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
b2388dfb88
SWDEV-506467 - Skip Abort in case of crash from the device. ( #60 )
...
Change-Id: I964b2f2647d068202e9c38fcddb1337da754df8d
2025-04-29 11:19:02 +05:30
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
b5c9cbc236
SWDEV-508632 - Align address to 2 MBs for hidden heap allocation. ( #29 )
2025-04-02 16:33:29 +05:30
28967982b2
SWDEV-517481 - Add dynamic queue management ( #37 )
...
Enabled by defaulty. DEBUG_HIP_DYNAMIC_QUEUES controls the feature
2025-03-19 11:22:50 -04:00
37d606d193
SWDEV-513197 - Unify getBuffer implementation
...
- Use getBuffer/releaseBuffer in BlitManager
- Cleanup XferBuffer as we use ManagedBuffer for both reads/writes
Change-Id: I2661b85dd012763b17a38a743fec1b1d79125f67
2025-02-28 12:47:51 -05:00
ba8e740be4
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
2025-02-20 11:09:54 -05:00
cc62a82347
SWDEV-488290 - Remove Stream to Engine logic and rely on engine query status HSA API.
...
Change-Id: I469ab6679360c8ee8d4ee515678a8aa8d4578ebf
2025-02-04 13:00:16 -05:00
4872b420c9
SWDEV-504383 - Cleaned up kForcedTimeout10us and removed IsHwEventReadyForcedWait
...
Also removed active_wait_timeout
Change-Id: I7a429f003c09a4df267b5c0983050704260094c6
2025-01-31 14:40:18 -05:00
0324014710
SWDEV-509280 - Combine multiple definitions of callbackQueue into a single function.
...
Change-Id: Ibbb56136bec2beed71c202d75e8aec9e82640a4e
2025-01-30 15:58:11 -05:00
ea0b092af8
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
2025-01-28 14:27:46 -05:00
d82d6a78cf
SWDEV-479958 - Support different address mode
...
Support different address modes in X, Y, Z directions
Change-Id: If1db5a8af33c92dd14b48968c3e8eceb97daea6c
2024-12-23 16:39:54 -05:00
14f58fc74d
SWDEV-501757 - Clean-up signal creation
...
Use hsa_amd_signal_create() if settings.system_scope_signal_ is true.
Change-Id: I6d440155dfbcd5bf03658583a93827cb1c56537c
2024-12-11 09:57:50 -05:00
f4b9d3b7bd
SWDEV-501757 - Use signals without interrupts
...
In active wait mode use signals without interrupts by default and switch
to the interrupts only if a callback is required.
Change-Id: Ibcde8f7d44c70f8fb8fa5e0a7fdd8b08a2982a8e
2024-12-09 15:16:15 -05:00
b498103f9b
SWDEV-485904 - propagate hsa_amd_vmem_address_free error to hip API
...
Unit_hipMemSetAccess_GrowVMM test fails with
HSA_STATUS_ERROR_RESOURCE_FREE silently
Change-Id: I7a78410e432de4a2e877062782abf8761645f392
2024-10-21 10:12:32 -04:00
29cc678d8d
SWDEV-483586 - Unblock staging H2D transfers
...
Although unpinned copies require synchronizations
in HIP, runtime can avoid syncs for H2D copies with
a staging buffer
Change-Id: If2203c6bc0cbd89742823688dc8e89e9acd873b2
2024-09-21 10:25:27 -04:00
12a39fbf22
SWDEV-480772 - Remove name variable from amd::Monitor class.
...
Change-Id: Ie2a4fa44f485786227230f8a892e090e718aa30e
2024-09-19 11:55:01 -04:00
07261002b1
SWDEV-439234 - Fix for Segfault in ValidateMemAccess
...
Change-Id: I251d277eb5af16ba5c0de85ffd142a5f64fa469d
2024-09-18 10:52:32 -04:00
6211037f63
SWDEV-439234 - Access check before memcpy and kernel operations.
...
