Gráfico de commits

64521 Commits

Autor SHA1 Mensaje Fecha
Charis Poag 6a5e94c451 [SWDEV-504146] Fix Device Name
Changes: - Fixed Device Name (market name)
  - Added new API rsmi_dev_market_name_get()
  - Updated tests
  - Updated amdgpu_drm.h to match latest mainline kernel
  - Fixed subsystem ID to only show hex value (not subsystem name)
  - rocm_smi_lib now has a recommended requirement for libdrm
Change-Id: Ic438529e16c8c3dbbdd620da664918148c40c997
2025-02-19 08:49:50 -06:00
Choudhary, Rahul cc0efa8ff8 Create kws-caller.yml
[ROCm/rocm-core commit: 6e83dde455]
2025-02-18 16:48:30 -08:00
Choudhary, Rahul 6e83dde455 Create kws-caller.yml 2025-02-18 16:48:30 -08:00
Choudhary, Rahul 920c928d46 Create rocm_ci_caller.yml and kws-caller.yml to trigger ROCM CI
[ROCm/rocm-core commit: 3e040d907c]
2025-02-18 16:47:05 -08:00
Choudhary, Rahul 3e040d907c Create rocm_ci_caller.yml and kws-caller.yml to trigger ROCM CI 2025-02-18 16:47:05 -08:00
Jatin Chaudhary 16f9dbff6c SWDEV-511239 - make fp8 standalone host compileable
- Use correct header in device_library_decl
- use std:: instead of __hip_internal:: for host compilation
- hide device specific stuff behind __clang__ and __HIP__ check

Change-Id: I2f3647e00555ed0e79f9954a459c41394c3cd49b


[ROCm/clr commit: c3f49c8788]
2025-02-18 19:07:45 -05:00
Jatin Chaudhary c3f49c8788 SWDEV-511239 - make fp8 standalone host compileable
- Use correct header in device_library_decl
- use std:: instead of __hip_internal:: for host compilation
- hide device specific stuff behind __clang__ and __HIP__ check

Change-Id: I2f3647e00555ed0e79f9954a459c41394c3cd49b
2025-02-18 19:07:45 -05:00
Elwazir, Ammar db152085be Temp: Disable CI for Mi300x (#221)
Update continuous_integration.yml

[ROCm/rocprofiler-sdk commit: b4b81f9095]
2025-02-18 11:41:49 -06:00
Elwazir, Ammar b4b81f9095 Temp: Disable CI for Mi300x (#221)
Update continuous_integration.yml
2025-02-18 11:41:49 -06:00
Jatin Chaudhary 508d043176 SWDEV-515255 - do not free bitcode object before code gen
- Also add a cache, which allows compiled code objects to be reused
  instead of compiling again. This should improve performance on
  multigpu systems.

Change-Id: Ib135d616c076b77f8aaf28de275d408b38021d89


[ROCm/clr commit: 0391aec14a]
2025-02-18 12:39:31 -05:00
Jatin Chaudhary 0391aec14a SWDEV-515255 - do not free bitcode object before code gen
- Also add a cache, which allows compiled code objects to be reused
  instead of compiling again. This should improve performance on
  multigpu systems.

Change-Id: Ib135d616c076b77f8aaf28de275d408b38021d89
2025-02-18 12:39:31 -05:00
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 8fcbc2acfe SWDEV-502248 - Parse file path with space characters
Signed-off-by: Tim Gu <Tim.Gu@amd.com>
Change-Id: I67fb9cf5559c9c06f24627a1b25fec3e89b2d1cf


[ROCm/clr commit: 84a867fb73]
2025-02-18 10:31:21 -05:00
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 52a1f5dbf7 SWDEV-507967 - Deprecate gfx9, gfx8, gfx7 on Windows
PAL_CLIENT_INTERFACE_MAJOR_VERSION from 872 --> 910

Change-Id: I03dfa2924ccdae4c2f13f09d5f34ee58298e1343


[ROCm/clr commit: ea804e16f8]
2025-02-17 02:59:41 -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
Longlong Yao 082c6b7830 libhsakmt: allocate va in host path
Change-Id: I40a4395aca99ea8dfd8ff0ecde64eb2c3840d867
Signed-off-by: Longlong Yao <Longlong.Yao@amd.com>


[ROCm/ROCR-Runtime commit: 26f001d3cb]
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 c6bea0ea59 SWDEV-469422 - hipgraph remove static typecast to parent
Change-Id: I339250cfd26a7c04543722a82301acbb41c7d5d7


[ROCm/clr commit: 199e464402]
2025-02-14 11:09:32 -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
Adel Johar fcd8d9795b Docs: Update environment variables page
[ROCm/ROCR-Runtime commit: b4f8b5c202]
2025-02-14 10:15:20 -05:00
Anusha GodavarthySurya 4465ce4e2b SWDEV-508023 - Disable hipDeviceGetGraphMemAttribute_Positive_DoubleMemory Linux psdb failure
Change-Id: Iacfdc1bc13e8da2f5df8750bb315a37d33cea666


[ROCm/hip-tests commit: 48989fbfc6]
2025-02-14 00:27:08 -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 bbf5311499 SWDEV-511125 - Don't use device# as it varies BlockDim & GridDim.
Change-Id: I3ddd0fc616c28adc2d35e64550bac4ca1c09bd6a


[ROCm/hip-tests commit: 28e93a178f]
2025-02-13 13:40:03 -05:00
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 2ad61701d5 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


[ROCm/hip-tests commit: 8ea926725b]
2025-02-13 13:37:36 -05:00
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 2be5ef4dfb SWDEV-504084 - Added multidevice testcases for hipModuleGetFunction/Global
Change-Id: I53d6d63f93c800efa2ec0ff2be5ae593756549e0


[ROCm/hip-tests commit: cddb658314]
2025-02-13 12:52:35 -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 4947316122 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


[ROCm/hip-tests commit: fc270bc90c]
2025-02-13 12:40:28 -05:00