Commit-Graf

825 Incheckningar

Upphovsman SHA1 Meddelande Datum
Zhang, Ava 7327e645c6 Merge branch 'amd-mainline' into amd-staging 2025-03-17 08:58:09 +08:00
Mallya, Ameya Keshava 8fe9882c49 Added release trigger for further releases 2025-03-14 14:06:21 -07:00
Arif, Maisam 1416c2043d [SWDEV-517717] Maintence Mode Notice (#20)
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
2025-03-09 14:23:33 -05:00
Kanangot Balakrishnan, Bindhiya d8de415960 SWDEV-510419: Restore compute partition after memory partition test (#15)
Memory partition test was changing original compute partiton based
on default compute mode. Corrected this to set back to original
compute partition.

Signed-off-by: Bindhiya Kanangot Balakrishnan <Bindhiya.KanangotBalakrishnan@amd.com>
2025-03-09 14:23:33 -05:00
Charis Poag 967493c39a [SWDEV-514998/SWDEV-511662] Fix tests for Guest and BM with static CPX config
Guest: Tests needed to account for not supporting changing compute
partitions.

BM: Tests need to account for invalid responses from Driver (due to
static CPX config).
2025-03-09 14:23:22 -05:00
Galantsev, Dmitrii 9c82706fc1 [SWDEV-508785] Bump version number to 7.6.0
Change-Id: I084f139802f73311f15c68f94bc98f631c7f2bd8
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>
2025-03-09 14:23:22 -05:00
Charis Poag b951a65cf2 [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
2025-03-09 14:23:22 -05:00
Galantsev, Dmitrii 59cbeb57d1 Fix warnings on CXX/linker flags (#12)
1) When `clang` is used as system compiler, libraries were built without respecting LDFLAGS. For example, this affected LTO flags, if any (and it only affected clang, not gcc).

2) Linker flags are registered as CXX flags, which produces warnings during compilation:
```
clang++: warning: -Wl,-z,noexecstack: 'linker' input unused [-Wunused-command-line-argument]
clang++: warning: -Wl,-znoexecheap: 'linker' input unused [-Wunused-command-line-argument]
clang++: warning: -Wl,-z,relro: 'linker' input unused [-Wunused-command-line-argument]
clang++: warning: -Wl,-z,now: 'linker' input unused [-Wunused-command-line-argument]
```

3) Clang does not support `-Wtrampolines` flag:
```
warning: unknown warning option '-Wtrampolines' [-Wunknown-warning-option]
```

4) No linkers support `noexecheap` anymore. `noexecheap` linker flag was a part of PaX patches to GNU ld, (which were dropped in 2017)[https://www.gentoo.org/support/news-items/2017-08-19-hardened-sources-removal.html]. Now ld/ld.lld/ld.gold don't support it and protection of heap is managed by NX bit. Therefore every compiler produces this warning:
```
ld.lld: warning: unknown -z value: noexecheap
```

Closes #210.

Co-authored-by: Sv. Lockal <lockalsash@gmail.com>
2025-03-09 14:23:22 -05:00
Johar, Adel fc61e40506 Docs: Fix broken links, warnings and use automodule (#11)
- Fixes the broken links in rocm_smi.h
- Uses automodule instead of autofunction in docs/reference/python_api.rst
- Fixes some warnings during docs build
- Update some of the versions in requirements.txt
2025-03-09 14:23:22 -05:00
Mallya, Ameya Keshava a938e743f0 Added !verify trigger 2025-03-09 14:23:22 -05:00
Kanangot Balakrishnan, Bindhiya 6337f7b05b [SWDEV-481004] Fix for incorrect gfx_version number (#8)
The target_graphics_version was not formatted properly and was
showing incorrect Target Name. Corrected this by fomatting
major, minor and revision numbers.

