115461cc04
File reorganization with backward compatibility
...
Updated the header file location and export path
2022-03-10 01:28:41 +00:00
676a4737c1
File reorganization as per the new defined standard
...
The header files will in /opt/rocm-xxx/include/rccl
Libraries and cmake will be in /opt/rocm-xxx/lib folder.
Added wrappers for header files using rocm-cmake functions for backward compatibility.
2022-03-08 17:32:02 +00:00
0687940b84
Changing initialization method for UnitTests ( #510 )
2022-03-07 09:22:55 -07:00
d6d6af710e
Force ring algorithm on single node ( #509 )
2022-03-04 10:29:02 -08:00
b634b2f1c2
Adding NCCL_DEBUG=INFO for CI runs ( #508 )
2022-03-03 18:04:28 -07:00
699dc30f05
[UnitTests] Check process mask for custom tests ( #507 )
2022-03-02 17:24:14 -07:00
ff54e79799
Added Unit test for nccl send recv ( #506 )
...
Added Send Receive test that tests through all pairs
2022-03-02 15:50:16 -05:00
3c223c105a
2.12.7-1
...
Add network communication through another GPU connected with NVLink
(PXN).
Add aggregation of messages coming from different local GPUs through
PXN and going to the same destination.
Add new v5 plugin API with grouped receives and tags.
Add compat for v4 plugins.
Add naming of NCCL threads to help debugging.
Fix NVLink detection and avoid data corruption when some NVLinks are
down.
Add support for Relaxed Ordering for IB.
Add profiling and timing infrastructure.
2022-03-02 20:48:56 +01:00
29ad0f5fbe
Unit test refactor ( #500 )
...
Refactoring and consolidating single-process / multi-process unit testing
2022-02-25 08:59:07 -07:00
b569c0a1db
Add Pivot AllToAll algorithm for Rome model ( #503 )
...
* add a2a pivot interface
* remove debug info
* address comments
* fix bug
* remove custom script
* address comments
* fix bug
2022-02-20 21:09:47 -08:00
94e0dc8bfd
Allow additional options to be passed in through model's definition ( #501 )
2022-02-17 08:28:58 -08:00
02096c9936
Add another Rome model ( #497 )
2022-02-12 10:30:16 -08:00
fbfb6ac5d7
Split IB parameter sanity check into two parts
...
First part on collective mismatch, second part on internal errors
2022-02-08 15:21:22 -08:00
f3c2cafd9d
[TransferBench] Fix for cases with subsets of configured numa nodes ( #495 )
2022-02-07 12:16:19 -07:00
84d5fce7dd
TransferBench: Adding ability to reindex GPUs based on PCIe address ( #494 )
2022-02-02 08:51:41 -07:00
0144073673
Fix ext-net/google-fastsocket build
2022-01-24 07:19:48 -08:00
cc78e9fab8
Revert "remove unused basePath"
...
This reverts commit 445bc19657
2022-01-21 12:30:34 +01:00
445bc19657
remove unused basePath
2022-01-21 12:12:26 +01:00
400df49dbe
Generate proper b-tree with non-repeating channels ( #493 )
2022-01-19 15:09:17 -08:00
e94720fe3b
Merge pull request #492 from wenkaidu/develop
...
Sync up with NCCL
2022-01-18 12:55:05 -08:00
b002ef1aaf
Search for GTest 1.11; fix detection of GTest after install ( #476 )
2022-01-17 15:18:01 -07:00
973d0111db
Merge remote-tracking branch 'nccl/master' into develop
2022-01-17 13:34:36 -08:00
336ff4fe5f
Add files via upload
2022-01-16 22:19:54 -08:00
f467fb57e8
Delete classification-maptest.xml
2022-01-16 22:19:33 -08:00
62ef66b656
Add files via upload
2022-01-16 08:12:03 -08:00
39cf27222c
Add files via upload
2022-01-16 08:11:40 -08:00
598c6fdded
Update Rome models ( #491 )
2022-01-14 10:03:30 -08:00
369c021992
topo_expl: update for 2.11.4 ( #490 )
...
* topo_expl: update for 2.11.4
* topo_expl: revert a few logging changes
2022-01-13 13:33:07 -08:00
6ff7690cb5
Use noinline and a few other fixes ( #489 )
...
