AI/rocm-systems
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
37,726 Commits 3 Branches 0 Tags
6150a119a4ed018c85a17c1945540b6116a1bae6
Commit Graph

37726 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Madsen, Jonathan e503b1f4cc SDK: remove majority of exceptions (#176) 
* SDK: remove majority of exceptions

- replace with ROCP_FATAL, ROCP_CI_LOG(WARNING), etc.
- improve logging of symbolic link
- add --readlink and --realpath (hidden options) to rocprofv3 to follow symlinks for preloaded libraries

* Add rocprofv3 --rocm-root argument

* Fix registration resolved_exists

* Fix rocprofv3_avail.py

* Update logging for rocprofiler_configure search

- relax failure conditions

* Misc clang-tidy fixes

* Fix merge

* Fix merge

---------

Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com>
Co-authored-by: Bhardwaj, Gopesh <Gopesh.Bhardwaj@amd.com>

[ROCm/rocprofiler-sdk commit: 470f347e50]
 2025-02-18 10:44:37 -06:00
Madsen, Jonathan 470f347e50 SDK: remove majority of exceptions (#176) 
* SDK: remove majority of exceptions

- replace with ROCP_FATAL, ROCP_CI_LOG(WARNING), etc.
- improve logging of symbolic link
- add --readlink and --realpath (hidden options) to rocprofv3 to follow symlinks for preloaded libraries

* Add rocprofv3 --rocm-root argument

* Fix registration resolved_exists

* Fix rocprofv3_avail.py

* Update logging for rocprofiler_configure search

- relax failure conditions

* Misc clang-tidy fixes

* Fix merge

* Fix merge

---------

Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com>
Co-authored-by: Bhardwaj, Gopesh <Gopesh.Bhardwaj@amd.com>
 2025-02-18 10:44:37 -06:00
Tim Gu 84a867fb73 SWDEV-502248 - Parse file path with space characters 
Signed-off-by: Tim Gu <Tim.Gu@amd.com>
Change-Id: I67fb9cf5559c9c06f24627a1b25fec3e89b2d1cf
 2025-02-18 10:31:21 -05:00
agunashe ea804e16f8 SWDEV-507967 - Deprecate gfx9, gfx8, gfx7 on Windows 
PAL_CLIENT_INTERFACE_MAJOR_VERSION from 872 --> 910

Change-Id: I03dfa2924ccdae4c2f13f09d5f34ee58298e1343
 2025-02-17 02:59:41 -05:00
Longlong Yao 26f001d3cb libhsakmt: allocate va in host path 
Change-Id: I40a4395aca99ea8dfd8ff0ecde64eb2c3840d867
Signed-off-by: Longlong Yao <Longlong.Yao@amd.com>
 2025-02-15 07:56:45 -05:00
ywang103-amd daf72ade4f fix missing parameter of spatial multiplexing for create_df_pmc (#567) 
[ROCm/rocprofiler-compute commit: b9fc44992a]
 2025-02-14 14:23:16 -05:00
ywang103-amd b9fc44992a fix missing parameter of spatial multiplexing for create_df_pmc (#567) 2025-02-14 14:23:16 -05:00
Anusha GodavarthySurya 199e464402 SWDEV-469422 - hipgraph remove static typecast to parent 
Change-Id: I339250cfd26a7c04543722a82301acbb41c7d5d7
 2025-02-14 11:09:32 -05:00
Adel Johar b4f8b5c202 Docs: Update environment variables page 2025-02-14 10:15:20 -05:00
Anusha GodavarthySurya 48989fbfc6 SWDEV-508023 - Disable hipDeviceGetGraphMemAttribute_Positive_DoubleMemory Linux psdb failure 
Change-Id: Iacfdc1bc13e8da2f5df8750bb315a37d33cea666
 2025-02-14 00:27:08 -05:00
Fei Zheng c6bb033e8b Update changelog 
[ROCm/rocprofiler-compute commit: 8c3895e1d1]
 2025-02-13 18:05:49 -07:00
Fei Zheng 8c3895e1d1 Update changelog 2025-02-13 18:05:49 -07:00
Welton, Benjamin 95ac740f25 Fix install for conversion-script (#211) 
[ROCm/rocprofiler-sdk commit: fd99654433]
 2025-02-13 19:00:20 -06:00
Welton, Benjamin fd99654433 Fix install for conversion-script (#211) 2025-02-13 19:00:20 -06:00
ywang103-amd 952b675890 Spatial multiplexing: part2, analysis (#542) 
Co-authored-by: Yang Wang <ywang103@amd.com>


