cd46294b31
SWDEV-520384 - Improve Fat Binary loading latency ( #390 )
...
Init and fini kernel needs to be launched when we load and unload code object. Avoid looping through all kernels within a code object just to run the init and fini kernels. Compiler currently only generates 1 init and fini kernel.
2025-08-05 14:02:05 -07:00
4121a860bf
SWDEV-505833 - Remove DEBUG_CLR_SKIP_RELEASE_SCOPE flag ( #735 )
...
Cleanup debug flag DEBUG_CLR_SKIP_RELEASE_SCOPE
2025-08-05 08:31:55 -07:00
1492328894
SWDEV-547614 - Demangle graph kernel names ( #809 )
2025-08-01 14:35:30 -07:00
3f6f9d6081
SWDEV-539710 - Defer allocation of managed variable ( #652 )
...
Co-authored-by: Rahul Manocha <rmanocha@amd.com >
2025-07-31 08:30:23 -07:00
a1f056bd11
SWDEV-483895 - Use ROCr to reserve memory for HMM ( #590 )
2025-07-15 21:40:13 +05:30
a5d932f160
SWDEV-460151 - add gfx1201 to amd-staging clr ( #183 )
...
* SWDEV-460151 - add gfx1201 to amd-staging clr
* SWDEV-460151 - removed pal macro
---------
Co-authored-by: Jimbo Xie <jiabaxie@amd.com >
2025-07-11 08:51:47 -07:00
1351cd7fa8
SWDEV-539145 - Simplify host memory pool management ( #668 )
...
* SWDEV-539145 - Simplify host memory pool management
Remove unnecessary variables and functions.
Make code simpler and clear.
* Change cpu_agent_info_ into pointer.
* Restore getPreferredNumaNode()
2025-07-11 10:38:40 -04:00
397f303d97
SWDEV-508776 - support VGPRs validation ( #274 )
...
Clarify some VGPRs terms description.
Fix some wrong query logics of availableVGPRs_ and
availableRegistersPerCU_ in device info.
Add hipDeviceAttributeMaxAvailableVgprsPerThread
attribute query.
Remove hardcoding of following
info_.vgprAllocGranularity_
info_.vgprsPerSimd_
2025-07-09 10:46:52 -04:00
46d766e4e2
SWDEV-539378 - Use agent of IPC memory owner ( #570 )
...
- Currently runtime just uses the local agent as it did not check for
IPCShared()
- With this fix we query hsa_amd_pointer_info and get the right agent
for the memory to pass it to the HSA copy api
2025-07-08 12:02:01 -07:00
9c1bff0ae7
SWDEV-540576 - Abort if user request a core dump ( #653 )
...
* SWDEV-539414 - Return error status from runtime handler when HIP_SKIP_ABORT_ON_GPU_ERROR is false
* SWDEV-539414 - default handler when GPU core file is generated
* SWDEV-540576 - Abort if user request a core dump
Change-Id: I9e2c640acf559880bd13641de9103e660ef822a3
---------
Co-authored-by: Assiouras, Ioannis <Ioannis.Assiouras@amd.com >
Co-authored-by: agunashe <ajay.gunashekar@amd.com >
2025-07-03 00:29:14 +05:30
a7d7687b8f
SWDEV-539145 - Support extended fine grained system memory pool ( #603 )
...
* Add hipHostMalloc() new flag hipHostMallocUncached which will force to allocate pinned
host memory on extended fine grained system memory pool.
* Add hipHostAlloc() new flag hipHostAllocUncached which will force to allocate pinned
host memory on extended fine grained system memory pool.
* Add hipHostRegister() new flag hipHostRegisterUncached which will force to map
host memory onto extended fine grained system momory pool.
2025-07-01 10:10:10 +05:30
b584fc8cd1
SWDEV-508869 - Replace asicRevision with gfxip triple in paldevice ( #601 )
...
asicRevision is not unique in pal path now, use gfxip triple to match isa is more straight forward in pal path.
2025-06-27 10:09:21 +08:00
9699cc3864
SWDEV-508869 - Fix Linux build error for HIP on PAL ( #176 )
2025-06-27 07:51:22 +08:00
f4d78d427c
SWDEV-539399 - Support ROCCLR_MEM_HSA_CONTIGUOUS ( #610 )
...
