AI/rocm-systems
2
0
フォーク 0
コード イシュー プルリクエスト Actions パッケージ プロジェクト リリース Wiki アクティビティ
76,333 コミット 3 ブランチ 0 タグ
develop
コミットグラフ

76333 コミット

このブランチ
このブランチ
すべてのブランチ
作成者 SHA1 メッセージ 日付
Lakshmi Kumar a05ef46999 av1 initial commit (#298) 
[ROCm/rocdecode commit: 6265f675c1]
 2024-03-26 18:59:15 -04:00
Lakshmi Kumar 6265f675c1 av1 initial commit (#298) 2024-03-26 18:59:15 -04:00
jeffqjiangNew f655289b43 * rocDecode/AVC: Fixed the decode failure of the conformance stream MR2_MW_A.264. (#297) 
- We should always clear the number of short term and long term references in DPB buffer structure when IDR occurs.

[ROCm/rocdecode commit: 7cf22e5920]
 2024-03-26 18:53:42 -04:00
jeffqjiangNew 7cf22e5920 * rocDecode/AVC: Fixed the decode failure of the conformance stream MR2_MW_A.264. (#297) 
- We should always clear the number of short term and long term references in DPB buffer structure when IDR occurs.
 2024-03-26 18:53:42 -04:00
Konstantin Zhuravlyov 9e8f185397 Add R_AMDGPU_ABS32 support 
Change-Id: I0ee0302d919ede44765adf02eab15015573efef2
 2024-03-26 18:47:29 -04:00
Konstantin Zhuravlyov 2a7fb7a808 Add R_AMDGPU_ABS32 support 
Change-Id: I0ee0302d919ede44765adf02eab15015573efef2


[ROCm/ROCR-Runtime commit: 9e8f185397]
 2024-03-26 18:47:29 -04:00
Konstantin Zhuravlyov c5e74b7d0a Add dynamic relocation types (NFC) 
Change-Id: I1b443003077ba241f34444da293e362266c2ae92
 2024-03-26 18:47:05 -04:00
Konstantin Zhuravlyov 853ccdecbb Add dynamic relocation types (NFC) 
Change-Id: I1b443003077ba241f34444da293e362266c2ae92


[ROCm/ROCR-Runtime commit: c5e74b7d0a]
 2024-03-26 18:47:05 -04:00
Konstantin Zhuravlyov b2c32ad6cb Rename existing relocation types to legacy/v1 (NFC) 
Change-Id: Ided7f656c34131b8067a19c0d3b2955fc8823628
 2024-03-26 18:46:50 -04:00
Konstantin Zhuravlyov ec66509986 Rename existing relocation types to legacy/v1 (NFC) 
Change-Id: Ided7f656c34131b8067a19c0d3b2955fc8823628


[ROCm/ROCR-Runtime commit: b2c32ad6cb]
 2024-03-26 18:46:50 -04:00
Benjamin Welton f29707c7b7 Make dimension error message print the counter name (#658) 
* temp

* source formatting (clang-format v11) (#659)

Co-authored-by: bwelton <1683479+bwelton@users.noreply.github.com>

---------

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: bwelton <1683479+bwelton@users.noreply.github.com>

[ROCm/rocprofiler-sdk commit: f0924c6aa7]
 2024-03-26 17:19:04 -05:00
Benjamin Welton f0924c6aa7 Make dimension error message print the counter name (#658) 
* temp

* source formatting (clang-format v11) (#659)

Co-authored-by: bwelton <1683479+bwelton@users.noreply.github.com>

---------

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: bwelton <1683479+bwelton@users.noreply.github.com>
 2024-03-26 17:19:04 -05:00
Gopesh Bhardwaj 9400df8992 counter collection header update in docs (#690) 
[ROCm/rocprofiler-sdk commit: f633278720]
 2024-03-26 17:18:39 -05:00
Gopesh Bhardwaj f633278720 counter collection header update in docs (#690) 2024-03-26 17:18:39 -05:00
Jonathan R. Madsen eede2ffea2 Update HSA copy table (#687) 
- two copies of HSA table: internal and tracing
- internal is used to invoke HSA function without any possibility of triggering tracing, etc.

