Commit Graph

64521 Commits

Author SHA1 Message Date
Jonathan Kim 71bd95ed9e hsakmt: Update HSA capabilites with per-queue reset
Per-queue reset is now supported and flagged in HSA capabilities.

Change-Id: I21e2421da73b9fafae19c903dc3eeeab1f84968d


[ROCm/ROCR-Runtime commit: 1a4adaf7bc]
2024-11-13 13:34:35 -05:00
Peter Park 23190fd3d9 [SWDEV-479054] update doc for rsmi_compute_process_info_get to note 2-step usage:w
Change-Id: I81608f807ab679a27be12be591193712d81232bd
Signed-off-by: Peter Park <peter.park@amd.com>


[ROCm/rocm_smi_lib commit: c3f1d2baf1]
2024-11-13 12:52:18 -05:00
Peter Park c3f1d2baf1 [SWDEV-479054] update doc for rsmi_compute_process_info_get to note 2-step usage:w
Change-Id: I81608f807ab679a27be12be591193712d81232bd
Signed-off-by: Peter Park <peter.park@amd.com>
2024-11-13 12:52:18 -05:00
Bill(Shuzhou) Liu 5e3ebecf80 Correct RDC_FI_PCIE_BANDWIDTH unit
The unit should be mbps instead of GB/second
2024-11-13 09:45:46 -05:00
Bill(Shuzhou) Liu b813ae3426 Correct RDC_FI_PCIE_BANDWIDTH unit
The unit should be mbps instead of GB/second


[ROCm/rdc commit: 5e3ebecf80]
2024-11-13 09:45:46 -05:00
Ioannis Assiouras bca7f67a2f SWDEV-487632,SWDEV-487634 - Fixed memleak in Unit_hipDrvMemcpy_Functional
Change-Id: If515c0f31acb5ca071f575458ef9eb06c5786df2


[ROCm/hip-tests commit: e248f1072a]
2024-11-13 07:06:19 -05:00
Ioannis Assiouras e248f1072a SWDEV-487632,SWDEV-487634 - Fixed memleak in Unit_hipDrvMemcpy_Functional
Change-Id: If515c0f31acb5ca071f575458ef9eb06c5786df2
2024-11-13 07:06:19 -05:00
Ioannis Assiouras d4ad29fd1e SWDEV-489354 - Fixed memleak in Unit_hipLaunchHostFunc_Diffpriority
Change-Id: I8a8b49b225e2b48973ae37727766a4af04d08f6f


[ROCm/hip-tests commit: 950bedf14f]
2024-11-13 07:06:00 -05:00
Ioannis Assiouras 950bedf14f SWDEV-489354 - Fixed memleak in Unit_hipLaunchHostFunc_Diffpriority
Change-Id: I8a8b49b225e2b48973ae37727766a4af04d08f6f
2024-11-13 07:06:00 -05:00
Ioannis Assiouras 2f4a9f3fd2 SWDEV-489358 - Fixed memleak in Unit_hipMultiStream_sameDevice
Change-Id: I5a662e46546125988d8a75f76aafcc905eab7147


[ROCm/hip-tests commit: d4f6a2defb]
2024-11-13 05:35:34 -05:00
Ioannis Assiouras d4f6a2defb SWDEV-489358 - Fixed memleak in Unit_hipMultiStream_sameDevice
Change-Id: I5a662e46546125988d8a75f76aafcc905eab7147
2024-11-13 05:35:34 -05:00
Rambabu Swargam c55f3d16b8 SWDEV-468261 - [catch2][dtest] Functional testcases for hipStreamLegacy
Change-Id: I37cf900d4cfdc244ba8d1d7e2e8c6d34f535a0c2


[ROCm/hip-tests commit: 96d4493c3a]
2024-11-13 00:00:43 -05:00
Rambabu Swargam 96d4493c3a SWDEV-468261 - [catch2][dtest] Functional testcases for hipStreamLegacy
Change-Id: I37cf900d4cfdc244ba8d1d7e2e8c6d34f535a0c2
2024-11-13 00:00:43 -05:00
stali d8fec06bab Enable RDCI policy subsystem
- Enable set and get for policy settings
- Enable register and clear policy events

Change-Id: If4eaaf9b80e668fb21691757210e0aa1532cecae
Signed-off-by: stali <Star.Li@amd.com>
2024-11-12 20:40:08 -06:00
stali f34e245ba1 Enable RDCI policy subsystem
- Enable set and get for policy settings
- Enable register and clear policy events

