Commit Graph

64650 Commits

Author SHA1 Message Date
Kandula, Venkateshwar reddy 94cbb26b35 SWDEV-524130: add reduced sum counters for new mi355 counters (#328)
add derived counter for td, tcc, ta.

Co-authored-by: Venkateshwar Reddy Kandula <vkandula@amd.com>

[ROCm/rocprofiler-sdk commit: bc85151a51]
2025-04-15 13:37:28 -07:00
Kandula, Venkateshwar reddy bc85151a51 SWDEV-524130: add reduced sum counters for new mi355 counters (#328)
add derived counter for td, tcc, ta.

Co-authored-by: Venkateshwar Reddy Kandula <vkandula@amd.com>
2025-04-15 13:37:28 -07:00
Welton, Benjamin bc4160833b Add SerializedAtomicRatio counter (#327)
Co-authored-by: Benjamin Welton <bewelton@amd.com>

[ROCm/rocprofiler-sdk commit: f143333df0]
2025-04-15 13:36:34 -07:00
Welton, Benjamin f143333df0 Add SerializedAtomicRatio counter (#327)
Co-authored-by: Benjamin Welton <bewelton@amd.com>
2025-04-15 13:36:34 -07:00
Bhardwaj, Gopesh 8778237298 doc improvements for 1.0.0 part 2 (#330)
* update installation steps

* Github Issue #50 Adding README's for samples

* Making name change to ROCprofiler-SDK for consistency

* Fix HIP trace documentation

* Fix HSA trace in docs

* Fix kernel trace in docs

* Fixing memory copy and memory allocation traces

* runtime trace and sys trace doc update

* Fix scratch memory doc

* kernel naming and filtering options

* Adding collection period in docs

* Perfetto configs update

* summary output file

* kernel trace format fix

* update CHANGELOG

* Agent index doc update

* rocm-smi output

* group by queue option

* Updated --group-by-queue description

* perfetto visualization

---------

Co-authored-by: Ian Trowbridge <Ian.Trowbridge@amd.com>

[ROCm/rocprofiler-sdk commit: ca7cce9e81]
2025-04-15 13:30:07 -07:00
Bhardwaj, Gopesh ca7cce9e81 doc improvements for 1.0.0 part 2 (#330)
* update installation steps

* Github Issue #50 Adding README's for samples

* Making name change to ROCprofiler-SDK for consistency

* Fix HIP trace documentation

* Fix HSA trace in docs

* Fix kernel trace in docs

* Fixing memory copy and memory allocation traces

* runtime trace and sys trace doc update

* Fix scratch memory doc

* kernel naming and filtering options

* Adding collection period in docs

* Perfetto configs update

* summary output file

* kernel trace format fix

* update CHANGELOG

* Agent index doc update

* rocm-smi output

* group by queue option

* Updated --group-by-queue description

* perfetto visualization

---------

Co-authored-by: Ian Trowbridge <Ian.Trowbridge@amd.com>
2025-04-15 13:30:07 -07:00
Andryeyev, German a9df586812 SWDEV-459758 - Pass workgroup size explicitly (#185)
It's easier for compiler to move explicit kernel arguments into user SGPRs

[ROCm/clr commit: 3fd7650fe3]
2025-04-15 15:22:15 -04:00
Andryeyev, German 3fd7650fe3 SWDEV-459758 - Pass workgroup size explicitly (#185)
It's easier for compiler to move explicit kernel arguments into user SGPRs
2025-04-15 15:22:15 -04:00
GunaShekar, Ajay e83d1967dc SWDEV-523281 - Include hipDrvLaunchKernel enums compatible to nv (#62)
[ROCm/hip commit: 11ff9f5345]
2025-04-15 12:05:30 -07:00
GunaShekar, Ajay 11ff9f5345 SWDEV-523281 - Include hipDrvLaunchKernel enums compatible to nv (#62) 2025-04-15 12:05:30 -07:00
Chaudhary, Jatin Jaikishan 7257b705ce SWDEV-512924 - add fp4 API (#52)
* Remove C-style include guard

* clean up issues in the PR


[ROCm/clr commit: 5d638d831c]
2025-04-15 17:53:50 +01:00
Chaudhary, Jatin Jaikishan 5d638d831c SWDEV-512924 - add fp4 API (#52)
* Remove C-style include guard

