39bddd8b9d
rocr: support reserving non-registered VA
...
Extend hsa_amd_vmem_address_reserve/hsa_amd_vmem_address_reserve_align
to support HSA_AMD_VMEM_ADDRESS_NO_REGISTER flag. This allocation can be
used to reserve virtual address ranges that can later be used by
hsa_amd_svm_attributes_set for SVM based memory allocations.
[ROCm/ROCR-Runtime commit: b3c48cc68c
2025-06-18 18:21:11 -04:00
979c59fadc
added progress printout in rocprof-compute profile ( #727 )
...
* added progress printout for profiler
* added comments and fixed readability
* removed redundant newlines
* moved format_time helper function to utils
* removed tqdm and redundant time calc
[ROCm/rocprofiler-compute commit: 036866fc12
2025-06-18 14:09:09 -04:00
036866fc12
added progress printout in rocprof-compute profile ( #727 )
...
* added progress printout for profiler
* added comments and fixed readability
* removed redundant newlines
* moved format_time helper function to utils
* removed tqdm and redundant time calc
2025-06-18 14:09:09 -04:00
9d50115bd7
Integrate roofline in tui ( #762 )
...
* Update changelog, remove unused code.
* enable roofline in TUI.
* Remove roofline section when data not available.
* Fix workload dir path.
[ROCm/rocprofiler-compute commit: 5d8fd55e36
2025-06-18 13:58:42 -04:00
5d8fd55e36
Integrate roofline in tui ( #762 )
...
* Update changelog, remove unused code.
* enable roofline in TUI.
* Remove roofline section when data not available.
* Fix workload dir path.
2025-06-18 13:58:42 -04:00
3ea7eedf3b
NCCL 2.27.5-1
...
Improvements for GB200 systems
* Optimize the network performance by alternating the direction of the
rings and the NIC to GPU assignment across communicators to limit
unnecessary sharing.
* Fix the detection of C2C links in case GPU Direct RDMA is disabled
between a GPU and a NIC.
* Fix PXN support on MNNVL systems, where NCCL would try (and fail) to
share regular host memory across multiple nodes.
* Fix P2C (PXN over C2C), which is now preferred over regular PXN. This
support is currently preliminary and is disabled by default; use
NCCL_PXN_C2C=1 to enable.
Further reduce the overheads of CUDA graph capturing, which increased in
NCCL 2.26.2 for large graphs.
Optimize the network performance on DGX B200 systems by adjusting the
bandwidths provided to the graph search algorithm.
Enable fp8 reductions in symmetric kernels on Blackwell with CUDA 12.8.
Restore the plugin name handling logic to make it possible to specify a
path to the plugin (Issue #1732 ).
Restore the ability to change NCCL_COLLNET_ENABLE during execution
(Issue #1741 ).
Add an example tuner plugin with CSV-based overrides.
Remove an x86 dependency from the example profiler.
2025-06-18 10:34:47 -07:00
337cbeba6f
SWDEV-531400 - Remove File reorganization backward computability (roctracer) ( #40 )
...
* SWDEV-531400 - Remove File reorganization backward computability (roctracer)
* removing no longer needed files
---------
Co-authored-by: Jonathan Luu <jonatluu@amd.com >
[ROCm/roctracer commit: 9a620d64d9
2025-06-18 13:33:41 -04:00
9a620d64d9
SWDEV-531400 - Remove File reorganization backward computability (roctracer) ( #40 )
...
* SWDEV-531400 - Remove File reorganization backward computability (roctracer)
* removing no longer needed files
---------
Co-authored-by: Jonathan Luu <jonatluu@amd.com >
2025-06-18 13:33:41 -04:00
0b6e03adb0
CLI: enable roofline plot ( #760 )
...
* enable roofline plot in cli.
* Add roofline to analysis config.
* Unify global variables.
* Disable roofline for baseline comparison and gfx908.
* Add check for roofline.csv
[ROCm/rocprofiler-compute commit: 80159ee117
2025-06-18 13:19:58 -04:00
80159ee117
CLI: enable roofline plot ( #760 )
...
* enable roofline plot in cli.
* Add roofline to analysis config.
* Unify global variables.
* Disable roofline for baseline comparison and gfx908.
* Add check for roofline.csv
2025-06-18 13:19:58 -04:00
0f7ae37ca6
Broken link to ROCprofiler-SDK updated ( #254 )
...
[ROCm/rocprofiler-systems commit: 66e71574ba
2025-06-18 13:15:18 -04:00
66e71574ba
Broken link to ROCprofiler-SDK updated ( #254 )
2025-06-18 13:15:18 -04:00
f155355b33
Add thread header to videodecode example ( #252 )
...
