AI/rocm-systems
2
0
Çatalla 0
Kod Konular Değişiklik İstekleri İşlemler Paketler Projeler Sürüm Viki Aktivite
4.772 İşleme 3 Dal 0 Etiketler
8278e869182183e7f4dcee0eceab66ea644bacaa
İşleme Grafiği

4772 İşleme

Bu Dal
Bu Dal
Tüm Dallar
Yazar SHA1 Mesaj Tarih
jiabaxie 8278e86918 SWDEV-366886 - force svm alloc for rocm 
Change-Id: If85a6aaeb5861ff1550a0bc3f0a25073ff8145e7
 2023-01-18 16:26:34 -05:00
German c8927cd84e SWDEV-377991 - Remove Liquidflash extension 
Initial check-in to untie dependencies with HIP and OCL repos

Change-Id: I363b63954c3f118f40a6ed893545d6a4ac44144c
 2023-01-18 13:16:20 -05:00
Alex Xie 60d413a5b9 SWDEV-374668 - Observed one subtest failure in ocltst32 
Don't force sysmem allocation

Change-Id: I792f0da231c6e8058f1bfb81ba1f88ecb59b7c8e
 2023-01-18 12:02:27 -05:00
Chauncey Hui 241bfcc033 SWDEV-2 - Change OpenCL version number from 3556 to 3557 2023-01-18 03:00:09 -05:00
Anusha GodavarthySurya 2b50636809 SWDEV-373173 - Correct max VGPRs and VGPR Granularity in Occupancy calculation for different asics 
Change-Id: I6f595428ed31733cdc04e65e7c3e383f454ab72b
 2023-01-18 00:22:02 -05:00
Tao Sang cb30ce4e06 SWDEV-377423 - Fix kernel attribute missing 
Fix missing issue of kernel attributes including vec_type_hint,
work_group_size_hint and reqd_work_group_size.
Make WorkGroupInfo's meta attributes initialized before other parameters
are initialized.
This way workGroupInfo_'s compileSizeHint_, compileSize_ and
compileVecTypeHint_ will be valid when they are used to create kernel
signature in Kernel::createSignature().
Fix a typo of ".workgorup_size_hint".

Change-Id: I4a1ede2210a25596ad7a935cd4debb896e0147f8
 2023-01-17 14:50:35 -05:00
Jiabao Xie 6c44353107 SWDEV-366886 - force alloc from svm 
Change-Id: I6a89aa46d944832e59491bb96ba3669e5031b636
 2023-01-17 12:12:27 -05:00
Anusha GodavarthySurya 0bd0c29b7d SWDEV-373173 - Add kernel metadata for WGP mode 
Change-Id: Ic270e90c46938b975513ff2bc19b7bb6b9485f9d
 2023-01-17 10:51:22 -05:00
Chauncey Hui 4595d88b04 SWDEV-2 - Change OpenCL version number from 3555 to 3556 2023-01-17 03:00:06 -05:00
German Andryeyev 5d83345c20 SWDEV-355281 - Add offset calculation 
Calculate memory location offset for requested memory

Change-Id: I7919523df1790d9eaad5827ee5bd98e4263a7554
 2023-01-16 14:19:40 -05:00
Jaydeep Patel d97b4e8c74 SWDEV-374360 - Handle free for external memory. 
Change-Id: I4a1ede2210a255960d7a935cd4debb806e0147f6
 2023-01-16 13:06:36 -05:00
Saleel Kudchadker 033d4c0463 SWDEV-345213 - Fix staged line-by-line copy path 
- Address an old bug in offset calculation that was causing out of bound
access.
- Improve logging

Change-Id: Iebdf34dddaa5e987cc72184a2152918adc6a96e0
 2023-01-16 11:04:30 -05:00
Juan Manuel MARTINEZ CAAMAÑO 8ab3fd58cf SWDEV-287018 - Remove requiredDump argument from Program::linkLLVMBitcode 
Weirdly, the `requiredDump` argument to linkLLVMBitcode was used to enable/disable
the keeping temporary bytecode files (those generated by -save-temps=all) after linking.

This patch removes this argument as there is no obvious benefit from keepeing it
(the user would only rely on -save-temps=all to control this).

