AI/rocm-systems
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
64,650 Commits 3 Branches 0 Tags
bebe65f104fbe4a9c16a23ed4cf197301e361b87
Commit Graph

64650 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
kcossett-amd 07bb699993 Add Pre-Commit Hooks (#212) 
Pre-commit hooks for: 
- clang-format
- cmake-format
- copyright header check
- YAML check
- Trailing whitespace and end-of-file newline check

---------

Co-authored-by: David Galiffi <David.Galiffi@amd.com>
Co-authored-by: Peter Park <git@peterjunpark.com>

[ROCm/rocprofiler-systems commit: 54e91f1c2d]
 2025-05-26 14:50:48 -04:00
kcossett-amd 54e91f1c2d Add Pre-Commit Hooks (#212) 
Pre-commit hooks for: 
- clang-format
- cmake-format
- copyright header check
- YAML check
- Trailing whitespace and end-of-file newline check

---------

Co-authored-by: David Galiffi <David.Galiffi@amd.com>
Co-authored-by: Peter Park <git@peterjunpark.com>
 2025-05-26 14:50:48 -04:00
Pham, Gabriel 87c455684d [SWDEV-533221] Synced rocm-smi with amd-smi lib to fix warning messages (#71) 
* Removed URL that was on prohibited source list

---------

Signed-off-by: Gabriel Pham <Gabriel.Pham@amd.com.>


[ROCm/rocm_smi_lib commit: 4243e42758]
 2025-05-26 10:08:16 -05:00
Pham, Gabriel 4243e42758 [SWDEV-533221] Synced rocm-smi with amd-smi lib to fix warning messages (#71) 
* Removed URL that was on prohibited source list

---------

Signed-off-by: Gabriel Pham <Gabriel.Pham@amd.com.>
 2025-05-26 10:08:16 -05:00
Eric Huang 8887d25304 libhsakmt: add big system buffer allocation support 
when allocating userptr buffer in system ram with size bigger
than or equal 512G, TTM has limit and returns error, to split one
big buffer into multiple small buffers in vm_object will solve
this issue.

Signed-off-by: Eric Huang <jinhuieric.huang@amd.com>
 2025-05-26 11:04:30 -04:00
Eric Huang 2c6f84b12c libhsakmt: add big system buffer allocation support 
when allocating userptr buffer in system ram with size bigger
than or equal 512G, TTM has limit and returns error, to split one
big buffer into multiple small buffers in vm_object will solve
this issue.

Signed-off-by: Eric Huang <jinhuieric.huang@amd.com>


[ROCm/ROCR-Runtime commit: 8887d25304]
 2025-05-26 11:04:30 -04:00
Brzak, Branislav d17388cd6b SWDEV-518962 - Match hipCtxGetApiVersion signature with Cuda (#327) 
[ROCm/clr commit: ee2d4a0358]
 2025-05-26 20:28:22 +05:30
Brzak, Branislav ee2d4a0358 SWDEV-518962 - Match hipCtxGetApiVersion signature with Cuda (#327) 2025-05-26 20:28:22 +05:30
Brzak, Branislav 159f1d3d93 SWDEV-518962 - Match hipCtxGetApiVersion signature with Cuda (#81) 
[ROCm/hip commit: c80b7f7cb1]
 2025-05-26 20:28:04 +05:30
Brzak, Branislav c80b7f7cb1 SWDEV-518962 - Match hipCtxGetApiVersion signature with Cuda (#81) 2025-05-26 20:28:04 +05:30
Castillo, Juan eaa2000af5 [SWDEV-523359] fan_read_write: Add set fan speed validation check. (#61) 
[SWDEV-523359] fan_read_write: Add set fan speed validation check.
- Handled NOT_SUPPORTED status which previously caused rsmitst to false fail
- Added continute statement to proceed with rest of FanReadWrite test.
- fixed spacing line 140

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

[ROCm/rocm_smi_lib commit: ac31c6e576]
 2025-05-26 09:54:41 -05:00
Castillo, Juan ac31c6e576 [SWDEV-523359] fan_read_write: Add set fan speed validation check. (#61) 
[SWDEV-523359] fan_read_write: Add set fan speed validation check.
- Handled NOT_SUPPORTED status which previously caused rsmitst to false fail
- Added continute statement to proceed with rest of FanReadWrite test.
- fixed spacing line 140

