abf265a911
Rework barriers and adjust scope of atomics ( #1019 )
2024-01-04 08:18:48 -08:00
0a53077c9c
Improve MSCCL algorithms ( #1023 )
2024-01-03 14:51:34 -08:00
f4858e14b2
rearranged how the min and max functions are part of msccl ( #1025 )
...
* rearranged how the min and max functions are part of msccl
* added more coverage on in place graph tests
2023-12-21 08:58:33 -07:00
81602814a7
msccl: fix data corruption with MTYPE_RW ( #1014 )
2023-12-11 20:33:15 -08:00
7965c8b53c
Fix memory fence and use non-temporal store ( #1007 )
...
* Fix memory fence and use non-temporal store
* Use amdgcn builtin instead of inline asm
* Move threadfence location
* Revert changes to gfx90a
* Rework gfx90a change
* Apply changes to gfx94x
2023-12-09 12:16:08 -08:00
baadda4bd8
Relax workgroup barrier implementation for MSCCL send/recv ops. ( #997 )
...
* Trim logic.
* Revert "Trim logic."
This reverts commit 8f2dba6c764108acf2bf5428366b9f41d4d206b9.
* Introduce MSCCL template parameters to send / recv.
* Address review feedbacks.
2023-12-08 17:46:53 -06:00
12c08fc52a
msccl: build same number of kernels as in ROCm 5.7 ( #1005 )
...
Removed fullOps kernels from build
2023-12-07 13:36:04 -06:00
7c0f49a878
IFC mix build ( #998 )
2023-12-02 18:49:52 -07:00
4ba65d1d6a
Increase max channles to 64 ( #993 )
2023-12-01 16:01:11 -08:00
56ce9ef05f
recreated pr 914 to work with current develop branch ( #979 )
2023-11-28 16:33:47 -07:00
569d3f7d59
msccl: allocate scratch as ext-scope fine-grained ( #968 )
2023-11-16 09:57:25 -06:00
df128879a6
Optimize MSCCL reduce primitive switching for gfx942 ( #962 )
...
* Optimize reduce primitive switching for gfx942
* address comment
2023-11-15 08:18:44 -08:00
5a800e00cd
msccl: enable basic collective trace ( #959 )
...
To avoid increasing number of kernels, colltrace is only enabled with
RCCL_MSCCL_FORCE_FULLOPS=1
2023-11-08 20:14:28 -08:00
efc42d9045
Use send instead of sendWithBarrier. ( #727 )
2023-11-07 13:47:24 -06:00
022735d208
Merge pull request #950 from nusislam/msccl-red2
...
msccl: remove cases from numReduction switch statement
2023-11-04 02:48:03 -05:00
dbcba2923b
Use parallel init of LDS and adjust P2P channels for gfx94x ( #943 )
...
* Use parallel init of LDS and adjust P2P channels for gfx94x
* Move another init to parallel
* Fix NCCL_NCHANNELS_PER_PEER setting
2023-11-03 16:06:49 -07:00
f545b94d4b
msccl: remove cases from numReduction switch statement
2023-11-03 16:56:51 -05:00
bb84345943
msccl: use 32-bit LDS access and add RCCL_MSCCL_FORCE_FULLOPS ( #953 )
2023-11-03 10:38:02 -07:00
f484ff17b9
msccl: add templated kernel ( #945 )
...
* msccl: add templated kernel
* Use defines to improve code readability
* Fix kernel indexing and review feedback
2023-11-02 17:21:53 -07:00
6b80a0d0d4
msccl: remove dereference of reduce args
...
It can be removed because the msccl kernel will never execute this code
according to the current msccl setup.
2023-11-02 13:20:00 -05:00
a7400218a2
msccl: use atomic to set dependency flags ( #941 )
2023-10-31 14:46:57 -07:00
a497722894
NPkit: misc fixes for MSCCL ( #936 )
...
* msccl: add xcc_id to timestamp sync
* NPKit: add timestamp for rrc operator
* NPKit: add timestamp for MSCCL init
2023-10-30 10:00:12 -07:00
dbb5611a3a
Remove LDS based software barriers from MSCCL ( #923 )
2023-10-19 16:39:41 -05:00
39812ce757
NPKit: add xcc_id field ( #918 )
2023-10-13 15:24:59 -07:00
7ee5c1c28b
Change MSCCL kernel signature to allow kernel arguments be preloaded via SGPR ( #911 )
...
* Adding a script that will download/compile/run TransferBench/RCCL/UCX/RCCL-tests/RCCL-Unittests/hip-mpi-testsuite (#895 )
Co-authored-by: Pedram Alizadeh <pmohamma@banff-pla-r27-05.pla.dcgpu >
* Only build gfx941
* demo
* fine tune malloc
* Fix merge errors
* Fix merge errors
* Disable parallel build
* Adopt --amdgpu-kernarg-preload-count
* Revert "Adding a script that will download/compile/run TransferBench/RCCL/UCX/RCCL-tests/RCCL-Unittests/hip-mpi-testsuite (#895 )"
This reverts commit f5e252dddf02a41b4d1bc512f306f45f97166304.
* Revert CMake changes.
* NPKIT changes.
* Remove some license declarations.
* Address code review feedbacks on msccl_kernel_impl.h
* Update CMakeLists.txt
* Add CMake logic to check the existence of --amdgpu-kernarg-preload-count
* Fix NPKIT trace logic.