Fix missing support of ROCCLR_MEM_HSA_CONTIGUOUS in
hipExtMallocWithFlags().
2025-06-26 14:05:23 -04:00
5d53c83806
SWDEV-535490 - Improve logging ( #441 )
...
- Include HIP version/githash in the logs
- Add a new method to print library path
2025-06-24 13:00:00 -07:00
494c0e3201
SWDEV-531996 - Add legacy fallback Mesa loading via dlsym ( #512 )
2025-06-11 08:02:51 +05:30
5fabfedbd1
SWDEV-531996 SWDEV-530154 - Use *getprocaddress to obtain Mesa functions ( #504 )
2025-06-10 13:31:32 +05:30
b72812d324
SWDEV-531711 - Fixing compilation error by moving static var to public. ( #438 )
2025-05-30 11:42:50 +05:30
5cc172c99c
SWDEV-533074 - Expose hipDeviceAttributeNumberOfXccs attribute ( #336 )
2025-05-21 22:35:42 +05:30
12131de4a9
SWDEV-529929 - hipMemGetHandleForAddressRange implementation. ( #245 )
2025-05-20 15:56:04 -04:00
bed454caa1
SWDEV-457749 - Use size of handle for range instead of actual size for physmem. ( #342 )
2025-05-20 15:24:49 -04:00
1b0ea080e4
SWDEV-523279 - Use preferred engine mask for SDMA ( #317 )
...
- ROCr now reports preferred engine for copy status. We can leverage
this for max bandwidth for inter-GPU copies
- Cleanup logging
2025-05-19 16:04:51 -07:00
5712944c7c
SWDEV-531518 - Fix offset accumulation ( #333 )
...
srcAddress/dstAddress accumulation was cumulative, which shouldnt be
done if we increment offset.
2025-05-19 18:03:06 +05:30
bb7750a946
Revert "SWDEV-522707 - Set phys_mem_handle type to sizeof(size_t) to avoid blocking address range. ( #105 )" ( #348 )
...
This reverts commit 6811fd90b8
2025-05-19 15:19:16 +05:30
f5b8db33f1
SWDEV-531711 - Report correct error code based on device failure. ( #286 )
2025-05-17 06:33:13 -04:00
f7482ef0a6
SWDEV-529449 - Bug fix when retrieving a memobj from the IPC mem handle
2025-05-13 19:18:22 +01:00
876de49b11
SWDEV-506467 - Fixing compilation issue seen on clang compilation for ASAN. ( #253 )
2025-05-12 17:16:56 -04:00
da198ac5b2
SWDEV-531678 - Remove split path from the dispatch ( #283 )
...
The split path for blit kernels are no longer necessary, since the new blit kernels
don't use the copy size as the global workload
2025-05-12 12:50:32 -04:00
a7492c516d
SWDEV-511204 - Mapped virtual memory should use device instead of host context ( #213 )
...
Since the sub-buffer(virtual memory that is mapped to device memory) is associated with device memory, it should utilize the device context instead of the host context. The original implementation caused hipMemcpyPeer to not take the P2P path, as the memory object was treated as host memory.
2025-05-12 16:55:25 +02:00
6858b0fca1
SWDEV-521135 - Make common way to set/parse UUID bytes from PAL props. ( #63 )
2025-05-12 17:00:30 +05:30
c35e9643ec
SWDEV-517078: Fix gfx11 trap handler ( #212 )
...
Fix incorrect edits done when porting the 2nd level trap handler from
the hsa-runtime.
Change-Id: I7bc5160be47b8f669efe05c4d194bc3c47fc0661
2025-05-11 01:12:28 +01:00
faac50c77a
SWDEV-528860 - reserve some memory in visible frame buffer ( #251 )
2025-05-09 20:08:23 -04:00
a320a3f214
SWDEV-528913 - support gfx950 in rocsetting ( #217 )
...
* SWDEV-528913 - support gfx950 in rocsetting
---------
Co-authored-by: Jimbo Xie <jiabaxie@amd.com >
2025-05-07 15:44:49 -04:00
6b12154583
SWDEV-518221 - Don't link against libamd_comgr.so at runtime
...
Convention is to always link against .so.* at runtime.
Having it link against .so will break on systems that package
the .so files in their dev/devel package.
This issue was found when building ROCm 6.4 for Fedora.