Change-Id: I7057125c03460db205409e19980145298c190fe2
2024-09-06 14:30:00 -04:00
ddbd7039b0
SWDEV-478921 - Destroy Queue created by Coop Launch
...
Change-Id: I7f31ce05421479ff1de138cae26aafa071e956e2
2024-09-02 02:35:08 -04:00
e7a7feb273
SWDEV-464828 - Initial implementation of VMM IPC on PAL/Windows.
...
Change-Id: I3d5e148fad9105704db6724b00df06bef4fc9d2f
2024-07-16 10:38:35 -04:00
57156c524d
SWDEV-467102 - Hidden heap init for graph capture
...
If the graph has kernels that does device side allocation, during packet capture, heap is
allocated because heap pointer has to be added to the AQL packet, and initialized during
graph launch.
Handle race with wait when 2 kernels with device heap are enqueued on multiple streams.
Change-Id: I45933b77fcaf7bc8fdf1bc906462e32b5d8d3688
2024-06-17 02:07:25 -04:00
775dc204aa
SWDEV-463865 - changed device,roc and pal namespaces to be nested under amd
...
Change-Id: Icad342843c039c634e249a13a7aa31400730b1dd
2024-06-07 12:23:06 -04:00
6ec5074d74
SWDEV-439581 - hip event flags clean up
...
Change-Id: I2197762d912da41a8b53b32b3446f0a958c988a6
2024-05-28 06:31:10 +00:00
a5a4b78606
SWDEV-439581 - hipEventBlockingSync flag for hip events
...
Change-Id: I0d7785a568f8007f82f999776a7ad23d0acc81b7
2024-05-28 06:31:10 +00:00
3d540ec113
SWDEV-457755 - Add TS only for kernel packets in the Accumulate command
...
Change-Id: I1b2f01c5763761808f49802fa117abc6306a22aa
2024-05-28 06:28:17 +00:00
1d48f2a1ab
SWDEV-456279 - Adding new hip flag to access contiguous memory and pass the flag to HSA API.
...
Change-Id: I1bafeaa3096395c729723af958d609bc41e7845c
2024-04-30 05:25:38 -04:00
7448113cfc
SWDEV-440746 - Remove obsolete code
...
The "optimized" version of memcpy is outdated and
was used in win32 only.
Change-Id: I7f2e0e9051e37cec95438266824b5b0025c324c6
2024-04-22 09:56:42 -04:00
56ebf5157a
SWDEV-413997 - VMM IPC implementation for Linux.
...
Change-Id: Icfeb83ca51e96be35abb67a94d6e3e1a1ca5a934
2024-04-18 11:28:13 -04:00
d52d16c8e6
SWDEV-413997 - Fixing multiple device cases.
...
Change-Id: I10ad3fbfca887e92cd81f68392fa1acf753cbd2b
2024-04-13 06:14:03 -04:00
3f0bcf7834
SWDEV-301667 - Fix SDMA mask reuse
...
If we are using the mask returned by getLastUsedSdmaEngine() then we
need to apply the SDMA Read/Write mask to it before using with HSA
copy_on_engine API.
Change-Id: I6e5dc6c187eeb3c61ee159e9d2a0fa7b4737c06e
2024-04-08 15:42:52 -04:00
f5ca620baa
SWDEV-423835 - Fixing kernel launch issues on Virtual Memory Management path.
...
Change-Id: I9f5e8a3d83af3809b2c50b21a10697e26113dd23
2024-03-12 17:22:07 -04:00
1f6d416684
SWDEV-446399 - Fixed segfault in hipMemSetAccess
...
Change-Id: Ia1200d9bee03e8abade211287505f081e635ceec
2024-02-20 18:51:05 -05:00
3ef829939a
SWDEV-413997 - Initial VMM changes for ROCm path.
...
Change-Id: I4405fd7b53182eb4c4622835c811c0dc08461537
2023-10-16 11:29:16 -04:00
077311153a
SWDEV-407533 - [ABI Break]Purge unused env vars
...