Change-Id: If4eaaf9b80e668fb21691757210e0aa1532cecae
Signed-off-by: stali <Star.Li@amd.com>


[ROCm/rdc commit: d8fec06bab]
2024-11-12 20:40:08 -06:00
Charis Poag ff46ab4258 Merge amd-staging into amd-master 20241112
Change-Id: I3fba6fb940aa19532037e2125fd1837de4d3f282
Signed-off-by: Charis Poag <Charis.Poag@amd.com>


[ROCm/rocm_smi_lib commit: 99c1b5a0df]
2024-11-12 16:43:50 -06:00
Charis Poag 99c1b5a0df Merge amd-staging into amd-master 20241112
Change-Id: I3fba6fb940aa19532037e2125fd1837de4d3f282
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
2024-11-12 16:43:50 -06:00
Saleel Kudchadker 3e10bf3e5e SWDEV-494221 - Fix hipPerfDispatchSpeed test
- Do an hipEventRecord on null stream, that creates the streams and
  avoids stream creation overhead when we time the core functionality

Change-Id: I117dccc42c92836fa113214d31bf14da49deba77


[ROCm/hip-tests commit: fb5e1d33d9]
2024-11-12 13:02:39 -05:00
Saleel Kudchadker fb5e1d33d9 SWDEV-494221 - Fix hipPerfDispatchSpeed test
- Do an hipEventRecord on null stream, that creates the streams and
  avoids stream creation overhead when we time the core functionality

Change-Id: I117dccc42c92836fa113214d31bf14da49deba77
2024-11-12 13:02:39 -05:00
Galantsev, Dmitrii e1b57c43f3 RVS - Fix cookie_t -> rdc_diag_callback_t types issue
Issue introduced in 37ddd5bf50

Change-Id: I2b6a8024d45fc44d92cf2770be9887dfc0fb3ede
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>
2024-11-12 10:36:52 -06:00
Galantsev, Dmitrii 8e657c165c RVS - Fix cookie_t -> rdc_diag_callback_t types issue
Issue introduced in ae9030ab1a

Change-Id: I2b6a8024d45fc44d92cf2770be9887dfc0fb3ede
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>


[ROCm/rdc commit: e1b57c43f3]
2024-11-12 10:36:52 -06:00
Charis Poag 2258c26c53 [SWDEV-488276/SWDEV-497613] Update memory partition set functionality
Changes:
  - Added warning screen to ROCm SMI users
    setting memory partition
  - Added new API (rsmi_dev_memory_partition_capabilities_get)
    to retrieve memory partition capabilities
    (What users can set memory partition modes to)
  - Increased time-bar for CLI sets display to 40 seconds
  - API now waits until the driver reloads with SYSFS files active
  - [SWDEV-475712] [CLI/API] Fixed target_graphics_version field
    not properly displaying for MI2x or Navi 3x ASICs.
  - Updated tests

Change-Id: Iaf89d1b7ad9ceb449b289bc82ea198fe3b23992e
Signed-off-by: Charis Poag <Charis.Poag@amd.com>


[ROCm/rocm_smi_lib commit: 46902274b6]
2024-11-12 12:18:44 -04:00
Charis Poag 46902274b6 [SWDEV-488276/SWDEV-497613] Update memory partition set functionality
Changes:
  - Added warning screen to ROCm SMI users
    setting memory partition
  - Added new API (rsmi_dev_memory_partition_capabilities_get)
    to retrieve memory partition capabilities
    (What users can set memory partition modes to)
  - Increased time-bar for CLI sets display to 40 seconds
  - API now waits until the driver reloads with SYSFS files active
  - [SWDEV-475712] [CLI/API] Fixed target_graphics_version field
    not properly displaying for MI2x or Navi 3x ASICs.
  - Updated tests

Change-Id: Iaf89d1b7ad9ceb449b289bc82ea198fe3b23992e
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
2024-11-12 12:18:44 -04:00
Ammar ELWazir e2892bc8b9 Adding rccl-dev package in core CI testing (#1197)
* Adding rccl-dev package in core CI testing

* Update continuous_integration.yml

[ROCm/rocprofiler-sdk commit: 0d764eb3c5]
2024-11-12 09:56:24 -06:00
Ammar ELWazir 0d764eb3c5 Adding rccl-dev package in core CI testing (#1197)
* Adding rccl-dev package in core CI testing

* Update continuous_integration.yml
2024-11-12 09:56:24 -06:00
Ioannis Assiouras bb2b3cdc89 SWDEV-493913 - Replaced calls to clGetExtensionFunctionAddress in ocltst
Replaced clGetExtensionFunctionAddress calls with
clGetExtensionFunctionAddressForPlatform to ensure
interoperability with distribution ICD loaders.

