Commit Graph

5353 Commits

Author SHA1 Message Date
Julia Jiang 1495cc77eb SWDEV-513294 - fix regression on SVM sub-test failure in Conformance
Change-Id: Ic2449dd34a9cd2b623d5f8fbe89fd042566a56e3


[ROCm/clr commit: b7eaec76fc]
2025-02-20 15:40:23 -05:00
kjayapra-amd 010253430f SWDEV-516303 - Remove SDMA retainer logic to select the engine.
Change-Id: I818129444131825cdb87e06cb495afa3e5cdb683


[ROCm/clr commit: 1f583a6870]
2025-02-20 11:34:38 -05:00
German Andryeyev a7f3ad7867 SWDEV-515356 - Make the round-robin queue selection
- Add custom compare to the map of queues, which will help with
 the round-robin selection

Change-Id: Ie67a820bfb1a5b484a1b3edced967eed94228bb8


[ROCm/clr commit: ba8e740be4]
2025-02-20 11:09:54 -05:00
German Andryeyev f9d9b2c441 SWDEV-497841 - Add virtual memory heap
Add initial implementation of virtual memory heap with
dynamic virtual memory mapping support for memory pools.
DEBUG_HIP_MEM_POOL_VMHEAP controls the new method.

Change-Id: I8dc5be2e0f34ab472f1800f43bb6243639a5e500


[ROCm/clr commit: 296dce5570]
2025-02-20 10:55:49 -05:00
German Andryeyev 6f2a603277 SWDEV-497619 - Allocate extra space in CB
Compute doesn't support IB chaining, but RGP may collect
perf counters, which require more space in CB.
Increase CB size if RGP is enabled.

Change-Id: Iaa0a620ead8541a679b0dfe5e5711af5afdba545


[ROCm/clr commit: 63cf3057ba]
2025-02-20 10:40:09 -05:00
Tim Gu 8fcbc2acfe SWDEV-502248 - Parse file path with space characters
Signed-off-by: Tim Gu <Tim.Gu@amd.com>
Change-Id: I67fb9cf5559c9c06f24627a1b25fec3e89b2d1cf


[ROCm/clr commit: 84a867fb73]
2025-02-18 10:31:21 -05:00
agunashe 52a1f5dbf7 SWDEV-507967 - Deprecate gfx9, gfx8, gfx7 on Windows
PAL_CLIENT_INTERFACE_MAJOR_VERSION from 872 --> 910

Change-Id: I03dfa2924ccdae4c2f13f09d5f34ee58298e1343


[ROCm/clr commit: ea804e16f8]
2025-02-17 02:59:41 -05:00
Vladana Stojiljkovic 7078aab436 SWDEV-510059 - Format CU mask properly
Change-Id: I80e94b4f3ea25f6988fc06d83aeb398e81ccddd1


[ROCm/clr commit: 061c5d877f]
2025-02-13 11:02:56 -05:00
Aidan Belton-Schure 4b4a35b86b SWDEV-508279 - Improve HIP event profiling
There are 2 functional changes to this patch:
* Use GPU timing for internal markers for HIP.
* Measure CPU time closer to GPU timer, to reduce delta between GPU/CPU timestamp measurements.

There are some smaller non-functional updates:
* waifForFence -> waitForFence typo
* Remove unused drmProfiling

Change-Id: I4c5fa600a842ab60e454888779edcac8449a902a


[ROCm/clr commit: 179801a750]
2025-02-13 04:15:40 -05:00
kjayapra-amd 1f648c7d94 SWDEV-511672 - Special case the Remote USWC memory usage for HIP, if the alloc size is large.
Change-Id: I524c1402b249cedfd58b56f494caa2ac057e1623


[ROCm/clr commit: cf6aabb823]
2025-02-11 06:42:18 -05:00
Saleel Kudchadker 71e1a0b10d SWDEV-504494 - Further copy improvements
- Fix regression for D2H pinned copies which adds systemscope release.
- Skip cpu wait for D2H unpinned copies as we can pass the signal of the
  barrier to rocr copy.
- Fix an old bug in sdmaEngineRetainCount_ logic
- Improve logging

