12517a957e
Re-apply unroll=1 and 112 channels for gfx950 ( #1706 )
...
* Reapply "[SRC] Enable unroll=1 for gfx950 (#1602 )" (#1667 )
This reverts commit 329e13efff#1596 )" (#1620 )
This reverts commit b17338d164
2025-05-28 14:58:10 -05:00
7b633d5844
Fixed errors in the CHANGELOG for ROCm 7.0 ( #1702 )
...
* Updated 6.5 release to be 7.0
* Corrected the RCCL version for 6.4.1
* Moved items to the correct releases
* Added NCCL 2.25.1 compatibility item
* Fixed wording
* Added entry for `ManagedMem` and `ManagedMemGraph` test fix
2025-05-23 15:47:59 -05:00
7f878baef0
Revert "[AG and RS channel tuning] Add thread work threshold to tuning models and precompute reg index in LL128 ( #1641 )"
...
This reverts commit 00c1eb098c
2025-05-21 20:21:27 -05:00
1710c27e77
CHANGELOG.md: Add UT failures as known issue for 6.4.1. ( #1698 )
...
* CHANGELOG.md: Add UT failures as known issue for 6.4.1.
---------
Co-authored-by: Jeffrey Novotny <jnovotny@amd.com >
2025-05-19 10:40:50 -05:00
e602497789
Added known issue for 6.4.1 release to CHANGELOG.md. ( #1697 )
2025-05-16 08:17:48 -05:00
f306c00671
Change GPU references to gfx950. ( #1695 )
2025-05-15 10:32:46 -05:00
00c1eb098c
[AG and RS channel tuning] Add thread work threshold to tuning models and precompute reg index in LL128 ( #1641 )
...
* Update LL128 elems per thread
* Precompute ix[g] in LL128 prim
* Make Threadthreshold part of tuning models
* Ignore channel tuning when channels are env controlled
* Tune LL128 max limit for AG
* Tune LL128 max limit for RS
* Retune AR LL128 limits due to changes
* Update CHANGELOG.md
---------
Co-authored-by: Jeffrey Novotny <jnovotny@amd.com >
2025-05-14 14:35:54 -05:00
d665547eef
Remove MSCCL single node AllGather XMLs ( #1693 )
...
* Remove MSCCL single node XMLs
* Remove comment on MSCCL AG single node support
2025-05-13 17:07:03 -05:00
9ef45df8f7
Fix when more than 64 channels are used for multi-collective group calls ( #1688 )
...
* Fix when more than 64 channels are used for multi-collective group calls
* Update CHANGELOG.md
Co-authored-by: Jeffrey Novotny <jnovotny@amd.com >
---------
Co-authored-by: Jeffrey Novotny <jnovotny@amd.com >
2025-05-12 18:05:57 -05:00
329e13efff
Revert "[SRC] Enable unroll=1 for gfx950 ( #1602 )" ( #1667 )
...
* Revert "[SRC] Enable unroll=1 for gfx950 (#1602 )"
This reverts commit 307bc10781Nilesh.Negi@amd.com >
2025-04-30 23:33:08 -05:00
aa7991dfc8
[AllGather MSCCL] Multinode and single node support up to certain send count ( #1650 )
...
* Add multinode and singlenode allgather XML
2025-04-24 09:02:03 -04:00
28ab8603d2
Add documentation for NPS4 and CPX partition modes ( #1555 )
2025-03-31 09:25:25 -06:00
b17338d164
Revert "[GRAPH] Increase default nChannels to 112 for gfx950 ( #1596 )" ( #1620 )
...
* Revert "[GRAPH] Increase default nChannels to 112 for gfx950 (#1596 )"
This reverts commit 1df73e209e
2025-03-28 17:57:06 -05:00
ddc5d58b93
Rail optimized trees ( #1540 )
...
* Allow disabling rail-optimized trees via RCCL_DISABLE_RAIL_TREES, Graphviz-friendly output via RCCL_OUTPUT_TREES
2025-02-20 15:18:29 -07:00
dc75209dd7
Add IB verbs logging and enable traces through install.sh ( #1511 )
...
* Add IB Verbs logging
* Simplify tracing and undo debug.h changes
* Update debug.h
* Update CHANGELOG.md
* Update CHANGELOG.md
* Update CHANGELOG.md
* Exchange remote comm device index
2025-01-31 12:35:39 -05:00
36343be84f
Merge remote-tracking branch 'nccl/master' into develop
2025-01-23 12:08:46 -06:00
2e35417fe5
Added RCCL env params to control setting the SO_REUSEADDR and SO_LINGER socket options ( #1418 )
...