Change-Id: I560a62459f2ad222750e65e869b98d6b6ec56665


[ROCm/clr commit: 9f1cc590d8]
2024-11-12 15:56:17 +00:00
Ioannis Assiouras 9f1cc590d8 SWDEV-493913 - Replaced calls to clGetExtensionFunctionAddress in ocltst
Replaced clGetExtensionFunctionAddress calls with
clGetExtensionFunctionAddressForPlatform to ensure
interoperability with distribution ICD loaders.

Change-Id: I560a62459f2ad222750e65e869b98d6b6ec56665
2024-11-12 15:56:17 +00:00
Konstantin Zhuravlyov ec3d4aa5e9 loader: add gfx12-generic support
Change-Id: I0bf5d48ec357278bdb7a9c4eae61a7b7995411f0
2024-11-11 16:27:47 -05:00
Konstantin Zhuravlyov 5133b16637 loader: add gfx12-generic support
Change-Id: I0bf5d48ec357278bdb7a9c4eae61a7b7995411f0


[ROCm/ROCR-Runtime commit: ec3d4aa5e9]
2024-11-11 16:27:47 -05:00
Konstantin Zhuravlyov cf9c2efbbd loader: add gfx1153 support
Change-Id: Ie3f0ecf1c6631d95cbff5e14ddc48e751f4c356d
2024-11-11 16:27:39 -05:00
Konstantin Zhuravlyov a384ada964 loader: add gfx1153 support
Change-Id: Ie3f0ecf1c6631d95cbff5e14ddc48e751f4c356d


[ROCm/ROCR-Runtime commit: cf9c2efbbd]
2024-11-11 16:27:39 -05:00
Konstantin Zhuravlyov 7d9a51e22a loader/nfc: reorder cases when switching on targets, specific first, generic second
Change-Id: I47f38c1691b9b6ff589f7ff445143997b0801dc6
2024-11-11 16:27:34 -05:00
Konstantin Zhuravlyov 048a6dc0bd loader/nfc: reorder cases when switching on targets, specific first, generic second
Change-Id: I47f38c1691b9b6ff589f7ff445143997b0801dc6


[ROCm/ROCR-Runtime commit: 7d9a51e22a]
2024-11-11 16:27:34 -05:00
Konstantin Zhuravlyov 4344f012b6 loader: add missing support for gfx700
Change-Id: Ia08e93b0e2d300a183a7a5fb92604cd801b2d52a
2024-11-11 16:27:27 -05:00
Konstantin Zhuravlyov 68f7fb4fa7 loader: add missing support for gfx700
Change-Id: Ia08e93b0e2d300a183a7a5fb92604cd801b2d52a


[ROCm/ROCR-Runtime commit: 4344f012b6]
2024-11-11 16:27:27 -05:00
Julia Jiang 17ca12c039 SWDEV-497618 - Adding Graphics Interop section for HIP API
Change-Id: I32df069d1b85c9e92a1578ff92c9e42ca2a5f443


[ROCm/hip commit: d2f176d2e6]
2024-11-11 16:22:59 -05:00
Julia Jiang d2f176d2e6 SWDEV-497618 - Adding Graphics Interop section for HIP API
Change-Id: I32df069d1b85c9e92a1578ff92c9e42ca2a5f443
2024-11-11 16:22:59 -05:00
Giovanni Baraldi e124053821 SWDEV-495349: Fixes for gfx12 ISA
Change-Id: Id8e6372a70cc3607616e9e26fe42faed7523922a
2024-11-11 13:43:55 -06:00
Giovanni Baraldi c8865a346e SWDEV-495349: Fixes for gfx12 ISA
Change-Id: Id8e6372a70cc3607616e9e26fe42faed7523922a


[ROCm/rocprofiler commit: e124053821]
2024-11-11 13:43:55 -06:00
itrowbri 343a842c81 SWDEV-496634: Revert deprecation of hipHostMalloc and hipHostFree functions (#1186)
[ROCm/rocprofiler-sdk commit: 0356446654]
2024-11-11 11:47:31 -06:00
itrowbri 0356446654 SWDEV-496634: Revert deprecation of hipHostMalloc and hipHostFree functions (#1186) 2024-11-11 11:47:31 -06:00
Jonathan R. Madsen 957b34e01a Fix navi3 kernel tracing (#1133)
* Fix navi3 kernel tracing

