Wykres commitów

37726 Commity

Autor SHA1 Wiadomość Data
David Yat Sin d6ec7b6489 rocr: Remove unnecessary function declarations
Change-Id: Ia2613ce74cac808f9239fc24049b57b7b1abaed9
2024-09-19 19:44:53 +00:00
David Yat Sin 12e299e8d4 rocr: Fix compile error
Change-Id: Iae6bf08e834a426f6f97cbc51d2a1a38199015bd
2024-09-19 19:44:53 +00:00
Shweta Khatri c30ff893a6 Add rocprofiler-register dependency to build
Ensure rocprofiler-register is linked and added to DEB and RPM package dependencies.
Github ticket - https://github.com/ROCm/ROCm/issues/3654

Change-Id: Iaaaca8bfa81ca33da147673ef1be798109b70aa5
2024-09-19 19:44:53 +00:00
David Yat Sin 924e11ba7f rocr: Increase queue size for co-op queues
Increase queue-size for co-op queues to 16K to improve performance on
some workloads

Change-Id: I4d3bf0ecbd30ebb648b68d9c5fdabadc670a386c
2024-09-19 19:44:53 +00:00
David Yat Sin 3cb25e5236 rocrtst: Add negative test for invalid buffer free
Add a negative test to try to free the ring buffer of a queue and
confirm that a memory error is generated.

Change-Id: I4afd95c69c62f7c3e1138d5d6c4a5fd237631e43
2024-09-19 19:44:53 +00:00
Wang, Yanyao c064218637 Remove hard-coded llvm-project folder for rocrtst
Signed-off-by: Wang, Yanyao <yanyao.wang@amd.com>
Change-Id: I9ba81c1182da812596d7d314f3a6dae7cbcd0c2d
2024-09-19 19:44:53 +00:00
Saleel Kudchadker 8c84a20b01 SWDEV-301667 - Improve logging
Change-Id: I3fa06791b7ac73d84b8a9586e6b3435fa8858d25
2024-09-19 15:09:03 -04:00
kjayapra-amd 12a39fbf22 SWDEV-480772 - Remove name variable from amd::Monitor class.
Change-Id: Ie2a4fa44f485786227230f8a892e090e718aa30e
2024-09-19 11:55:01 -04:00
Zhang Ava da7bf7e366 Merge amd-staging into amd-master 20240917
Signed-off-by: Zhang Ava <niandong.zhang@amd.com>
Change-Id: I198c849530508a90eee8ae5454035b9c610b3f5a


[ROCm/rocm_smi_lib commit: af2507807f]
2024-09-19 18:44:19 +08:00
Zhang Ava af2507807f Merge amd-staging into amd-master 20240917
Signed-off-by: Zhang Ava <niandong.zhang@amd.com>
Change-Id: I198c849530508a90eee8ae5454035b9c610b3f5a
2024-09-19 18:44:19 +08:00
Marko Arandjelovic 0112ed5137 SWDEV-465206 - Enable Unit_hipModuleLaunchCooperativeKernel_Negative_Parameters
Change-Id: I35037f1b6cae5416b724499ac916ba1a70f9556e
2024-09-19 04:00:50 -04:00
David Galiffi 5c2b64ddca Update data-collection-modes.rst (#386)
Fixed a typo.
"fewer than 1024 instructions" should be "at least 1024 instructions"

[ROCm/rocprofiler-systems commit: ce1cea95e4]
2024-09-18 21:05:56 -04:00
David Galiffi ce1cea95e4 Update data-collection-modes.rst (#386)
Fixed a typo.
"fewer than 1024 instructions" should be "at least 1024 instructions"
2024-09-18 21:05:56 -04:00
Marko Arandjelovic cfdc9dfc36 Revert "SWDEV-441296 - Allign hipTexObjectCreate error handling to CUDA"
This reverts commit 7d3c0c5e10.

Changing the error code is considered as a breaking change,
so it should be done in major releases only.

The other reason for reverting the commit is that this change itself
is incorrect. Cuda behaves in the same way as hip when
pResDesc or pTexDesc are nullptr.

