* use correct MPI initialization method
rocSHMEM requires that the MPI library is initialized using
THREAD_MULTIPLE support. Lets use that function therefore in our
examples.
* Update examples/rocshmem_init_attr_test.cc
Co-authored-by: Aurelien Bouteiller <Aurelien.bouteiller@gmail.com>
---------
Co-authored-by: Aurelien Bouteiller <Aurelien.bouteiller@gmail.com>
[ROCm/rocshmem commit: 2e01af22ca]
* use correct MPI initialization method
rocSHMEM requires that the MPI library is initialized using
THREAD_MULTIPLE support. Lets use that function therefore in our
examples.
* Update examples/rocshmem_init_attr_test.cc
Co-authored-by: Aurelien Bouteiller <Aurelien.bouteiller@gmail.com>
---------
Co-authored-by: Aurelien Bouteiller <Aurelien.bouteiller@gmail.com>
`pthread.h` is included in `src/common.h` but lib is not properly
linked, resulting in the build failing with unresolved symbols when
trying to link.
[ROCm/rccl-tests commit: 5b27b961b2]
* * Decoder utility: Removed a couple of incorrect asserts. Changed other asserts to error messages.
* * Changed rocDecode version from 0.12.0 to 0.13.0. Updated change log.
* * Decoder utility: Updated change log based on review comments.
* * Decoder utility: Minor format change based on review: removed the extra space.
[ROCm/rocdecode commit: 4b10fa5a1a]
* * Decoder utility: Removed a couple of incorrect asserts. Changed other asserts to error messages.
* * Changed rocDecode version from 0.12.0 to 0.13.0. Updated change log.
* * Decoder utility: Updated change log based on review comments.
* * Decoder utility: Minor format change based on review: removed the extra space.
* SWDEV-520352 - Remove HostThread and legacy monitor
Remove HostThread, semaphore and legacy monitor.
Make original logics of thread and command queue stricker.
Add more comments to make logics clearer.
Some other minor improvement.
Also part of SWDEV-458943.
[ROCm/clr commit: 96cadbc9e9]
* SWDEV-520352 - Remove HostThread and legacy monitor
Remove HostThread, semaphore and legacy monitor.
Make original logics of thread and command queue stricker.
Add more comments to make logics clearer.
Some other minor improvement.
Also part of SWDEV-458943.
* unify handling of env variables
create a class containing all (most?) environment variables used by rocshmem and an object that is instatiated
before library_init, since some of the environment variables need to be
set before we start the bootstraping process.
This allows us to remove two files from the bootstrap directory.
* replace INFO and TRACE macros with DPRINTF
to be more consistent with the rest of the rocSHMEM code
[ROCm/rocshmem commit: db74307195]
* unify handling of env variables
create a class containing all (most?) environment variables used by rocshmem and an object that is instatiated
before library_init, since some of the environment variables need to be
set before we start the bootstraping process.
This allows us to remove two files from the bootstrap directory.
* replace INFO and TRACE macros with DPRINTF
to be more consistent with the rest of the rocSHMEM code
Rework of roofline binaries generated from rocm-amdgpu-bench
- removed arch identifier in bin name
- removed rocm5 bins altogether
Updated required distros for roofline
- updated distro checks and bin naming
- moved up ubuntu20.04->22.04 and sles15.3->15.6 per rocm support
Enabled ctests for mi350 for test_roof_*
- removed mi350 series check to skip these specific tests
---------
Signed-off-by: Carrie Fallows <Carrie.Fallows@amd.com>
[ROCm/rocprofiler-compute commit: 41e73650d5]
Rework of roofline binaries generated from rocm-amdgpu-bench
- removed arch identifier in bin name
- removed rocm5 bins altogether
Updated required distros for roofline
- updated distro checks and bin naming
- moved up ubuntu20.04->22.04 and sles15.3->15.6 per rocm support
Enabled ctests for mi350 for test_roof_*
- removed mi350 series check to skip these specific tests
---------
Signed-off-by: Carrie Fallows <Carrie.Fallows@amd.com>
Add rp-compute technical writer directly for any documentation review.
Remove existing packaging review requests for single user; every repo owner should be notified.
---------
Signed-off-by: Carrie Fallows <Carrie.Fallows@amd.com>
[ROCm/rocprofiler-compute commit: ad17c4d587]
Add rp-compute technical writer directly for any documentation review.
Remove existing packaging review requests for single user; every repo owner should be notified.
---------
Signed-off-by: Carrie Fallows <Carrie.Fallows@amd.com>
The 'amd-smi metric --clock' was listing values with N/A. Filtered these outputs to show only available values.
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
The 'amd-smi metric --clock' was listing values with N/A. Filtered these outputs to show only available values.
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
[ROCm/amdsmi commit: 797e4fba07]
* Add test for 9fx942 number of xcds.
* Improve the structure of mi gpu specs, add num_xcds_spec_class test.
* Add to ctest.
---------
Signed-off-by: xuchen-amd <xuchen@amd.com>
[ROCm/rocprofiler-compute commit: 85bfa73e2c]
* Add test for 9fx942 number of xcds.
* Improve the structure of mi gpu specs, add num_xcds_spec_class test.
* Add to ctest.
---------
Signed-off-by: xuchen-amd <xuchen@amd.com>
Edgar Gabriel
Marius Brehler
jeffqjiangNew
Cheruvally, Aravindan
Godavarthy Surya, Anusha
GunaShekar, Ajay
Jiang, Julia
Guan, Zichuan
Sang, Tao
Nilesh M Negi
Jayaprakash, Karthik
Betigeri, Sourabh
cfallows-amd
Yiltan
Daniel Su
Kanangot Balakrishnan, Bindhiya
Pryor, Adam
Maisam Arif
xuchen-amd
Rahul Vaidya