[ROCm/rocprofiler-compute commit: 808a9a79ed]
 2025-02-13 15:38:59 -08:00
ywang103-amd 808a9a79ed Spatial multiplexing: part2, analysis (#542) 
Co-authored-by: Yang Wang <ywang103@amd.com>
 2025-02-13 15:38:59 -08:00
Peter Park a36e280903 Fix links in docs (#564) 
[ROCm/rocprofiler-compute commit: 9643afa62d]
 2025-02-13 16:24:48 -05:00
Peter Park 9643afa62d Fix links in docs (#564) 2025-02-13 16:24:48 -05:00
Bhardwaj, Gopesh 1fcb951d0e swdev-515336: removing deprecated features from documentation (#12) 2025-02-13 13:04:29 -06:00
Bhardwaj, Gopesh 11888f953a swdev-515336: removing deprecated features from documentation (#12) 
[ROCm/rocprofiler commit: 1fcb951d0e]
 2025-02-13 13:04:29 -06:00
Elwazir, Ammar a28b3b6d19 Lowering log level for COMGR logs (#210) 
* Lowering log level for COMGR logs

* Format Fix

[ROCm/rocprofiler-sdk commit: 376c2a96ad]
 2025-02-13 12:59:29 -06:00
Elwazir, Ammar 376c2a96ad Lowering log level for COMGR logs (#210) 
* Lowering log level for COMGR logs

* Format Fix
 2025-02-13 12:59:29 -06:00
Bhardwaj, Gopesh e3b2d94005 Adding CodeQL Analysis Workflow (#172) 
* adding codeql.yml

* update codeql

* update codeql

* excluding external repos

* filter external

* filter external  and build

* Apply suggestions from code review

* Removed experimental test line

* Adding config

* moving codeql config out of workflows

* Disable Cdash

* update codeql

* replacing run-ci with simple cmake build

* cmake fix

* removing codeql_config

* Adding rule for python and actions

---------

Co-authored-by: Madsen, Jonathan <Jonathan.Madsen@amd.com>

[ROCm/rocprofiler-sdk commit: 215875de32]
 2025-02-13 12:55:44 -06:00
Bhardwaj, Gopesh 215875de32 Adding CodeQL Analysis Workflow (#172) 
* adding codeql.yml

* update codeql

* update codeql

* excluding external repos

* filter external

* filter external  and build

* Apply suggestions from code review

* Removed experimental test line

* Adding config

* moving codeql config out of workflows

* Disable Cdash

* update codeql

* replacing run-ci with simple cmake build

* cmake fix

* removing codeql_config

* Adding rule for python and actions

---------

Co-authored-by: Madsen, Jonathan <Jonathan.Madsen@amd.com>
 2025-02-13 12:55:44 -06:00
Jaydeep Patel 28e93a178f SWDEV-511125 - Don't use device# as it varies BlockDim & GridDim. 
Change-Id: I3ddd0fc616c28adc2d35e64550bac4ca1c09bd6a
 2025-02-13 13:40:03 -05:00
Madsen, Jonathan fba0d6ba76 SWDEV-514449: Fix missing thread pre/post callbacks (#204) 
* SWDEV-514449: Fix missing thread pre/post callbacks

- invoke pre/post-callback around internal thread creation

* Update changelog

---------

Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com>

[ROCm/rocprofiler-sdk commit: 0d7ca72d84]
 2025-02-13 12:39:10 -06:00
Madsen, Jonathan 0d7ca72d84 SWDEV-514449: Fix missing thread pre/post callbacks (#204) 
* SWDEV-514449: Fix missing thread pre/post callbacks