Change-Id: I3abee6b79279b81ab01c7f8466c7f8e3776c4109
2024-09-18 16:38:16 -04:00
Rahul Manocha 4d1ded9eaf SWDEV-479575 - Add marker to parent graph dependencies in childgraph node
1) Child Graph nodes need to have parent graph dependencies in waitlist.
2) Marker is placed on base stream with parent graph waitlist

Change-Id: Iec65a0171ea387be05b0733abcc708fb630e4be4
2024-09-18 15:12:50 -04:00
Sam Wu 7475783cb9 Add dependabot config for updating documentation requirements (#1018)
[ROCm/rocprofiler-sdk commit: cc45896bf5]
2024-09-18 11:31:17 -06:00
Sam Wu cc45896bf5 Add dependabot config for updating documentation requirements (#1018) 2024-09-18 11:31:17 -06:00
pghafari 365ffd4805 SWDEV-444447 - Fix regression for verbose printing for AMD_LOG_LEVEL=4
Change-Id: Id245caef711b7ccdf4e999e934993beb43d7c3d5
2024-09-18 13:08:10 -04:00
AravindanC 38eedf86cf SWDEV-342167, SWDEV-461080 - Remove Hard Coded Install Permission
Change-Id: Ie42cf83cc9a665715e76966378237d479202e0a7
2024-09-18 11:48:03 -04:00
Rahul Manocha 07261002b1 SWDEV-439234 - Fix for Segfault in ValidateMemAccess
Change-Id: I251d277eb5af16ba5c0de85ffd142a5f64fa469d
2024-09-18 10:52:32 -04:00
Daniel Livingston e550032d25 SWDEV-77148 - Add UberTrace support to PAL device
This PR adds UberTrace-based tracing support to ROCclr's PAL device class.
Legacy RGP-based tracing is still available and is the default.
If UberTrace support is enabled tool-side, this new code path will activate.

Change-Id: I268b2dcef70e850a50e2caef8355f38bf51d4641
2024-09-17 16:06:37 -04:00
Bill(Shuzhou) Liu 9800528c19 Update the hsaco for diagonstic on MI300X
Add hsaco for gfx940, gfx941 and gfx942

Change-Id: Ibd55fcc2d036d1190357e1e86d4e170568426d94
2024-09-17 14:15:35 -05:00
Bill(Shuzhou) Liu 6372df9447 Update the hsaco for diagonstic on MI300X
Add hsaco for gfx940, gfx941 and gfx942

Change-Id: Ibd55fcc2d036d1190357e1e86d4e170568426d94


[ROCm/rdc commit: 9800528c19]
2024-09-17 14:15:35 -05:00
Satyanvesh Dittakavi 8ee065c5bd SWDEV-478776 - Fix segfault with streamsync using hipStreamLegacy
Change-Id: Ifb412d0bcfa33bc1130b47b757ee276ca9bc1c3a
2024-09-17 15:02:18 -04:00
Marko Arandjelovic 6867852a89 SWDEV-454656 Correct test setup, Unit_hipGraphExecMemcpyNodeSetParams_Positive_Basic
Pitch cannot be lower then width

Change-Id: I929672fad4ca62d21ffd7bfec8bbc837e7bbcee2
2024-09-17 11:57:29 -04:00
Jonathan R. Madsen 7dbe1d0650 Fix roctracer-roctx test (#1088)
- original format using generator expressions (`$<IF:$<TARGET_EXISTS:...>,$<TARGET_FILE:...>,>`) appears to cause issues with older CMake versions

[ROCm/rocprofiler-sdk commit: d7874f3496]
2024-09-17 08:59:34 -05:00
Jonathan R. Madsen d7874f3496 Fix roctracer-roctx test (#1088)
- original format using generator expressions (`$<IF:$<TARGET_EXISTS:...>,$<TARGET_FILE:...>,>`) appears to cause issues with older CMake versions
2024-09-17 08:59:34 -05:00
Jatin Chaudhary 4b03017e8a SWDEV-478065 - Embed host thread in shared_ptr
This shows up in some valgrind runs. Make sure the resources are
released.

