AI/rocm-systems
2
0
Forka 0
Codice Problemi Pull Request Actions Pacchetti Progetti Rilasci Wiki Attività
4.426 Commit 3 Rami (Branch) 0 Tag
ffbd63e7746d33a07bbfb1e410ecdc9dfc7a31bf
Grafico dei commit

4426 Commit

This Branch
This Branch
Tutti i branch
Autore SHA1 Messaggio Data
Chauncey Hui ffbd63e774 SWDEV-2 - Change OpenCL version number from 3422 to 3423 2022-02-18 03:00:06 -05:00
German Andryeyev fbf531398a SWDEV-323364 - Fix a typo 
Change-Id: I2031296ab9451342d5930b8b2d3d2e6277946647
 2022-02-17 20:50:29 -05:00
Chauncey Hui 0a2baa91b1 SWDEV-2 - Change OpenCL version number from 3421 to 3422 2022-02-17 03:00:05 -05:00
Saleel Kudchadker 041ddc0c1c SWDEV-322605 - Fix infinite loop condition 
If GlobalMemCacheLine reported is 0, runtime may run into an
infinite loop as the KernelSegmentAlignment is chosen as size of the
cache line.

Change-Id: Ide547940cc0407f16fab10ee210b4fd3ae4eaafc
 2022-02-16 13:16:18 -05:00
German Andryeyev 3fd4a67670 SWDEV-316824 - Fix P2P compute copy path 
Use device memory object for the GPU VA address look-up.

Change-Id: I76bf58b29205f7b3ba1bf68e9fcca69421267203
 2022-02-15 13:20:13 -05:00
Chauncey Hui 07d3044160 SWDEV-2 - Change OpenCL version number from 3420 to 3421 2022-02-12 03:00:09 -05:00
German Andryeyev 525a1bbf1a SWDEV-286150 - Remove GSL backend 
Change-Id: Iba9a997ee7d5ff6ac00d5888ff189a4514958fe9
 2022-02-09 17:16:39 -05:00
Chauncey Hui c640b395c7 SWDEV-2 - Change OpenCL version number from 3419 to 3420 2022-02-09 03:00:06 -05:00
German Andryeyev 0bf395af39 SWDEV-286150 - Don't report OCL2.2 support 
OCL2.2 requires SPIR-V and runtime doesn't support it.
Make sure PAL backend doesn't report any SPIR-V support.

Change-Id: I8d179069674205b54f7d20d149bcb675bee5cdb0
 2022-02-07 17:34:39 -05:00
German Andryeyev be6a06384e SWDEV-307184 - Add support for the new metadata 
Metadata in Codeobject version 5 is the extension of CO3 and CO4.
Add the detection of the new fields and program them in
the setup of the kernel arguments.

Change-Id: I27e58df77320ad00f4f16d35912668db803826af
 2022-02-07 14:05:58 -05:00
Chauncey Hui d554960ae7 SWDEV-2 - Change OpenCL version number from 3418 to 3419 2022-02-04 03:00:04 -05:00
Satyanvesh Dittakavi 824704c87b SWDEV-317716 - Add uuid in device info structure 
Change-Id: Ie7f48d0faf7d722bd9bb8bd0f8962a7832dbe4f6
 2022-02-03 12:17:28 -05:00
Todd tiantuo Li fbbae8055f SWDEV-297292 - add gfx90c:xnack+ support as gfx90d 
Change-Id: I90e28981a7cbc0f9a0105c16e9dda3ad8ac57f51
 2022-02-02 14:24:19 -08:00
Chauncey Hui 00f724e465 SWDEV-2 - Change OpenCL version number from 3417 to 3418 2022-02-01 03:00:44 -05:00
Saleel Kudchadker 33aca5a4a6 SWDEV-301947 - Use new enum for CU count 
Use HSA_AMD_AGENT_INFO_COOPERATIVE_COMPUTE_UNIT_COUNT to get compute
units. This is needed to work around assymentric CU harvesting bug on
gfx90a. Add a new device property to get the max available CUs on the
device.

