Auto-tuning CVARs and AllReduce benchmark harness (#2701)#2701
Open
Scusemua wants to merge 3 commits into
Open
Auto-tuning CVARs and AllReduce benchmark harness (#2701)#2701Scusemua wants to merge 3 commits into
Scusemua wants to merge 3 commits into
Conversation
meta-cla
Bot
added
the
CLA Signed
Contributor
|
@Scusemua has exported this pull request. If you are a Meta employee, you can view the originating Diff in D104703792. |
Scusemua
added a commit
to Scusemua/torchcomms
that referenced
this pull request
May 27, 2026
Summary: Add auto-tuning support for the pipesring AllReduce algorithm with two new CVARs (`NCCL_CTRAN_ALLREDUCE_PIPES_NUM_RINGS`, `_NUM_BLOCKS`) that default to -1 (auto-select based on message size). Add a comprehensive benchmark comparing Pipes Ring AllReduce against NCCL AllReduce across message sizes from 256KB to 512MB with 1 and 2 rings. Also fix the ncclx `AlgoConfig.cc` switch exhaustiveness for the new `pipesring` enum value. Differential Revision: D104703792
Scusemua
added a commit
to Scusemua/torchcomms
that referenced
this pull request
May 27, 2026
Summary: Add auto-tuning support for the pipesring AllReduce algorithm with two new CVARs (`NCCL_CTRAN_ALLREDUCE_PIPES_NUM_RINGS`, `_NUM_BLOCKS`) that default to -1 (auto-select based on message size). Add a comprehensive benchmark comparing Pipes Ring AllReduce against NCCL AllReduce across message sizes from 256KB to 512MB with 1 and 2 rings. Also fix the ncclx `AlgoConfig.cc` switch exhaustiveness for the new `pipesring` enum value. Differential Revision: D104703792
meta-codesync
Bot
changed the title
Scusemua
added a commit
to Scusemua/torchcomms
that referenced
this pull request
May 27, 2026
Summary: Add auto-tuning support for the pipesring AllReduce algorithm with two new CVARs (`NCCL_CTRAN_ALLREDUCE_PIPES_NUM_RINGS`, `_NUM_BLOCKS`) that default to -1 (auto-select based on message size). Add a comprehensive benchmark comparing Pipes Ring AllReduce against NCCL AllReduce across message sizes from 256KB to 512MB with 1 and 2 rings. Also fix the ncclx `AlgoConfig.cc` switch exhaustiveness for the new `pipesring` enum value. Differential Revision: D104703792
Scusemua
force-pushed
the
export-D104703792
branch
from
1ed57a0 to
df1a677
Compare
Scusemua
added a commit
to Scusemua/torchcomms
that referenced
this pull request
May 27, 2026
Summary: Add auto-tuning support for the pipesring AllReduce algorithm with two new CVARs (`NCCL_CTRAN_ALLREDUCE_PIPES_NUM_RINGS`, `_NUM_BLOCKS`) that default to -1 (auto-select based on message size). Add a comprehensive benchmark comparing Pipes Ring AllReduce against NCCL AllReduce across message sizes from 256KB to 512MB with 1 and 2 rings. Also fix the ncclx `AlgoConfig.cc` switch exhaustiveness for the new `pipesring` enum value. Differential Revision: D104703792
Scusemua
force-pushed
the
export-D104703792
branch
from
df1a677 to
473725a
Compare
Scusemua
added a commit
to Scusemua/torchcomms
that referenced
this pull request
May 27, 2026
Summary: Add auto-tuning support for the pipesring AllReduce algorithm with two new CVARs (`NCCL_CTRAN_ALLREDUCE_PIPES_NUM_RINGS`, `_NUM_BLOCKS`) that default to -1 (auto-select based on message size). Add a comprehensive benchmark comparing Pipes Ring AllReduce against NCCL AllReduce across message sizes from 256KB to 512MB with 1 and 2 rings. Also fix the ncclx `AlgoConfig.cc` switch exhaustiveness for the new `pipesring` enum value. Differential Revision: D104703792
Scusemua
added a commit