* Added RCCL env params to control setting the SO_REUSEADDR and SO_LINGER socket options. This can allow control over the number of file descriptors created during bootstrapping.
* Casted the linger value to `int` sooner to avoid a scope of unknown typed-ness.
* Added CHANGELOG entry for this feature.
2025-01-14 10:26:04 -07:00
e42f10a361
Update rccl changelog for 6.3.1 ( #1433 )
...
* Update rccl changelog for 6.3.1
* Fix version number
* Correct RCCL release version
* Added details to 6.3.0 changelog
---------
Co-authored-by: corey-derochie-amd <161367113+corey-derochie-amd@users.noreply.github.com >
2024-11-26 08:46:37 -05:00
6ed513e1b9
Update CHANGELOG to match release branches 6.2 and 6.3 ( #1391 )
...
* [CHANGELOG] Add Known issues for ROCm 6.2.1
Signed-off-by: nileshnegi <Nilesh.Negi@amd.com >
* Updated 6.2.1 known issues to match the content in develop.
* Updated CHANGELOG for ROCm 6.3 release. (#1380 )
* Updated CHANGELOG for ROCm 6.3 release.
* Update CHANGELOG to new format.
Co-authored-by: Jeffrey Novotny <jnovotny@amd.com >
---------
Co-authored-by: Jeffrey Novotny <jnovotny@amd.com >
---------
Signed-off-by: nileshnegi <Nilesh.Negi@amd.com >
Co-authored-by: nileshnegi <Nilesh.Negi@amd.com >
Co-authored-by: Jeffrey Novotny <jnovotny@amd.com >
2024-10-23 13:49:40 -06:00
7f87b0cd85
Updated the information for 6.2.1 in the changelog so that it reflects what's in the 6.2.1 release notes
2024-09-23 14:27:58 -04:00
dcc75797a1
Update CHANGELOG.md for RCCL 2.20.5 ( #1150 )
2024-04-24 09:07:49 -06:00
a14137c062
Updated CHANGELOG for next release ( #1146 )
...
* Updated CHANGELOG to release for ROCm 6.1.0 (#1142 )
* Fixed missing CHANGELOG notes from ROCm 5.5 through unreleased 6.1 (#1141 )
* Update CHANGELOG.md for ROCm release 5.5
(cherry picked from commit 975327be45f2313dc7249f9c54ad90870e833a4a)
* Update CHANGELOG.md for ROCm 5.7.0
(cherry picked from commit ac8db8d8e0853f1783c10e2858f6c3b86e4d27cb)
* Added ROCm 6.0 and 6.1 CHANGELOG notes.
---------
Co-authored-by: gilbertlee-amd <44450918+gilbertlee-amd@users.noreply.github.com >
(cherry picked from commit 3361abe786
2024-04-15 16:29:40 -06:00
4cb62f999a
Rail optimization for rings ( #1140 )
...
- Modifies the ring creation algorithm to be friendlier to rail-optimized topologies (should not affect classic fabric topologies)
2024-04-15 12:03:57 -06:00
3361abe786
Fixed missing CHANGELOG notes from ROCm 5.5 through unreleased 6.1 ( #1141 )
...
* Update CHANGELOG.md for ROCm release 5.5
(cherry picked from commit 975327be45f2313dc7249f9c54ad90870e833a4a)
* Update CHANGELOG.md for ROCm 5.7.0
(cherry picked from commit ac8db8d8e0853f1783c10e2858f6c3b86e4d27cb)
* Added ROCm 6.0 and 6.1 CHANGELOG notes.
---------
Co-authored-by: gilbertlee-amd <44450918+gilbertlee-amd@users.noreply.github.com >
2024-04-11 15:04:40 -06:00
503a472a25
Replaced ROCmSoftwarePlatform and RadeonOpenCompute links with ROCm links. ( #1125 )
2024-03-25 16:29:13 -06:00
1c166046a2
Add back __syncthreads() in barrier and adjust stack size ( #688 )
2023-02-18 08:50:31 -08:00
e1cb45ff22
Merge remote-tracking branch 'nccl/master' into HEAD
2023-02-04 01:44:43 +00:00
3e8ab4e46e
Updating CHANGELOG ( #669 )
2022-12-19 09:36:57 -07:00
36ac8107bd
Update CHANGELOG up to ROCm 5.4 ( #649 )
...