Change-Id: If074bddb05564b15949b0d5f9bf12acd3692174e


[ROCm/clr commit: 4c95ee5e1e]
2025-02-11 00:55:52 -05:00
victzhan 7cd780c1cb SWDEV-485042 - Remove -I option passed into comgr when file type is not FILE_TYPE_ASM_TEXT
Change-Id: If8e469f881651f7b3dae364e8182ef1ba6f3a0d1


[ROCm/clr commit: ca35d93672]
2025-02-10 11:47:04 -05:00
Ioannis Assiouras 6a00aa8d61 SWDEV-508435 - Added a fix for double free of hsaImageObject
Change-Id: I9397f7c9dbbad7c249b359155df312cb920eba6c


[ROCm/clr commit: d05ecea253]
2025-02-05 22:21:24 +00:00
Ioannis Assiouras c0b728fcad SWDEV-513323 - Fix for BatchMemOp on devices with no image support
BatchMemop should be positioned before the image support kernels
because the total number of kernels is determined by BlitLinearTotal,
when there is no image support on the device.

Change-Id: I8e53caf744ba54259ac04bad1762eef21806f3f2


[ROCm/clr commit: 3e01da3dac]
2025-02-05 04:45:22 -05:00
taosang2 27e87ccca6 SWDEV-513458 - Add gfx950 target ID
Add gfx950 target ID

Cherry-picked
https://gerrit-git.amd.com/c/compute/ec/clr/+/997678
https://gerrit-git.amd.com/c/compute/ec/clr/+/1063519

Change-Id: I0228c5e87ceec366983fd4afb1c25e7f8161c2c2


[ROCm/clr commit: 29cc394510]
2025-02-04 18:30:23 -05:00
kjayapra-amd 892d7bb064 SWDEV-488290 - Remove Stream to Engine logic and rely on engine query status HSA API.
Change-Id: I469ab6679360c8ee8d4ee515678a8aa8d4578ebf


[ROCm/clr commit: cc62a82347]
2025-02-04 13:00:16 -05:00
Juan Manuel Martinez Caamaño 5356f13902 SWDEV-132637: Remove OpenCL cl_khr_depth_images workaround that is not needed anymore
The cl_khr_depth_images associated macro definition is defined twice in
the compiler: in opencl-c.h and automatically by the compiler deduced
from the cl-ext list. These two co-exist and there is no need to remove
cl_khr_depth_images from the cl-ext list.

If we remove cl_khr_depth_images from the cl-ext list, and we do not
include opencl-c.h the macro is not defined.

This fixes conformance test ./test_compiler compiler_defines_for_extensions
when using Comgr with -include opencl-c-base.h -fdeclare-opencl-builtins
without including opencl-c.h.

Before we got the error `ERROR: Supported extension cl_khr_depth_images
not defined in kernel`

This change is needed to eventually get rid of the opencl-c.pch that is embedded in comgr, and that makes implementing a compilation cache in comgr hard.

Change-Id: I76497874ebe7163966420d4ac23a0788b93a36fd


[ROCm/clr commit: 8c9e6d0fa5]
2025-02-04 03:14:31 -05:00
Jimbo Xie cc229f251f SWDEV-504383 - Cleaned up kForcedTimeout10us and removed IsHwEventReadyForcedWait
Also removed active_wait_timeout

Change-Id: I7a429f003c09a4df267b5c0983050704260094c6


[ROCm/clr commit: 4872b420c9]
2025-01-31 14:40:18 -05:00
taosang2 40df900647 SWDEV-501963 - Add missing codes for gfx950
Cherry-pick https://gerrit-git.amd.com/c/compute/ec/clr/+/1162997