to Scusemua/torchcomms
that referenced
this pull request
May 27, 2026
Summary: Add auto-tuning support for the pipesring AllReduce algorithm with two new CVARs (`NCCL_CTRAN_ALLREDUCE_PIPES_NUM_RINGS`, `_NUM_BLOCKS`) that default to -1 (auto-select based on message size). Add a comprehensive benchmark comparing Pipes Ring AllReduce against NCCL AllReduce across message sizes from 256KB to 512MB with 1 and 2 rings. Also fix the ncclx `AlgoConfig.cc` switch exhaustiveness for the new `pipesring` enum value. Differential Revision: D104703792
Scusemua
added a commit
to Scusemua/torchcomms
that referenced
this pull request
May 27, 2026
Summary: Add auto-tuning support for the pipesring AllReduce algorithm with two new CVARs (`NCCL_CTRAN_ALLREDUCE_PIPES_NUM_RINGS`, `_NUM_BLOCKS`) that default to -1 (auto-select based on message size). Add a comprehensive benchmark comparing Pipes Ring AllReduce against NCCL AllReduce across message sizes from 256KB to 512MB with 1 and 2 rings. Also fix the ncclx `AlgoConfig.cc` switch exhaustiveness for the new `pipesring` enum value. Differential Revision: D104703792
Scusemua
pushed a commit
to Scusemua/torchcomms
that referenced
this pull request
May 27, 2026
Summary: Pull Request resolved: meta-pytorch#2701 Add auto-tuning support for the pipesring AllReduce algorithm with two new CVARs (`NCCL_CTRAN_ALLREDUCE_PIPES_NUM_RINGS`, `_NUM_BLOCKS`) that default to -1 (auto-select based on message size). Add a comprehensive benchmark comparing Pipes Ring AllReduce against NCCL AllReduce across message sizes from 256KB to 512MB with 1 and 2 rings. Also fix the ncclx `AlgoConfig.cc` switch exhaustiveness for the new `pipesring` enum value. Differential Revision: D104703792
Scusemua
added a commit
to Scusemua/torchcomms
that referenced
this pull request
May 27, 2026
Summary: Add auto-tuning support for the pipesring AllReduce algorithm with two new CVARs (`NCCL_CTRAN_ALLREDUCE_PIPES_NUM_RINGS`, `_NUM_BLOCKS`) that default to -1 (auto-select based on message size). Add a comprehensive benchmark comparing Pipes Ring AllReduce against NCCL AllReduce across message sizes from 256KB to 512MB with 1 and 2 rings. Also fix the ncclx `AlgoConfig.cc` switch exhaustiveness for the new `pipesring` enum value. Differential Revision: D104703792
Scusemua
added a commit
to Scusemua/torchcomms
that referenced
this pull request
May 27, 2026
Summary: Add auto-tuning support for the pipesring AllReduce algorithm with two new CVARs (`NCCL_CTRAN_ALLREDUCE_PIPES_NUM_RINGS`, `_NUM_BLOCKS`) that default to -1 (auto-select based on message size). Add a comprehensive benchmark comparing Pipes Ring AllReduce against NCCL AllReduce across message sizes from 256KB to 512MB with 1 and 2 rings. Also fix the ncclx `AlgoConfig.cc` switch exhaustiveness for the new `pipesring` enum value. Differential Revision: D104703792
Scusemua
force-pushed
the
export-D104703792
branch
from
473725a to
3c7a08f
Compare
Scusemua
added a commit
to Scusemua/torchcomms
that referenced
this pull request
May 27, 2026
Summary: Add auto-tuning support for the pipesring AllReduce algorithm with two new CVARs (`NCCL_CTRAN_ALLREDUCE_PIPES_NUM_RINGS`, `_NUM_BLOCKS`) that default to -1 (auto-select based on message size). Add a comprehensive benchmark comparing Pipes Ring AllReduce against NCCL AllReduce across message sizes from 256KB to 512MB with 1 and 2 rings. Also fix the ncclx `AlgoConfig.cc` switch exhaustiveness for the new `pipesring` enum value. Differential Revision: D104703792
Scusemua
