2c02ee0a99
changing the HIP-VERSION to 6.3 to avoid using hip_fp8 for older ROCm versions ( #1764 )
...
Co-authored-by: Marzieh Berenjkoub <mberenjk@.amd.com>
[ROCm/rccl commit: 5fb9d8f828
2025-06-26 11:15:01 -05:00
5fb9d8f828
changing the HIP-VERSION to 6.3 to avoid using hip_fp8 for older ROCm versions ( #1764 )
...
Co-authored-by: Marzieh Berenjkoub <mberenjk@.amd.com>
2025-06-26 11:15:01 -05:00
ffb17bd9d7
Revert LL64 cutoff points based on internal tuning ( #1771 )
...
[ROCm/rccl commit: 7e2ac00980
2025-06-26 11:59:42 -04:00
7e2ac00980
Revert LL64 cutoff points based on internal tuning ( #1771 )
2025-06-26 11:59:42 -04:00
1d59cbb06d
Add support for MI 100 with rocprofiler-sdk ( #768 )
...
* Add custom rocprofiler-sdk counter definitions file for MI 100
* Update CHANGELOG to mention that accumulation counters will not be
collected when profiling on MI 100 using rocprofiler-sdk/rocprofv3
* Migrate accum_counters.yaml to code
[ROCm/rocprofiler-compute commit: a95a45d69a
2025-06-26 09:03:18 -04:00
a95a45d69a
Add support for MI 100 with rocprofiler-sdk ( #768 )
...
* Add custom rocprofiler-sdk counter definitions file for MI 100
* Update CHANGELOG to mention that accumulation counters will not be
collected when profiling on MI 100 using rocprofiler-sdk/rocprofv3
* Migrate accum_counters.yaml to code
2025-06-26 09:03:18 -04:00
069e097234
SWDEV-123456 - fix runners name ( #208 )
...
[ROCm/hip commit: 2ec7b7fdb4
2025-06-26 12:15:49 +02:00
2ec7b7fdb4
SWDEV-123456 - fix runners name ( #208 )
2025-06-26 12:15:49 +02:00
34507629ef
SWDEV-123456 - fix runners names ( #18 )
...
[ROCm/hipother commit: 1992d81122
2025-06-26 12:15:39 +02:00
1992d81122
SWDEV-123456 - fix runners names ( #18 )
2025-06-26 12:15:39 +02:00
f2c4dd51b1
SWDEV-123456 - fix runners name ( #351 )
...
[ROCm/hip-tests commit: c9ce31fb24
2025-06-26 12:15:36 +02:00
c9ce31fb24
SWDEV-123456 - fix runners name ( #351 )
2025-06-26 12:15:36 +02:00
f890d0d4f7
SWDEV-461599 - scrub HCC in hip documents ( #178 )
...
[ROCm/hip commit: 8eca6453dc
2025-06-26 15:06:31 +05:30
8eca6453dc
SWDEV-461599 - scrub HCC in hip documents ( #178 )
2025-06-26 15:06:31 +05:30
cc2129b2f4
SWDEV-461599 - scrub HCC in clr documents ( #569 )
...
[ROCm/clr commit: b5cd8321d3
2025-06-26 15:05:59 +05:30
b5cd8321d3
SWDEV-461599 - scrub HCC in clr documents ( #569 )
2025-06-26 15:05:59 +05:30
dbfd869936
SWDEV-533232 Add num_threads API in cooperative_groups ( #437 )
...
* Add num_threads API in cooperative_groups
* Reimplementsize API as its alias.
* Update changelog
[ROCm/clr commit: a4631b5700
2025-06-26 15:05:17 +05:30
a4631b5700
SWDEV-533232 Add num_threads API in cooperative_groups ( #437 )
...
* Add num_threads API in cooperative_groups
* Reimplementsize API as its alias.
* Update changelog
2025-06-26 15:05:17 +05:30
c530e72a7c
SWDEV-512344 - Allow unmapping of only complete subbuffers ( #608 )
...
* Do not allow partial unmapping
* Add check to prevent out of bounds unmap
* Improve code quality
* Use getOrigin instead of getOffset
[ROCm/clr commit: 349b83c1f6
2025-06-26 15:01:33 +05:30
349b83c1f6
SWDEV-512344 - Allow unmapping of only complete subbuffers ( #608 )
...
* Do not allow partial unmapping
* Add check to prevent out of bounds unmap
* Improve code quality
* Use getOrigin instead of getOffset
2025-06-26 15:01:33 +05:30
18dc7b2d24
SWDEV-123456 - use explicit PR head SHA for clang-format ( #623 )
...
* SWDEV-123456 - use explicit PR head SHA for clang-format
* SWDEV-123456 - set new runners name
[ROCm/clr commit: 704fea29cf
2025-06-26 10:46:02 +02:00
704fea29cf
SWDEV-123456 - use explicit PR head SHA for clang-format ( #623 )
...
* SWDEV-123456 - use explicit PR head SHA for clang-format
* SWDEV-123456 - set new runners name
2025-06-26 10:46:02 +02:00
dee5bdc679
rocr: replace direct libhsakmt calls with driver interfaces
...