Change-Id: I878f38f14f16c1af01fc0a77157aea1e816a63b8
 2022-01-31 12:57:50 -05:00
Chauncey Hui 87dd8dd0d7 SWDEV-2 - Change OpenCL version number from 3416 to 3417 2022-01-28 03:00:07 -05:00
German Andryeyev b169956c78 SWDEV-318505 - Update HSAIL xnack path 
Fix a typo with new line

Change-Id: I7fee63409b491a1f214117b68cfffa0492aa0743
 2022-01-27 13:07:11 -05:00
Chauncey Hui 87b6c5f14c SWDEV-2 - Change OpenCL version number from 3415 to 3416 2022-01-27 03:00:09 -05:00
Konstantin Zhuravlyov 511065e301 SWDEV-320486 - Correctly set HSAIL_ELFTOOLCHAIN_DIR 
Change-Id: Icb39b376eaf3a8132b210bd1bd4eeecaa97bea9d
 2022-01-26 18:38:25 -05:00
Payam b473a80f6a SWDEV-245531 - GLInterop adding svm support 
Change-Id: Id7f2a7a214f5ad692b4a7acf26cfb1dc423ed54a
 2022-01-26 08:17:58 -05:00
Chauncey Hui 7727ea394c SWDEV-2 - Change OpenCL version number from 3414 to 3415 2022-01-26 03:00:06 -05:00
German Andryeyev a543d4a860 SWDEV-318505 - Update HSAIL xnack path 
Report proper target id for xnack in HSAIL path. Runtime
will use ISA table and report hsailName().
Fix offline compilation path for PAL.

Change-Id: Ic0250bf6b9c193d867aec9800a319da1bf00c3ee
 2022-01-24 09:27:32 -05:00
Chauncey Hui e6225e07d0 SWDEV-2 - Change OpenCL version number from 3413 to 3414 2022-01-19 03:00:08 -05:00
Alex Xie 15101e704b SWDEV-312368 - Segmentation fault in test_gl 
When OCL failed to obtain function pointer from GL, we should not call it.

Change-Id: I50f69d270ce445386906a286e44c4e8c83722302
 2022-01-14 17:35:31 -05:00
Chauncey Hui d04fdd9356 SWDEV-2 - Change OpenCL version number from 3412 to 3413 2022-01-13 03:00:05 -05:00
Satyanvesh Dittakavi e20dd61932 SWDEV-306939 - Fix vdi errors/warnings by CppCheck 
Change-Id: I56d910f8363787f1050d5d7e8064ed553c5827fd
 2022-01-12 00:22:16 -05:00
Chauncey Hui 8b5b2a2d79 SWDEV-2 - Change OpenCL version number from 3411 to 3412 2022-01-08 03:00:04 -05:00
German Andryeyev 5f98028a48 SWDEV-316665 - Add ATI_BITS_32 define to cmake build 
Some logic in ROCclr relies on ATI_BITS_32 define

Change-Id: I2f0ef535e8d7717f9aa8646bdc80c09880bd2bee
 2022-01-06 13:14:19 -05:00
Chauncey Hui f892de68a3 SWDEV-2 - Change OpenCL version number from 3410 to 3411 2022-01-05 03:00:05 -05:00
German Andryeyev e0a4e0df0e SWDEV-317061 - Fix 32-bit HSAIL complib load 
Use __stdcall decl to match the library defines

Change-Id: Id4178443d5a9bb4e5401d80b3b5d15c7bbea0330
 2022-01-04 16:48:18 -05:00
Chauncey Hui c04d650b67 SWDEV-2 - Change OpenCL version number from 3409 to 3410 2021-12-29 03:00:09 -05:00
haoyuan2 3d5d9e2691 SWDEV-316150 - align with OCL to use wavefront64 on Navi21/22/23/24 
Change-Id: Ic47bc7cc6300c217c02c2bbbda9940a3b5c9597d
 2021-12-28 12:39:18 -08:00
Chauncey Hui a6948a31f2 SWDEV-2 - Change OpenCL version number from 3408 to 3409 2021-12-19 03:00:03 -05:00
Saleel Kudchadker 1fbd75b825 SWDEV-313306 - Fix Co-operative groups dtests 
Add a state indicator to retain ExternalSignals when needed.
Co-operative group launch uses external signals to indicate a dependency
to the next command.