added a commit
to Scusemua/torchcomms
that referenced
this pull request
May 27, 2026
Summary: Add auto-tuning support for the pipesring AllReduce algorithm with two new CVARs (`NCCL_CTRAN_ALLREDUCE_PIPES_NUM_RINGS`, `_NUM_BLOCKS`) that default to -1 (auto-select based on message size). Add a comprehensive benchmark comparing Pipes Ring AllReduce against NCCL AllReduce across message sizes from 256KB to 512MB with 1 and 2 rings. Also fix the ncclx `AlgoConfig.cc` switch exhaustiveness for the new `pipesring` enum value. Differential Revision: D104703792
Scusemua
added a commit
to Scusemua/torchcomms
that referenced
this pull request
May 27, 2026
Summary: Add auto-tuning support for the pipesring AllReduce algorithm with two new CVARs (`NCCL_CTRAN_ALLREDUCE_PIPES_NUM_RINGS`, `_NUM_BLOCKS`) that default to -1 (auto-select based on message size). Add a comprehensive benchmark comparing Pipes Ring AllReduce against NCCL AllReduce across message sizes from 256KB to 512MB with 1 and 2 rings. Also fix the ncclx `AlgoConfig.cc` switch exhaustiveness for the new `pipesring` enum value. Differential Revision: D104703792
Scusemua
added a commit
to Scusemua/torchcomms
that referenced
this pull request
May 27, 2026
Summary: Add auto-tuning support for the pipesring AllReduce algorithm with two new CVARs (`NCCL_CTRAN_ALLREDUCE_PIPES_NUM_RINGS`, `_NUM_BLOCKS`) that default to -1 (auto-select based on message size). Add a comprehensive benchmark comparing Pipes Ring AllReduce against NCCL AllReduce across message sizes from 256KB to 512MB with 1 and 2 rings. Also fix the ncclx `AlgoConfig.cc` switch exhaustiveness for the new `pipesring` enum value. Differential Revision: D104703792
Scusemua
added a commit
to Scusemua/torchcomms
that referenced
this pull request
May 27, 2026
Summary: Add auto-tuning support for the pipesring AllReduce algorithm with two new CVARs (`NCCL_CTRAN_ALLREDUCE_PIPES_NUM_RINGS`, `_NUM_BLOCKS`) that default to -1 (auto-select based on message size). Add a comprehensive benchmark comparing Pipes Ring AllReduce against NCCL AllReduce across message sizes from 256KB to 512MB with 1 and 2 rings. Also fix the ncclx `AlgoConfig.cc` switch exhaustiveness for the new `pipesring` enum value. Differential Revision: D104703792
Scusemua
force-pushed
the
export-D104703792
branch
from
3c7a08f to
217ed1c
Compare
Scusemua
added a commit
to Scusemua/torchcomms
that referenced
this pull request
May 27, 2026
Summary: Add auto-tuning support for the pipesring AllReduce algorithm with two new CVARs (`NCCL_CTRAN_ALLREDUCE_PIPES_NUM_RINGS`, `_NUM_BLOCKS`) that default to -1 (auto-select based on message size). Add a comprehensive benchmark comparing Pipes Ring AllReduce against NCCL AllReduce across message sizes from 256KB to 512MB with 1 and 2 rings. Also fix the ncclx `AlgoConfig.cc` switch exhaustiveness for the new `pipesring` enum value. Differential Revision: D104703792
Scusemua
added a commit
to Scusemua/torchcomms
that referenced
this pull request
May 27, 2026
Summary: Add auto-tuning support for the pipesring AllReduce algorithm with two new CVARs (`NCCL_CTRAN_ALLREDUCE_PIPES_NUM_RINGS`, `_NUM_BLOCKS`) that default to -1 (auto-select based on message size). Add a comprehensive benchmark comparing Pipes Ring AllReduce against NCCL AllReduce across message sizes from 256KB to 512MB with 1 and 2 rings. Also fix the ncclx `AlgoConfig.cc` switch exhaustiveness for the new `pipesring` enum value. Differential Revision: D104703792
Scusemua
pushed a commit