Change-Id: I34c25c00370a221585895655744831215136d5f4
2024-09-17 09:53:51 -04:00
Jaydeep Patel 2494992695 SWDEV-478049 - Clear packets list as it is being added back later during submitKernelInternal while setting params for graph node.
Change-Id: I7451ffda93d94eeda5e1be05bb87558ae86d2a19
2024-09-16 23:10:32 -04:00
kjayapra-amd 53c362295c SWDEV-470571 - Disabling fence tests wont work since fine grain mem is MTYPE_NC for gfx12.
Change-Id: I663d836d5ff17345ad0d4902f3d995dedb6070c4
2024-09-16 18:39:30 -04:00
David Galiffi 83a16cd842 Update opensuse.yml (#383)
Update nick-fields/retry to v3
Updates to Node20

[ROCm/rocprofiler-systems commit: 079cdd5512]
2024-09-16 17:03:02 -04:00
David Galiffi 079cdd5512 Update opensuse.yml (#383)
Update nick-fields/retry to v3
Updates to Node20
2024-09-16 17:03:02 -04:00
Ioannis Assiouras bcc545e6b8 SWDEV-476929 - Introduce an activeQueues set
The new set tracks only the queues that have a command
submitted to them. This allows for fast iteration
in waitActiveStreams.

Change-Id: I2c832eefa01280d9a87a5f57874d36d2e9441de7
2024-09-16 15:53:49 -04:00
James Xu ddba959395 SWDEV-478077 - logging.warn used instead of logging.warning
- logging.warn() is deprecated in favour of logging.warning()
- for some reason, this is the only place in all of rocm_smi.py
	that uses logging.warn() as pointed out on github
	https://github.com/ROCm/rocm_smi_lib/issues/187

Change-Id: Ie1e4a0ea16b996fbed2e902c8edfe68087a5a5fa


[ROCm/rocm_smi_lib commit: fe6a49d186]
2024-09-16 13:50:26 -04:00
James Xu fe6a49d186 SWDEV-478077 - logging.warn used instead of logging.warning
- logging.warn() is deprecated in favour of logging.warning()
- for some reason, this is the only place in all of rocm_smi.py
	that uses logging.warn() as pointed out on github
	https://github.com/ROCm/rocm_smi_lib/issues/187

Change-Id: Ie1e4a0ea16b996fbed2e902c8edfe68087a5a5fa
2024-09-16 13:50:26 -04:00
Gopesh Bhardwaj d7aa58e291 comparing tool options in rocprof/rocprofv2/rocprofv3 (#1050)
* comparing tool options in rocprof/rocprofv2/rocprofv3

* Added more perfetto options

* Added new summary optipons

* Added Category for all options

* Apply suggestions from code review

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

* changes requested in SWDEV-484472

* Correct broken table formatting

* detailed explanation on json custom format

* Feedback Resolution

---------

Co-authored-by: Jonathan R. Madsen <jrmadsen@users.noreply.github.com>
Co-authored-by: Ammar ELWazir <ammar.elwazir@amd.com>

[ROCm/rocprofiler-sdk commit: 863b608ae3]
2024-09-16 20:08:11 +05:30
Gopesh Bhardwaj 863b608ae3 comparing tool options in rocprof/rocprofv2/rocprofv3 (#1050)
* comparing tool options in rocprof/rocprofv2/rocprofv3

* Added more perfetto options

* Added new summary optipons

* Added Category for all options

* Apply suggestions from code review

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

* changes requested in SWDEV-484472

* Correct broken table formatting

* detailed explanation on json custom format

* Feedback Resolution

---------

Co-authored-by: Jonathan R. Madsen <jrmadsen@users.noreply.github.com>
Co-authored-by: Ammar ELWazir <ammar.elwazir@amd.com>
2024-09-16 20:08:11 +05:30
kjayapra-amd d81c5d3d7f SWDEV-484188 - Change few std::array style globals to C style to avoid optimization on Static Libs.
Change-Id: Iab6d3c040b8d088013daa08093898be99dd3a971
2024-09-16 09:46:56 -04:00
kjayapra-amd 4ecd77df5e SWDEV-484188 - Moving std::maps into struct const and into amd::Kernel class.
Change-Id: Ie4d5a64511412fdb498b045aaffb52c3a1286de6
2024-09-15 09:14:51 -04:00
David Galiffi 484dba05ce Correct perfetto submodule pointer
Signed-off-by: David Galiffi <David.Galiffi@amd.com>


