AI/rocm-systems
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
1,349 Commits 3 Branches 0 Tags
da835cff9c6795d4bf2e274ccc57cb86b9fb52e9
Commit Graph

218 Commits

Author SHA1 Message Date
mberenjk da835cff9c replacing rccl_bfloat16 with hip_bfloat16 (#1126) 
Co-authored-by: mberenjk <mberenjk@amd.com>

[ROCm/rccl commit: 428837ffe4]
 2024-04-11 11:30:37 -05:00
Wenkai Du 99c7fc29ba NPKit: doubling size of event buffers following MAXCHANNELS change (#1135) 
[ROCm/rccl commit: 0ce68f21d4]
 2024-04-09 08:02:58 -07:00
Andy li e373bd44bf Enable fp8 support (#1101) 
* initial checkin

* resolve cr comments

* resolve the build issue

* fix the data correctless issue

* update fp8 header file and update the unit test for fp8 support

* remove fp16 from fp8 headers

* fix ut issue and catch up the latest code from develop

* udate according to cr comments

* update ut according to cr comments

* update num floats for each SumPostDiv from 4 to 6

* update fp8 header file name

* fix the typo

[ROCm/rccl commit: 6777e65c1d]
 2024-03-08 15:17:53 -08:00
Wenkai Du 2354601589 Improve debug messages of memory allocations (#1107) 
[ROCm/rccl commit: ff951e607d]
 2024-03-08 10:55:10 -08:00
Wenkai Du e5aedb153e Add support for using contiguous for GPU direct RDMA (#1096) 
Enabled by env var RCCL_NET_CONTIGUOUS_MEM=1

[ROCm/rccl commit: cbd955627e]
 2024-02-29 10:06:43 -08:00
Bertan Dogancay cee279fd99 Implement ROCTX (#1094) 
* Implement roctx

[ROCm/rccl commit: b617aecc31]
 2024-02-27 15:46:15 -07:00
Wenkai Du d5f5091e5d Merge remote-tracking branch 'rccl/develop' into 2.19.4 
[ROCm/rccl commit: d999d9ad21]
 2024-02-09 11:31:03 -06:00
Bertan Dogancay 45ed3ef4e7 Nvtx support (#1076) 
* NVTX support

[ROCm/rccl commit: 8a442faa12]
 2024-02-08 14:08:24 -07:00
BertanDogancay b17f5947ba Revert re-usage of connect and listen ports 
[ROCm/rccl commit: 12ac20ade5]
 2024-02-01 10:03:13 -08:00
Wenkai Du 4f4e52aafe Merge remote-tracking branch 'rccl/develop' into 2.19.4 
[ROCm/rccl commit: 1a134b283b]
 2024-01-31 11:53:10 -06:00
BertanDogancay c2c9ed2acb Merge remote-tracking branch 'nccl/master' into develop 
[ROCm/rccl commit: 9ff53eeeae]
 2024-01-30 14:43:43 -08:00
Bertan Dogancay 96479caeda Include common.h in enqueue.cc instead (#1067) 
[ROCm/rccl commit: 01b359027b]
 2024-01-30 08:24:22 -08:00
BertanDogancay 404d398bac Merge remote-tracking branch 'nccl/v2.19' into develop 
[ROCm/rccl commit: 81ddf9de89]
 2024-01-24 15:25:33 -08:00
Wenkai Du 17f70df058 Revert "msccl: build same number of kernels as in ROCm 5.7" (#1058) 
This reverts commit f960174d03be7e5174baa83b256526d388a38842.

[ROCm/rccl commit: 7987015a19]
 2024-01-24 08:43:50 -08:00
Bertan Dogancay 56482a8be8 Fix collective trace when rccl is configured (#1056) 
* Fix collective trace when rccl is configured

[ROCm/rccl commit: c4dbf8a914]
 2024-01-22 09:26:44 -07:00
Wenkai Du 8b8179a689 Use new HIP graph API compatible with CUDA 11030 (#991) 
* Use new HIP graph API compatible with CUDA 11030

* Update dependency to ROCm 6.1

* Fix single stream use case

[ROCm/rccl commit: 7e25d5bc55]
 2024-01-21 19:00:50 -08:00
Bertan Dogancay 11674674fc [DEV] Configure functions in RCCL (#986) 
* configure functions in rccl