Signed-off-by: Bindhiya Kanangot Balakrishnan <Bindhiya.KanangotBalakrishnan@amd.com>
2025-03-09 14:23:22 -05:00
Mallya, Ameya Keshava 685c057acb Fixed Workflow for updated KWS structure 2025-03-09 14:23:22 -05:00
Mallya, Ameya Keshava d5cbe04ecf Create kws-caller.yml 2025-03-09 14:23:22 -05:00
Galantsev, Dmitrii 898ae4ffc1 [SWDEV-495169] Update ROCm SMI CLI and Error handling (#3)
Issues include:

Update ROCm SMI displaying None or Not Supported to N/A
Update ROCm SMI displaying err msg to instead log err

Signed-off-by: Juan Castillo juan.castillo@amd.com
Change-Id: I1a2ce6e4f329666b5666664a7d7b4475d6c1cbc7
2025-03-09 14:23:22 -05:00
James Xu fdc8d73c64 [SWDEV-501108] Update Doxygen note on rsmi_dev_pci_id_get
- To address https://github.com/ROCm/rocm_smi_lib/issues/208
where use of fake BDFs for partitions can cause confusion. This note
is already in the comments of the function definition, but was not
updated in the function declaration.
- Fix broken formatting for the location table for PCIE coordinate fields
- Tracked in SWDEV-501108

Change-Id: Ic85439866cb836bb43acc52314a7f1d026c3215d
2025-03-09 14:23:21 -05:00
Choudhary, Rahul 78f66f81de Create rocm_ci_caller.yml init file to call shared workflow 2025-03-09 14:23:21 -05:00
gabrpham 76ac0808fe Fixed reset event issues
Issues include:
	SWDEV-480250
	SWDEV-480255
	SWDEV-480248

Signed-off-by: gabrpham <Gabriel.Pham@amd.com>
Change-Id: Icf12211e4b136f26fce18f09a7bf8b7e9cd20691
2025-03-09 14:23:21 -05:00
Charis Poag 88a7e4b8ad [SWDEV-496693] GPU metrics 1.7
Changes:
    - Added new GPU metrics:
      1) XGMI link status - Up/Down; 1 = up; 0 = down
      2) Graphics clocks below host limit (per XCP)
         accumulators -> used to help calculate a violation status
      3) VRAM max bandwidth at max memory clock
    - Updated rocm-smi --showmetrics to include new metrics.
    Units/values reflect as indicated by driver, may differ
    from AMD SMI or other ROCm SMI interfaces which
    use these fields.
    - N/A fields means the device does not support providing this
    data.

Change-Id: I17b313345f15070a76b3a30dd8d5645d212d601b
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
2025-03-09 14:23:21 -05:00
Charis Poag d2efac3d93 [SWDEV-475712] Fix MI2x target_graphics_version
Removed correcting target_graphics_version by
product name. Instead detected target_graphics_version which
needs to be corrected -> populate accordingly.

Change-Id: I90765c87e0629daea5c732dace8acfd17e8c62c7
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
2025-03-09 14:23:21 -05:00
Poag, Charis 23e945c6b3 [SWDEV-514998/SWDEV-511662] Fix tests for Guest and BM with static CPX config (#26)
Guest: Tests needed to account for not supporting changing compute
partitions.

BM: Tests need to account for invalid responses from Driver (due to
static CPX config).

Change-Id: I09ccee981c6b73684b64e5053068920a6c1b6439

Signed-off-by: Charis Poag <Charis.Poag@amd.com>
2025-03-09 14:08:02 -05:00
Poag, Charis 08fee73075 Revert "[SWDEV-514998/SWDEV-511662] Fix tests for Guest and BM with static CPX config" (#25)
* Revert - this reverts commit a73e47591c7ea0ed5a7fc217211872d74be64206.

* Revert "[SWDEV-514998/SWDEV-511662] Fix tests for Guest and BM with static CPX config"

This reverts commit 5a71fd9d75d4d6a9bdd7fa3e652eeb12336a1d6a.
2025-03-09 14:08:02 -05:00
Arif, Maisam d953b2ce66 [SWDEV-517717] Maintence Mode Notice (#20)
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
2025-03-09 14:08:02 -05:00
Kanangot Balakrishnan, Bindhiya 1d6b8d9422 SWDEV-510419: Restore compute partition after memory partition test (#15)
Memory partition test was changing original compute partiton based
on default compute mode. Corrected this to set back to original
compute partition.