Change-Id: I0c00486f95eb1d4e296b5247c488407c47f0b2d9
 2023-01-16 03:34:21 -05:00
Chauncey Hui 097e8f270a SWDEV-2 - Change OpenCL version number from 3554 to 3555 2023-01-16 03:00:05 -05:00
Ajay ecea27eb2d SWDEV-372757 - thread check workaround for windows hang 
Change-Id: Ie9f87b88dd0f3078ad1919edc336f297f6b40373
 2023-01-13 04:05:35 -05:00
Chauncey Hui 8a973ee882 SWDEV-2 - Change OpenCL version number from 3553 to 3554 2023-01-13 03:00:09 -05:00
Anusha GodavarthySurya 710749c291 SWDEV-374778 - Select SDMA path when HSA_XNACK is enabled 
Change-Id: I052675186238eb24b910a0a558d6b8ede36d1413
 2023-01-12 23:34:21 -05:00
Ioannis Assiouras 4d49204fb9 SWDEV-374401 - Surface the ammount of used constant memory by kernel 
Change-Id: I6de0e46482f27b9068582fdaee0e562f9f71f9f0
 2023-01-12 05:22:37 -05:00
Saleel Kudchadker 77ceb7e9ad SWDEV-371123 - Fix barrier value packet header 
- Use correct header for vendor packet
- Pass one dependent signal when submitting a marker if there is one

Change-Id: I4efc70dd5204b559de26f899d0637f50421c8834
 2023-01-12 04:06:03 -05:00
Chauncey Hui 6b4577c8d7 SWDEV-2 - Change OpenCL version number from 3552 to 3553 2023-01-12 03:00:09 -05:00
jatang 6647882773 SWDEV-287018 - Only generate _optimized.bc when both requiredDump and DUMP_BC_LINKED are true 
The current code generates a _optimized.bc regardlessly, so put back the original logic.

Change-Id: I3f84d10934b3e983f5f828af8d0943449a6e1d94
 2023-01-11 17:51:35 -05:00
Chauncey Hui ed10cb76c1 SWDEV-2 - Change OpenCL version number from 3551 to 3552 2023-01-10 03:00:08 -05:00
Anusha GodavarthySurya 274f2de391 SWDEV-364576 - initialize device malloc heap state using blit kernel 
Change-Id: I5d0172aff7d2c04b322a4d828b8a2b438158b80f
 2023-01-07 06:53:53 +00:00
Chauncey Hui 69ffa7bcb8 SWDEV-2 - Change OpenCL version number from 3550 to 3551 2023-01-06 03:00:08 -05:00
Saleel Kudchadker 6651aab28d SWDEV-371123 - Fix typo for log print 
Change-Id: I18297a032d6fc9a030863eac7c525e86e9fdcd29
 2023-01-05 17:46:22 -05:00
kjayapra-amd 79f0b8b794 SWDEV-241902 - Disable COMGR unbundler and use legacy Runtime unbundler. 
Change-Id: I04128a40f67f3e5ce0db935a0a733b7044d75c34
 2023-01-03 09:31:11 -08:00
Chauncey Hui 2eef0f8dd3 SWDEV-2 - Change OpenCL version number from 3549 to 3550 2022-12-29 03:00:08 -05:00
jatang 05a8eaaf0f SWDEV-372791 - Default UniformWorkGroupSize to true for CL1.x 
Change-Id: If03396b5a7a3a69e05fdb4c43791a0d84d9f4127
 2022-12-28 12:59:08 -05:00
Chauncey Hui 6c1a250331 SWDEV-2 - Change OpenCL version number from 3548 to 3549 2022-12-28 03:00:09 -05:00
Jaydeep Patel 070ae4e6d4 SWDEV-374370 - Propogate element size to blit kernel. 
Change-Id: I06d1ae6feebd238e9a63c617eb4c4dcf485d9ee0
 2022-12-26 09:33:50 +00:00
Chauncey Hui b8faaf8458 SWDEV-2 - Change OpenCL version number from 3547 to 3548 2022-12-21 03:00:11 -05:00
Jaydeep Patel 9076d9a518 SWDEV-366087 - Pass pitch and slice pitch to blit kernel from rect struct. 
Change-Id: I1ffe54929db59a40e2a1ae19c125f8d8e81b07ec
 2022-12-20 16:43:49 +00:00
Chauncey Hui d37bf7d22b SWDEV-2 - Change OpenCL version number from 3546 to 3547 2022-12-16 03:00:08 -05:00
Saleel Kudchadker e0384f9f6b SWDEV-373334 - Use copyMetadata for blit decisions 
- Check isAsync flag for small host copies on large bar as it synchronizes
- Use CopyEngine Preference hint if HMM is enabled.

