AI/rocm-systems
2
0
Форкнуть 0
Код Задачи Запросы на слияние Действия Пакеты Проекты Релизы Вики Активность
74 713 коммитов 3 Ветки 0 Теги
fc4422d73bbe21d38d13fac621710e663eaec4c9
Граф коммитов

74713 Коммитов

This Branch
This Branch
Все ветки
Автор SHA1 Сообщение Дата
Galantsev, Dmitrii 059d015ea4 CMAKE - Add BUILD_INTERFACE include dirs for rdc_bootstrap 
Change-Id: I93df878b21e245277c7a8d9589102a15c2517f4f
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>
 2025-03-27 23:29:30 -05:00
Galantsev, Dmitrii 7ce869c8d6 CMAKE - Add BUILD_INTERFACE include dirs for rdc_bootstrap 
Change-Id: I93df878b21e245277c7a8d9589102a15c2517f4f
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>


[ROCm/rdc commit: 059d015ea4]
 2025-03-27 23:29:30 -05:00
Arif, Maisam 5e3b10bf8c [SWDEV-524147] Patch for handling new ras filenames (#34) 
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>

[ROCm/rocm_smi_lib commit: 847ac53444]
 2025-03-27 22:14:28 -05:00
Arif, Maisam 847ac53444 [SWDEV-524147] Patch for handling new ras filenames (#34) 
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
 2025-03-27 22:14:28 -05:00
Arif, Maisam a5707dfced [SWDEV-500518] Updated AMDSMI sanity checks (#209) 2025-03-27 21:58:09 -05:00
Arif, Maisam 2ce2d46609 [SWDEV-500518] Updated AMDSMI sanity checks (#209) 
[ROCm/amdsmi commit: a5707dfced]
 2025-03-27 21:58:09 -05:00
Galantsev, Dmitrii 51de344be7 Profiler - Add CPC and CPF metrics 
Change-Id: I27fd725e9e1868c9afe7624d6e4aafad2a42d47e
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>
 2025-03-27 19:01:23 -05:00
Galantsev, Dmitrii bfee4ae9ee Profiler - Add CPC and CPF metrics 
Change-Id: I27fd725e9e1868c9afe7624d6e4aafad2a42d47e
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>


[ROCm/rdc commit: 51de344be7]
 2025-03-27 19:01:23 -05:00
Justin Williams 4e3a197dcc [SWDEV-500518] Updated AMDSMI sanity checks 
Signed-off-by: Justin Williams <Justin.Williams@amd.com>
 2025-03-27 18:35:13 -05:00
Justin Williams 2914543174 [SWDEV-500518] Updated AMDSMI sanity checks 
Signed-off-by: Justin Williams <Justin.Williams@amd.com>


[ROCm/amdsmi commit: 4e3a197dcc]
 2025-03-27 18:35:13 -05:00
Nilesh M Negi 210f90ae0f [SRC] Enable unroll=1 for gfx950 (#1602) 
* [SRC] Enable unroll=1 for gfx950

* Fix typo from rebase in generate.py

* Support for unroll=1 and gfx90a when building for all GPU targets

---------

Signed-off-by: nileshnegi <Nilesh.Negi@amd.com>

[ROCm/rccl commit: 307bc10781]
 2025-03-27 18:21:35 -05:00
Nilesh M Negi 307bc10781 [SRC] Enable unroll=1 for gfx950 (#1602) 
* [SRC] Enable unroll=1 for gfx950

* Fix typo from rebase in generate.py

* Support for unroll=1 and gfx90a when building for all GPU targets

---------

Signed-off-by: nileshnegi <Nilesh.Negi@amd.com>
 2025-03-27 18:21:35 -05:00
ywang103-amd ad070d94db fix the wrong number of channels of TCC counters to put in pmc txt file (#633) 
[ROCm/rocprofiler-compute commit: 7c1f14123a]
 2025-03-27 18:15:41 -04:00
ywang103-amd 7c1f14123a fix the wrong number of channels of TCC counters to put in pmc txt file (#633) 2025-03-27 18:15:41 -04:00
Apurv Mishra 10530fa2a7 kfdtest: support for upstream kernel driver 
detect if the loaded driver is upstream or DKMS version and
add a filter for for the tests that fail in upstream driver

Signed-off-by: Apurv Mishra <Apurv.Mishra@amd.com>
 2025-03-27 16:55:21 -04:00
Apurv Mishra b490aec8e6 kfdtest: support for upstream kernel driver 
detect if the loaded driver is upstream or DKMS version and
add a filter for for the tests that fail in upstream driver

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


[ROCm/ROCR-Runtime commit: 10530fa2a7]
 2025-03-27 16:55:21 -04:00
Liu, Shuzhou (Bill) 9b6e0432b2 [SWDEV-524147] Patch for handling new ras filenames (#205) 
The code is changed to handle both original and ACA based ECC counters
for backward compatibilities.

Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Co-authored-by: Maisam Arif <Maisam.Arif@amd.com>
 2025-03-27 15:36:43 -05:00
Liu, Shuzhou (Bill) c3a0ec4f9a [SWDEV-524147] Patch for handling new ras filenames (#205) 
The code is changed to handle both original and ACA based ECC counters
for backward compatibilities.

Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Co-authored-by: Maisam Arif <Maisam.Arif@amd.com>

[ROCm/amdsmi commit: 9b6e0432b2]
 2025-03-27 15:36:43 -05:00
ywang103-amd 79a333231c fix ip block test by changing ways of extracting agent id (#639) 
[ROCm/rocprofiler-compute commit: cdb93b7a4c]
 2025-03-27 16:28:00 -04:00
ywang103-amd cdb93b7a4c fix ip block test by changing ways of extracting agent id (#639) 2025-03-27 16:28:00 -04:00
David Galiffi 70b456f2a3 Fix "ROCPROFSYS_USE_ROCM" runtime config setting. (#144) 
[ROCm/rocprofiler-systems commit: b6b39af011]
 2025-03-27 16:03:46 -04:00
David Galiffi b6b39af011 Fix "ROCPROFSYS_USE_ROCM" runtime config setting. (#144) 2025-03-27 16:03:46 -04:00
Pryor, Adam 47692d3ed5 [SWDEV-498711] RDC Partition Implementation (#119) 
* [SWDEV-498711] RDC Partition Implementation

Change-Id: Ibfc3709793770537e4c9d36458f34c6b4f461724
Signed-off-by: adapryor <Adam.pryor@amd.com>
 2025-03-27 14:10:11 -05:00
Pryor, Adam fe868f6763 [SWDEV-498711] RDC Partition Implementation (#119) 
* [SWDEV-498711] RDC Partition Implementation

Change-Id: Ibfc3709793770537e4c9d36458f34c6b4f461724
Signed-off-by: adapryor <Adam.pryor@amd.com>

[ROCm/rdc commit: 47692d3ed5]
 2025-03-27 14:10:11 -05:00
BertanDogancay 8ed27fde74 Merge remote-tracking branch 'nccl/master' into develop 
[ROCm/rccl commit: 0b2062c560]
 2025-03-27 12:53:04 -05:00
BertanDogancay 0b2062c560 Merge remote-tracking branch 'nccl/master' into develop 2025-03-27 12:53:04 -05:00
Yiannis Papadopoulos 0bd4acb5d4 rocr/aie: Returning error code if query not recognized 2025-03-27 13:15:13 -04:00
Yiannis Papadopoulos 2c731096c6 rocr/aie: Returning error code if query not recognized 
[ROCm/ROCR-Runtime commit: 0bd4acb5d4]
 2025-03-27 13:15:13 -04:00
Yiannis Papadopoulos e55503e7f8 rocr/aie: Bundling XDNA BOs and addresses, adding cleanup guard in case of error 2025-03-27 13:15:13 -04:00
Yiannis Papadopoulos c142b04fc1 rocr/aie: Bundling XDNA BOs and addresses, adding cleanup guard in case of error 
[ROCm/ROCR-Runtime commit: e55503e7f8]
 2025-03-27 13:15:13 -04:00
Yiannis Papadopoulos f4e1c9b0ba rocr/aie: Avoiding XdnaDriver class in queue API 2025-03-27 13:15:13 -04:00
Yiannis Papadopoulos 4c0e8b5f70 rocr/aie: Avoiding XdnaDriver class in queue API 
[ROCm/ROCR-Runtime commit: f4e1c9b0ba]
 2025-03-27 13:15:13 -04:00
Yiannis Papadopoulos 8dcbbf31c7 rocr/aie: Remove unused struct from HSA API 2025-03-27 13:15:13 -04:00
Yiannis Papadopoulos bd109ec288 rocr/aie: Remove unused struct from HSA API 
[ROCm/ROCR-Runtime commit: 8dcbbf31c7]
 2025-03-27 13:15:13 -04:00
Aleksandar Djordjevic 95503cde21 Disable RCCL, load libamdhip64.so (#150) 
Disable RCCL and load libamdhip64.so as a fix for sw509497.