* clean up issues in the PR
2025-04-15 17:53:50 +01:00
Chaudhary, Jatin Jaikishan a401a8883d SWDEV-512924 - add fp4/fp6 headers (#30)
[ROCm/hip commit: 269f54925b]
2025-04-15 17:19:15 +01:00
Chaudhary, Jatin Jaikishan 269f54925b SWDEV-512924 - add fp4/fp6 headers (#30) 2025-04-15 17:19:15 +01:00
Xie, Pengda 9c1d61fbb0 SWDEV-518317 - Remove Redundant Error Message in removeFatBinary (#164)
[ROCm/clr commit: e92ea151b2]
2025-04-15 09:00:39 -07:00
Xie, Pengda e92ea151b2 SWDEV-518317 - Remove Redundant Error Message in removeFatBinary (#164) 2025-04-15 09:00:39 -07:00
Andryeyev, German db3c5f87ea SWDEV-526836 - Switch PAL backend to CmdReleaseThenAcquire() (#175)
[ROCm/clr commit: f6c804edc0]
2025-04-15 11:49:53 -04:00
Andryeyev, German f6c804edc0 SWDEV-526836 - Switch PAL backend to CmdReleaseThenAcquire() (#175) 2025-04-15 11:49:53 -04:00
Stojiljkovic, Vladana e6ddf21492 SWDEV-511290 - Remove invalid Unit_hipMemSetAccess_MapPhysChksFromMulDev test (#93)
Co-authored-by: agodavar_amdeng <Anusha.GodavarthySurya@amd.com>

[ROCm/hip-tests commit: 0d72e7fc8f]
2025-04-15 17:28:20 +02:00
Stojiljkovic, Vladana 0d72e7fc8f SWDEV-511290 - Remove invalid Unit_hipMemSetAccess_MapPhysChksFromMulDev test (#93)
Co-authored-by: agodavar_amdeng <Anusha.GodavarthySurya@amd.com>
2025-04-15 17:28:20 +02:00
Chaudhary, Jatin Jaikishan c72604a2af SWDEV-509213 - make cmake_minimum_required consistent across clr (#51)
Change-Id: Ib0b1df7af8984a37d6bf7ca68ec99597d5978821

[ROCm/clr commit: fcaefe97b8]
2025-04-15 15:23:41 +05:30
Chaudhary, Jatin Jaikishan fcaefe97b8 SWDEV-509213 - make cmake_minimum_required consistent across clr (#51)
Change-Id: Ib0b1df7af8984a37d6bf7ca68ec99597d5978821
2025-04-15 15:23:41 +05:30
Chaudhary, Jatin Jaikishan 7c3dcb707e SWDEV-520627 - include warp functions header for warpSize (#177)
Change-Id: Id3fff8f2722d521071ef0ff71b09fc365ef6fa82

[ROCm/clr commit: 588cf0fc69]
2025-04-15 14:40:27 +05:30
Chaudhary, Jatin Jaikishan 588cf0fc69 SWDEV-520627 - include warp functions header for warpSize (#177)
Change-Id: Id3fff8f2722d521071ef0ff71b09fc365ef6fa82
2025-04-15 14:40:27 +05:30
Chaudhary, Jatin Jaikishan e9e207d7b0 SWDEV-517941 - use device bitcode before spirv (#95)
Also add flag: HIP_FORCE_SPIRV_CODEOBJECT to allow override to force use
SPIRV.

* use cache for already compiled code objects

* address review comments and use the two spirv isa names

[ROCm/clr commit: 07e57a1f0d]
2025-04-14 23:40:52 +01:00
Chaudhary, Jatin Jaikishan 07e57a1f0d SWDEV-517941 - use device bitcode before spirv (#95)
Also add flag: HIP_FORCE_SPIRV_CODEOBJECT to allow override to force use
SPIRV.

* use cache for already compiled code objects

* address review comments and use the two spirv isa names
2025-04-14 23:40:52 +01:00
Charis Poag aacf23778d [SWDEV-518325/SWDEV-518320/SWDEV-443309] Fix Partition Enumeration
* Changes:
  - Updates to DRM renderD* / card* pathing for partition devices
  - Now use KFD to discover AMD devices and populate accordingly
    Device MUST have an accessible KFD node (via cgroups)
  - Updated several ROCm SMI CLI outputs to handle SYSFS files
    which are not accessible on partition nodes
  - Added a new method to help get card/drm info
    (rsmi_dev_device_identifiers_get) from ROCm SMI