to Scusemua/torchcomms
that referenced
this pull request
May 27, 2026
Summary: Pull Request resolved: meta-pytorch#2701 Add auto-tuning support for the pipesring AllReduce algorithm with two new CVARs (`NCCL_CTRAN_ALLREDUCE_PIPES_NUM_RINGS`, `_NUM_BLOCKS`) that default to -1 (auto-select based on message size). Add a comprehensive benchmark comparing Pipes Ring AllReduce against NCCL AllReduce across message sizes from 256KB to 512MB with 1 and 2 rings. Also fix the ncclx `AlgoConfig.cc` switch exhaustiveness for the new `pipesring` enum value. Differential Revision: D104703792
Scusemua
pushed a commit
to Scusemua/torchcomms
that referenced
this pull request
May 27, 2026
Summary: Pull Request resolved: meta-pytorch#2701 Add auto-tuning support for the pipesring AllReduce algorithm with two new CVARs (`NCCL_CTRAN_ALLREDUCE_PIPES_NUM_RINGS`, `_NUM_BLOCKS`) that default to -1 (auto-select based on message size). Add a comprehensive benchmark comparing Pipes Ring AllReduce against NCCL AllReduce across message sizes from 256KB to 512MB with 1 and 2 rings. Also fix the ncclx `AlgoConfig.cc` switch exhaustiveness for the new `pipesring` enum value. Differential Revision: D104703792
Scusemua
added a commit
to Scusemua/torchcomms
that referenced
this pull request
May 27, 2026
Summary: Add auto-tuning support for the pipesring AllReduce algorithm with two new CVARs (`NCCL_CTRAN_ALLREDUCE_PIPES_NUM_RINGS`, `_NUM_BLOCKS`) that default to -1 (auto-select based on message size). Add a comprehensive benchmark comparing Pipes Ring AllReduce against NCCL AllReduce across message sizes from 256KB to 512MB with 1 and 2 rings. Also fix the ncclx `AlgoConfig.cc` switch exhaustiveness for the new `pipesring` enum value. Differential Revision: D104703792
Scusemua
pushed a commit
to Scusemua/torchcomms
that referenced
this pull request
May 27, 2026
Summary: Pull Request resolved: meta-pytorch#2701 Add auto-tuning support for the pipesring AllReduce algorithm with two new CVARs (`NCCL_CTRAN_ALLREDUCE_PIPES_NUM_RINGS`, `_NUM_BLOCKS`) that default to -1 (auto-select based on message size). Add a comprehensive benchmark comparing Pipes Ring AllReduce against NCCL AllReduce across message sizes from 256KB to 512MB with 1 and 2 rings. Also fix the ncclx `AlgoConfig.cc` switch exhaustiveness for the new `pipesring` enum value. Differential Revision: D104703792
Scusemua
added a commit
to Scusemua/torchcomms
that referenced
this pull request
May 27, 2026
Summary: Add auto-tuning support for the pipesring AllReduce algorithm with two new CVARs (`NCCL_CTRAN_ALLREDUCE_PIPES_NUM_RINGS`, `_NUM_BLOCKS`) that default to -1 (auto-select based on message size). Add a comprehensive benchmark comparing Pipes Ring AllReduce against NCCL AllReduce across message sizes from 256KB to 512MB with 1 and 2 rings. Also fix the ncclx `AlgoConfig.cc` switch exhaustiveness for the new `pipesring` enum value. Differential Revision: D104703792
Scusemua
added a commit
to Scusemua/torchcomms
that referenced
this pull request
May 27, 2026
Summary: Add auto-tuning support for the pipesring AllReduce algorithm with two new CVARs (`NCCL_CTRAN_ALLREDUCE_PIPES_NUM_RINGS`, `_NUM_BLOCKS`) that default to -1 (auto-select based on message size). Add a comprehensive benchmark comparing Pipes Ring AllReduce against NCCL AllReduce across message sizes from 256KB to 512MB with 1 and 2 rings. Also fix the ncclx `AlgoConfig.cc` switch exhaustiveness for the new `pipesring` enum value. Differential Revision: D104703792