[ROCm/rocprofiler-sdk commit: bc9f86ec62]
 2024-03-26 17:11:34 -05:00
Jonathan R. Madsen bc9f86ec62 Update HSA copy table (#687) 
- two copies of HSA table: internal and tracing
- internal is used to invoke HSA function without any possibility of triggering tracing, etc.
 2024-03-26 17:11:34 -05:00
Maisam Arif e2e4349bd2 SWDEV-445664 - Aligned metric --ecc & --ecc-blocks with Host 
Signed-off-by: Maisam Arif <maisarif@amd.com>
Change-Id: I93cf2bdab8c4c066bacf0e910e5620d37b362b07
 2024-03-26 16:30:31 -04:00
Maisam Arif 980da3b329 SWDEV-445664 - Aligned metric --ecc & --ecc-blocks with Host 
Signed-off-by: Maisam Arif <maisarif@amd.com>
Change-Id: I93cf2bdab8c4c066bacf0e910e5620d37b362b07


[ROCm/amdsmi commit: e2e4349bd2]
 2024-03-26 16:30:31 -04:00
Maisam Arif 93b81e5012 SWDEV-445664 - Aligned metric --clock with Host 
Change-Id: Ib4dc372aed61f6301680ac746eccf448e9d0ed00
Signed-off-by: Maisam Arif <maisarif@amd.com>
 2024-03-26 16:30:31 -04:00
Maisam Arif 4d62fc8bd6 SWDEV-445664 - Aligned metric --clock with Host 
Change-Id: Ib4dc372aed61f6301680ac746eccf448e9d0ed00
Signed-off-by: Maisam Arif <maisarif@amd.com>


[ROCm/amdsmi commit: 93b81e5012]
 2024-03-26 16:30:31 -04:00
Maisam Arif 8bf2bd4b89 SWDEV-447333 - Corrected amdsmi_init() python documentation 
Signed-off-by: Maisam Arif <maisarif@amd.com>
Change-Id: If46e7236316687cd97cf1a69770f87154e2681ff
 2024-03-26 16:30:22 -04:00
Maisam Arif 9fcbd0f477 SWDEV-447333 - Corrected amdsmi_init() python documentation 
Signed-off-by: Maisam Arif <maisarif@amd.com>
Change-Id: If46e7236316687cd97cf1a69770f87154e2681ff


[ROCm/amdsmi commit: 8bf2bd4b89]
 2024-03-26 16:30:22 -04:00
Shweta.Khatri 00b63f7452 Replace lazy_ptr's Init() with reset() method 
The function Init() called by one of the constructors of lazy_ptr is undefined.
Replacing with reset method sets the object to an uninitialized state and assigns a new constructor function

Fix submitted on github by zhoumin2 - https://github.com/ROCm/ROCR-Runtime/pull/184

Change-Id: I7d906d526ce7fe7e2548b01810e6395b13497bf3
 2024-03-26 15:07:34 -04:00
Shweta.Khatri 565dbac2d4 Replace lazy_ptr's Init() with reset() method 
The function Init() called by one of the constructors of lazy_ptr is undefined.
Replacing with reset method sets the object to an uninitialized state and assigns a new constructor function

Fix submitted on github by zhoumin2 - https://github.com/ROCm/ROCR-Runtime/pull/184

Change-Id: I7d906d526ce7fe7e2548b01810e6395b13497bf3


[ROCm/ROCR-Runtime commit: 00b63f7452]
 2024-03-26 15:07:34 -04:00
Saleel Kudchadker f3aedfbec0 SWDEV-301667 - Create TS for each node recorded in graph 
- Create a vector to allow multiple TS to be stored in Command.
- This would mean we dont wait for entire batch in Accumulate command
to finish when we exhaust signals.
- Reduce the number of signals created at init to 64. This min value
may still need to be tuned but the KFD allows max of 4094 interrupt
signals per device.
- Store kernel names whenever they are available and not just when
profiling. If we dynamically enable profiling like for Torch, a crash
can happen if hipGraphInstantiate wasnt included in Torch profile scope
beacuse we previously entered kernel names only when profiler is
attached.