Change-Id: If844f27ffc595942272abe9c8167ed90a0b0e225
Signed-off-by: Charis Poag <Charis.Poag@amd.com>


[ROCm/rocm_smi_lib commit: a0df877fdf]
2025-04-14 16:03:24 -05:00
Charis Poag a0df877fdf [SWDEV-518325/SWDEV-518320/SWDEV-443309] Fix Partition Enumeration
* Changes:
  - Updates to DRM renderD* / card* pathing for partition devices
  - Now use KFD to discover AMD devices and populate accordingly
    Device MUST have an accessible KFD node (via cgroups)
  - Updated several ROCm SMI CLI outputs to handle SYSFS files
    which are not accessible on partition nodes
  - Added a new method to help get card/drm info
    (rsmi_dev_device_identifiers_get) from ROCm SMI

Change-Id: If844f27ffc595942272abe9c8167ed90a0b0e225
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
2025-04-14 16:03:24 -05:00
Trowbridge, Ian 5a5fe7f4bf Copyright Compliance (#333)
* Added copyright information to requested files

* Formatting

* Fix bad function name error

[ROCm/rocprofiler-sdk commit: 4fbcfd142c]
2025-04-14 13:07:32 -05:00
Trowbridge, Ian 4fbcfd142c Copyright Compliance (#333)
* Added copyright information to requested files

* Formatting

* Fix bad function name error
2025-04-14 13:07:32 -05:00
Castillo, Juan 07c06318ad [SWDEV-516013]-rocm-smi runtime status check fix (#28)
rocm-smi is not working in mGPU, Blocking DLM tests
Updates include:
 - Creating check_runtime_status function to check for device status of active.
 - Added warning to users that No AMD GPUs are available, check power status/control.
 - Added check for empty string coming from HWMON, if emtpy returns unexpected data.

---------

Signed-off-by: Juan Castillo <juan.castillo@amd.com>

[ROCm/rocm_smi_lib commit: 2630bf0a8c]
2025-04-14 13:05:22 -05:00
Castillo, Juan 2630bf0a8c [SWDEV-516013]-rocm-smi runtime status check fix (#28)
rocm-smi is not working in mGPU, Blocking DLM tests
Updates include:
 - Creating check_runtime_status function to check for device status of active.
 - Added warning to users that No AMD GPUs are available, check power status/control.
 - Added check for empty string coming from HWMON, if emtpy returns unexpected data.

---------

Signed-off-by: Juan Castillo <juan.castillo@amd.com>
2025-04-14 13:05:22 -05:00
David Galiffi d629a890a1 Fix RPM generation on RHEL 10 (#162)
* Set version for RPM_PACKAGE_OBSOLETES

* Not setting a version of omnitrace which rocprofiler-systems obsoletes will result in a warning

* Patch RPATH in libunwind files

* Update Timemory pointer

Signed-off-by: David Galiffi <David.Galiffi@amd.com>

---------

Signed-off-by: David Galiffi <David.Galiffi@amd.com>

[ROCm/rocprofiler-systems commit: 75916f8876]
2025-04-14 11:34:53 -04:00
David Galiffi 75916f8876 Fix RPM generation on RHEL 10 (#162)
* Set version for RPM_PACKAGE_OBSOLETES

* Not setting a version of omnitrace which rocprofiler-systems obsoletes will result in a warning

* Patch RPATH in libunwind files

* Update Timemory pointer

Signed-off-by: David Galiffi <David.Galiffi@amd.com>

---------

Signed-off-by: David Galiffi <David.Galiffi@amd.com>
2025-04-14 11:34:53 -04:00
Elwazir, Ammar f23fe43c29 SWDEV-526393: HSA_TOOLS_LIB is not respected for some pytorch APPs (#24)
HSA_TOOLS_LIB is not respected for some pytorch APPs

Instead of depending on HSA_TOOLS_LIB, move to depending on LD_PRELOAD for loading the rocprofiler library.
2025-04-14 08:41:00 -05:00
Elwazir, Ammar 0270964ce6 SWDEV-526393: HSA_TOOLS_LIB is not respected for some pytorch APPs (#24)
HSA_TOOLS_LIB is not respected for some pytorch APPs

Instead of depending on HSA_TOOLS_LIB, move to depending on LD_PRELOAD for loading the rocprofiler library.