[ROCm/rocprofiler-systems commit: 2a77770486]
2024-09-13 19:06:00 -04:00
David Galiffi 2a77770486 Correct perfetto submodule pointer
Signed-off-by: David Galiffi <David.Galiffi@amd.com>
2024-09-13 19:06:00 -04:00
Li Ma ca569346a3 SWDEV-445415 - Pthread detach instead of pthread join
Detcah the thread which handle shutdown signals instead of joining
thread can avoid the segfault issue on specific ASIC.

Signed-off-by: Li Ma <li.ma@amd.com>
Change-Id: I74ac53c027ac370605caaa87115c83fd8027526a
2024-09-13 18:32:37 -04:00
Li Ma 5ad5406de3 SWDEV-445415 - Pthread detach instead of pthread join
Detcah the thread which handle shutdown signals instead of joining
thread can avoid the segfault issue on specific ASIC.

Signed-off-by: Li Ma <li.ma@amd.com>
Change-Id: I74ac53c027ac370605caaa87115c83fd8027526a


[ROCm/rdc commit: ca569346a3]
2024-09-13 18:32:37 -04:00
Jonathan R. Madsen 120a358069 Update HIP tracing ABI (#1025)
* Update HIP ABI tracing

* Minor HIP abi.cpp updates

* Misc roctx updates (version.h + more)

* Common static thread-local template struct

- static_tl_object
- similar to static_object but with thread-local semantics

* rocprofiler-sdk/version.h updates

* Update for HIP_RUNTIME_API_TABLE_STEP_VERSION == {4,5,6}

* Fix roctx.cpp tweaks

[ROCm/rocprofiler-sdk commit: 7861dcc6c6]
2024-09-13 17:10:35 -05:00
Jonathan R. Madsen 7861dcc6c6 Update HIP tracing ABI (#1025)
* Update HIP ABI tracing

* Minor HIP abi.cpp updates

* Misc roctx updates (version.h + more)

* Common static thread-local template struct

- static_tl_object
- similar to static_object but with thread-local semantics

* rocprofiler-sdk/version.h updates

* Update for HIP_RUNTIME_API_TABLE_STEP_VERSION == {4,5,6}

* Fix roctx.cpp tweaks
2024-09-13 17:10:35 -05:00
Sam Wu b5df3a2135 Bump rocm-docs-core to 1.7.2
Update documentation requirements

Change-Id: I19cd1a96309844898e112777412e9c006a8874a0
2024-09-13 14:01:46 -06:00
Sam Wu b60da58d74 Bump rocm-docs-core to 1.7.2
Update documentation requirements

Change-Id: I19cd1a96309844898e112777412e9c006a8874a0


[ROCm/rdc commit: b5df3a2135]
2024-09-13 14:01:46 -06:00
Peter Park 5fb052bede Fix links in readme (#379)
fix links in readme


[ROCm/rocprofiler-systems commit: 5a42457afe]
2024-09-13 16:00:08 -04:00
Peter Park 5a42457afe Fix links in readme (#379)
fix links in readme
2024-09-13 16:00:08 -04:00
jamesxu2 93b92d2d7f Change Perfetto Source to Github (#373)
- Current Perfetto source repo is from android.googlesource
        which is censored in China and causes an infinite
        hang when building Omnitrace
- This commit changes the Perfetto source repo to Github which acts
        as a read-only mirror to the googlesource perfetto
        repo.

Co-authored-by: David Galiffi <David.Galiffi@amd.com>

[ROCm/rocprofiler-systems commit: 6f22b2d2e5]
2024-09-13 15:59:27 -04:00