Change-Id: I34e7881a25bbc763f82fdeb3408a8ea58e1ec006


[ROCm/clr commit: c157bfb202]
 2024-03-26 14:47:24 -04:00
Saleel Kudchadker c157bfb202 SWDEV-301667 - Create TS for each node recorded in graph 
- Create a vector to allow multiple TS to be stored in Command.
- This would mean we dont wait for entire batch in Accumulate command
to finish when we exhaust signals.
- Reduce the number of signals created at init to 64. This min value
may still need to be tuned but the KFD allows max of 4094 interrupt
signals per device.
- Store kernel names whenever they are available and not just when
profiling. If we dynamically enable profiling like for Torch, a crash
can happen if hipGraphInstantiate wasnt included in Torch profile scope
beacuse we previously entered kernel names only when profiler is
attached.

Change-Id: I34e7881a25bbc763f82fdeb3408a8ea58e1ec006
 2024-03-26 14:47:24 -04:00
Julia Jiang 8ef3c8e59e SWDEV-452786 - Adding Updates in kernel_language rst 
Change-Id: I1fc96d598bcdb8fdaabe0b84d8b638de76d98905


[ROCm/hip commit: fc4e762c43]
 2024-03-26 14:32:16 -04:00
Julia Jiang fc4e762c43 SWDEV-452786 - Adding Updates in kernel_language rst 
Change-Id: I1fc96d598bcdb8fdaabe0b84d8b638de76d98905
 2024-03-26 14:32:16 -04:00
Aryan Salmanpour de0714a4ac code cleanup - update the setup script (#3) 
* code cleanup - update the setup script

* fix few typo erros

[ROCm/rocjpeg commit: 1ef7c21641]
 2024-03-26 12:48:27 -04:00
Aryan Salmanpour 1ef7c21641 code cleanup - update the setup script (#3) 
* code cleanup - update the setup script

* fix few typo erros
 2024-03-26 12:48:27 -04:00
Aryan Salmanpour 805ecd6ee8 Organizing the install location of the rocdecode utils headers (#296) 
[ROCm/rocdecode commit: 592195b652]
 2024-03-26 12:47:37 -04:00
Aryan Salmanpour 592195b652 Organizing the install location of the rocdecode utils headers (#296) 2024-03-26 12:47:37 -04:00
Rakesh Roy 150144a05f SWDEV-445096 - Fix -O0 crash in OpenCL tests 
- With https://gerrit-git.amd.com/c/lightning/ec/llvm-project/+/1002628 applied, at -O0 Kernel::dynamicParallelism() returns true but virtual queue isn't created
- This causes segfault inside VirtualGPU::submitKernelInternal() when getVQVirtualAddress() is called

Change-Id: Ia7af042adad2329e870c142caaac3e8fa886f8b8


[ROCm/clr commit: d1fff7cea2]
 2024-03-26 11:42:33 -04:00
Rakesh Roy d1fff7cea2 SWDEV-445096 - Fix -O0 crash in OpenCL tests 
- With https://gerrit-git.amd.com/c/lightning/ec/llvm-project/+/1002628 applied, at -O0 Kernel::dynamicParallelism() returns true but virtual queue isn't created
- This causes segfault inside VirtualGPU::submitKernelInternal() when getVQVirtualAddress() is called

Change-Id: Ia7af042adad2329e870c142caaac3e8fa886f8b8
 2024-03-26 11:42:33 -04:00
Aryan Salmanpour 7d197c4c23 modify the condition of using visble_devices by making sure that the requsted device id is valid (#295) 
[ROCm/rocdecode commit: 4d5497eec8]
 2024-03-26 11:40:59 -04:00
Aryan Salmanpour 4d5497eec8 modify the condition of using visble_devices by making sure that the requsted device id is valid (#295) 2024-03-26 11:40:59 -04:00
arvindcheru a285fda3a1 Static Build update - Moved all cmake install() to rocm-cmake APIs, static build update (#1123) 
[ROCm/rccl commit: c0a51dc84b]
 2024-03-26 11:11:09 -04:00
arvindcheru c0a51dc84b Static Build update - Moved all cmake install() to rocm-cmake APIs, static build update (#1123) 2024-03-26 11:11:09 -04:00
Jaydeep Patel c4239ed8e8 SWDEV-446992 - Request can be for bytes OR dptr OR both. 
Change-Id: Ib479c744b90125b74d99cbf18b7f4b8cf765bf1c


