Research and ACM SRC Posters Archive

OpenCCL: A Proposed Open Standard and Reference Implementation Unifying *CCLs for Performance, Portability, and Productivity


Poster Type: Research Posters

Author: Anthony Skjellum (Tennessee Tech University), Purushotham Bangalore (University of Alabama), Thomas Hines (Tennessee Tech University), Kayla Humphrey (Tennessee Tech University), Javontae Martin (Tennessee Tech University), Amr Akmal Abouelmagd (Tennessee Tech University), Riley Shipley (Tennessee Tech University), Rajat Bisht (Tennessee Tech University), Zulkar Nine (Arkansas Tech University)

Abstract: NVIDIA's NCCL is the de-facto GPU communication API for distributed AI, but it is a toolkit rather than a specification: its semantics are thin, it is tied to one vendor's stack, and other *CCLs re-implement or fork it. OpenCCL proposes an open standard and reference implementation: a normative specification with an ABI-stable header over pluggable transports and collective engines, so one library spans vendors and fabrics without application changes. OpenCCL runs unmodified NCCL codes and addresses all 33 entry points of NCCL 2.23.4. On Slingshot-11 it builds on RAPIDS Cascade APIs: kernel-initiated transfers behind a stream-triggered interface that fits NCCL semantics. Preliminary results on LLNL's Tuolumne, an El Capitan-class system, outperform RCCL and Cray MPICH for Allreduce from 256 bytes to 16 KiB, and Cascade outperforms Cray MPICH and our earlier stream-triggered MPI for small messages. MSCCL's AllToNext is implemented. The poster invites participation in standardization, implementation, and AI adoption.

Best Poster Finalist (BP): no
Poster: PDF
Poster Summary: PDF


Back to Poster Archive Listing