Hawkeye is a system that allows perfect, precision-preserving reproduction of GPU-level matrix multiplication operations on a CPU, enabling efficient and trustworthy third-party auditing of machine le…

The paper characterizes 'dead-entry' TLB misses in GPUs, which occur when recently evicted translations are immediately re-walked, and proposes DEPOT, a Bloom filter mechanism that significantly reduc…

This paper reports on SciGMark 1.5, a benchmark study of specialized and generic implementations in modern languages, examining the consequences of various generic-realization strategies and extending…

This paper presents a method for compressing matrices using a RePair straight-line program (SLP), allowing matrix-vector products with time and space proportional to the compressed size, and demonstra…

First implementation of a 3D Gaussian renderer on an Intelligence Processing Unit (IPU) with 1,472 independent tiles using only on-chip SRAM.

The paper analyzes the bit-flip vulnerability of shared KV-cache blocks in LLM serving systems, demonstrating that these blocks are susceptible to silent, persistent, and selective data corruption.

TileSight is a tile-centric performance-modeling tool that predicts single-GPU kernel latency and cache hit rates with low error, outperforming state-of-the-art baselines and transferring well across…

This paper introduces DGNA, a methodology to unveil the Non-Uniform Memory Access (NUMA) architecture of GPU memory hierarchy through microbenchmarking and data analysis.

This paper quantifies the polymorphic capacity of a commercial LLM, demonstrating that it can cheaply generate large populations of structurally diverse, yet behaviorally equivalent, offensive code pa…

The paper proposes a method to improve the performance of fine-grained offloads on servers by overlapping the offload with other requests using server-side routing.

This paper presents a GPU-accelerated implementation of a Learning with Errors (LWE)-based Key Encapsulation Mechanism (KEM), demonstrating significant speedups and energy efficiency gains on modern G…

This paper proposes Gleam, a framework for efficient GPU sharing across local-area CUDA devices, reducing bandwidth overhead, improving API call latency, and ensuring context consistency.

The paper introduces BOUNDARY FLOW, an LLVM-based framework that enhances kernel fuzzing and analysis by extracting per-task, state-aware data-flow information (arguments and return values) at functio…

The paper introduces $g$MAGNUS, a new algorithm for sparse matrix-matrix multiplication on GPUs that addresses heavy rows by reordering intermediate products and achieves significant speedups.

The paper proposes moving the query instead of the KV-cache during cross-instance attention, demonstrating that this approach is significantly cheaper than moving the cache, especially on modern GPU f…

The paper introduces performance ruggedness analysis to quantify performance variance in GEMM workloads, proposing a two-stage software stack that significantly smooths the performance landscape and b…

This paper proposes approaches for guiding a fuzzer using feedback derived from a control-flow-graph-like structure during the fuzzing of black-box devices and obfuscated compiled binaries.

Researchers developed SolSmith, a tool for finding miscompilation bugs in the Solidity compiler, discovering 25 previously unnoticed bugs over three years.