Metraipolis › archive › dc_ceb0914dac5f
T-CCL: Resource Efficient and Performant Collective Communication using Tensor Memory Accelerator — arXiv:2610.07098
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.07098
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T11:20:16.438Z
- SHA-256 of the archived text
cdf97e9e06a08797752bf16e2be758f3cfea3b7be393a639498f903651c143e4- Stable URL of this page
https://metraipolis.com/documento/dc_ceb0914dac5f
How to cite
T-CCL: Resource Efficient and Performant Collective Communication using Tensor Memory Accelerator — arXiv:2610.07098 — arXiv (en), https://arxiv.org/abs/2610.07098 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ceb0914dac5f (Metraipolis archive dc_ceb0914dac5f, sha256 cdf97e9e06a08797752bf16e2be758f3cfea3b7be393a639498f903651c143e4)
BibTeX
@misc{dcceb0914dac5f,
title = {T-CCL: Resource Efficient and Performant Collective Communication using Tensor Memory Accelerator — arXiv:2610.07098},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.07098},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ceb0914dac5f; sha256 cdf97e9e06a08797752bf16e2be758f3cfea3b7be393a639498f903651c143e4},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.07098. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large transformer-based models increasingly depend on multi-GPU execution, which requires frequent collective communication among GPUs. Existing communication libraries often rely on many GPU threads to achieve high bandwidth or low latency, resulting in a large streaming multiprocessor (SM)-side resource footprint. This footprint can limit the resources available to other GPU work, particularly when communication and computation execute concurrently. Thus, efficient collective communication should not only achieve high collective performance but also reduce its SM-side resource usage. This paper presents T-CCL, a resource-efficient collective communication library based on the Tensor Memory Accelerator (TMA) for intra-node communication. T-CCL offloads both data movement and reduction operations to TMA and executes each collective as a pipelined series of asynchronous TMA operations, reducing the SM resources required for collective communication while maintaining high bandwidth. Evaluated across AllReduce, AllGather, and ReduceScatter collectives, T-CCL outperforms NCCL by up to 2.4x with unrestricted communication resources and up to 3.42x under restricted resource budgets, remains competitive with NCCL's recent symmetric-memory kernels, and occupies the same or fewer SMs in profiled cases. In a GEMM-collective overlap case study, switching the communication backend from NCCL to T-CCL raises the average operator-level speedup over a sequential baseline from 1.12x to 1.25x on two GPUs and from 1.04x to 1.14x on four GPUs, as T-CCL uses fewer SMs for communication, leaving more SMs available to the overlapped GEMM. Integrated into vLLM as a communication backend, T-CCL improves end-to-end inference throughput over vLLM's automatic backend dispatch by up to 1.31x, outperforming it at every evaluated batch size on both the conversation and decode-heavy workloads. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Distributed, Parallel, and Cluster Computing (cs.DC) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.07098 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T11:15:24.673Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).