Replace direct hsakmt API calls with calls through the driver abstraction layer
in queue management related functions. This includes:
- CreateQueue/DestroyQueue operations
- Queue update and GWS allocation
- CU masking configuration
Also update the corresponding error status types from HSAKMT_STATUS to
hsa_status_t and adjust error handling accordingly.
Signed-off-by: Honglei Huang <Honglei1.Huang@amd.com >
2025-06-26 15:53:01 +08:00
5e7fd3b5ba
rocr: replace direct libhsakmt calls with driver interfaces
...
Replace direct hsakmt API calls with calls through the driver abstraction layer
in queue management related functions. This includes:
- CreateQueue/DestroyQueue operations
- Queue update and GWS allocation
- CU masking configuration
Also update the corresponding error status types from HSAKMT_STATUS to
hsa_status_t and adjust error handling accordingly.
Signed-off-by: Honglei Huang <Honglei1.Huang@amd.com >
[ROCm/ROCR-Runtime commit: dee5bdc679
2025-06-26 15:53:01 +08:00
046591419f
rocr: use driver interface for memory and cache properties query
...
Replace direct libhsakmt calls with driver interface methods
in GpuAgent initialization:
- Replace hsaKmtGetNodeMemoryProperties with driver().GetMemoryProperties
- Replace hsaKmtGetNodeCacheProperties with driver().GetCacheProperties
Signed-off-by: Honglei Huang <Honglei1.Huang@amd.com >
2025-06-26 15:53:01 +08:00
75a7da05be
rocr: use driver interface for memory and cache properties query
...
Replace direct libhsakmt calls with driver interface methods
in GpuAgent initialization:
- Replace hsaKmtGetNodeMemoryProperties with driver().GetMemoryProperties
- Replace hsaKmtGetNodeCacheProperties with driver().GetCacheProperties
Signed-off-by: Honglei Huang <Honglei1.Huang@amd.com >
[ROCm/ROCR-Runtime commit: 046591419f
2025-06-26 15:53:01 +08:00
ffa07e28e7
rocr: remove unused agent properties reference in scratch initialization
...
The agent properties variable `agent_props` was declared but never used
in the `InitScratchSRD()` function. Which casued compile warning:
runtime/core/runtime/amd_aql_queue.cpp:1880:15: warning:
unused variable ‘agent_props’ [-Wunused-variable]
1880 | const auto& agent_props = agent_->properties();
No functional changes, purely a code cleanup commit.
2025-06-26 13:05:40 +08:00
97992b809f
rocr: remove unused agent properties reference in scratch initialization
...
The agent properties variable `agent_props` was declared but never used
in the `InitScratchSRD()` function. Which casued compile warning:
runtime/core/runtime/amd_aql_queue.cpp:1880:15: warning:
unused variable ‘agent_props’ [-Wunused-variable]
1880 | const auto& agent_props = agent_->properties();
No functional changes, purely a code cleanup commit.
[ROCm/ROCR-Runtime commit: ffa07e28e7
2025-06-26 13:05:40 +08:00
d34a38ccfc
Add proxyTrace ( #1732 )
...
This feature tracks the proxy events and status of each send/recv op. ProxyTrace keeps a fixed number of active ops in host mem and dumps the status of each op when the program crashes or hangs.
[ROCm/rccl commit: 020dcf0a7c
2025-06-25 23:01:34 -05:00
020dcf0a7c
Add proxyTrace ( #1732 )
...
This feature tracks the proxy events and status of each send/recv op. ProxyTrace keeps a fixed number of active ops in host mem and dumps the status of each op when the program crashes or hangs.
2025-06-25 23:01:34 -05:00
9cb96eafdb
added new gfx target ( #171 )
...
[ROCm/rocshmem commit: e2bae5131a
2025-06-25 17:35:54 -06:00
e2bae5131a
added new gfx target ( #171 )
2025-06-25 17:35:54 -06:00
1a339feb1f
rocr: Move OpenSMI call to Driver
2025-06-25 15:53:02 -07:00
8daec0261f
rocr: Move OpenSMI call to Driver
...
[ROCm/ROCR-Runtime commit: 1a339feb1f
2025-06-25 15:53:02 -07:00
58532974bc
Modified test for agent.cpp where GPUs are missing the UUID ( #405 )
...
* Modified test for agent.cpp where multiple GPUs share th same UUID
* Updated for review comments
[ROCm/rocprofiler-sdk commit: eb8c9af720
2025-06-25 17:36:56 -05:00
eb8c9af720
Modified test for agent.cpp where GPUs are missing the UUID ( #405 )
...
* Modified test for agent.cpp where multiple GPUs share th same UUID
* Updated for review comments
2025-06-25 17:36:56 -05:00
75895ce046
Fixing Docker Pull Rate Issue ( #483 )
...
Update rocm_release_compatibility.yml
[ROCm/rocprofiler-sdk commit: 73ee59244d
2025-06-25 17:16:22 -05:00
73ee59244d
Fixing Docker Pull Rate Issue ( #483 )
...