Signed-off-by: Bindhiya Kanangot Balakrishnan <Bindhiya.KanangotBalakrishnan@amd.com>
2025-03-09 14:08:02 -05:00
Charis Poag 1dd9ca9df4 [SWDEV-514998/SWDEV-511662] Fix tests for Guest and BM with static CPX config
Guest: Tests needed to account for not supporting changing compute
partitions.

BM: Tests need to account for invalid responses from Driver (due to
static CPX config).
2025-03-09 14:07:51 -05:00
Galantsev, Dmitrii ceb47b0b04 [SWDEV-508785] Bump version number to 7.6.0
Change-Id: I084f139802f73311f15c68f94bc98f631c7f2bd8
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>
2025-02-21 14:46:56 -06:00
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
Galantsev, Dmitrii 4dbc2b6d57 Fix warnings on CXX/linker flags (#12)
1) When `clang` is used as system compiler, libraries were built without respecting LDFLAGS. For example, this affected LTO flags, if any (and it only affected clang, not gcc).

2) Linker flags are registered as CXX flags, which produces warnings during compilation:
```
clang++: warning: -Wl,-z,noexecstack: 'linker' input unused [-Wunused-command-line-argument]
clang++: warning: -Wl,-znoexecheap: 'linker' input unused [-Wunused-command-line-argument]
clang++: warning: -Wl,-z,relro: 'linker' input unused [-Wunused-command-line-argument]
clang++: warning: -Wl,-z,now: 'linker' input unused [-Wunused-command-line-argument]
```

3) Clang does not support `-Wtrampolines` flag:
```
warning: unknown warning option '-Wtrampolines' [-Wunknown-warning-option]
```

4) No linkers support `noexecheap` anymore. `noexecheap` linker flag was a part of PaX patches to GNU ld, (which were dropped in 2017)[https://www.gentoo.org/support/news-items/2017-08-19-hardened-sources-removal.html]. Now ld/ld.lld/ld.gold don't support it and protection of heap is managed by NX bit. Therefore every compiler produces this warning:
```
ld.lld: warning: unknown -z value: noexecheap
```

Closes #210.

Co-authored-by: Sv. Lockal <lockalsash@gmail.com>
2025-02-04 22:16:57 -06:00
Johar, Adel e5c5a1d5b7 Docs: Fix broken links, warnings and use automodule (#11)
- Fixes the broken links in rocm_smi.h
- Uses automodule instead of autofunction in docs/reference/python_api.rst
- Fixes some warnings during docs build
- Update some of the versions in requirements.txt
2025-01-29 08:06:09 -06:00
Mallya, Ameya Keshava 2764498bbf Added !verify trigger 2025-01-28 20:11:45 -08:00
Kanangot Balakrishnan, Bindhiya 94dca7073b [SWDEV-481004] Fix for incorrect gfx_version number (#8)
The target_graphics_version was not formatted properly and was
showing incorrect Target Name. Corrected this by fomatting
major, minor and revision numbers.

Signed-off-by: Bindhiya Kanangot Balakrishnan <Bindhiya.KanangotBalakrishnan@amd.com>
2025-01-21 15:46:56 -06:00
Mallya, Ameya Keshava aefc865bf4 Fixed Workflow for updated KWS structure 2025-01-17 08:26:52 -08:00
Mallya, Ameya Keshava dcdaf7389e Add KWS Check (#9) 2025-01-15 12:05:09 -08:00
Mallya, Ameya Keshava c6ce9a5aa0 Create kws-caller.yml 2025-01-15 11:12:25 -08:00
Galantsev, Dmitrii 55ee3cc442 [SWDEV-495169] Update ROCm SMI CLI and Error handling (#3)
Issues include:

Update ROCm SMI displaying None or Not Supported to N/A
Update ROCm SMI displaying err msg to instead log err

Signed-off-by: Juan Castillo juan.castillo@amd.com
Change-Id: I1a2ce6e4f329666b5666664a7d7b4475d6c1cbc7
2025-01-14 17:15:18 -06:00
James Xu 67a0de4279 [SWDEV-501108] Update Doxygen note on rsmi_dev_pci_id_get
- To address https://github.com/ROCm/rocm_smi_lib/issues/208
where use of fake BDFs for partitions can cause confusion. This note
is already in the comments of the function definition, but was not
updated in the function declaration.
- Fix broken formatting for the location table for PCIE coordinate fields
- Tracked in SWDEV-501108

