cs.DC · 2026-09-11 · No. 112

Distributed, Parallel, and Cluster Computing, 2026-09-11.

7 new papers in cs.DC. Titles, authors, abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →

01 — The papers

7 entries
  1. 01

    GPU-CFR: 80x Faster Counterfactual Regret Minimization by Compiling the Game to Static Dataflow and CUDA Graph Replay

    Boning Li, Longbo Huang

    cs.DC · cs.AI · cs.GT · cs.MS · cs.PL

    Counterfactual regret minimization (CFR) is one of the few large numerical workloads that still runs faster on CPUs than on GPUs. Each iteration sweeps a game tree with up to billions of states in millions of small, interdependent gather and scatter steps issued through a generic tree interface. On a GPU every kernel finishes in microseconds, so kernel launches and framework dispatch dominate the run time, and prior GPU implementations have...

    arxiv.org/abs/2609.11923 · PDF

  2. 02

    Building py-kvcache: A Performance Characterization of External KV Caching for vLLM with NVMe SSDs

    Joseph Kanichai, Tiziano De Matteis, Animesh Trivedi

    cs.DC · cs.LG

    Prefix caching can reduce the time to first token (TTFT) of long-context LLM requests by reusing previously computed key-value (KV) states, but for short prefixes or fast GPUs, recomputation can be faster than loading from an external cache. We characterize this tradeoff in vLLM across GPU, CPU, and NVMe tiers using synthetic workloads, long-context benchmarks, production traces, and find that cache performance depends on transfer...

    arxiv.org/abs/2609.11744 · PDF

  3. 03

    Entwine: Coordinating Tiled Computation and Fine-Grained Communication across GPUs

    Kai Ma, Quanfeng Lv, Jingguo Ge, Bowei Dai, Kefan Ruan

    cs.DC · cs.AR

    Modern high-performance GPU computations partition tensors into tiles to exploit data reuse and parallelism. Individual tile computations complete earlier than the full tensor computation, creating opportunities to overlap computation and communication. However, a mismatch between computation and communication progress can limit these opportunities. Communication stalls when no data is ready, and may lag when data arrives in bursts....

    arxiv.org/abs/2609.11562 · PDF

  4. 04

    Taming Bitwise Behavior in GPU Kernels with Tensor Core: Black-Box Reconstruction, Compiler Enforcement, and Static Verification

    Ziteng Yang, Nicholas J. Riasanovsky, Warren Deng, Vivek Sarkar

    cs.DC · cs.PF · cs.PL

    Determinism and numerical reproducibility are increasingly required of GPU kernels in machine learning systems, yet deterministic implementations of the same kernel can still differ bit for bit. Floating-point reduction order is the primary cause, alongside partial-sum precision, fused multiply-add operations, and rounding placement. These choices may be hand-coded, selected by a block-level language such as Triton, or hidden inside a...

    arxiv.org/abs/2609.11356 · PDF

  5. 05

    Rethinking Sparse Formats for RISC-V: A Hierarchical Approach to High-Performance SpMV

    Anna Pirova, Anastasia Vodeneeva, Konstantin Kovalev, Alexander Ustinov, Maksim Zagriadskov, Daniil Litvyakov,...

    cs.DC · cs.PF

    The sparse matrix-vector multiplication (SpMV) algorithm is a fundamental computational kernel of linear algebra and serves as a building block for numerous applications, primarily iterative solvers for systems of linear equations used in scientific and engineering simulations. This paper compares vectorized implementations of the SpMV algorithm across eight established sparse matrix storage formats and proposes a novel modification of the...

    arxiv.org/abs/2609.11352 · PDF

  6. 06

    Can AI Remediate Backend Failures Safely? GuardedAct with Blast-Radius-Aware Sandboxing

    Wanrong Cai, Tianyu Yu, Shaorui Pi, Xiaoxuan Sun, Wenrui Ma

    cs.DC · cs.SE

    Large Language Models (LLMs) have shown promising capabilities in generating remediation actions for microservice failures. However, directly executing AI-generated repair actions in production risks cascading collateral damage. We propose GuardedAct, a sandbox-first remediation framework that interposes a blast-radius-aware verification layer between the LLM action generator and the production environment. GuardedAct operates in four phases:...

    arxiv.org/abs/2609.11264 · PDF

  7. 07

    The Computing Channel: How Modulation Programs the Airwaves

    Saeed Razavikia, Carlo Fischione

    cs.DC

    Distributed computing and distributed artificial intelligence require frequent exchanges of intermediate results, although many applications need only an aggregate rather than messages from individual devices. Conventional systems recover each message before computing the aggregate, whereas over-the-air computation (OAC) exploits simultaneous transmission to obtain it directly. However, dominant OAC implementations rely on analog signaling,...

    arxiv.org/abs/2609.11145 · PDF

This edition is part of The Daily Abstract — cs.DC archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.

Colophon Set in Georgia, with system sans for interface chrome and a monospaced stack for code and paper identifiers. Sole accent: amber #D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.