- conditional aql::set_profiler_active_on_queue only when counter collection is registered

* Update changelog

* Update following name change

[ROCm/rocprofiler-sdk commit: f7c87e455d]
2024-11-11 11:14:59 -06:00
Jonathan R. Madsen f7c87e455d Fix navi3 kernel tracing (#1133)
* Fix navi3 kernel tracing

- conditional aql::set_profiler_active_on_queue only when counter collection is registered

* Update changelog

* Update following name change
2024-11-11 11:14:59 -06:00
Mythreya 36d357337d Report page migration events as start/end (#793)
* Squashed commit of the following:

commit b76f2635f4b65599f03812a73d0cf410f5ada213
Author: Mythreya <mythreya.kuricheti@amd.com>
Date:   Fri Apr 26 00:29:09 2024 +0000

    Changed for PR feedback

commit bedb8ad566ff42fbf117b19202c26c507abcf8ac
Author: Jonathan R. Madsen <jonathanrmadsen@gmail.com>
Date:   Thu Apr 25 19:20:06 2024 -0500

    Fix installation

commit a98f8a69459a1450a1be9c98e20b3c1e7f2568c2
Author: Jonathan R. Madsen <jonathanrmadsen@gmail.com>
Date:   Thu Apr 25 19:16:35 2024 -0500

    Restructure the headers

commit 46489a020ffafdd5f4ce3f580469ff233ef67fe1
Author: Mythreya <mythreya.kuricheti@amd.com>
Date:   Tue Apr 23 23:31:10 2024 +0000

    Update hsa include

commit 8e795282cce348fc6aa736b7857b21aeb32aa20a
Author: Mythreya <mythreya.kuricheti@amd.com>
Date:   Tue Apr 23 23:02:32 2024 +0000

    Report page migration events as start/end

    * Updated tests accordingly
    * Page migration events are reported independently

commit 8784e5ad4895a626a2a8e4ac12f8021b34172bd4
Author: Mythreya <mythreya.kuricheti@amd.com>
Date:   Tue Apr 16 17:01:57 2024 +0000

    Update handling of dropped page migration events

    Previously, we dropped all locally buffered events when we detect that
    KFD has dropped some events. This may drop too many pending events too eagerly.

    When we receive an end event and cannot find the corresponding start,
    we can be sure that KFD has dropped some events in the immediate past.

    When this happens, we look through all locally buffered events and report
    the start events that are older than 10s as partial events --- they have
    no "end" information (we expect that the end events have been dropped).

    We also set the polling timeout to 10s to prevent the local buffer from
    getting too large with events waiting to be paired up.

    Updated tests

commit 2e8e0b07eeda9b5990e1ae8d28dcd3a035ce38e1
Author: Mythreya <mythreya.kuricheti@amd.com>
Date:   Tue Apr 16 17:01:31 2024 +0000

    Docs for triggers

* Fix page migration sample

* Fix hasher, kfd install

* Add hsa include
* Install KFD include dir

* Updates from code review

- single timestamp field
- node_id -> agent_id
- from_node -> from_agent
- to_node -> to_agent

* Misc revisions

* Remove page-migration install target

* Update page-migration pytest

* Tweak to serialization

* Address PR comments

* Update page-migration test

* Add cli args, update iterations

* Address PR comments

* Add abi.cpp for static_asserts
* Update page_migration gtest with only runtime tests
* Moved helpers into utils.hpp

---------

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

[ROCm/rocprofiler-sdk commit: 363f85dc72]
2024-11-11 11:08:47 -06:00
Mythreya 363f85dc72 Report page migration events as start/end (#793)
* Squashed commit of the following:

commit b76f2635f4b65599f03812a73d0cf410f5ada213
Author: Mythreya <mythreya.kuricheti@amd.com>
Date:   Fri Apr 26 00:29:09 2024 +0000

    Changed for PR feedback

commit bedb8ad566ff42fbf117b19202c26c507abcf8ac
Author: Jonathan R. Madsen <jonathanrmadsen@gmail.com>
Date:   Thu Apr 25 19:20:06 2024 -0500

    Fix installation

commit a98f8a69459a1450a1be9c98e20b3c1e7f2568c2
Author: Jonathan R. Madsen <jonathanrmadsen@gmail.com>
Date:   Thu Apr 25 19:16:35 2024 -0500

    Restructure the headers

commit 46489a020ffafdd5f4ce3f580469ff233ef67fe1
Author: Mythreya <mythreya.kuricheti@amd.com>
Date:   Tue Apr 23 23:31:10 2024 +0000

    Update hsa include

commit 8e795282cce348fc6aa736b7857b21aeb32aa20a
Author: Mythreya <mythreya.kuricheti@amd.com>
Date:   Tue Apr 23 23:02:32 2024 +0000

    Report page migration events as start/end

    * Updated tests accordingly
    * Page migration events are reported independently

commit 8784e5ad4895a626a2a8e4ac12f8021b34172bd4
Author: Mythreya <mythreya.kuricheti@amd.com>
Date:   Tue Apr 16 17:01:57 2024 +0000

    Update handling of dropped page migration events

    Previously, we dropped all locally buffered events when we detect that
    KFD has dropped some events. This may drop too many pending events too eagerly.