Commiting on behalf of GitHub user Mystro256
2025-05-07 11:56:41 -07:00
65a0181a7c
SWDEV-528808 - Release all HW queues even if only one is idle ( #240 )
...
Pytorch may not explicitly idle each queue. Thus, some queues can be considered as busy,
but have idle state in reality
2025-05-05 19:09:01 -04:00
9b018165ce
SWDEV-528808 - Disable dynamic queue by default ( #256 )
...
Dynamic queue management will be disabled by default and
the original sort logic is restored
2025-05-05 10:56:35 -04:00
9d6a0d1a4d
SWDEV-521011 - Fix alignment in PalResource::CreateSvm
2025-05-01 02:22:49 +01:00
84a4f293f4
SWDEV-526836 - add PipelineStageBlt flag ( #229 )
...
CP sync requires PipelineStageBlt flag.
2025-04-30 14:27:41 -04:00
d3fb8eda8b
SWDEV-525593, SWDEV-527293 - Acquire active queue after xferQueue is created ( #165 )
...
For xferQueue VirtualGPU::create is called after ProfilingBegin
so the active queue needs to be acquired.
2025-04-30 09:21:11 +01:00
eb62fe9f62
SWDEV-522634 - Fix device properties in hipInfo ( #203 )
2025-04-29 11:29:47 -04:00
96cadbc9e9
SWDEV-520352 - Remove HostThread and legacy monitor ( #230 )
...
* SWDEV-520352 - Remove HostThread and legacy monitor
Remove HostThread, semaphore and legacy monitor.
Make original logics of thread and command queue stricker.
Add more comments to make logics clearer.
Some other minor improvement.
Also part of SWDEV-458943.
2025-04-29 09:55:24 -04:00
99ef573399
SWDEV-523028 - print PAL failure return values in logs ( #81 )
...
* print PAL failure return values in logs
* dump kernel info incase of PAL failure
2025-04-29 11:23:43 +05:30
6811fd90b8
SWDEV-522707 - Set phys_mem_handle type to sizeof(size_t) to avoid blocking address range. ( #105 )
2025-04-29 11:19:16 +05:30
b2388dfb88
SWDEV-506467 - Skip Abort in case of crash from the device. ( #60 )
...
Change-Id: I964b2f2647d068202e9c38fcddb1337da754df8d
2025-04-29 11:19:02 +05:30
7e9d5eab7c
SWDEV-523611 - [Tools][OCL] OpenCL fails to capture with PalTrace ( #198 )
...
Finalize DevDriver initialization after device creation
2025-04-28 08:02:34 -07:00
072fb0804e
SWDEV-521647 - Fix tracking of hw_event ( #206 )
...
- When a command may possibly have two packets(like device heap
initializer), and if there is no signal on the main kernel packet the
tracking was broken as it marked HW event of the command as the first
packet signal.
- Make sure if no completion signal is attached to the second packet
then clear the HW event for the command.
2025-04-25 08:46:44 -07:00
ce24936970
SWDEV-510186 - Improve logging ( #220 )
...
- Print all arguments for logs, this is useful for debug
2025-04-25 08:40:31 -07:00
95cdc83eaf
SWDEV-511055 - fix HIP PAL memory allocation workaround for APU ( #40 )
2025-04-24 15:07:16 -07:00
1113eff3f9
SWDEV-493275 - Support scratch limit ( #20 )
...
Support programmatic query and change of scratch limit on
AMD devices.
Change-Id: Id5da355a77366f97868e462847f3916e87fd2af6
2025-04-24 17:15:25 -04:00
4f2a4b12a9
SWDEV-527731 - [Ubertrace] OpenCL driver reports wrong Instrumentation API Version ( #211 )
2025-04-24 14:06:17 -07:00
Xie, Pengda
Kudchadker, Saleel
Manocha, Rahul
Betigeri, Sourabh
Xie, Jiabao(Jimbo)
Sang, Tao
Lin, Qun
Brzak, Branislav
Jayaprakash, Karthik
Andryeyev, German
Assiouras, Ioannis
Arandjelovic, Marko
Patel, Jaydeepkumar
Six, Lancelot
Xie, AlexBin
Lambert, Jacob
Jiang, Julia
GunaShekar, Ajay
Critchley, Paul
Li, Todd tiantuo