---------
Co-authored-by: Pedram Alizadeh <pmohamma@amd.com >
Co-authored-by: Pedram Alizadeh <pmohamma@banff-pla-r27-05.pla.dcgpu >
Co-authored-by: Ziyue Yang <ziyyang@microsoft.com >
2023-10-12 20:17:08 -05:00
26e982d913
Reduce NPKit latency overhead in MSCCL kernel ( #893 )
...
* Reduce NPKit latency overhead in MSCCL kernel
* Fix build error without NPKit enable
2023-09-15 13:28:26 -07:00
e1dc4d5e42
enable hip graph on multi-node ( #884 )
...
* initial checkin
* enable msccl when hip graph is on
* remove the commented out code of msccl enable check
* clean up the code
* remove the msccl HighestTransportType check logic
2023-09-11 15:30:04 -07:00
a283f55f12
msccl: add NPKIT profiling for MSCCL send-recv
2023-09-08 13:11:16 -05:00
e7f27c66e0
optimizing COLL_UNROLL for MI100 machines ( #863 )
2023-08-29 12:49:06 -04:00
6a0a6a37d9
Use relaxed atomics for LL on GFX11 ( #859 )
2023-08-21 16:28:39 -07:00
f70e3e569b
gfx11: don't use LL for sendrecv ( #853 )
...
* gfx11: don't use LL for sendrecv
* Use builtin instead of inline asm
2023-08-17 08:50:51 -07:00
d33a70e620
NPKit update ( #844 )
...
* NPKit update
1. Enable NPKit for MSCCL kernels
2. Fix NPKit context index calculation for sendrecv kernels
* Update build script for npkit
2023-08-08 17:30:40 -07:00
8e58b65873
gfx11xx: disable LL protocol to workaround mtype issue ( #840 )
2023-08-04 07:53:07 -07:00
60efe26549
Fix merge error and replace inline asm ( #838 )
2023-08-03 13:46:40 -07:00
c8085eb704
Improve collective trace ( #835 )
2023-08-03 07:16:12 -07:00
3db371c9a5
Revert "Enable Ll128 on gfx90a ( #823 )" ( #829 )
...
This reverts commit 420f8af6a0
2023-07-27 20:25:18 -07:00
420f8af6a0
Enable Ll128 on gfx90a ( #823 )
2023-07-26 11:44:15 -07:00
4d20b4b758
Replace atomicExch with __atomic_store_n ( #818 )
...
* Replace atomicExch with __atomic_store_n
* Remove extra semicolon
2023-07-25 11:15:21 -07:00
47f754e6f5
Merge pull request #810 from nusislam/tune-send-recv
...
device: fine-tune RCCL send-recv on MI250/MI200
2023-07-25 10:18:12 -05:00
a7fcd58a97
Enable gfx94x ( #808 ) ( #816 )
...
(cherry picked from commit 94da229a7788d74685d1591a4e75a8341de64f41)
2023-07-21 07:31:27 -07:00
b2a0a0bd3a
device: fine-tune RCCL send-recv
2023-07-17 21:45:52 -05:00
58e53dfd37
device: fine tune MI200/MI250 simple protocol performance
...
With Simple protocol, unroll factor of 4 offers better
performance for most of the collectives (on MI200. MI250, and
MI300) except large message allreduce with Ring algorithm
on MI250 and MI200). This PR changes the default unroll factor
to 4 while adding fine tuning for reduction operations.
2023-07-08 20:21:18 -05:00
ce6a2ffac8
Merge pull request #782 from ROCmSoftwarePlatform/2.18.3
...
Sync up with NCCL 2.18.3
2023-06-29 15:04:16 -07:00
9bba4a2f2a
added npkit support into the all_gather run ring algorithm ( #790 )
2023-06-29 13:59:54 -06:00
abd0615351
Merge remote-tracking branch 'nccl/master' into develop
2023-06-26 22:51:56 +00:00
0c77c66221
Disable Colltrace for --fast option ( #778 )
...
* Disable Colltrace for --fast option
* Limit nprocs for CI
2023-06-21 14:16:09 -06:00
52a28ff2fc
Switching to using atomicAdd_system within kernel for collective trace ( #780 )
2023-06-20 17:49:52 -06:00
3a741787bf
device: use unroll factor based on platforms
2023-06-14 13:36:15 -05:00
f35777e9b0
improve compilation time and create timetrace plot ( #773 )
...
* improve compilation time and create time-trace plot
* set default value for nproc
2023-06-14 09:17:51 -06:00
ea38312273
2.18.3-1
...
Fix data corruption with Tree/LL128 on systems with 1GPU:1NIC.
Fix hang with Collnet on bfloat16 on systems with less than one NIC
per GPU.
Fix long initialization time.
Fix data corruption with Collnet when mixing multi-process and
multi-GPU per process.
Fix crash when shared memory creation fails.
Fix Avg operation with Collnet/Chain.
Fix performance of alltoall at scale with more than one NIC per GPU.
Fix performance for DGX H800.
Fix race condition in connection progress causing a crash.
Fix network flush with Collnet.
Fix performance of aggregated allGather/reduceScatter operations.
Fix PXN operation when CUDA_VISIBLE_DEVICES is set.
Fix NVTX3 compilation issues on Debian 10.
2023-06-14 01:29:17 -07:00
Wenkai Du
Ziyue Yang
akolliasAMD
Wen-Heng (Jack) Chung
Bertan Dogancay
Nusrat Islam
Andy li
Pedram Alizadeh
Wenkai Du
gilbertlee-amd
Sylvain Jeaugey