Change-Id: I1ffc4b2604ed03cf5979cdc454178648c5ae5cba
 2022-12-15 17:09:02 -05:00
Chauncey Hui 7e3e528441 SWDEV-2 - Change OpenCL version number from 3545 to 3546 2022-12-15 03:00:08 -05:00
Jacob Lambert 50d77d17fd SWDEV-356171 - Adding new Comgr mangled name fetching APIs 
amd::Comgr::populate_mangled_names()
  amd::Comgr::get_mangled_name()

Change-Id: Ie6ebf3aae76632f7e7cfef3c90642b2e3cd10b48
 2022-12-14 12:40:18 -05:00
jatang a4fadb191a SWDEV-1 - Fix another build warning. 
Change-Id: Ifed33732752e9d9ec74a244a0104bf571a9fc6c5
 2022-12-14 10:14:49 -05:00
Chauncey Hui 5aee3d3018 SWDEV-2 - Change OpenCL version number from 3544 to 3545 2022-12-14 03:00:06 -05:00
jatang e8cd1e93e8 SWDEV-1 - Not to truncate size_t in print when it's 64bit 
Change-Id: Iab8b7eb128c767b6808b19cbeac5169b7a97f1ad
 2022-12-13 09:13:33 -05:00
Chauncey Hui edb515eabf SWDEV-2 - Change OpenCL version number from 3543 to 3544 2022-12-13 03:00:08 -05:00
kjayapra-amd e56a611b92 SWDEV-371904 - Adding pseudo fine grain flag to hsa memory allocation for device fine grained memory. 
Change-Id: I8cada90f0e3880dfbc5bf5a3fac4554e7a0cb08e
 2022-12-11 08:15:17 -05:00
Chauncey Hui dc6bbe303b SWDEV-2 - Change OpenCL version number from 3542 to 3543 2022-12-10 03:00:08 -05:00
Todd tiantuo Li 9168415ca2 SWDEV-354868 - Queue::Create() for RT queue should fail when number of reserved CU's for RT queue is zero (most likely due to being aligned down by dedicatedCuGranularity). 
Change-Id: I234e7ff83cb312bf44f5ad4b1a897c079f5106a9
 2022-12-09 16:45:10 -05:00
Chauncey Hui 9c8cfc7f98 SWDEV-2 - Change OpenCL version number from 3541 to 3542 2022-12-09 03:00:07 -05:00
Ioannis Assiouras 72b45e2a1f SWDEV-369581 - Convey copy API metadata to ROCclr 
Change-Id: I569462d6d268700d419510255e201bf7d80d6714
 2022-12-09 00:27:15 -05:00
pghafari 402504f548 SWDEV-366279 - updating p2p error msg 
Change-Id: I294e7770efd11f511dd5817eb28bd3c97d9d4926
 2022-12-09 00:05:04 -05:00
Jaydeep Patel cd7034c9bb SWDEV-370537 - PAL does 64kb alignment so no need to do it in runtime. Reverting alignment to 4kb. 
Change-Id: If3eaac65bf63bb9b8b73a3cad1bb34d357f1adeb
 2022-12-08 14:54:46 -05:00
German 8cf53e7dff SWDEV-370901 - Force sysmem allocation 
Adobe AE allocates/destroys system memory per each frame
in some effects, which is a very expensive operation.
Disable pinning and force sysmem allocation in VidMM.
That allows to trigger resource cache in runtime and
avoid paging operations, caused by pinning.
The actual benchmark doesn't have significant improvement
from the change, but GPU view traces are much cleaner.

Change-Id: I92cdd87d37c64611788f05250f71d6fe489b4d7e
 2022-12-08 13:06:51 -05:00
kjayapra-amd 7319dc36c1 SWDEV-363865 - Use COMGR path to unbundle code object in HIPRTC. 
Change-Id: Ie6a48ab2792bb3f7ae1e62d716ecc35b8e24fe16
 2022-12-08 08:34:33 -05:00
Chauncey Hui cbc66bf89d SWDEV-2 - Change OpenCL version number from 3540 to 3541 2022-12-08 03:00:09 -05:00