Signed-off-by: Juan Castillo <juan.castillo@amd.com>
 2025-05-26 09:54:41 -05:00
Lytovchenko, Danylo 436c25aa47 SWDEV-12345 Add PR title and commit message validation (#349) 
[ROCm/clr commit: 7f6020d599]
 2025-05-26 15:13:31 +02:00
Lytovchenko, Danylo 7f6020d599 SWDEV-12345 Add PR title and commit message validation (#349) 2025-05-26 15:13:31 +02:00
Lytovchenko, Danylo e3a6d00822 SWDEV-123456 - Add PR description validation (#354) 
[ROCm/clr commit: e12c7200b9]
 2025-05-26 15:13:15 +02:00
Lytovchenko, Danylo e12c7200b9 SWDEV-123456 - Add PR description validation (#354) 2025-05-26 15:13:15 +02:00
Lytovchenko, Danylo 600f07f580 SWDEV-123456 - add keywords scan (#395) 
[ROCm/clr commit: d42622b4c0]
 2025-05-26 15:12:43 +02:00
Lytovchenko, Danylo d42622b4c0 SWDEV-123456 - add keywords scan (#395) 2025-05-26 15:12:43 +02:00
Dittakavi, Satyanvesh 104cc15010 SWDEV-418904 - Link the hiprtc tests with hiprtc library explicitly (#201) 
[ROCm/hip-tests commit: a837598032]
 2025-05-26 18:42:10 +05:30
Dittakavi, Satyanvesh a837598032 SWDEV-418904 - Link the hiprtc tests with hiprtc library explicitly (#201) 2025-05-26 18:42:10 +05:30
Dittakavi, Satyanvesh f3da3d39fe SWDEV-508973 - Fix the catch tests failures due to change in kernel validation error codes to match CUDA (#198) 
[ROCm/hip-tests commit: 1be3aa8283]
 2025-05-26 18:41:58 +05:30
Dittakavi, Satyanvesh 1be3aa8283 SWDEV-508973 - Fix the catch tests failures due to change in kernel validation error codes to match CUDA (#198) 2025-05-26 18:41:58 +05:30
Harrymanoharan, Jessey 1868e4e595 SWDEV-531711 - Enable skipping host side abort when GPU crashes. (#380) 
Co-authored-by: kjayapra-amd <karthik.jayaprakash@amd.com>

[ROCm/clr commit: 3930ae2524]
 2025-05-26 17:52:02 +05:30
Harrymanoharan, Jessey 3930ae2524 SWDEV-531711 - Enable skipping host side abort when GPU crashes. (#380) 
Co-authored-by: kjayapra-amd <karthik.jayaprakash@amd.com>
 2025-05-26 17:52:02 +05:30
Flora Cui e884650952 rocrtst: performance::memory_async_copy test fix on DXG 
Signed-off-by: Flora Cui <flora.cui@amd.com>
 2025-05-26 15:01:27 +08:00
Flora Cui 4360679cb7 rocrtst: performance::memory_async_copy test fix on DXG 
Signed-off-by: Flora Cui <flora.cui@amd.com>


[ROCm/ROCR-Runtime commit: e884650952]
 2025-05-26 15:01:27 +08:00
Amber Lin 31d51acb26 kfdtest: blacklist KFDSVMEvictTest.QueueTest 
Temporarily blacklist KFDSVMEvictTest.QueueTest on gfx950

Signed-off-by: Amber Lin <Amber.Lin@amd.com>
 2025-05-23 01:22:11 -04:00
Amber Lin 9c6828647b kfdtest: blacklist KFDSVMEvictTest.QueueTest 
Temporarily blacklist KFDSVMEvictTest.QueueTest on gfx950

Signed-off-by: Amber Lin <Amber.Lin@amd.com>


[ROCm/ROCR-Runtime commit: 31d51acb26]
 2025-05-23 01:22:11 -04:00
Bhardwaj, Gopesh abf3f869e9 Making ROCTx API doxygen generated document more readable (#385) 
* Making ROCTx API doxygen generated document more readable

* fixing build

* Fix linking errors

* Fixing header

* Fixing Topics and Types

* doxygen configuration fixes

* Fixing build

* Fix unnecessory doc parsing warnings

* formatting and linting fixes

* rebasing SDK modular PR

* Fixing missing line

* Fixing ROCtx documentation after merge

* Removing flake changes

* changed back WARN_IF_DOC_ERROR to Yes

[ROCm/rocprofiler-sdk commit: b48fa532bc]
 2025-05-22 18:08:55 -05:00
Bhardwaj, Gopesh b48fa532bc Making ROCTx API doxygen generated document more readable (#385) 
* Making ROCTx API doxygen generated document more readable

* fixing build

* Fix linking errors

* Fixing header

* Fixing Topics and Types

* doxygen configuration fixes

* Fixing build

* Fix unnecessory doc parsing warnings

* formatting and linting fixes

* rebasing SDK modular PR

* Fixing missing line

* Fixing ROCtx documentation after merge

* Removing flake changes

* changed back WARN_IF_DOC_ERROR to Yes
 2025-05-22 18:08:55 -05:00
David Yat Sin da2607024b rocr: Perform memcpy for small code-object loads 
On large BAR systems, for small-sized code-objects, we get performance
using direct memcpy due to latencies when doing the blit-copy.
 2025-05-22 18:39:19 -04:00
David Yat Sin 342e478e7d rocr: Perform memcpy for small code-object loads 
On large BAR systems, for small-sized code-objects, we get performance
using direct memcpy due to latencies when doing the blit-copy.


