9350ef26 SWDEV-388956 - renable Unit_hipGraphAddMemsetNode_Positive_Basic test on linux 
Change-Id: I91bf9aba6a93d8fec2595cd1a3d5e1fb2c422e0f


[ROCm/hip-tests commit: 4305328f37]
 2024-01-08 01:13:45 -05:00
Jatin Chaudhary 4305328f37 SWDEV-388956 - renable Unit_hipGraphAddMemsetNode_Positive_Basic test on linux 
Change-Id: I91bf9aba6a93d8fec2595cd1a3d5e1fb2c422e0f
 2024-01-08 01:13:45 -05:00
Jatin Chaudhary 938994cd60 SWDEV-431399 - fix randomly failing timing based tests 
use blocking context instead of time based kernel launch

Change-Id: Ib4cdf913f18c80ce8173317811c0e6e3eb5acb76


[ROCm/hip-tests commit: c364656420]
 2024-01-08 01:13:00 -05:00
Jatin Chaudhary c364656420 SWDEV-431399 - fix randomly failing timing based tests 
use blocking context instead of time based kernel launch

Change-Id: Ib4cdf913f18c80ce8173317811c0e6e3eb5acb76
 2024-01-08 01:13:00 -05:00
Ranjith Ramakrishnan a7d8b1c287 Use relative path rather than hard coded path in package config file 
Change-Id: Ia35fadeead69f84f4f4d32ab0c04f2f391aba4f4
 2024-01-07 20:51:59 -08:00
Ranjith Ramakrishnan ed4861e951 Use relative path rather than hard coded path in package config file 
Change-Id: Ia35fadeead69f84f4f4d32ab0c04f2f391aba4f4


[ROCm/ROCR-Runtime commit: a7d8b1c287]
 2024-01-07 20:51:59 -08:00
Giovanni LB 43ee268b60 SWDEV-439965: Moved occupancy to simpler format 
Change-Id: I7db4719e6bcb4a70a36497d49c11bf188d0fcd69
 2024-01-07 15:44:34 -05:00
Giovanni LB f8f84af1f7 SWDEV-439965: Moved occupancy to simpler format 
Change-Id: I7db4719e6bcb4a70a36497d49c11bf188d0fcd69


[ROCm/rocprofiler commit: 43ee268b60]
 2024-01-07 15:44:34 -05:00
Giovanni LB 2a45bb7a8a SWDEV-439965: Fixing user-supplied ISA 
Change-Id: I69b4984b8e6655832506d9bb2c6f73073e59e871
 2024-01-06 23:13:43 -05:00
Giovanni LB 71e7f6d8c5 SWDEV-439965: Fixing user-supplied ISA 
Change-Id: I69b4984b8e6655832506d9bb2c6f73073e59e871


[ROCm/rocprofiler commit: 2a45bb7a8a]
 2024-01-06 23:13:43 -05:00
Giovanni LB bae8c664bb Temp workaround for compilation errors in CTF 
Change-Id: If9fc45f4d76a85ebe38ebc03a4fba9fe069730d7
 2024-01-06 17:58:33 -03:00
Giovanni LB c6a6c372af Temp workaround for compilation errors in CTF 
Change-Id: If9fc45f4d76a85ebe38ebc03a4fba9fe069730d7


[ROCm/rocprofiler commit: bae8c664bb]
 2024-01-06 17:58:33 -03:00
ksankisa 82fd83009c SWDEV-404921 - Add dynamic LDS size hidden kernel argument 
Change-Id: If99019058e4bfdc988ef5fc4cef001b772380453


[ROCm/clr commit: f554a075c7]
 2024-01-06 08:46:55 +05:30
ksankisa f554a075c7 SWDEV-404921 - Add dynamic LDS size hidden kernel argument 
Change-Id: If99019058e4bfdc988ef5fc4cef001b772380453
 2024-01-06 08:46:55 +05:30
Benjamin Welton 2f08904cd8 Build fixes for clang 10 (#339) 
* Build fixes for clang 10

fixes build warnings in clang10

* source formatting (clang-format v11) (#340)

