On some systems, pthread_addr_setaffinity_np does not exist, so we need
to use pthread_setaffinity_np on thread after pthread_create
Provided by Julian Samaroo on github
https: //github.com/RadeonOpenCompute/ROCR-Runtime/pull/143
Change-Id: I4649f94333f2d7b0a5993b370a4bfc48d92acecb
On some systems, pthread_addr_setaffinity_np does not exist, so we need
to use pthread_setaffinity_np on thread after pthread_create
Provided by Julian Samaroo on github
https: //github.com/RadeonOpenCompute/ROCR-Runtime/pull/143
Change-Id: I4649f94333f2d7b0a5993b370a4bfc48d92acecb
[ROCm/ROCR-Runtime commit: 6333fdecf3]
* Initial overhaul of Analyze mode. Basic CLI is enabled.
Signed-off-by: colramos-amd <colramos@amd.com>
* Merge branch '2.x' of github.com:AMDResearch/omniperf into 2.x-dev
Signed-off-by: colramos-amd <colramos@amd.com>
* fix comment typo
Signed-off-by: Karl W Schulz <karl.schulz@amd.com>
* Move error logging to util.py
Signed-off-by: colramos-amd <colramos@amd.com>
* Move perfmon_configs dir into omniperf_soc dir. Rename config dirs for clarity
Signed-off-by: colramos-amd <colramos@amd.com>
* Add a supported_archs property to Omniperf base class
Signed-off-by: colramos-amd <colramos@amd.com>
* Add css assets for GUI styling
Signed-off-by: colramos-amd <colramos@amd.com>
* Re-organize roofline class. Improved useability
Signed-off-by: colramos-amd <colramos@amd.com>
* Enable standalone GUI
Signed-off-by: colramos-amd <colramos@amd.com>
* Remove outdated metric_configs. This was moved to omniperf_soc dir
Signed-off-by: colramos-amd <colramos@amd.com>
* Fix small bug in GUI to enable Mi100 visualization
Signed-off-by: colramos-amd <colramos@amd.com>
---------
Signed-off-by: colramos-amd <colramos@amd.com>
Signed-off-by: Karl W Schulz <karl.schulz@amd.com>
Signed-off-by: Cole Ramos <colramos@amd.com>
Co-authored-by: Karl W Schulz <karl.schulz@amd.com>
- Disable tests that are failing on Linux during PSDB stress testing
Change-Id: I1711d2d67afd3d23a27f84684a06602236cece45
[ROCm/hip-tests commit: 24e2f429ca]
When an offset is applied to the source or destination pointers plus the kind is set to
hipMemcpyDefault and the source or destination is allocated with hipMallocManaged
hipMemCpy2D erroneously fails with hipErrorInvalidValue.
Change-Id: I0db4c17514f743652d8f9a2691da6601a2abb2a1
[ROCm/clr commit: d3bfb55d7a]
When an offset is applied to the source or destination pointers plus the kind is set to
hipMemcpyDefault and the source or destination is allocated with hipMallocManaged
hipMemCpy2D erroneously fails with hipErrorInvalidValue.
Change-Id: I0db4c17514f743652d8f9a2691da6601a2abb2a1
Fix sporatic segment fault in texture test
via retaining image in texture object which
references the image.
The image will be released when the texture
object is destroyed.
Change-Id: Ic3fefa2d5dda6afebd1acd4d41ad310b138af6dd
[ROCm/clr commit: d6d235a111]
Fix sporatic segment fault in texture test
via retaining image in texture object which
references the image.
The image will be released when the texture
object is destroyed.
Change-Id: Ic3fefa2d5dda6afebd1acd4d41ad310b138af6dd
Recent changes disabled system memory allocation
in the abstraciton layer. That requires memory
allocation/destruction in ROCR. Add destruction logic.
Change-Id: I68fe6b0a620ca743fe5850052ea0efa8bb7931c2
[ROCm/clr commit: a6d480e098]
Recent changes disabled system memory allocation
in the abstraciton layer. That requires memory
allocation/destruction in ROCR. Add destruction logic.