* Use noinline and a few other fixes
* Tune collectives
2022-01-11 16:51:06 -08:00
7add135529
Updating CHANGELOG.md ( #488 )
2022-01-10 11:34:31 -07:00
3669e12432
Use hipGraph instead of cudaGraph ( #487 )
2022-01-10 08:26:01 -08:00
565fbeb5e9
Tune collectives for 2.11.4 ( #486 )
2022-01-10 08:25:47 -08:00
2530a2f084
[TransferBench] Updating for 2.11.4. Decoupling from RCCL kernel ( #485 )
2022-01-05 16:33:25 -07:00
6268b87c16
Unit tests: fix number of GPU detection ( #484 )
2022-01-05 15:06:12 -08:00
4234a638b5
Merge pull request #482 from ROCmSoftwarePlatform/2.11.4
...
Sync up with 2.11.4
2022-01-05 09:31:51 -08:00
f8d0775a6f
Add another Rome model ( #483 )
2022-01-05 09:26:31 -08:00
434ecb0e1f
Merge remote-tracking branch 'origin/develop' into 2.11.4
2022-01-03 09:54:16 -08:00
bbbb35ceec
Fixing setting of GPUs to 2 when 1 or less GPUs on system for unit tests ( #481 )
2021-12-09 11:04:31 -07:00
c5790b3672
Build fastsocket plugin from ext-net
2021-12-09 08:41:05 +01:00
c88c9f873f
Add env NCCL_NET_DISABLE_INTRA
...
Disable NET transport for intra-node communication by setting the env to 1
It provides an option to error out instead of falling back to NET when superior intra-node transports (P2P and SHM) are unavailable
2021-12-08 16:28:19 +01:00
a94b953bcc
Update Rome model ( #479 )
2021-12-03 08:24:51 -08:00
f589932130
Improve warning message about truncated messages
...
Display hints of cause so that it would be easier for user to debug.
Also change the error type from InternalError to InvalidUsage as most
of time this is caused by a mismatch in collective size or env settings.
2021-12-02 16:13:15 -08:00
8a08a2f579
Update tuning parameters ( #478 )
2021-11-30 08:51:11 -08:00
1157c2edfe
[TransferBench] Adding more preset benchmarks to filter read mode, cpu vs gpu pairs ( #477 )
2021-11-24 18:05:37 -07:00
539de1216f
Minor cppcheck fixes, adding suppression file ( #475 )
...
* Minor cppcheck fixes, adding suppression file
2021-11-24 10:23:59 -07:00
e9bf01fb7e
Determine fine grained memory availability at RCCL bootstrapping ( #471 )
2021-11-19 08:12:53 -08:00
8cf7325d69
Perform busIdToInt64 on the stack.
...
I noticed when I enabled `NCCL_DEBUG_SUBSYS=ALLOC` that this function is
called thousands of times, making the log output unintelligible.
Fortunately, this function can be implemented without heap allocations.
2021-11-19 09:35:55 +01:00
7b8b54955b
Set ROCM_PATH CMake variable in install script ( #470 )
...
* Fixing cmake_install_prefix search to include /opt/rocm-xxxx
* Removing all hard references to /opt/rocm with ROCM_PATH
* Setting ROCM_PATH CMake variable in install script
2021-11-18 14:44:19 -07:00
03a830293c
gtest: dynamically generate tests based on test machine's GPU count ( #467 )
...
* gtest: dynamically generate tests based on test machine's GPU count
* Adjust test element size and bfloat16 threshold for up to 16 GPUs
2021-11-16 10:28:26 -08:00
a6dba6b9dd
Remove hardcoded references to /opt/rocm when using chrpath ( #469 )
...
* Fixing cmake_install_prefix search to include /opt/rocm-xxxx
* Removing all hard references to /opt/rocm with ROCM_PATH
2021-11-15 15:00:55 -07:00
Nirmal Unnikrishnan
gilbertlee-amd
Wenkai Du
akolliasAMD
Sylvain Jeaugey
Ziyue Yang
Ke Wen
void-main
Stanley Tsang
Wenkai Du
Roopa Malavally
Chang Lan
Chris Jones