Change-Id: Ic85439866cb836bb43acc52314a7f1d026c3215d
2025-01-14 15:49:55 -06:00
Choudhary, Rahul bb122efeae Merge pull request #1 from AMD-ROCm-Internal/rahchoud_amdeng-patch-1
Create rocm_ci_caller.yml init file to call shared workflow
2025-01-07 12:11:25 -08:00
Choudhary, Rahul 3c01c13dfd Create rocm_ci_caller.yml init file to call shared workflow 2025-01-07 11:53:58 -08:00
gabrpham 6f51cd651e Fixed reset event issues
Issues include:
	SWDEV-480250
	SWDEV-480255
	SWDEV-480248

Signed-off-by: gabrpham <Gabriel.Pham@amd.com>
Change-Id: Icf12211e4b136f26fce18f09a7bf8b7e9cd20691
2024-12-30 13:12:46 -05:00
Charis Poag 4de2168866 [SWDEV-496693] GPU metrics 1.7
Changes:
    - Added new GPU metrics:
      1) XGMI link status - Up/Down; 1 = up; 0 = down
      2) Graphics clocks below host limit (per XCP)
         accumulators -> used to help calculate a violation status
      3) VRAM max bandwidth at max memory clock
    - Updated rocm-smi --showmetrics to include new metrics.
    Units/values reflect as indicated by driver, may differ
    from AMD SMI or other ROCm SMI interfaces which
    use these fields.
    - N/A fields means the device does not support providing this
    data.

Change-Id: I17b313345f15070a76b3a30dd8d5645d212d601b
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
2024-12-15 16:48:13 -05:00
Charis Poag 8488518b1c [SWDEV-475712] Fix MI2x target_graphics_version
Removed correcting target_graphics_version by
product name. Instead detected target_graphics_version which
needs to be corrected -> populate accordingly.

Change-Id: I90765c87e0629daea5c732dace8acfd17e8c62c7
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
2024-12-08 22:01:43 -06:00
Charis Poag 562575c73d Merge amd-staging into amd-master 20241125
Change-Id: I801dcda853066d8d2e19a8727b2b07dcafc253b4
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
2024-11-25 08:39:32 -06:00
Charis Poag d04cec7f1d [SWDEV-499029] Fix unable to change memory partition modes
Changes:
  * [API] Removed checking board name, fixes for other MI ASICs
  * [CLI] Increased progress bar to change memory partition modes
    to 140 seconds, since driver reload is variable per system

Change-Id: Ifcaf40d28b4adf5eaa800c9e3748d33749dc414a
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
2024-11-22 20:19:29 -05:00
Zhang Ava c827c54093 Merge amd-staging into amd-master 20241114
Signed-off-by: Zhang Ava <niandong.zhang@amd.com>
Change-Id: I97175c160d157e6f8ad0d94b65d2b6f2a2384949
2024-11-15 11:38:47 +08:00
gabrpham 5428d29b19 [SWDEV-478748] Changing PCIE Read/Write message TEST FAILURE to WARNING
Signed-off-by: gabrpham <Gabriel.Pham@amd.com>
Change-Id: I534a94b358f7fddbe3c11d249c6e090cf3fa121e
2024-11-13 15:05:26 -06:00
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
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
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
Peter Park 568cc6e7c7 Update changelog fmt to internal standard
Change-Id: Icdb7eb59c6770f46ddae401f23b84cd06e6d3b09
2024-11-08 16:20:49 -05:00
Zhang Ava fa2c9180d7 Merge amd-staging into amd-master 20241106
Signed-off-by: Zhang Ava <niandong.zhang@amd.com>
Change-Id: Ib125dee62e5a893871f5c6df7715177973361a02
2024-11-08 08:42:13 +08:00
Jorge López 35c1d00f5a Updates driverInitialized() to support amdgpu built as module as well as kernel built-in. Fixes ROCm/rocm_smi_lib#102 and is an updated version of ROCm/rocm_smi_lib#104
Change-Id: Icb3abe820bc67035b822358a1c04bd09a7c22b6b
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>
Reviewed-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>
2024-11-05 16:30:37 -05:00