Change-Id: I627950e8ebb6299affc602754a20d442dbe42b14
2023-08-24 14:11:40 -04:00
6f5277c701
SWDEV-408473 - Add wait time of 10 us if the waiting signal copy was < 24K.
...
Change-Id: I438ec9eb07e5034042a4a9a5e6e51d74daba2c83
2023-08-23 10:46:33 -04:00
aca7d9e14a
FEAT-47686 - Changes to support new uncached memory segment in ROCr.
...
Change-Id: I0ba8769d6737cdf1cc8a8644b2e82109f584a430
2023-07-05 20:47:51 -04:00
98e0607f0e
SWDEV-1 - Fix -Winconsistent-missing-override
...
Change-Id: Ie69f234c755b112b7fe8ef7d00b8720bc178044c
2023-06-23 09:04:28 -04:00
9aa6f25f1c
SWDEV-311270 - Clean-up IPC path in ROCclr
...
- Make IPC interfaces generic between devices and rely on the IPC buffer
for attach/detach logic
Change-Id: Id3c18d122030329b7ee532bbb6317de9dd6a0bbe
2023-06-20 15:18:21 -04:00
5436d362b1
SWDEV-301667 - Add a flag for gpuvm kernargs
...
HIP_FORCE_DEV_KERNARG=1 will create a device allocation for kernel arg
segment. Flag is 0 by default.
Change-Id: Iaaf5a149f3be8596568878d5d272268baf067c60
2023-05-22 11:23:48 -04:00
0b475284e9
SWDEV-398151 - Partly relax static engine allocation
...
Change-Id: I4903b51a34b597a2e84d771b52cf629f877dba05
2023-05-11 00:52:18 -04:00
afa15ddb89
SWDEV-367145 - adding support for timeline semaphore
...
Change-Id: I654359b48abe8bbaac2def5118d3ad0bb05d9492
2023-04-25 10:02:43 -04:00
5865c642d4
SWDEV-384557 - Fix engine status query
...
- Maintain a map of SDMA engine# to stream allocated following a greedy
approach
- Anything past that will query SDMA engine status always and go with a
SDMA or Blit copy path
Change-Id: Ibfaed7f951ab84d80cb0430596a4d11b5aec9202
2023-04-21 00:57:26 -04:00
f98dcf9d7f
SWDEV-366636 - Fix performance drop in TF-RCCL models
...
Change-Id: Idc845bb0dab858b94b9d2720cae8308cac2e7328
2023-02-17 00:48:13 -05:00
5dc104b3ea
SWDEV-368235 - Revert "Remove obsolete env variables"
...
This reverts commit 7b50c935f8
2023-02-15 07:25:00 +00:00
fa35239b4b
SWDEV-380035 - Check for agent and ptr match for hsa LOCKED ptr
...
Change-Id: I2503aa05512aebc3535963e188ca8d1dbfab08f0
2023-02-15 00:12:42 -05:00
67af16bdf3
SWDEV-381633 - Use blit manager on app's queue
...
Heap initialization used device queue, but it shoudl be used for
cooperative launches only. Heap initialization must use the same queue
as the current dispatch.
Change-Id: I856621bf82bbdeb1c2d0fbc4970e90d09af805cb
2023-02-09 09:43:13 -05:00
7b50c935f8
SWDEV-368235 - Remove obsolete env variables
...
Change-Id: I7e14d53297e79e2f68b3a6cc40251ad7db9eb5ab
2023-02-03 13:44:24 -05:00
6dad2fc306
SWDEV-377991 - Remove liquidflash support
...
Remove amdgpu-pro interface for persistent memory,
used in Liquidflash
Change-Id: I7d1720ad0875a62ebb2d7f96cba39601d560a5df
2023-01-23 10:40:57 -05:00
Andryeyev, German
Jayaprakash, Karthik
Sang, Tao
Patel, Jaydeepkumar
Saleel Kudchadker
Jimbo Xie
Anusha GodavarthySurya
Rahul Manocha
Ioannis Assiouras
Ajay
Satyanvesh Dittakavi
Matt Arsenault
pghafari
Maneesh Gupta