[ROCm/rocprofiler-systems commit: 475d6c0f1f
2025-06-18 12:40:24 -04:00
475d6c0f1f
Add thread header to videodecode example ( #252 )
2025-06-18 12:40:24 -04:00
311f83e921
SWDEV-504756 - Prevent the modification of python interpreter directives ( #27 )
...
"/usr/bin/env python3" is getting converted to "/usr/libexec/platform-python" in RHEL8. Undefining __brp_mangle_shebangs will prevent the same
[ROCm/rocm-core commit: 0d7160da9a
2025-06-18 09:27:05 -07:00
0d7160da9a
SWDEV-504756 - Prevent the modification of python interpreter directives ( #27 )
...
"/usr/bin/env python3" is getting converted to "/usr/libexec/platform-python" in RHEL8. Undefining __brp_mangle_shebangs will prevent the same
2025-06-18 09:27:05 -07:00
5ed9fba9be
[SWDEV-538604] Sync Unified Header and AMDSMI Comments
...
Signed-off-by: josnarlo <Joseph.Narlo@amd.com >
2025-06-18 09:13:01 -05:00
ed9086505d
[SWDEV-538604] Sync Unified Header and AMDSMI Comments
...
Signed-off-by: josnarlo <Joseph.Narlo@amd.com >
[ROCm/amdsmi commit: 5ed9fba9be
2025-06-18 09:13:01 -05:00
615b904729
SWDEV-535738 - Properly define size_t for windows ( #481 )
...
[ROCm/clr commit: adda2602e1
2025-06-18 19:32:11 +05:30
adda2602e1
SWDEV-535738 - Properly define size_t for windows ( #481 )
2025-06-18 19:32:11 +05:30
0ea9dbf7a8
Adding doc links for trace decoder, aqlprofile and viewer ( #464 )
...
Adding interlinks for trace decoder, aqlprofile and viewer
Co-authored-by: Giovanni Baraldi <gbaraldi@amd.com >
Co-authored-by: Bhardwaj, Gopesh <Gopesh.Bhardwaj@amd.com >
[ROCm/rocprofiler-sdk commit: 9dadbbace5
2025-06-18 14:10:18 +02:00
9dadbbace5
Adding doc links for trace decoder, aqlprofile and viewer ( #464 )
...
Adding interlinks for trace decoder, aqlprofile and viewer
Co-authored-by: Giovanni Baraldi <gbaraldi@amd.com >
Co-authored-by: Bhardwaj, Gopesh <Gopesh.Bhardwaj@amd.com >
2025-06-18 14:10:18 +02:00
10abe4220a
SWDEV-537686 - Remove unmaintained text editor metadata ( #154 )
...
[ROCm/hip commit: 41f4f1c040
2025-06-18 13:13:35 +05:30
41f4f1c040
SWDEV-537686 - Remove unmaintained text editor metadata ( #154 )
2025-06-18 13:13:35 +05:30
24f36de037
rocr: Add missing close of dmabuf after import
2025-06-17 20:22:34 -04:00
14b5faf333
rocr: Add missing close of dmabuf after import
...
[ROCm/ROCR-Runtime commit: 24f36de037
2025-06-17 20:22:34 -04:00
ab985464ef
Add docker files for testing ( #761 )
...
[ROCm/rocprofiler-compute commit: b16256fd07
2025-06-17 16:18:35 -04:00
b16256fd07
Add docker files for testing ( #761 )
2025-06-17 16:18:35 -04:00
b9b44070c9
Create external PR Workflow ( #118 )
...
Create external-pr.yml
Update external-pr.yml
Update external-pr.yml
Update external-pr.yml
Update external-pr.yml
Separating Internal and External Workflows (#119 )
* Separating Internal and External Workflows
* Update continuous_integration.yml
Update external-pr.yml
Update external-pr.yml
Update external-pr.yml
Update external-pr.yml
Update external-pr.yml
Update external-pr.yml
Update external-pr.yml
Update external-pr.yml
Update external-pr.yml
Update external-pr.yml
Update external-pr.yml
Create external-pr-sync.yml (#121 )
* Create external-pr-sync.yml
* Update external-pr.yml
Update external-pr-sync.yml
Update external-pr-sync.yml
Update external-pr.yml
Update external-pr-sync.yml
Update external-pr-sync.yml
Update external-pr-sync.yml
Update external-pr.yml
Update external-pr.yml
Update external-pr-sync.yml
Update external-pr-sync.yml
Update external-pr-sync.yml
Update external-pr-sync.yml
Update external-pr-sync.yml
Create external-pr-close.yml
Fixing External PR Workflows
Fixing External PR Workflows
Fixing External PR Workflows
[ROCm/aqlprofile commit: 2f771e6107
2025-06-17 14:55:35 -05:00
2f771e6107
Create external PR Workflow ( #118 )
...