[ROCm/rccl commit: 28d9b170c9]
 2024-01-18 15:07:16 -07:00
Nilesh M Negi cec06d59d1 Un-escaped character causes error with address sanitizer builds (#992) 
Signed-off-by: Nilesh M Negi <Nilesh.Negi@amd.com>
Co-authored-by: Jenkins <jenkins-compute@amd.com>

[ROCm/rccl commit: 249e9f7f65]
 2024-01-09 13:28:32 -06:00
Pedram Alizadeh d3a47bb387 Merge pull request #1022 from PedramAlizadeh/sync_nccl_2.18.6 
Sync to nccl 2.18.6

[ROCm/rccl commit: aa5c84c997]
 2024-01-09 13:29:29 -05:00
akolliasAMD 0c1f773021 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

[ROCm/rccl commit: f4858e14b2]
 2023-12-21 08:58:33 -07:00
PedramAlizadeh 401a104c5a resolved conflicts, fixed the localNetCount/0 bug 
[ROCm/rccl commit: 0d515f9388]
 2023-12-18 08:11:34 +00:00
Ziyue Yang e4b63a8ba0 Fully disable MSCCL when machine is not matched (#1017) 
* Disable MSCCL algorithm meta loading when machine is not matched

* fully disable init

* fix potential segfault

[ROCm/rccl commit: 655742a3a6]
 2023-12-13 08:36:21 -08:00
Wenkai Du 22730bdc4d msccl: build same number of kernels as in ROCm 5.7 (#1005) 
Removed fullOps kernels from build

[ROCm/rccl commit: 12c08fc52a]
 2023-12-07 13:36:04 -06:00
Wen-Heng (Jack) Chung 33aa8b67be Use a map to host scratch buffers (#1004) 
* Use a map to host scratch buffers

* Address review feedbacks. Deliberately keep mscclSetupScratch function.

[ROCm/rccl commit: 293f0fb752]
 2023-12-05 13:15:28 -06:00
Bertan Dogancay ae0bdad45c IFC mix build (#998) 
[ROCm/rccl commit: 7c0f49a878]
 2023-12-02 18:49:52 -07:00
Wenkai Du b38b7fa3a2 Increase max channles to 64 (#993) 
[ROCm/rccl commit: 4ba65d1d6a]
 2023-12-01 16:01:11 -08:00
Ziyue Yang f0c47d085e Move MSCCL algorithm loading to initialization to workaround HIP graph conflict (#982) 
* MSCCL: pre-specify channels and pre-load algorithms

* add mutex

* fix bug

* clean include

* disable all-gathers temporarily

[ROCm/rccl commit: 4bb0b4a380]
 2023-11-30 09:47:20 -08:00
akolliasAMD bd982864d5 recreated pr 914 to work with current develop branch (#979) 
[ROCm/rccl commit: 56ce9ef05f]
 2023-11-28 16:33:47 -07:00
Ziyue Yang 6ce074d92d Fix MSCCL work FIFO allocation with HIP graph enabled (#967) 
[ROCm/rccl commit: 7fc891bc8d]
 2023-11-15 16:43:28 -08:00
Sylvain Jeaugey b16882a024 2.19.4-1 
Split transport connect phase into multiple steps to avoid port
exhaustion when connecting alltoall at large scale. Defaults to 128
peers per round.
Fix memory leaks on CUDA graph capture.
Fix alltoallv crash on self-sendrecv.
Make topology detection more deterministic when PCI speeds are not
available (fix issue #1020).
Properly close shared memory in NVLS resources.
Revert proxy detach after 5 seconds.
Add option to print progress during transport connect.
Add option to set NCCL_DEBUG to INFO on first WARN.


[ROCm/rccl commit: 88d44d777f]
 2023-11-13 10:36:12 -08:00
Wenkai Du 534af85d0f msccl: enable basic collective trace (#959) 
To avoid increasing number of kernels, colltrace is only enabled with
RCCL_MSCCL_FORCE_FULLOPS=1

[ROCm/rccl commit: 5a800e00cd]
 2023-11-08 20:14:28 -08:00
Wenkai Du 297023a7a6 msccl: add templated kernel (#945) 
* msccl: add templated kernel

* Use defines to improve code readability

* Fix kernel indexing and review feedback

[ROCm/rccl commit: f484ff17b9]
 2023-11-02 17:21:53 -07:00
Wenkai Du b736b506c0 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

[ROCm/rccl commit: a497722894]
 2023-10-30 10:00:12 -07:00
Nilesh M Negi 8b1254a4f1 Fix gcnArchName bug in topology dump (#937) 
Signed-off-by: nileshnegi <Nilesh.Negi@amd.com>

