* SWDEV-518831 - fix streams' sync issue in mthreads
1. Fix sync issue of null stream and non-null streams in
multithreads.
2. Remove assert(GetSubmissionBatch() == nullptr) as it
is invalid in multithreads.
3. Update getActiveQueues() to deal with the state of
being terminated.
[ROCm/clr commit: 27aad09bd4]
* SWDEV-518831 - fix streams' sync issue in mthreads
1. Fix sync issue of null stream and non-null streams in
multithreads.
2. Remove assert(GetSubmissionBatch() == nullptr) as it
is invalid in multithreads.
3. Update getActiveQueues() to deal with the state of
being terminated.
Fix monitor hang in cts integer_ops.
Improve notify().
Won't affect notifyAll() and Hip in direct
dispatch mode.
Change-Id: I95a458358e1cab9c76aefde117db09cdbd1fd3af
[ROCm/clr commit: 78f92901d8]
Fix monitor hang in cts integer_ops.
Improve notify().
Won't affect notifyAll() and Hip in direct
dispatch mode.
Change-Id: I95a458358e1cab9c76aefde117db09cdbd1fd3af
Show and log what the functional test driver is running
* Log errors in the log file
* list all failed tests at the end
* pretty colors :x
* Print stderr when the test has failed
---------
Signed-off-by: Aurelien Bouteiller <aurelien.bouteiller@amd.com>
[ROCm/rocshmem commit: 67bc5b9e5a]
Show and log what the functional test driver is running
* Log errors in the log file
* list all failed tests at the end
* pretty colors :x
* Print stderr when the test has failed
---------
Signed-off-by: Aurelien Bouteiller <aurelien.bouteiller@amd.com>
Earlier, the amd-smi metric and static json output
was not in valid json format. Changes are done to
get the output in valid json format.
---------
Change-Id: I5576333269509f63b3c800f225c3d73127ce80cf
Signed-off-by: Bindhiya Kanangot Balakrishnan <Bindhiya.KanangotBalakrishnan@amd.com>
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Co-authored-by: Maisam Arif <Maisam.Arif@amd.com>
Earlier, the amd-smi metric and static json output
was not in valid json format. Changes are done to
get the output in valid json format.
---------
Change-Id: I5576333269509f63b3c800f225c3d73127ce80cf
Signed-off-by: Bindhiya Kanangot Balakrishnan <Bindhiya.KanangotBalakrishnan@amd.com>
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Co-authored-by: Maisam Arif <Maisam.Arif@amd.com>
[ROCm/amdsmi commit: 8e5f6b1a8d]
* Small Fixes
* CLI Help text and parser formatting updates
* Changed metavar for set partition
---------
Change-Id: Ia8809665f6fac670452cd4db4e5e8f9c7270faba
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Signed-off-by: Pham, Gabriel <Gabriel.Pham@amd.com>
Co-authored-by: Pham, Gabriel <Gabriel.Pham@amd.com>
* Small Fixes
* CLI Help text and parser formatting updates
* Changed metavar for set partition
---------
Change-Id: Ia8809665f6fac670452cd4db4e5e8f9c7270faba
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Signed-off-by: Pham, Gabriel <Gabriel.Pham@amd.com>
Co-authored-by: Pham, Gabriel <Gabriel.Pham@amd.com>
[ROCm/amdsmi commit: 53dbb7bf58]
* Reduced Load times for CLI in partition mode
* Change rsmi_dev_id_get() to use KFD, if KGD interface does not exist
* Make gpu_device_uuid fallback to rsmi_wrapper
* Moved Enumeration info calls in list for more speed
* Moved made group check excluded from recursion
---------
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
Co-authored-by: Charis Poag <Charis.Poag@amd.com>
Co-authored-by: gabrpham_amdeng <Gabriel.Pham@amd.com>
* Reduced Load times for CLI in partition mode
* Change rsmi_dev_id_get() to use KFD, if KGD interface does not exist
* Make gpu_device_uuid fallback to rsmi_wrapper
* Moved Enumeration info calls in list for more speed
* Moved made group check excluded from recursion
---------
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
Co-authored-by: Charis Poag <Charis.Poag@amd.com>
Co-authored-by: gabrpham_amdeng <Gabriel.Pham@amd.com>
[ROCm/amdsmi commit: 63b13ecb05]
Changes:
- Unique Id tries reading from KGD
-> falls back to use KFD if not found
Change-Id: I8fb8f38df5db7413805f4a20621ad12ed3fc89a3
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
[ROCm/rocm_smi_lib commit: 4276207ff8]
Changes:
- Unique Id tries reading from KGD
-> falls back to use KFD if not found
Change-Id: I8fb8f38df5db7413805f4a20621ad12ed3fc89a3
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
Changes:
- Unique Id tries reading from KGD
-> falls back to use KFD if not found
Change-Id: I05456dd79715e04d83f118b5bb4f1d3612822173
---------
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
Signed-off-by: Arif, Maisam <Maisam.Arif@amd.com>
Changes:
- Unique Id tries reading from KGD
-> falls back to use KFD if not found
Change-Id: I05456dd79715e04d83f118b5bb4f1d3612822173
---------
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
Signed-off-by: Arif, Maisam <Maisam.Arif@amd.com>
[ROCm/amdsmi commit: b58625cafa]
Minimize the performance impact of the device kernel profiling support when
the profiler plugin is not loaded.
Reduce the overheads of CUDA graph capturing, which increased in NCCL
2.26.2 for large graphs.
Fix the exchange of enhanced connection establishment (ECE) options to
address potential slowdowns on networks utilizing RoCE.
Test if cuMem host allocations work and if not, disable them. Enabled by
default since NCCL 2.24 if the CUDA driver version is at least 12.6, such
allocations rely on NUMA support, which is by default not available under
Docker. We recommend invoking Docker with "--cap-add SYS_NICE" to enable
it.
Fix an initialization error when running with NCCL_NET_GDR_C2C=1 on
multiple MNNVL domains with non-uniform network configurations across
nodes.
Fix the printing of sub-seconds in the debug log when using a custom
NCCL_DEBUG_TIMESTAMP_FORMAT setting.
[ROCm/rccl commit: 0524aef7a0]
Minimize the performance impact of the device kernel profiling support when
the profiler plugin is not loaded.
Reduce the overheads of CUDA graph capturing, which increased in NCCL
2.26.2 for large graphs.
Fix the exchange of enhanced connection establishment (ECE) options to
address potential slowdowns on networks utilizing RoCE.
Test if cuMem host allocations work and if not, disable them. Enabled by
default since NCCL 2.24 if the CUDA driver version is at least 12.6, such
allocations rely on NUMA support, which is by default not available under
Docker. We recommend invoking Docker with "--cap-add SYS_NICE" to enable
it.
Fix an initialization error when running with NCCL_NET_GDR_C2C=1 on
multiple MNNVL domains with non-uniform network configurations across
nodes.
Fix the printing of sub-seconds in the debug log when using a custom
NCCL_DEBUG_TIMESTAMP_FORMAT setting.
- Add a new AMD extension API to return preferred SDMA engine mask.
This can use used in conjunction with copy_on_engine API to get
optimal bandwidth.
[ROCm/ROCR-Runtime commit: 57c0c643ce]
Tim
Sang, Tao
Jeffrey Novotny
Xie, Jiabao(Jimbo)
Aurelien Bouteiller
Kanangot Balakrishnan, Bindhiya
Arif, Maisam
AL Musaffar, Yazen
Hila, Nino
Choudhary, Rahul
xuchen-amd
Poag, Charis
Kamil Iskra
Saleel Kudchadker
cfallows-amd