[ROCm/clr commit: 09328f45b3]
 2024-03-26 11:10:24 -04:00
Jaydeep Patel 09328f45b3 SWDEV-446992 - Request can be for bytes OR dptr OR both. 
Change-Id: Ib479c744b90125b74d99cbf18b7f4b8cf765bf1c
 2024-03-26 11:10:24 -04:00
Maisam Arif dad2c430ea SWDEV-435406 - Corrected amdsmi_get_power_info() to return N/A for invalid values 
Signed-off-by: Maisam Arif <maisarif@amd.com>
Change-Id: I2aeb6f6670f6f47cd496faf7fc41192647f7d58c
 2024-03-26 10:43:28 -04:00
Maisam Arif 0079a66c5b SWDEV-435406 - Corrected amdsmi_get_power_info() to return N/A for invalid values 
Signed-off-by: Maisam Arif <maisarif@amd.com>
Change-Id: I2aeb6f6670f6f47cd496faf7fc41192647f7d58c


[ROCm/amdsmi commit: dad2c430ea]
 2024-03-26 10:43:28 -04:00
Maisam Arif 72b0a6efe5 SWDEV-431924 - Corrected amdsmi_get_gpu_board_info() to return N/A for invalid values 
Signed-off-by: Maisam Arif <maisarif@amd.com>
Change-Id: I3f7e7c873c24b8f5ddd6784700f193c2fdf199e0
 2024-03-26 10:43:16 -04:00
Maisam Arif c872b4b1ea SWDEV-431924 - Corrected amdsmi_get_gpu_board_info() to return N/A for invalid values 
Signed-off-by: Maisam Arif <maisarif@amd.com>
Change-Id: I3f7e7c873c24b8f5ddd6784700f193c2fdf199e0


[ROCm/amdsmi commit: 72b0a6efe5]
 2024-03-26 10:43:16 -04:00
kjayapra-amd 0f8a9567e6 SWDEV-413997 - Save hsa_handle as ptr in hipMemCreate path. 
Change-Id: Ica32017ef7b00326dfb6d1f604e126d40ad5b786


[ROCm/clr commit: 5cbd74b554]
 2024-03-26 10:24:29 -04:00
kjayapra-amd 5cbd74b554 SWDEV-413997 - Save hsa_handle as ptr in hipMemCreate path. 
Change-Id: Ica32017ef7b00326dfb6d1f604e126d40ad5b786
 2024-03-26 10:24:29 -04:00
kjayapra-amd a17f9d2d75 SWDEV-448288 - Remove references to deprecated llvm references. 
Change-Id: I7b58177c41dc0c6c59813977cb90e65a6cb3be72


[ROCm/clr commit: 5b28e386f6]
 2024-03-26 10:23:18 -04:00
kjayapra-amd 5b28e386f6 SWDEV-448288 - Remove references to deprecated llvm references. 
Change-Id: I7b58177c41dc0c6c59813977cb90e65a6cb3be72
 2024-03-26 10:23:18 -04:00
Mihai Preda fa0c182325 Free the malloc'ed event on page alloc failure 
Change-Id: I009a9a6e2f67545c51470e86eac1adb78d6181b4
Signed-off-by: Mihai Preda <preda@users.noreply.github.com>
Signed-off-by: Kent Russell <kent.russell@amd.com>
 2024-03-26 09:57:26 -04:00
Mihai Preda 69c283ef3d Free the malloc'ed event on page alloc failure 
Change-Id: I009a9a6e2f67545c51470e86eac1adb78d6181b4
Signed-off-by: Mihai Preda <preda@users.noreply.github.com>
Signed-off-by: Kent Russell <kent.russell@amd.com>


[ROCm/ROCR-Runtime commit: fa0c182325]
 2024-03-26 09:57:26 -04:00