- invoke pre/post-callback around internal thread creation

* Update changelog

---------

Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com>
 2025-02-13 12:39:10 -06:00
Tao Sang 8ea926725b SWDEV-503359 - Fix Unit_hipExtMallocWithFlags_CoherentTst 
Fix Unit_hipExtMallocWithFlags_CoherentTst hang on device fine
grain access memory because host builtin atomic functions malfunctions
on it.
Fix SWDEV-507938 also.
Change-Id: Ie26dbf6b7e5aa8cb898d11ae5ed5ecf1267c3228
 2025-02-13 13:37:36 -05:00
Marko Arandjelovic cddb658314 SWDEV-504084 - Added multidevice testcases for hipModuleGetFunction/Global 
Change-Id: I53d6d63f93c800efa2ec0ff2be5ae593756549e0
 2025-02-13 12:52:35 -05:00
Rahul Manocha fc270bc90c SWDEV-503246 - Fix atomic memory order test hangs for AGENT scope 
1) Cannot assume that blockIdx.x = 0 and threadIdx.x = 0 will be
run first in TestKernel. Initialize flags outside kernels.
2) use __hip_atomic_store in device code and __atomic_store_n for host.

Change-Id: If4e9274d2c16af55b53a626c3ba2fb0db7052d4b
 2025-02-13 12:40:28 -05:00
David Salinas c942833b34 Deprecate roc-obj* tooling 
- make Perl packages RECOMENDS/SUGGESTS for hip-dev
  - update CHANGE log

  SWDEV-511528 - TECH Remove ROCM Perl dependency - hip-dev
  SWDEV-333176 - Shift functionality of 'roc-obj-*' perl scripts into llvm-objdump

Change-Id: Iec3ba245848781f95c825f0d37aff4b4fb54f5e4
 2025-02-13 11:42:57 -05:00
Vladana Stojiljkovic 061c5d877f SWDEV-510059 - Format CU mask properly 
Change-Id: I80e94b4f3ea25f6988fc06d83aeb398e81ccddd1
 2025-02-13 11:02:56 -05:00
Bhardwaj, Gopesh b8033b785f SWDEV-514046 documentation build fix (#208) 
[ROCm/rocprofiler-sdk commit: 848242eb5c]
 2025-02-13 09:25:30 -06:00
Bhardwaj, Gopesh 848242eb5c SWDEV-514046 documentation build fix (#208) 2025-02-13 09:25:30 -06:00
Welton, Benjamin 4d43482e3b Update VERSION (#207) 
* Update VERSION

Update version to 0.7.0

* Fixing test install build step issue

* Updates from editor

---------

Co-authored-by: Ammar ELWazir <Ammar.ELWazir@amd.com>

[ROCm/rocprofiler-sdk commit: 27c4277222]
 2025-02-13 08:51:10 -06:00
Welton, Benjamin 27c4277222 Update VERSION (#207) 
* Update VERSION

Update version to 0.7.0

* Fixing test install build step issue

* Updates from editor

---------

Co-authored-by: Ammar ELWazir <Ammar.ELWazir@amd.com>
 2025-02-13 08:51:10 -06:00
harkgill-amd 935b538261 Specify C++ language mode for warning post amdgpu-arch failure 
Change-Id: I55bf6734a1e8dc06dd0a1ee12086b7667332206f
 2025-02-13 09:40:13 -05:00
Aidan Belton-Schure 179801a750 SWDEV-508279 - Improve HIP event profiling 
There are 2 functional changes to this patch:
* Use GPU timing for internal markers for HIP.
* Measure CPU time closer to GPU timer, to reduce delta between GPU/CPU timestamp measurements.

There are some smaller non-functional updates:
* waifForFence -> waitForFence typo
* Remove unused drmProfiling

Change-Id: I4c5fa600a842ab60e454888779edcac8449a902a
 2025-02-13 04:15:40 -05:00
David Galiffi c1479bb70b Add note to documentation about Perfetto workaround (#103) 
Users viewing the "latest" documentation may still be using a version of omnitrace / rocprofiler-systems prior to 6.3.1. Re-add this warning so it is easier to find a workaround.