Change-Id: I6b3c6bf55c61cffd43cd6f17b75998f751b75723


[ROCm/clr commit: 32daa8f384]
2025-01-31 14:34:49 -05:00
kjayapra-amd 712987ed08 SWDEV-509280 - Combine multiple definitions of callbackQueue into a single function.
Change-Id: Ibbb56136bec2beed71c202d75e8aec9e82640a4e


[ROCm/clr commit: 0324014710]
2025-01-30 15:58:11 -05:00
Saleel Kudchadker d0656c944b SWDEV-504494 - Resolve signal dependencies
- Resolve signal dependencies for barrier value packet if there are > 1
  depenent signals. Barrier Value packet accounts for only 1 dep signal
- Better log

Change-Id: Ia506ad5d80b91d598f92e7b539f41756e9b4b64b


[ROCm/clr commit: 2d450e8b06]
2025-01-29 19:49:02 +00:00
Jimbo Xie 0a30936c67 SWDEV-510869 - add gfx1153 id
Change-Id: I36d39a1db2392990ad9b01d70676c3c986435707


[ROCm/clr commit: 4abedf2a0e]
2025-01-28 18:15:46 -05:00
German Andryeyev ae379965dd SWDEV-459826 - Add a crash dump for a failed queue
The logic can analyze the AQL queue state and
find a failed AQL packet with the kernel's name

Change-Id: I1a478fa2c25462cd07a194784958bdf22454b897


[ROCm/clr commit: ea0b092af8]
2025-01-28 14:27:46 -05:00
Tao Sang 7803594aea SWDEV-458943 - Add fast path in wait()
wait() is redesigned with two pathes:
fast path: Use spinlock to wait for notify signal. If the
 signal hasn't been received for some loops, go to slow path.
slow path: Use condition_variable's wait().

Improve monitor wrapper for better performance.

Fix some bugs left from name removing patch.

Change-Id: I893a8353121a25d11e37c8e631caf31cc1fc1f24


[ROCm/clr commit: f2ff56af9c]
2025-01-28 12:19:55 -05:00
Saleel Kudchadker c6eef97e3e SWDEV-504494 - Set active engine for SDMA
Change-Id: I4cec84e71903c5813a7063e8b9ff1ea4473f4720


[ROCm/clr commit: d208e8052f]
2025-01-27 17:54:36 -05:00
Jacob Lambert d7371306b0 SWDEV-360440 - Prepare CLR CMake for Comgr V3 transition
Change-Id: Ia279928fd3549a45bae561d0d2d8fcf110d8c245


[ROCm/clr commit: 1fc7c6bb9a]
2025-01-27 01:09:23 -05:00
Ioannis Assiouras 8169855390 SWDEV-510319 - Fixed random segfaults in graph tests
This change fixes random segfaults in graph tests that
are seen after the change make internal callbacks non-blocking.
The callback thread that decreases the GraphExec ref count
may now run after the runtime shutdown. This can cause a segfault
because the hip::device that is accessed in GraphExec destructor
is already destroyed during runtime shutdown. This patch ensures
that the hip::device object  stays alive until after the
callback thread completes.

Change-Id: I75a6ac01f27a0b2250bbd10ed389ebfb322927af


[ROCm/clr commit: 21c223f8df]
2025-01-25 09:54:15 -05:00
Saleel Kudchadker ae7e2ecb85 SWDEV-510186 - Improve logging of kernel names
- Demangle kernel names in logs

Change-Id: I9aa58e8c109becb45ef7fc747d991bd657c4190a


[ROCm/clr commit: 9b7e0ad48a]
2025-01-24 11:43:02 -05:00
taosang2 590465543d SWDEV-507969 - Fix wrong VGPRs for some devices
Change-Id: Ia8fc19564272e2c7171d991376bf896a99085a97


[ROCm/clr commit: 799e54aa0d]
2025-01-22 10:11:47 -05:00
Pengda Xie 86921cd750 SWDEV-508590 - Fix segfault issue with hipModuleLoad
- Ensuring devProgram pointer isn't nullptr