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

---------

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

[ROCm/rocprofiler-sdk commit: 0dd0cad2e4]
 2024-01-05 15:20:11 -08:00
Benjamin Welton 0dd0cad2e4 Build fixes for clang 10 (#339) 
* Build fixes for clang 10

fixes build warnings in clang10

* source formatting (clang-format v11) (#340)

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

---------

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: bwelton <bwelton@users.noreply.github.com>
 2024-01-05 15:20:11 -08:00
Oliveira, Daniel c0335b2695 rocm_smi_lib: Fix gpu_metrics_v1_5 support 
Adds support and implement APIs for 'gpu_metrics_v1_5'

Code changes related to the following:
  * gpu metrics 1.5 support
  * Unit tests
  * Examples

Build changes related to the following: None

Change-Id: Ie8917dd63c1dd1a94467b100fa44b634cebe62b6
Signed-off-by: Oliveira, Daniel <daniel.oliveira@amd.com>


[ROCm/rocm_smi_lib commit: 373621aed3]
 2024-01-05 14:24:34 -06:00
Oliveira, Daniel 373621aed3 rocm_smi_lib: Fix gpu_metrics_v1_5 support 
Adds support and implement APIs for 'gpu_metrics_v1_5'

Code changes related to the following:
  * gpu metrics 1.5 support
  * Unit tests
  * Examples

Build changes related to the following: None

Change-Id: Ie8917dd63c1dd1a94467b100fa44b634cebe62b6
Signed-off-by: Oliveira, Daniel <daniel.oliveira@amd.com>
 2024-01-05 14:24:34 -06:00
Karl W Schulz 74ded7f4d0 restore full profile execution in parallel 
Signed-off-by: Karl W Schulz <karl.schulz@amd.com>


[ROCm/rocprofiler-compute commit: d425b8468a]
 2024-01-05 10:06:10 -06:00
Karl W Schulz d425b8468a restore full profile execution in parallel 
Signed-off-by: Karl W Schulz <karl.schulz@amd.com>
 2024-01-05 10:06:10 -06:00
Karl W Schulz fbb8f8c9bc tweak job name 
Signed-off-by: Karl W Schulz <karl.schulz@amd.com>


[ROCm/rocprofiler-compute commit: 0b7ec07216]
 2024-01-05 09:56:46 -06:00
Karl W Schulz 0b7ec07216 tweak job name 
Signed-off-by: Karl W Schulz <karl.schulz@amd.com>
 2024-01-05 09:56:46 -06:00
Karl W Schulz a0c52bee17 tweak job name 
Signed-off-by: Karl W Schulz <karl.schulz@amd.com>


[ROCm/rocprofiler-compute commit: b7345a9c19]
 2024-01-05 09:53:03 -06:00
Karl W Schulz b7345a9c19 tweak job name 
Signed-off-by: Karl W Schulz <karl.schulz@amd.com>
 2024-01-05 09:53:03 -06:00
Karl W Schulz 30b97324e7 include another rocm version to test 
Signed-off-by: Karl W Schulz <karl.schulz@amd.com>


[ROCm/rocprofiler-compute commit: e104ce5fd3]
 2024-01-05 09:44:48 -06:00
Karl W Schulz e104ce5fd3 include another rocm version to test 
Signed-off-by: Karl W Schulz <karl.schulz@amd.com>
 2024-01-05 09:44:48 -06:00
Karl W Schulz ad225e8ce3 update to matrix job 
Signed-off-by: Karl W Schulz <karl.schulz@amd.com>


[ROCm/rocprofiler-compute commit: 7b7059c2a7]
 2024-01-05 09:41:37 -06:00
Karl W Schulz 7b7059c2a7 update to matrix job 
Signed-off-by: Karl W Schulz <karl.schulz@amd.com>
 2024-01-05 09:41:37 -06:00