arXiv:2410.22229v2 Announce Type: replace-cross
Abstract: Offloading stateful network functions to multi-threaded SoC SmartNICs promises significant performance and cost benefits. However, realizing...
By Shaoke Xi, Jiaqi Gao, Fuliang Li, Minlan Yu, Ennan Zhai
SWE-Opt is a new benchmark that evaluates large language models (LLMs) on repository‑level software performance optimization. It is built from 102 expert‑written optimizations from open‑source projects and measures runtime, peak memory, and Time‑Weighted Memory Usage (TWMU) under varied input data, execution conditions, and noise‑aware measurements. The study finds that current LLMs achieve few runtime gains and almost no memory improvements, whereas expert implementations deliver a 15.5× speedup and 171.3× memory reduction.
By Ezgi Sar{\i}kayak, Wenchao Gu, Hesham Ghonim, Chunyang Chen
arXiv:2606. 04023v1 Announce Type: cross Abstract: While large language models (LLMs) have been extensively evaluated on code generation tasks for general-purpose programming and GPU-accelerated environments (e.
By Jie Li, Wenzhao Wu, Junqi Hu, Qinrui Zheng, Bowen Wu, Juepeng Zheng, Yutong Lu, Haohuan Fu
HoliBench is a modular benchmarking and deployment toolkit that jointly measures accuracy, latency, and energy for foundation models across a wide range of devices, from single-board computers to GPU servers. It provides a platform abstraction layer that calibrates cross-device measurements and supports multiple model modalities, inference engines, and quantization levels. Using HoliBench, the authors evaluated 20 models on 7 device types, revealing tradeoffs such as limited latency gains from quantization on low‑precision hardware and diminishing accuracy returns relative to energy consumption, while also showing that single-model profiles can predict multi-model pipeline performance within a few percent.
By Inesh Chakrabarti, Zejun Xiong, Pragya Sharma, Mani Srivastava
The paper introduces AutoProfiler, a feedback-driven framework that learns a deterministic profiling tree for GPU kernel optimization. By iteratively refining the tree with REWRITE and SPLIT operations guided by an LLM and empirical evaluation, it selects the most useful profiling metrics for each kernel rather than relying on a fixed set. Experiments on KernelBench demonstrate that this adaptive profiling approach outperforms static configurations under limited profiling budgets.
By Yihan Wang, Peiyu Liu, Runyu Chen, Wei Xu
arXiv:2606. 20373v1 Announce Type: cross Abstract: Large Language Models (LLMs) show promise for code compilation tasks, but applying them to runtime performance tuning is difficult due to complex microarchitectural effects and noisy runtime measurements.
By Zepeng Li, Jie Ren, Zhanyong Tang, Jie Zheng, Zheng Wang