• 学术搜索
  • 科研智能体
    • Research Labs
    • AI 阅读
    • AI 文库
    • 深度研究
    • 学者亮点
  • 学术资源
    • AI2000
    • 期刊/会议
    • 学者库
    • 学术API
      MCP&Skill
    • 溯源树
    • 数据集
  • 知识沉淀
    • 学术空间
订阅小程序
旧版功能
aminer vip
开通会员低至0.73元/天
一次搞定AI科研
立即登录
  • English
  • 联系方式
    International Conference on Architectural Support for Programming Languages and Operating Systems

    International Conference on Architectural Support for Programming Languages and Operating Systems

    ConferenceCCF 计算机体系结构/并行与分布计算/存储系统 A

    年发文量

    研究主题

    论文(2728)

    排序
    1STRAW: Stress-Aware WL-Based Read Disturbance Management for High-Density NAND Flash Memory.
    Myoungjun Chun,Jaeyong Lee,Inhyuk Choi,Jisung Park,Myungsuk Kim,Jihong Kim

    While NAND flash memory has continuously increased its storage density over decades, this progress has exacerbated the read-disturbance problem. In this work, we identify two fundamental limitations of existing read-disturbance management techniques that trigger read reclaim (RR) at the block granularity: (i) they overlook the heterogeneous reliability impact of read disturbance across individual word-lines (WLs), leading to unnecessary RR in many cases; and (ii) they address read disturbance only after disturbance-induced errors have already accumulated, which forces substantial RR-induced copy overheads in read-disturbanceprone modern NAND flash memory. To address these limitations, we propose STRAW (STRess-Aware Wordline-based read-disturbance management), a new technique that minimizes RR overheads through two key ideas: (i) stress-aware WL-based read reclaim, which monitors the accumulated read-disturbance effect on each WL and reclaims only heavily disturbed WLs, and (ii) stress-reduced read, which mitigates disturbance on valid WLs during each read operation by scaling pass-through voltages based on WL validity. Our experimental results using a modern SSD emulator show that STRAW reduces RR-induced page-copy overhead by 88.6% on average compared with the state-of-the-art technique.

    2026引用:1
    引用
    AI阅读
    加入学术空间
    2I/O Analysis is All You Need: an I/O Analysis for Long-Sequence Attention.
    Xiaoyang Lu,Boyu Long,Xiaoming Chen,Yinhe Han,Xian-He Sun

    As GPUs and other accelerators become increasingly popular, optimizing I/O operations between on-chip and off-chip memory is increasingly critical. I/O analysis, however, is complex, requiring a deep understanding of application dataflow and memory hierarchy. Developing a practical I/O analysis methodology remains a timely challenge. Self-attention is employed extensively in transformer models, but its quadratic memory complexity poses significant challenges to modern memory systems. In this study, we explore how to use I/O analysis to develop optimal solutions for accelerating exact long-sequence self-attention. We first introduce a novel I/O analysis for tall-and-skinny matrix-matrix multiplication, which captures the dominant data movement behavior of long-sequence self-attention. Guided by systematic I/O analysis, we develop AttenIO, an I/O-driven accelerator for exact long-sequence self-attention with three key optimizations: (1) an analytically derived I/O-optimal tiling and scheduling to minimize I/O operations, (2) fine-grained three-level communication-computation overlapping to hide I/O stalls, and (3) parallel execution patterns for efficient softmax. Our evaluation shows that AttenIO achieves a 1.6x8.8x speedup over the state-of-the-art solutions. Although AttenIO is designed for self-attention, it also highlights the broader potential of I/O analysis as a principled foundation for guiding high-performance I/O optimizations.

    2026引用:1
    引用
    AI阅读
    加入学术空间
    3Wax: Optimizing Data Center Applications with Stale Profile.
    Tawhid Bhuiyan, Sumya Hoque, Angelica Aparecida Moreira,Tanvir Ahmed Khan

    Data center applications' large instruction footprints cause frequent front-end stalls by overwhelming on-chip micro-architectural structures such as instruction cache (I-cache), instruction translation look-aside buffer (iTLB), and branch target buffer (BTB). To reduce pressure on these structures, data center providers leverage profile-guided optimizations by reordering binary layout along a relatively small number of hot code paths. Such reordering provides the highest benefit if profile collection and optimization happen on the same version of the binary. In practice, companies have to optimize and deploy a fresh version of the binary with a profile from a previous version, making a large fraction of the profile stale. In this paper, we propose Wax(1), a novel technique to optimize data center applications with stale profiles. Wax's key insight is to leverage the debug and source code information while optimizing fresh binaries with stale profiles. We evaluate Wax for 5 data center applications to show that Wax provides significant (5.76%-26.46%) performance speedups. Wax achieves 1.20%-7.86% greater speedups than the state of the art, obtaining 65%-93% of fresh profiles' benefits.