[ROCm/rocprofiler-systems commit: 2bad0e941b]
 2025-03-27 16:02:17 +01:00
Aleksandar Djordjevic 2bad0e941b Disable RCCL, load libamdhip64.so (#150) 
Disable RCCL and load libamdhip64.so as a fix for sw509497.
 2025-03-27 16:02:17 +01:00
Sang, Tao d49a2a51d6 SWDEV-508863 - Support generic target in compressed fatbin (#44) 
[ROCm/clr commit: 8d90b44a1b]
 2025-03-27 20:13:51 +05:30
Sang, Tao 8d90b44a1b SWDEV-508863 - Support generic target in compressed fatbin (#44) 2025-03-27 20:13:51 +05:30
Yiannis Papadopoulos bf8ab493c4 rocr: Remove unused lambda 2025-03-27 10:33:40 -04:00
Yiannis Papadopoulos a11d693a47 rocr: Remove unused lambda 
[ROCm/ROCR-Runtime commit: bf8ab493c4]
 2025-03-27 10:33:40 -04:00
Yiannis Papadopoulos b066e0eefa rocr/aie: Resolve parentheses warning 2025-03-27 10:33:40 -04:00
Yiannis Papadopoulos 13723c6308 rocr/aie: Resolve parentheses warning 
[ROCm/ROCR-Runtime commit: b066e0eefa]
 2025-03-27 10:33:40 -04:00
vedithal-amd 04dbdc5c5d Inject SQ_ACCUM_PREV_HIRES for LEVEL counters only (#641) 
[ROCm/rocprofiler-compute commit: af76525baa]
 2025-03-27 10:24:21 -04:00
vedithal-amd af76525baa Inject SQ_ACCUM_PREV_HIRES for LEVEL counters only (#641) 2025-03-27 10:24:21 -04:00
Wileam Phan 25a3da829f Fix rocprof-sys-instrument default linkage and visibility criteria (#95) 
* Fix default linkage and visibility criteria
* Fix processing of linkage and visibility CLI flags
* Format source

Signed-off-by: Wileam Yonatan Phan <wileamyonatan.phan@amd.com>
Signed-off-by: David Galiffi <David.Galiffi@amd.com>
Co-authored-by: David Galiffi <David.Galiffi@amd.com>

[ROCm/rocprofiler-systems commit: 2805631ccd]
 2025-03-27 18:33:35 +08:00
Wileam Phan 2805631ccd Fix rocprof-sys-instrument default linkage and visibility criteria (#95) 
* Fix default linkage and visibility criteria
* Fix processing of linkage and visibility CLI flags
* Format source

Signed-off-by: Wileam Yonatan Phan <wileamyonatan.phan@amd.com>
Signed-off-by: David Galiffi <David.Galiffi@amd.com>
Co-authored-by: David Galiffi <David.Galiffi@amd.com>
 2025-03-27 18:33:35 +08:00
Bhardwaj, Gopesh d40b6e62b6 Deprecation message update (#320) 
* Deprecation message update

* Updated Support DL

[ROCm/rocprofiler-sdk commit: 633a32bad7]
 2025-03-27 12:29:34 +05:30
Bhardwaj, Gopesh 633a32bad7 Deprecation message update (#320) 
* Deprecation message update

* Updated Support DL
 2025-03-27 12:29:34 +05:30
Edgar Gabriel c7297b1d6b Performance tuning for inter-node communication (#66) 
This PR addresses two issues:
 - reduce the number of contexts supported by the host-interface by
   default to 1, we are not using those at the moment, and hence
   we now create fewer MPI_Win at the startup
 - introduces a micro-sleep in RO progress engine in case there are no
   pending requests. This leads significant performance improvements
   observed for inter-node communication with THor2 NICs.

[ROCm/rocshmem commit: 12561783de]
 2025-03-26 21:09:26 -05:00
Edgar Gabriel 12561783de Performance tuning for inter-node communication (#66) 
This PR addresses two issues:
 - reduce the number of contexts supported by the host-interface by
   default to 1, we are not using those at the moment, and hence
   we now create fewer MPI_Win at the startup
 - introduces a micro-sleep in RO progress engine in case there are no
   pending requests. This leads significant performance improvements
   observed for inter-node communication with THor2 NICs.
 2025-03-26 21:09:26 -05:00