    When we receive an end event and cannot find the corresponding start,
    we can be sure that KFD has dropped some events in the immediate past.

    When this happens, we look through all locally buffered events and report
    the start events that are older than 10s as partial events --- they have
    no "end" information (we expect that the end events have been dropped).

    We also set the polling timeout to 10s to prevent the local buffer from
    getting too large with events waiting to be paired up.

    Updated tests

commit 2e8e0b07eeda9b5990e1ae8d28dcd3a035ce38e1
Author: Mythreya <mythreya.kuricheti@amd.com>
Date:   Tue Apr 16 17:01:31 2024 +0000

    Docs for triggers

* Fix page migration sample

* Fix hasher, kfd install

* Add hsa include
* Install KFD include dir

* Updates from code review

- single timestamp field
- node_id -> agent_id
- from_node -> from_agent
- to_node -> to_agent

* Misc revisions

* Remove page-migration install target

* Update page-migration pytest

* Tweak to serialization

* Address PR comments

* Update page-migration test

* Add cli args, update iterations

* Address PR comments

* Add abi.cpp for static_asserts
* Update page_migration gtest with only runtime tests
* Moved helpers into utils.hpp

---------

Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com>
2024-11-11 11:08:47 -06:00
venkat1361 46cb82b75f Dimension support for reduce operator (#1147)
* cache reference nodes

* evaluation based on dim args

* format

* add dimensions for reduce operator

* add dimensions for reduce operator

* add dimensions for reduce operator docs

* add dimensions for reduce operator.

* refactor switch cases

* Update CHANGELOG.md

* updated doc with data example

* updated doc with data example for reduce operation.

* added fallthrough in switch case sum.

* changelog.md

* format

* fix bug in constuct_test_data()

[ROCm/rocprofiler-sdk commit: 472907a576]
2024-11-11 18:37:28 +05:30
venkat1361 472907a576 Dimension support for reduce operator (#1147)
* cache reference nodes

* evaluation based on dim args

* format

* add dimensions for reduce operator

* add dimensions for reduce operator

* add dimensions for reduce operator docs

* add dimensions for reduce operator.

* refactor switch cases

* Update CHANGELOG.md

* updated doc with data example

* updated doc with data example for reduce operation.

* added fallthrough in switch case sum.

* changelog.md

* format

* fix bug in constuct_test_data()
2024-11-11 18:37:28 +05:30
Jaydeep Patel 89b9d22e6c SWDEV-496544 - Reset mem alloc node count for AutoFreeOnLaunch.
Change-Id: Ib32b04584548a46632606ecd85b58c6ce4a5894d


[ROCm/clr commit: 24c57cb984]
2024-11-11 11:03:32 +00:00
Jaydeep Patel 24c57cb984 SWDEV-496544 - Reset mem alloc node count for AutoFreeOnLaunch.
Change-Id: Ib32b04584548a46632606ecd85b58c6ce4a5894d
2024-11-11 11:03:32 +00:00
venkat1361 1a369af8fa SWDEV-477244: Select() Expression Dimension Support (#1091)
* add support for select function in derived counters

* formatting

* renaming select dims variable name from set to map

* format

* Update doc with select() for dimensions

* use : for defining range of values in select dims

* - update dimension for metric after select.
- make sure to raise runtime error if user provides range for a dimension.

* use map instead of unordered_map for select dim info

* new line EOF

* fix bug: select() operator.

* Update evaluate_ast.cpp

format

* added a check for dim value exceeds max.

* Update source/lib/rocprofiler-sdk/counters/evaluate_ast.cpp

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

* Update source/lib/rocprofiler-sdk/counters/evaluate_ast.cpp

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

* updated doc with data example for select operation.

* changelog.md

* Update CHANGELOG.md

---------

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

[ROCm/rocprofiler-sdk commit: cc4811d27d]
2024-11-11 15:14:22 +05:30