Change-Id: I68fe6b0a620ca743fe5850052ea0efa8bb7931c2
* Restructured tests
- support standalone compilation
- move tests/kernel-tracing/serialization.hpp to tests/common/serialization.hpp
- created tests/common library
- handle cloning of cereal library in standalone build
* Update install and packaging
* Update cmake/rocprofiler_config_packaging.cmake
- condense core, samples, development, and tools install components into single rocprofiler-sdk package
- keep tests install component in separate rocprofiler-sdk-tests package
* Update CI workflow to test install and packaging
* Update CI workflow
- install newer cmake for packaging checks
* Update cmake/rocprofiler_config_packaging.cmake
- disable auto-generation of shared-lib deps and provides for tests package
* Update CI workflow
- add sbin to PATH for dpkg install
* Update CI workflow
- remove using github.workspace when installing packages
* Update CI workflow
- hack to fix ordering of dpkg install
* Update CI workflow
- whitespace cleanup
[ROCm/rocprofiler-sdk commit: 8ed68ce4f3]
* Restructured tests
- support standalone compilation
- move tests/kernel-tracing/serialization.hpp to tests/common/serialization.hpp
- created tests/common library
- handle cloning of cereal library in standalone build
* Update install and packaging
* Update cmake/rocprofiler_config_packaging.cmake
- condense core, samples, development, and tools install components into single rocprofiler-sdk package
- keep tests install component in separate rocprofiler-sdk-tests package
* Update CI workflow to test install and packaging
* Update CI workflow
- install newer cmake for packaging checks
* Update cmake/rocprofiler_config_packaging.cmake
- disable auto-generation of shared-lib deps and provides for tests package
* Update CI workflow
- add sbin to PATH for dpkg install
* Update CI workflow
- remove using github.workspace when installing packages
* Update CI workflow
- hack to fix ordering of dpkg install
* Update CI workflow
- whitespace cleanup
When xnack is on shadder code in this test triggers gpu page fault that migrate
data from system ram to vram. Use svm range granularity to move all data from
system buffer to vram to reduce system ram pressure to avoid system ram oom for
systems that has less system ram.
Signed-off-by: Xiaogang Chen <Xiaogang.Chen@amd.com>
Change-Id: I219472210756be319491f7827f7209fe32726f81
When xnack is on shadder code in this test triggers gpu page fault that migrate
data from system ram to vram. Use svm range granularity to move all data from
system buffer to vram to reduce system ram pressure to avoid system ram oom for
systems that has less system ram.
Signed-off-by: Xiaogang Chen <Xiaogang.Chen@amd.com>
Change-Id: I219472210756be319491f7827f7209fe32726f81
[ROCm/ROCR-Runtime commit: 1a7162731e]
Extra CPU read back will be performed before every submission to make sure
previous writes over PCIE reached GPU. HDP flush is done by CP.
Change-Id: I402d28ca26c8cee4a3920feb3599af8c285d0889
[ROCm/clr commit: cfc07c88ee]
Extra CPU read back will be performed before every submission to make sure
previous writes over PCIE reached GPU. HDP flush is done by CP.
Change-Id: I402d28ca26c8cee4a3920feb3599af8c285d0889
- remove static asserts on the HSA table step versions
- ifdef/else the amd_ext size based on HSA_AMD_EXT_API_TABLE_STEP_VERSION
[ROCm/rocprofiler-sdk commit: f96ab90067]
Persistent memory should use direct access for write map and
indirect for read map.
Change-Id: I9fc84836d60088b24012ed25f7ef8c16e33796a3
[ROCm/clr commit: c8b3253a24]
David Yat Sin
Cole Ramos
Rakesh Roy
Giovanni Lenzi Baraldi
Ioannis Assiouras
Anusha GodavarthySurya
Ranjith Ramakrishnan
gobhardw
Rupam Chetia
taosang2
German Andryeyev
Jonathan R. Madsen
Xiaogang Chen
kjayapra-amd
Rahul Manocha
Rahul Garg