[ROCm/rocprofiler-systems commit: 349c7d3de6]
 2025-02-12 21:16:00 -05:00
David Galiffi 349c7d3de6 Add note to documentation about Perfetto workaround (#103) 
Users viewing the "latest" documentation may still be using a version of omnitrace / rocprofiler-systems prior to 6.3.1. Re-add this warning so it is easier to find a workaround.
 2025-02-12 21:16:00 -05:00
Jakaraddi, Manjunath 0608bbb4db SWDEV-499989: Conversion Script to change counter collection output format from v3 to v1 (#107) 
* SWDEV-499989: Add script to convert rocprofv3 counter collection output format to that of v1

* Add logging and argparsing

* Dropping duplicated counters in pmc multiple lines

* Adding test for conversion

* moving conversion script to test files

* copy conversion script from scripts folder

[ROCm/rocprofiler-sdk commit: c77596b703]
 2025-02-12 11:31:17 -08:00
Jakaraddi, Manjunath c77596b703 SWDEV-499989: Conversion Script to change counter collection output format from v3 to v1 (#107) 
* SWDEV-499989: Add script to convert rocprofv3 counter collection output format to that of v1

* Add logging and argparsing

* Dropping duplicated counters in pmc multiple lines

* Adding test for conversion

* moving conversion script to test files

* copy conversion script from scripts folder
 2025-02-12 11:31:17 -08:00
Trowbridge, Ian 3a26de9e53 Memory Allocation Counter Track Shows Total Allocation (#71) 
* Counter track for memory allocation is now a running sum showing total allocation

* Address review comments

* Update source/lib/output/generatePerfetto.cpp

Co-authored-by: Meserve, Mark <Mark.Meserve@amd.com>

* Updated to reflect review comments

* Fix compilation errors on CI

* remove braces on scalar

* Fix struct compilation issues

* Removed name_to_id for sanitizer

---------

Co-authored-by: Meserve, Mark <Mark.Meserve@amd.com>

[ROCm/rocprofiler-sdk commit: cc0c401615]
 2025-02-12 12:59:53 -06:00
Trowbridge, Ian cc0c401615 Memory Allocation Counter Track Shows Total Allocation (#71) 
* Counter track for memory allocation is now a running sum showing total allocation

* Address review comments

* Update source/lib/output/generatePerfetto.cpp

Co-authored-by: Meserve, Mark <Mark.Meserve@amd.com>

* Updated to reflect review comments

* Fix compilation errors on CI

* remove braces on scalar

* Fix struct compilation issues

* Removed name_to_id for sanitizer

---------

Co-authored-by: Meserve, Mark <Mark.Meserve@amd.com>
 2025-02-12 12:59:53 -06:00
Nagaraj, Sriraksha 547ce227c3 target cu to string input (#198) 
* target cu to string input

* review comments

* review comments

[ROCm/rocprofiler-sdk commit: 5d0b220c37]
 2025-02-12 12:51:39 -06:00
Nagaraj, Sriraksha 5d0b220c37 target cu to string input (#198) 
* target cu to string input

* review comments

* review comments
 2025-02-12 12:51:39 -06:00
Kandula, Venkateshwar reddy 7fde16067f Accum_vgpr support in Rocprofv3 (#70) 
* output accumulate vgpr count

* fix logic for computing accum_vgpr

* add accum_vgpr to csv.

* accumulation vgpr's docs and support for rocprofv3

* CHANGELOG.md

---------

Co-authored-by: Madsen, Jonathan <Jonathan.Madsen@amd.com>
Co-authored-by: Elwazir, Ammar <Ammar.Elwazir@amd.com>

[ROCm/rocprofiler-sdk commit: 6427fbafc2]
 2025-02-12 10:47:46 -08:00
Kandula, Venkateshwar reddy 6427fbafc2 Accum_vgpr support in Rocprofv3 (#70) 
* output accumulate vgpr count

* fix logic for computing accum_vgpr

* add accum_vgpr to csv.

* accumulation vgpr's docs and support for rocprofv3

* CHANGELOG.md

---------

Co-authored-by: Madsen, Jonathan <Jonathan.Madsen@amd.com>
Co-authored-by: Elwazir, Ammar <Ammar.Elwazir@amd.com>
 2025-02-12 10:47:46 -08:00
Jatin Chaudhary c23913f6e7 SWDEV-474146 - use __bf16 to do operations 
Change-Id: I568dfa97238fd760f5362a8e560c33402f96cff3
 2025-02-12 07:03:05 -05:00
Jatin Chaudhary e560d94d2c SWDEV-504769 - Allow hipEvent_t to record on hipStreamLegacy 
Change-Id: Ib86412255adad172598620ea81214e5eb56020ea
 2025-02-12 07:02:35 -05:00