Create external-pr.yml
Update external-pr.yml
Update external-pr.yml
Update external-pr.yml
Update external-pr.yml
Separating Internal and External Workflows (#119 )
* Separating Internal and External Workflows
* Update continuous_integration.yml
Update external-pr.yml
Update external-pr.yml
Update external-pr.yml
Update external-pr.yml
Update external-pr.yml
Update external-pr.yml
Update external-pr.yml
Update external-pr.yml
Update external-pr.yml
Update external-pr.yml
Update external-pr.yml
Create external-pr-sync.yml (#121 )
* Create external-pr-sync.yml
* Update external-pr.yml
Update external-pr-sync.yml
Update external-pr-sync.yml
Update external-pr.yml
Update external-pr-sync.yml
Update external-pr-sync.yml
Update external-pr-sync.yml
Update external-pr.yml
Update external-pr.yml
Update external-pr-sync.yml
Update external-pr-sync.yml
Update external-pr-sync.yml
Update external-pr-sync.yml
Update external-pr-sync.yml
Create external-pr-close.yml
Fixing External PR Workflows
Fixing External PR Workflows
Fixing External PR Workflows
2025-06-17 14:55:35 -05:00
8de9854a62
[SDK] [CI] Update HSA EXT Step Version ( #460 )
...
Update HSA EXT step version
[ROCm/rocprofiler-sdk commit: 883a57ece7
2025-06-17 08:55:58 -07:00
883a57ece7
[SDK] [CI] Update HSA EXT Step Version ( #460 )
...
Update HSA EXT step version
2025-06-17 08:55:58 -07:00
191778f071
Add copyright disclaimer for new files ( #16 )
...
[ROCm/rocprofiler-register commit: 19fe192e8f
2025-06-17 10:34:21 -05:00
19fe192e8f
Add copyright disclaimer for new files ( #16 )
2025-06-17 10:34:21 -05:00
ca571e5d13
Add test target to the default build target ( #117 )
...
Signed-off-by: zichguan-amd <zichuan.guan@amd.com >
Co-authored-by: zichguan-amd <zichuan.guan@amd.com >
[ROCm/aqlprofile commit: 8dad9518dc
2025-06-17 10:13:37 -05:00
8dad9518dc
Add test target to the default build target ( #117 )
...
Signed-off-by: zichguan-amd <zichuan.guan@amd.com >
Co-authored-by: zichguan-amd <zichuan.guan@amd.com >
2025-06-17 10:13:37 -05:00
133834335d
Unhandled enum in switch statement ( #247 )
...
Signed-off-by: David Galiffi <David.Galiffi@amd.com >
[ROCm/rocprofiler-systems commit: 244c193a57
2025-06-17 09:57:27 -04:00
244c193a57
Unhandled enum in switch statement ( #247 )
...
Signed-off-by: David Galiffi <David.Galiffi@amd.com >
2025-06-17 09:57:27 -04:00
4d79e1df30
[SDK] Support CMake option for using internal RCCL tracing + (temporary) enable in CI ( #457 )
...
* Temp: disable RCCL tracing
* Update continuous_integration.yml
* Update continuous_integration.yml
* Update continuous_integration.yml
* Adding option to disable rccl tracing from CMake
* Update codeql.yml
* Misc updates
- ROCPROFILER_BUILD_RCCL -> ROCPROFILER_INTERNAL_RCCL_API_TRACE
- env.EXTRA_TEMP_CMAKE_OPTIONS -> env.GLOBAL_CMAKE_OPTIONS
- add (advanced) option ROCPROFILER_INTERNAL_RCCL_API_TRACE
* Fix rocprofiler::sdk::get_enum_label
- missing enum labels for HIP_RUNTIME_API_TABLE_STEP_VERSION > 8
* Update tests/rocprofv3/advanced-thread-trace/CMakeLists.txt
- improve various aspect of cmake -- particularly echoing where attdecoder_LIBRARY was found
* Use CMAKE_MESSAGE_INDENT
- add prefix to cmake messages to help indicate where messages are coming from
- make find_package(Python3 ...) QUIET for bindings
* Fix rocprofiler::sdk::get_enum_label
- handle HSA_AMD_EXT_API_TABLE_MAJOR_VERSION
* Fix rocprofv3 message for att library path
* Fix tests/rocprofv3/advanced-thread-trace/att_input.yml config
* Fix rocprofv3 check_att_capability + soversion/version library resolution
- Account for ROCPROF_ATT_LIBRARY_PATH in env in check_att_capability
- Add resolve_library_path
- supports resolution of library names to SOVERSION and VERSION paths
* Fix python linting error (unused import)
---------
Co-authored-by: Ammar ELWazir <aelwazir@amd.com >
Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com >
[ROCm/rocprofiler-sdk commit: aeb1621c2b
2025-06-17 08:32:54 -05:00
aeb1621c2b
[SDK] Support CMake option for using internal RCCL tracing + (temporary) enable in CI ( #457 )
...