[ROCm/ROCR-Runtime commit: da2607024b]
 2025-05-22 18:39:19 -04:00
David Yat Sin e969e01f54 rocr: Perform range based cache invalidates 
Invalidate only the address range that covers the newly copied
code-object. This avoids invalidating I$ for old code objects and thus
might increase I$ hit rate.
 2025-05-22 18:39:19 -04:00
David Yat Sin 9c5bb61708 rocr: Perform range based cache invalidates 
Invalidate only the address range that covers the newly copied
code-object. This avoids invalidating I$ for old code objects and thus
might increase I$ hit rate.


[ROCm/ROCR-Runtime commit: e969e01f54]
 2025-05-22 18:39:19 -04:00
Vaddireddy, Sushma 4d29b74750 Unit test fix - calculate aggregate sum based on instance size (#410) 
* Unit test fix- calculate aggregate sum based on instance size

* Update GRBM instance size

* aggregate sum

---------

Co-authored-by: Sushma Vaddireddy <svaddire@amd.com>

[ROCm/rocprofiler-sdk commit: 7045a4c689]
 2025-05-22 13:35:38 -07:00
Vaddireddy, Sushma 7045a4c689 Unit test fix - calculate aggregate sum based on instance size (#410) 
* Unit test fix- calculate aggregate sum based on instance size

* Update GRBM instance size

* aggregate sum

---------

Co-authored-by: Sushma Vaddireddy <svaddire@amd.com>
 2025-05-22 13:35:38 -07:00
Baraldi, Giovanni cfea25a13a ATT Doc updates. Fix trace-decode return error. (#406) 
* Doc updates. Some cleanup.

* Formatting

---------

Co-authored-by: Giovanni Baraldi <gbaraldi@amd.com>

[ROCm/rocprofiler-sdk commit: 3cb0c87f53]
 2025-05-22 14:50:45 -05:00
Baraldi, Giovanni 3cb0c87f53 ATT Doc updates. Fix trace-decode return error. (#406) 
* Doc updates. Some cleanup.

* Formatting

---------

Co-authored-by: Giovanni Baraldi <gbaraldi@amd.com>
 2025-05-22 14:50:45 -05:00
anujshuk-amd ef90bab236 Update transpose-rocprofiler-* tests (#210) 
- Updating counters collected and tested for on Navi-based machines
- Update add CMake function to query GPU architectures
- Update decode tests to use new functions

[ROCm/rocprofiler-systems commit: 4c24975626]
 2025-05-22 14:04:33 -04:00
anujshuk-amd 4c24975626 Update transpose-rocprofiler-* tests (#210) 
- Updating counters collected and tested for on Navi-based machines
- Update add CMake function to query GPU architectures
- Update decode tests to use new functions
 2025-05-22 14:04:33 -04:00
Belton-Schure, Aidan 983a5925c6 SWDEV-508966 - hipGetTextureAlignmentOffset return hipErrorInvalidTexture (#389) 
[ROCm/clr commit: 7aae33951b]
 2025-05-22 23:19:45 +05:30
Belton-Schure, Aidan 7aae33951b SWDEV-508966 - hipGetTextureAlignmentOffset return hipErrorInvalidTexture (#389) 2025-05-22 23:19:45 +05:30
Belton-Schure, Aidan 5d4ae6346e SWDEV-508977 - return error in global capture mode for hipEventQuery (#388) 
[ROCm/clr commit: 51dd60a64f]
 2025-05-22 23:17:57 +05:30
Belton-Schure, Aidan 51dd60a64f SWDEV-508977 - return error in global capture mode for hipEventQuery (#388) 2025-05-22 23:17:57 +05:30
Ramakrishnan, Ranjith 1785cff6a5 CMake: Remove file reorganization backward compatibility code (#176) 
The feature has already been disabled, and the related source code is no longer required
 2025-05-22 09:47:26 -07:00
Ramakrishnan, Ranjith 85cd72987f CMake: Remove file reorganization backward compatibility code (#176) 
The feature has already been disabled, and the related source code is no longer required

[ROCm/ROCR-Runtime commit: 1785cff6a5]
 2025-05-22 09:47:26 -07:00
Roy, Rakesh 0bd2233a69 SWDEV-533670 - Bump major version for ROCm 7.0 (#87) 
[ROCm/hip commit: c3050b93c6]
 2025-05-22 20:55:59 +05:30
Roy, Rakesh c3050b93c6 SWDEV-533670 - Bump major version for ROCm 7.0 (#87) 2025-05-22 20:55:59 +05:30
Stojiljkovic, Vladana 1a36230bf2 Match hipStreamAddCallback capture behavior with nvidia (#386) 
Co-authored-by: Anusha GodavarthySurya <Anusha.GodavarthySurya@amd.com>

[ROCm/clr commit: a0e946c2cc]
 2025-05-22 20:54:04 +05:30
Stojiljkovic, Vladana a0e946c2cc Match hipStreamAddCallback capture behavior with nvidia (#386) 
Co-authored-by: Anusha GodavarthySurya <Anusha.GodavarthySurya@amd.com>
 2025-05-22 20:54:04 +05:30