    2026
    引用
    AI阅读
    加入学术空间
    4Maverick: Rethinking TFHE Bootstrapping on GPUs Via Algorithm-Hardware Co-Design.
    Zhiwei Wang, Haoqi He,Lutan Zhao, Qingyun Niu,Dan Meng,Rui Hou

    Fully homomorphic encryption (FHE) enables arbitrary computation over encrypted data (ciphertext) without compromising confidentiality. Within this family, TFHE features versatile bootstrapping mechanisms that is attractive for security-critical applications. However, its prohibitive computational cost severely limits practical deployment. While hardware acceleration is promising, mere compute scaling fails to overcome the inherent barriers. In particular, the combination of limited algorithmic parallelism and inadequate understanding of hardware behaviors prevents full exploitation of the available performance headroom. In this paper, we present Maverick, a GPU-based solution that rethinks TFHE bootstrapping acceleration through joint algorithm-hardware co-design. At the algorithmic level, we reconstruct blind rotation by shifting test vectors from pre-loading to post-injection. This reformulation turns the original length-.. single chain into a multi-chain structure with root n sub-chains of depth root n, raising external-product (EP) parallelism from 1 to the theoretical bound of root n. At the hardware level, we introduce a partial-domain transformation strategy that terminates the NTT early in a stage-aware manner and selectively shifts computation to downstream operators, redefining operator boundaries to balance the workload across EP operators. Experimental results show that Maverick delivers state-of-the-art GPU acceleration. It outperforms the best existing CPU and GPU baselines by 331.2x and 3.4x, respectively, on programmable bootstrapping, and achieves up to 108.5x speedup over CPU-based circuit bootstrapping. Together, these results highlight the substantial potential of algorithm-hardware co-design for advancing FHE performance on general-purpose platforms.

    2026
    引用
    AI阅读
    加入学术空间
    5SwiftSpec: Disaggregated Speculative Decoding and Fused Kernels for Low-Latency LLM Inference.
    Ziyi Zhang,Ziheng Jiang,Chengquan Jiang,Menghan Yu,Size Zheng,Haibin Lin, Xin Liu,Henry Hoffmann

    Low-latency, single-request decoding of large language models is critical for interactive systems with tight SLA demands. Prior work reduces latency through speculative decoding (combining a small draft model with a larger target model), but the draft model remains on the critical path, and communication overhead limits scaling across GPUs due to the small batch size associated with single-request decoding. To address these limitations, this paper introduces SwiftSpec: a system architecture that disaggregates draft and target models across homogeneous GPUs within a single node and utilizes NCCL-low-latency primitives directly to improve the performance of core GEMM and attention kernels. Our implementation includes 3k lines of custom CUDA for fused kernels and an evolving tree cache for KV-cache consistency and maximized reuse between draft and target models. On a single 8xH800 GPU node, SwiftSpec achieves 347 tokens/s for Llama-3-70B-1.3x faster than NVIDIA's own benchmarks on a higher-performance 8xH200 setup-and averages 1.75x faster decoding than state-of-the-art speculative decoding across five model families and six datasets. Specifically, we find that for Llama-3-70B SwiftSpec is significantly faster across all 480 tested queries, showing 1.7x speedup over the best open-source baseline for 95th percentile requests.

    2026引用:4
    引用
    AI阅读
    加入学术空间
    立即登录,查看全部 2728 篇论文

    高被引作者

    作者引用发文
    David E. Culler77347
    Christina Delimitrou558914
    Seth Hollar54391
    Jason Hill54391
    Robert Szewczyk54391
    Kristofer S. J. Pister54391
    Christos Kozyrakis530319
    Anoop Gupta493413
    Yuanyuan Zhou424013
    Babak Falsafi411114

    高产作者

    作者引用发文
    Josep Torrellas113724
    Onur Mutlu298021
    Luis Ceze265719
    Christos Kozyrakis530319
    Fred Chong154019
    Xuehai Qian223218
    Parthasarathy Ranganathan281218
    Minyi Guo67317
    Shan Lu334117
    Christopher W. Fletcher79416

    相关期刊

    ACM Transactions on Architecture and Code Optimization
    ACM Transactions on Computer Systems
    ACM Transactions on Storage
    ACM SIGPLAN Symposium on Principles & Practice of Parallel Programming
    USENIX Conference on File and Storage Technologies
    High Performance Computing and Applications
    IEEE International Symposium on Workload Characterization
    Asia Pacific Workshop on Systems
    Proceedings. IEEE International Conference on Cluster Computing
    Networking, Architecture and Storages