Update rocm_release_compatibility.yml
2025-06-25 17:16:22 -05:00
d2ee7ba673
[gfx12] Add support for gfx1200 ( #131 )
...
* [gfx12] Add support for gfx1200
* [gfx12] Rename CP_PERFMON_CNTL_1 to CP_PERFMON_CNTL for better compatibility
[ROCm/aqlprofile commit: c872dcda53
2025-06-25 13:28:51 -07:00
c872dcda53
[gfx12] Add support for gfx1200 ( #131 )
...
* [gfx12] Add support for gfx1200
* [gfx12] Rename CP_PERFMON_CNTL_1 to CP_PERFMON_CNTL for better compatibility
2025-06-25 13:28:51 -07:00
1a807c27de
Python Lint Fix ( #482 )
...
Update python.yml
[ROCm/rocprofiler-sdk commit: 9ec3cc7f62
2025-06-25 14:58:56 -05:00
9ec3cc7f62
Python Lint Fix ( #482 )
...
Update python.yml
2025-06-25 14:58:56 -05:00
b4a7550214
Fixing Core RPM Jobs ( #132 )
...
Update continuous_integration.yml
[ROCm/aqlprofile commit: 5bcad05345
2025-06-25 13:42:04 -05:00
5bcad05345
Fixing Core RPM Jobs ( #132 )
...
Update continuous_integration.yml
2025-06-25 13:42:04 -05:00
469137eb7d
Multiple CI Fixes & Clean up ( #477 )
...
* Update continuous_integration.yml
* Update continuous_integration.yml
* Update continuous_integration.yml
* Update continuous_integration.yml
* Update continuous_integration.yml
* Update continuous_integration.yml
* Update continuous_integration.yml
* Update continuous_integration.yml
* Update continuous_integration.yml
* Update continuous_integration.yml
* Update continuous_integration.yml
* Update continuous_integration.yml
* Update continuous_integration.yml
* Update continuous_integration.yml
* Update continuous_integration.yml
* Update continuous_integration.yml
* Update continuous_integration.yml
* Update continuous_integration.yml
* Update continuous_integration.yml
* updating build essentials
* updating build essentials
* Update continuous_integration.yml
* Update continuous_integration.yml
* Update continuous_integration.yml
* Update continuous_integration.yml
* Update continuous_integration.yml
* Update continuous_integration.yml
* Update continuous_integration.yml
* Update continuous_integration.yml
* Update continuous_integration.yml
* Update continuous_integration.yml
---------
Co-authored-by: gobhardw <gopesh.bhardwaj@amd.com >
[ROCm/rocprofiler-sdk commit: 25f5cbc0c7
2025-06-25 13:38:13 -05:00
25f5cbc0c7
Multiple CI Fixes & Clean up ( #477 )
...
* Update continuous_integration.yml
* Update continuous_integration.yml
* Update continuous_integration.yml
* Update continuous_integration.yml
* Update continuous_integration.yml
* Update continuous_integration.yml
* Update continuous_integration.yml
* Update continuous_integration.yml
* Update continuous_integration.yml
* Update continuous_integration.yml
* Update continuous_integration.yml
* Update continuous_integration.yml
* Update continuous_integration.yml
* Update continuous_integration.yml
* Update continuous_integration.yml
* Update continuous_integration.yml
* Update continuous_integration.yml
* Update continuous_integration.yml
* Update continuous_integration.yml
* updating build essentials
* updating build essentials
* Update continuous_integration.yml
* Update continuous_integration.yml
* Update continuous_integration.yml
* Update continuous_integration.yml
* Update continuous_integration.yml
* Update continuous_integration.yml
* Update continuous_integration.yml
* Update continuous_integration.yml
* Update continuous_integration.yml
* Update continuous_integration.yml
---------
Co-authored-by: gobhardw <gopesh.bhardwaj@amd.com >
2025-06-25 13:38:13 -05:00
738627af29
Fixed NoDRM Failures
...
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com >
Signed-off-by: Williams, Justin <Justin.Williams@amd.com >
2025-06-25 13:18:25 -05:00
21f5755794
Fixed NoDRM Failures
...
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com >
Signed-off-by: Williams, Justin <Justin.Williams@amd.com >
[ROCm/amdsmi commit: 738627af29
2025-06-25 13:18:25 -05:00
bad4868f39
Fixed NoDRM Failures
...
Signed-off-by: Justin Williams <Justin.Williams@amd.com >
2025-06-25 13:18:25 -05:00
010f95bfb7
Fixed NoDRM Failures
...
Signed-off-by: Justin Williams <Justin.Williams@amd.com >
[ROCm/amdsmi commit: bad4868f39
2025-06-25 13:18:25 -05:00
mberenjk
Mustafa Abduljabbar
vedithal-amd
Lytovchenko, Danylo
Jiang, Julia
Sicarov, Dragoslav
Arandjelovic, Marko
Honglei Huang
Dingming Wu
akolliasAMD
Tony Gutierrez
Trowbridge, Ian
Elwazir, Ammar
Ma, Bing
Williams, Justin