Change-Id: Ia5786d0a2441f3a512d79b4998eb314beb98b35e


[ROCm/clr commit: f76733e5b8]
2025-01-21 11:38:37 -05:00
Sourabh Betigeri ac32b2e77e SWDEV-507104 - Removes alignment requirement for Semaphore class to resolve runtime misaligned memory issues
Change-Id: I1be3eb6e9fdcf12e995c8fe8ee30592c94f7f97a


[ROCm/clr commit: e4ba0b6262]
2025-01-20 11:27:47 -05:00
Jatin Chaudhary 0795f00a14 SWDEV-341217 - Initial work to use SPIRV in HIP
Change-Id: If5c09b5e86b498e7ac5eb05adf28cb7a1fac8101


[ROCm/clr commit: 6a5d19059d]
2025-01-20 03:54:23 -05:00
Branislav Brzak 05057b2a88 SWDEV-508743 - [6.4 Preview] Add ROCm 7.0 breaking change fields
Change-Id: I07bff42731e74a4c409505cf8981342e22ce26be


[ROCm/clr commit: 3fd46a3783]
2025-01-17 06:25:27 -05:00
Aidan Belton-Schure dc2fa93f37 SWDEV-482851 - Do not release last suballocator chunk
Change-Id: Ib28dc9df68e454ee0c0c699c1ff17588fd55f802


[ROCm/clr commit: 451b0ce768]
2025-01-13 10:14:40 -05:00
Daniel Livingston 50387f6eb5 SWDEV-489003 - [Ubertrace] OCL/HIP profiles are missing event instrumentation
Adds UberTrace support for pre-dispatch markers and barrier begin/end markers.

Moves shared definitions out of palgpuopen.hpp into shared header
palcapturemgr.hpp.

Change-Id: I9f464c689e7ff12c54eca043fc1ad65e1836a64f


[ROCm/clr commit: 541c449ce2]
2025-01-10 11:28:52 -05:00
Anusha GodavarthySurya 08c92f4793 SWDEV-480209 - Make internal callbacks non-blocking
Change-Id: Ic918d08f341abfd9a7c167d09f9c723cdc43157f


[ROCm/clr commit: 683a942364]
2025-01-10 02:16:11 -05:00
Saleel Kudchadker 16f14e4b00 SWDEV-504494 - Use system scope for D2H
- When using shader copy, make sure to use release scope for the AQL
  packet. This is a potential bug but is hidden as hipMemcpyAsync always
needs synchronization(which inserts a barrier with release scope). For
hipMemcpy we use a barrier packet to make sure its blocking. Eitherways
a barrier gets always used and hides in some ways a potential bug.

Change-Id: I57fb7f769c3179e76d712471c0905104c801d7ba


[ROCm/clr commit: c9dd95bf6c]
2025-01-10 00:34:08 -05:00
Evgenii Averin ef2a812d0a SWDEV-505769 - Fix typo
Change-Id: I2d3f65ed68157718c4439a9da7d2dcdfcbb9f93d


[ROCm/clr commit: b62995ce1a]
2025-01-08 21:31:17 -05:00
Sourabh Betigeri 36f3d7647c SWDEV-505971 - Fix size mismatch of count type to uint32_t
Change-Id: Ie526f828f816e6681ef1735d5edb2db895dace57


[ROCm/clr commit: f5b2516f5d]
2025-01-08 12:47:36 -05:00
Saleel Kudchadker d4594531ef SWDEV-506251 - Disable blit copy thresold for OpenCL
Change-Id: Id0ca43b13d5792791a42da263f6aa4496382cea6


[ROCm/clr commit: 39801b5750]
2025-01-08 02:46:01 +00:00
Saleel Kudchadker a18f2c549c SWDEV-504494 - Flush to systemscope when copying non-coherent mem
- When we use blit(compute) copies, two subsequent copies may read for
  the same source buffer, the buffer may get modified by the host in
between and if the src buffer was allocated with non-coherent flag, the
device may simply use stale value from previous cacheline fetch. This is
a corner case.