[ROCm/rccl commit: 1e5ca6820b]
 2023-10-28 12:30:36 -05:00
Ziyue Yang e1dfb82023 Fix MSCCL work FIFO out-of-bound issue (#935) 
[ROCm/rccl commit: 4c117e5335]
 2023-10-27 11:24:52 -07:00
Nilesh M Negi 706750597c remove gcnArch support (#920) 
Signed-off-by: nileshnegi <Nilesh.Negi@amd.com>

[ROCm/rccl commit: f22df90e5c]
 2023-10-26 12:09:15 -05:00
Wen-Heng (Jack) Chung dfa0d98f9e 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>

[ROCm/rccl commit: 7ee5c1c28b]
 2023-10-12 20:17:08 -05:00
Sylvain Jeaugey 69ee68b6d3 2.19.3-1 
H800/H100 fixes and tuning.
Re-enable intra-process direct pointer buffer access when CUMEM is
enabled.


[ROCm/rccl commit: 8c6c595185]
 2023-09-26 05:57:15 -07:00
Sylvain Jeaugey 216dfe3d55 Merge remote-tracking branch 'origin/master' into v2.19 
[ROCm/rccl commit: 3435178b6c]
 2023-09-26 05:55:56 -07:00
Sylvain Jeaugey 506d6c332c 2.19.1-1 
Add local user buffer registration for NVLink SHARP.
Add tuning plugin support.
Increase net API to v7 to allow for device-side packet reordering;
remove support for v4 plugins.
Add support for RoCE ECE.
Add support for C2C links.
Better detect SHM allocation failures to avoid crash with Bus Error.
Fix missing thread unlocks in bootstrap (Fixes #936).
Disable network flush by default on H100.
Move device code from src/collectives/device to src/device.


[ROCm/rccl commit: f9c3dc251e]
 2023-09-26 05:50:33 -07:00
Kaiming Ouyang d03ae00bac Fix cudaMemcpyAsync bug 
We are trying to use the copy result of first cudaMemcpyAsync in the
second cudaMemcpyAsync without sync in between. This patch fixes it
by allocating a CPU side array to cache device side addr so that we
can avoid this consecutive cuda mem copy.

Fixes #957


[ROCm/rccl commit: 4365458757]
 2023-09-20 05:51:14 -07:00
akolliasAMD 6f7eb65308 changed the form that RCCL_TREE uses (#888) 
* changed the form that RCCL_TREE uses

[ROCm/rccl commit: b85d73c02e]
 2023-09-15 15:01:33 -06:00
Wenkai Du 3cc41809dd Reduce NPKit latency overhead in MSCCL kernel (#893) 
* Reduce NPKit latency overhead in MSCCL kernel

* Fix build error without NPKit enable

[ROCm/rccl commit: 26e982d913]
 2023-09-15 13:28:26 -07:00
Audrey MP 2e3d45a53a Gcn arch name (#886) 
We use CMake to determine if we're compiling against a version of ROCm that supports gcnArchName and handles architecture checking appropriately. It includes a few helper functions as drop ins for the functionality we used gcnArch for before; sometimes to enable flags, and sometimes to set frequencies.

[ROCm/rccl commit: e58ec78d35]
 2023-09-12 15:34:40 -04:00
Andy li 43a9fd00ee 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

[ROCm/rccl commit: e1dc4d5e42]
 2023-09-11 15:30:04 -07:00
Nusrat Islam ffbfe43500 msccl: add NPKIT profiling for MSCCL send-recv 
[ROCm/rccl commit: a283f55f12]
 2023-09-08 13:11:16 -05:00
David Pagan 75e3927f50 Fix static_assert string literal that contains a "\%". This is no longer (#860) 
valid. They can only be simple escape sequences. Removing '\' fixes
issue. Assert message now compiles and emits the '%' as expected.

[ROCm/rccl commit: 2ec2648247]
 2023-08-21 16:19:59 -07:00
Ziyue Yang 18811f6159 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

[ROCm/rccl commit: d33a70e620]
 2023-08-08 17:30:40 -07:00
Wenkai Du cb291157f4 Detect HIP_UNCACHED_MEMORY support from HIP version (#842) 
[ROCm/rccl commit: d65c0830c6]
 2023-08-04 10:17:04 -07:00
Wenkai Du c0729f28c8 Improve collective trace (#835) 
[ROCm/rccl commit: c8085eb704]
 2023-08-03 07:16:12 -07:00