Change-Id: I6d0daa006e2377c3bbf4aeca0fd5b63c7ac8fbbb
 2021-12-17 12:41:37 -08:00
Chauncey Hui e5122e3bc7 SWDEV-2 - Change OpenCL version number from 3407 to 3408 2021-12-15 03:00:05 -05:00
Saleel Kudchadker 3239222516 SWDEV-313306 - Clear external signals 
Crash was due to the fact that external signal structure was stale even
after destroyign the command. That is because we skipped wait due to a
missing check.
Detect external signals and dispatch a barrier in ReleaseGpuMemoryFence.
Also clear external_signals_ at ProfilingBegin.

Change-Id: I991387edcfe928b511bf5e780988ee131321ed5a
 2021-12-13 23:03:33 -08:00
Chauncey Hui 1b5de6e562 SWDEV-2 - Change OpenCL version number from 3406 to 3407 2021-12-11 03:00:08 -05:00
German Andryeyev f613831471 SWDEV-300515 - Apply CU granularity on the CU count 
Report granularity for possible app query

Change-Id: I98857c6f4cc7ae590927ea35ce57d181abe7860b
 2021-12-10 10:47:28 -05:00
Chauncey Hui 7abd2827b5 SWDEV-2 - Change OpenCL version number from 3405 to 3406 2021-12-10 03:00:08 -05:00
haoyuan2 439af94dd9 SWDEV-290298 - add a flag to indicate the primary context active status 
Change-Id: Ia31790706d3f855bc1eedf5ef874e471
 2021-12-09 23:28:54 -05:00
Sarbojit Sarkar aedbad0109 SWDEV-314254 - Fix for hipMemcpy3D test crash 
Change-Id: Iac70bfe0d351cfb5b56fefc9a6487d3f26f2b4ef
 2021-12-09 11:46:52 -05:00
Chauncey Hui 84af5eed4e SWDEV-2 - Change OpenCL version number from 3404 to 3405 2021-12-09 03:00:06 -05:00
German Andryeyev 008133cf41 SWDEV-305016 - Improve MGPU scaling in Tensorflow 
Add a threshold for ROCR/SDMA P2P transfers. ROCR copy path
requires extra barriers in compute for synchronization. That costs
extra performance with tiny transfers.
Reduce active wait time to 10us. Tensorflow uses extra thread
per GPU with constant hipEventQuery() calls. Longer active waits
in ROCr affect CPU performance.

Change-Id: I9020358438615fa2d4617f862f00a562f0a588e7
 2021-12-08 11:59:37 -05:00
Chauncey Hui 587cda0c91 SWDEV-2 - Change OpenCL version number from 3403 to 3404 2021-12-08 03:00:05 -05:00
Julia Jiang 376ea1e293 SWDEV-308644 - reorganize extra blit kernel in PAL stack 
Change-Id: I9d853e8d417ef75b522184d83646ec4b9fa8669b
 2021-12-07 14:55:20 -05:00
Christophe Paquot 5243552768 SWDEV-307109 - Don't force Persistent for HIP 
With SAM on, don't force Persistent for allocations
in HIP. This makes ROCCLR go down paths we don't want
for HIP.

Change-Id: If54cc16fa891d4cfdc761c6ab21ad707627e822a
 2021-12-06 12:16:08 -05:00
Chauncey Hui 1a677effa8 SWDEV-2 - Change OpenCL version number from 3402 to 3403 2021-12-03 03:00:05 -05:00
Satyanvesh Dittakavi 9dabdcdc3e SWDEV-309286 - save the max system mem size in device info 
Change-Id: I9955625aca6ceda059aef6354d909de636b610ba
 2021-12-02 10:59:07 -05:00
Chauncey Hui 1df0ddefe4 SWDEV-2 - Change OpenCL version number from 3401 to 3402 2021-12-02 03:00:03 -05:00
Saleel Kudchadker 3f82b99f5d SWDEV-308843 - Increase MaxPinnedXferSize to 128 
This allows experimenting with env var GPU_PINNED_XFER_SIZE which is
still at a default of 32MB

Change-Id: I85ade700ed58d498eba29d1737601dc74d4c26a4
 2021-12-01 20:37:56 -05:00