Change-Id: I2ce261c6f6fa4e5bb608f116548e5cc711ae6f3c


[ROCm/clr commit: b63005d550]
2025-01-07 12:49:22 -05:00
Jatin Jaikishan Chaudhary 8b1d0cff83 Revert "SWDEV-505971 - change setArgument arg from uint32_t to uint64_t"
This reverts commit 0830d95f6d.

Reason for revert: There needs to be memcpy size change

Change-Id: If4f51769731e54743ac705b19b4f81b2d5925d5a


[ROCm/clr commit: 446ed661a0]
2025-01-06 18:03:23 -05:00
Jatin Chaudhary 0830d95f6d SWDEV-505971 - change setArgument arg from uint32_t to uint64_t
We are passing this arg as an address, and memcpy complains about
overreading (8 bytes instead of 4).

Change-Id: Ica9207f6c5f6056a4bfc968280c76e779ded13ae


[ROCm/clr commit: a6f2a2c2af]
2025-01-06 08:16:59 -05:00
Pengda Xie 612ae28524 SWDEV-505833 - Provide functionality to avoid L2 flush for CPX mode for dispatch packets
- Added DEBUG_CLR_SKIP_RELEASE_SCOPE flag to force release scope to
   SCOPE_NONE in AQL packet header

Change-Id: Ife02cddb9d5cd4749103ce585d3d5fe9024c6868


[ROCm/clr commit: 8155943c5f]
2025-01-03 17:28:21 -05:00
Amit Pandey 81a25f9614 SWDEV-490256 - Fix uri_decode logic to handle Memory URI.
Uri decoder logic currently silently ignores processing of memory uri.
This patch enables the existing logic to handle the processing of offset
and size related to loaded code-object having memory URI.

Change-Id: If03579cefb11d91f667410464dc89404df9270a3


[ROCm/clr commit: 11cd37ce0b]
2024-12-25 11:07:16 -05:00
taosang2 da613fbbeb SWDEV-479958 - Support different address mode
Support different address modes in X, Y, Z directions

Change-Id: If1db5a8af33c92dd14b48968c3e8eceb97daea6c


[ROCm/clr commit: d82d6a78cf]
2024-12-23 16:39:54 -05:00
sonadeem ad3d2b0679 SWDEV-503436 - Fix incorrect OptionGroup for FSanitize option
NOPTION is meant for component options or alias runtime options so
the option group must not be OA_RUNTIME or OA_MISC_ALIAS must be set,
otherwise we incorrectly assume that it has an option variable and
attempting to write to it causes corruption of OptionVariables.

Change-Id: Iafb5a8f743e5ed0f87be36061c44578178f6cfde


[ROCm/clr commit: caa10572cb]
2024-12-20 10:14:51 -05:00
Saleel Kudchadker fda4ff1f9d SWDEV-504340 - Move cast of cl_mem inside the condition
Change-Id: I9c91f5d945a8d8bd2b2f55e3d11ede66afe4eef7


[ROCm/clr commit: fa63919a63]
2024-12-17 12:58:12 -05:00
Ioannis Assiouras 2c8805e536 SWDEV-483134 - Remove hipExtHostAlloc API
Change-Id: I60777ef5c56b60dd8100d0d794ca10fb3b96a555


[ROCm/clr commit: e8b2fdab96]
2024-12-16 17:13:49 -05:00
Pengda Xie 17c7b3b270 SWDEV-503764 - Add wptr and rptr to ClPrint for dispatch barrier methods
- added wptr and rptr to ClPrint in dispatchBarrierPacket and dispatchBarrierValuePacket

Change-Id: I8a62289deb23c9f657a9b0ac6138bb55eafecba2


[ROCm/clr commit: 078fe7e5de]
2024-12-16 16:45:30 -05:00