* Temp: disable RCCL tracing
* Update continuous_integration.yml
* Update continuous_integration.yml
* Update continuous_integration.yml
* Adding option to disable rccl tracing from CMake
* Update codeql.yml
* Misc updates
- ROCPROFILER_BUILD_RCCL -> ROCPROFILER_INTERNAL_RCCL_API_TRACE
- env.EXTRA_TEMP_CMAKE_OPTIONS -> env.GLOBAL_CMAKE_OPTIONS
- add (advanced) option ROCPROFILER_INTERNAL_RCCL_API_TRACE
* Fix rocprofiler::sdk::get_enum_label
- missing enum labels for HIP_RUNTIME_API_TABLE_STEP_VERSION > 8
* Update tests/rocprofv3/advanced-thread-trace/CMakeLists.txt
- improve various aspect of cmake -- particularly echoing where attdecoder_LIBRARY was found
* Use CMAKE_MESSAGE_INDENT
- add prefix to cmake messages to help indicate where messages are coming from
- make find_package(Python3 ...) QUIET for bindings
* Fix rocprofiler::sdk::get_enum_label
- handle HSA_AMD_EXT_API_TABLE_MAJOR_VERSION
* Fix rocprofv3 message for att library path
* Fix tests/rocprofv3/advanced-thread-trace/att_input.yml config
* Fix rocprofv3 check_att_capability + soversion/version library resolution
- Account for ROCPROF_ATT_LIBRARY_PATH in env in check_att_capability
- Add resolve_library_path
- supports resolution of library names to SOVERSION and VERSION paths
* Fix python linting error (unused import)
---------
Co-authored-by: Ammar ELWazir <aelwazir@amd.com >
Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com >
2025-06-17 08:32:54 -05:00
1f4084c7b5
Adding rocpd documenation ( #449 )
...
* Adding rocpd docuemenation
* rocpd format
* CHANGELOG update and indexing
* Fixing links
* format fixes
* fixing table
* major edits
* fixed logical error
* fixing rocprofv3 avail
[ROCm/rocprofiler-sdk commit: 3e43b1f019
2025-06-17 15:41:53 +05:30
3e43b1f019
Adding rocpd documenation ( #449 )
...
* Adding rocpd docuemenation
* rocpd format
* CHANGELOG update and indexing
* Fixing links
* format fixes
* fixing table
* major edits
* fixed logical error
* fixing rocprofv3 avail
2025-06-17 15:41:53 +05:30
d42c7875a6
SWDEV-123456 - add AI CodeQL workflows ( #558 )
...
[ROCm/clr commit: a2550e0a9e
2025-06-17 09:30:58 +02:00
a2550e0a9e
SWDEV-123456 - add AI CodeQL workflows ( #558 )
2025-06-17 09:30:58 +02:00
92a5d225d9
[MSCCLPP] Disable MSCCLPP Executor ( #1744 )
...
Signed-off-by: nileshnegi <Nilesh.Negi@amd.com >
2025-06-17 01:29:55 -05:00
649ec63a4f
rocrtst: Reduce host memory limit to 90%
...
Further reduce upper bound for rocrtstFunc.Memory_Max_Mem
as previous limit of 95% can still trigger OOM killer.
2025-06-16 21:02:20 -04:00
b0e43cc426
rocrtst: Reduce host memory limit to 90%
...
Further reduce upper bound for rocrtstFunc.Memory_Max_Mem
as previous limit of 95% can still trigger OOM killer.
[ROCm/ROCR-Runtime commit: 649ec63a4f
2025-06-16 21:02:20 -04:00
fa0422f174
generic net plugin ctxt that is extensible for use in multiple APIs ( #1735 )
...
Co-authored-by: Sarat Kamisetty <sakamiset@amd.com >
2025-06-16 14:48:08 -07:00
488cfd467c
rocr: Always send free scratch notifications
...
Always send notification to profiler tools when scratch memory is freed.
2025-06-16 17:39:33 -04:00
e3b013b208
rocr: Always send free scratch notifications
...
Always send notification to profiler tools when scratch memory is freed.
[ROCm/ROCR-Runtime commit: 488cfd467c
2025-06-16 17:39:33 -04:00
David Yat Sin
jamessiddeley-amd
xuchen-amd
Kamil Iskra
Luu, Jonathan
Pratik Basyal
Daniel Su
Ramakrishnan, Ranjith
josnarlo
Belton-Schure, Aidan
Baraldi, Giovanni
Brzak, Branislav
Chris Freehill
vedithal-amd
Elwazir, Ammar
Trowbridge, Ian
David Galiffi
Bhardwaj, Gopesh
Lytovchenko, Danylo
Nilesh M Negi
Sarat Kamisetty