[ROCm/rocprofiler commit: f23fe43c29]
2025-04-14 08:41:00 -05:00
ywang103-amd 46bf2453cc configure rocprofv3 as default for unit test (#668)
[ROCm/rocprofiler-compute commit: fe2035d166]
2025-04-11 19:30:18 -04:00
ywang103-amd fe2035d166 configure rocprofv3 as default for unit test (#668) 2025-04-11 19:30:18 -04:00
Galantsev, Dmitrii ac50573e67 CMAKE - Bump version to 1.1.0
Change-Id: I0fbc0f6d842c034ad858f30fa6418afd01e11a4f
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>
2025-04-11 17:27:27 -05:00
Galantsev, Dmitrii e15c5a15fa CMAKE - Bump version to 1.1.0
Change-Id: I0fbc0f6d842c034ad858f30fa6418afd01e11a4f
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>


[ROCm/rdc commit: ac50573e67]
2025-04-11 17:27:27 -05:00
Galantsev, Dmitrii dfae9cd37f Profiler - Remove buffer to fix memory leaks
Change-Id: Ia3717ccfc147221557f5469965c2abb76b3f451c
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>
2025-04-11 17:27:27 -05:00
Galantsev, Dmitrii 0a05e0db08 Profiler - Remove buffer to fix memory leaks
Change-Id: Ia3717ccfc147221557f5469965c2abb76b3f451c
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>


[ROCm/rdc commit: dfae9cd37f]
2025-04-11 17:27:27 -05:00
Trowbridge, Ian 5467c83188 rocDecode Buffer Tracing Support (#315)
* Added buffer tracing support for rocdecode and updated tests to work with buffer tracing

* Updated perfetto to output args individually rather than as a string list

* Updated docstrings and operation type, changed OTF2 code to remove warning due to change in operation type

* Updated tests for review comments

* Test args exist and return value

* Updated to use string entry

* Change function name

* Updated PR to reflect review comments

* Updated for PR review comments

* Change function name

[ROCm/rocprofiler-sdk commit: 077723337a]
2025-04-11 21:56:36 +00:00
Trowbridge, Ian 077723337a rocDecode Buffer Tracing Support (#315)
* Added buffer tracing support for rocdecode and updated tests to work with buffer tracing

* Updated perfetto to output args individually rather than as a string list

* Updated docstrings and operation type, changed OTF2 code to remove warning due to change in operation type

* Updated tests for review comments

* Test args exist and return value

* Updated to use string entry

* Change function name

* Updated PR to reflect review comments

* Updated for PR review comments

* Change function name
2025-04-11 21:56:36 +00:00
cfallows-amd 10d304f365 Add roofline support for rhel10 (#667)
-add check for rhel10 (platform:el10), force use rhel roof binary
-update changelog in 'unreleased- added' section

Signed-off-by: Carrie Fallows <Carrie.Fallows@amd.com>

[ROCm/rocprofiler-compute commit: c056a39db4]
2025-04-11 17:45:53 -04:00
cfallows-amd c056a39db4 Add roofline support for rhel10 (#667)
-add check for rhel10 (platform:el10), force use rhel roof binary
-update changelog in 'unreleased- added' section

Signed-off-by: Carrie Fallows <Carrie.Fallows@amd.com>
2025-04-11 17:45:53 -04:00
cfallows-amd ffa47d197e Fix rpath checks during RPM generation on RHEL10 (#669)
Invalid rpath on roofline binaries reported during build testing for new RHEL10 addition, removed rpaths to prevent rpath check failures.

Signed-off-by: Carrie Fallows <Carrie.Fallows@amd.com>

[ROCm/rocprofiler-compute commit: 03732d3719]
2025-04-11 17:40:59 -04:00
cfallows-amd 03732d3719 Fix rpath checks during RPM generation on RHEL10 (#669)
Invalid rpath on roofline binaries reported during build testing for new RHEL10 addition, removed rpaths to prevent rpath check failures.

Signed-off-by: Carrie Fallows <Carrie.Fallows@amd.com>
2025-04-11 17:40:59 -04:00
anujshuk-amd 36f7de25a2 Change the default value of ROCPROFSYS_SAMPLING_CPUS to "none" (#164)
[ROCm/rocprofiler-systems commit: 807a622b04]
2025-04-11 17:09:26 -04:00
anujshuk-amd 807a622b04 Change the default value of ROCPROFSYS_SAMPLING_CPUS to "none" (#164) 2025-04-11 17:09:26 -04:00