Scusemua
added a commit
to Scusemua/torchcomms
that referenced
this pull request
May 27, 2026
Summary: Add auto-tuning support for the pipesring AllReduce algorithm with two new CVARs (`NCCL_CTRAN_ALLREDUCE_PIPES_NUM_RINGS`, `_NUM_BLOCKS`) that default to -1 (auto-select based on message size). Add a comprehensive benchmark comparing Pipes Ring AllReduce against NCCL AllReduce across message sizes from 256KB to 512MB with 1 and 2 rings. Also fix the ncclx `AlgoConfig.cc` switch exhaustiveness for the new `pipesring` enum value. Differential Revision: D104703792
Scusemua
added a commit
to Scusemua/torchcomms
that referenced
this pull request
May 27, 2026
Summary: Add auto-tuning support for the pipesring AllReduce algorithm with two new CVARs (`NCCL_CTRAN_ALLREDUCE_PIPES_NUM_RINGS`, `_NUM_BLOCKS`) that default to -1 (auto-select based on message size). Add a comprehensive benchmark comparing Pipes Ring AllReduce against NCCL AllReduce across message sizes from 256KB to 512MB with 1 and 2 rings. Also fix the ncclx `AlgoConfig.cc` switch exhaustiveness for the new `pipesring` enum value. Differential Revision: D104703792
Scusemua
force-pushed
the
export-D104703792
branch
from
217ed1c to
b5f949a
Compare
Scusemua
pushed a commit
to Scusemua/torchcomms
that referenced
this pull request
May 27, 2026
Summary: Pull Request resolved: meta-pytorch#2701 Add auto-tuning support for the pipesring AllReduce algorithm with two new CVARs (`NCCL_CTRAN_ALLREDUCE_PIPES_NUM_RINGS`, `_NUM_BLOCKS`) that default to -1 (auto-select based on message size). Add a comprehensive benchmark comparing Pipes Ring AllReduce against NCCL AllReduce across message sizes from 256KB to 512MB with 1 and 2 rings. Also fix the ncclx `AlgoConfig.cc` switch exhaustiveness for the new `pipesring` enum value. Differential Revision: D104703792
Scusemua
pushed a commit
to Scusemua/torchcomms
that referenced
this pull request
May 27, 2026
Summary: Pull Request resolved: meta-pytorch#2701 Add auto-tuning support for the pipesring AllReduce algorithm with two new CVARs (`NCCL_CTRAN_ALLREDUCE_PIPES_NUM_RINGS`, `_NUM_BLOCKS`) that default to -1 (auto-select based on message size). Add a comprehensive benchmark comparing Pipes Ring AllReduce against NCCL AllReduce across message sizes from 256KB to 512MB with 1 and 2 rings. Also fix the ncclx `AlgoConfig.cc` switch exhaustiveness for the new `pipesring` enum value. Differential Revision: D104703792
Scusemua
added a commit
to Scusemua/torchcomms
that referenced
this pull request
May 28, 2026
Summary: Add auto-tuning support for the pipesring AllReduce algorithm with two new CVARs (`NCCL_CTRAN_ALLREDUCE_PIPES_NUM_RINGS`, `_NUM_BLOCKS`) that default to -1 (auto-select based on message size). Add a comprehensive benchmark comparing Pipes Ring AllReduce against NCCL AllReduce across message sizes from 256KB to 512MB with 1 and 2 rings. Also fix the ncclx `AlgoConfig.cc` switch exhaustiveness for the new `pipesring` enum value. Differential Revision: D104703792
Scusemua
added a commit
to Scusemua/torchcomms
that referenced
this pull request
May 28, 2026
Summary: Add auto-tuning support for the pipesring AllReduce algorithm with two new CVARs (`NCCL_CTRAN_ALLREDUCE_PIPES_NUM_RINGS`, `_NUM_BLOCKS`) that default to -1 (auto-select based on message size). Add a comprehensive benchmark comparing Pipes Ring AllReduce against NCCL AllReduce across message sizes from 256KB to 512MB with 1 and 2 rings. Also fix the ncclx `AlgoConfig.cc` switch exhaustiveness for the new `pipesring` enum value. Differential Revision: D104703792