* Update CHANGELOG for ROCm 5.4.0
2022-11-23 09:40:19 -07:00
47b2fc3a30
Adding opt-in hipGraph support for RCCL via RCCL_ENABLE_HIPGRAPH ( #608 )
...
Adding opt-in hipGraph support via RCCL_ENABLE_HIPGRAPH
2022-09-06 10:29:46 -06:00
80f53cc171
Reduce AlltoAll port usage in send/recv proxy ( #577 )
...
* Reduce AlltoAll port usage when connecting proxy
Reuse socket ports when connecting proxies in AlltoAll.
Existing port usage in AlltoAll is O(n) for recv and O(n) for send,
reusing socket ports in server or client side will make one of them
O(1), reusing both will reduce the total port usage to O(1) and enables
AlltoAll in >64 MI200 nodes.
* Update changelog accordingly
Update changelog accordingly.
2022-07-07 16:15:52 -07:00
2e65881a79
Revert "Adding the missing roc:: namespace ( #570 )" ( #576 )
...
This reverts commit d5bea2cfaa
2022-07-06 10:07:35 -07:00
d5bea2cfaa
Adding the missing roc:: namespace ( #570 )
...
* Adding the missing roc:: namespace, effectively changing the value of RCCL_LIBRARY from rccl to roc::rccl.
The important difference is that rccl is treated as a symbolic "-lrccl" by linker (and fail the linking
due to a missing library search path), while roc::rccl is a target name, which can resolve into an absolute
library path.
Co-authored-by: Paul Fultz II <pfultz2@yahoo.com >
* Adding a changelog entry
* minor updates to wording
* missing period
Co-authored-by: Paul Fultz II <pfultz2@yahoo.com >
Co-authored-by: Saad Rahim <44449863+saadrahim@users.noreply.github.com >
2022-06-27 11:44:43 -06:00
0336ffdf70
Introduce multi-rank support per device.
...
This is a single commit of the source code changes required to
introduce support for multiple ranks per device.
A new interface (ncclCommRankInitMulti) has to be used to make use of
this new feature.
2022-06-10 14:23:12 +00:00
700b473211
Moving opt-in custom signal handler from UnitTests into RCCL ( #550 )
...
* Enable via RCCL_ENABLE_SIGNALHANDLER=1
2022-05-20 09:56:38 -06:00
a8f1e61f48
Packages for test and benchmark executables on all supported OSes using CPack. ( #512 )
2022-03-21 15:04:14 -06:00
7add135529
Updating CHANGELOG.md ( #488 )
2022-01-10 11:34:31 -07:00
e579de7ec2
Update changelog with packaging information ( #409 )
2021-07-27 10:38:36 -06:00
6842429a14
Updating changelog to show install script fix ( #384 )
2021-06-08 13:00:40 -06:00
903c84050d
ROCm 4.3 changelog update ( #379 )
...
* Update CHANGELOG.md (#378 )
* Updating CHANGELOG.md for ROCm 4.3
2021-06-03 10:56:02 -06:00
9d7232c091
Clique tuning upgrade ( #352 )
...
* Enabling clique for any XGMI-connected topology, adding tuning
* Updating CHANGELOG for clique tuning
* Re-working clique barrier system to work on multi-process / multi-gpu
2021-05-06 09:50:07 -06:00
69c0b44553
Updating CHANGELOG.md for ROCm 4.1.0 ( #336 )
2021-03-25 21:44:24 -06:00
41bcfb8878
Clique kernel support ( #295 )
...
* Adding experimental clique-based kernels (opt-in only)
Co-authored-by: Stanley Tsang <stanley.tsang@amd.com >
Co-authored-by: Gilbert Lee <gilbert.lee@amd.com >
Co-authored-by: Wenkai Du <43822138+wenkaidu@users.noreply.github.com >
2020-11-10 15:44:10 -07:00
bdd8adf1ca
Adding a CHANGELOG ( #296 )
2020-11-05 13:38:30 -07:00
Nilesh M Negi
corey-derochie-amd
PedramAlizadeh
Arm Patinyasakdikul
Mustafa Abduljabbar
gilbertlee-amd
Istvan Kiss
BertanDogancay
Jeffrey Novotny
Sandra Polifroni
Bertan Dogancay
Wenkai Du
Wenkai Du
Yifan Xiong
Dmitry Mikushin
Edgar
Liam Wrubleski
Stanley Tsang