…orch#2689) Summary: Add a composed Ring AllReduce launcher to the Pipes collectives library. The launcher sequentially launches the existing `ring_reduce_scatter_kernel` and `ring_allgather_kernel` on a user-specified CUDA stream using the "Option B" buffer layout (no scratch buffer; RS writes directly to `recvbuf[my_rank * chunk_bytes]`, AG reads from the same position). Supports 1, 2, or 4 rings with configurable block count and timeout. Reviewed By: siyengar Differential Revision: D104701021
…pytorch#2700) Summary: Wire Pipes-based Ring AllReduce into the Ctran dispatch as a new `pipesring` algorithm. Add three new CVARs (`NCCL_CTRAN_PIPES_SENDRECV_ENABLE`, `_MAX_GROUPS`, `_PIPELINE_DEPTH`) to enable pipelined send/recv staging buffers on the IBGDA transport, as required by ring collectives' `send()`/`recv()`/`forward()` protocol. Add `AllReducePipesRing.cc` implementing the Ctran-side dispatch that builds ring topology, gets per-peer IBGDA transport handles, and launches the Pipes AllReduce. Uses the scratch-free "Option B" buffer layout. Currently supports float32 + Sum only, `nLocalRanks=1` (IB-only, matching PAFT inter-replica topology). Differential Revision: D104701020
Summary: Add auto-tuning support for the pipesring AllReduce algorithm with two new CVARs (`NCCL_CTRAN_ALLREDUCE_PIPES_NUM_RINGS`, `_NUM_BLOCKS`) that default to -1 (auto-select based on message size). Add a comprehensive benchmark comparing Pipes Ring AllReduce against NCCL AllReduce across message sizes from 256KB to 512MB with 1 and 2 rings. Also fix the ncclx `AlgoConfig.cc` switch exhaustiveness for the new `pipesring` enum value. Differential Revision: D104703792
Scusemua
force-pushed
the
export-D104703792
branch
from
b5f949a to
0b470ea
Compare
Scusemua
added a commit
to Scusemua/torchcomms
that referenced
this pull request
May 28, 2026
Summary: Add auto-tuning support for the pipesring AllReduce algorithm with two new CVARs (`NCCL_CTRAN_ALLREDUCE_PIPES_NUM_RINGS`, `_NUM_BLOCKS`) that default to -1 (auto-select based on message size). Add a comprehensive benchmark comparing Pipes Ring AllReduce against NCCL AllReduce across message sizes from 256KB to 512MB with 1 and 2 rings. Also fix the ncclx `AlgoConfig.cc` switch exhaustiveness for the new `pipesring` enum value. Differential Revision: D104703792
Scusemua
pushed a commit
to Scusemua/torchcomms
that referenced
this pull request
May 28, 2026
Summary: Pull Request resolved: meta-pytorch#2701 Add auto-tuning support for the pipesring AllReduce algorithm with two new CVARs (`NCCL_CTRAN_ALLREDUCE_PIPES_NUM_RINGS`, `_NUM_BLOCKS`) that default to -1 (auto-select based on message size). Add a comprehensive benchmark comparing Pipes Ring AllReduce against NCCL AllReduce across message sizes from 256KB to 512MB with 1 and 2 rings. Also fix the ncclx `AlgoConfig.cc` switch exhaustiveness for the new `pipesring` enum value. Differential Revision: D104703792
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary:
Add auto-tuning support for the pipesring AllReduce algorithm with two new CVARs (
NCCL_CTRAN_ALLREDUCE_PIPES_NUM_RINGS,_NUM_BLOCKS) that default to -1 (auto-select based on message size).Add a comprehensive benchmark comparing Pipes Ring AllReduce against NCCL AllReduce across message sizes from 256KB to 512MB with 1 and 2 rings. Also fix the ncclx
AlgoConfig.ccswitch exhaustiveness for the newpipesringenum value.Differential Revision: D104703792