20 results for βkernel performanceβ
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.β
Want pure semantic search? Try claim verification β
Jiasheng Zhou, Longbin Zeng, Clavis Chen, Ruiming Lu +4 more
ARGUS is a low-overhead, fine-grained, always-on tracing and real-time analysis system for training workloads in large production clusters.
Supun Kuruppu, Pranav Dangi, Wei Li, Zhenyu Bai +1 more
This paper improves kernel performance on GPUs by accounting for physical non-idealities in hardware resources.
This paper analyzes data access patterns in large language model workloads on multi-partition GPUs and presents optimization strategies based on inter-workgroup sharing patterns.
This paper demonstrates that Large Language Models (LLMs) can serve as accurate and selective surrogates for costly GPU kernel performance measurements, significantly expanding the search space for opβ¦
Zhiwen Mo, Yu Cheng, Lei Wang, Zhengju Tang +11 more
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 acrossβ¦
Haozhe Wang, Lina Chen, Fanqi Wan, Qi Han +4 more
This paper presents Metal Sandbox, a system for efficient on-device inference on macOS that combines restricted file access, native command execution, and command-level scheduling.
Nhat Minh Le, Yisen Xu, Zhijie Wang, Tse-Hsun +1 more
This paper evaluates the performance of large language models on popular benchmarks and finds that only a small percentage of the performant implementations are significantly faster than canonical solβ¦
This paper studies software aging in GPU-based LLM serving systems using a 216-hour campaign.
Shushu Yi, Wenbo Wu, Guoci Chen, Junrong Zhu +5 more
GNStor is a GPU-native AFA system that enables direct GPU access to remote AFA without CPU intervention.
Rania Zitouni, Nadine Bousdjira, Sarah Hasnaoui, Amel Sadoun +1 more
This paper compares and optimizes CUDA strategies for a shallow neural network, achieving a 1.41x speedup on a large dataset.
The paper introduces Rotary GPU, an exploratory execution approach demonstrating that large Mixture-of-Experts models can be run locally on consumer GPUs with limited VRAM, achieving usable decode thrβ¦
Keisuke Kamahori, Neil Adit, Kan Zhu, Yuqi Mai +12 more
A new hardware-software interface for data prefetching is proposed to reduce useless prefetches in datacenter workloads by 40%.
Jihu Guo, Sitian Lu, Tenghui Ma, Wei Gao +3 more
This paper presents SpecGen, a system that optimizes GPU kernel tuning by leveraging speculative generation and dynamic resource allocation.
This paper presents EmuGEMM, a set of fused integer Tensor Core kernels for NVIDIA GPUs that improve the performance of high-precision matrix multiplication.
This paper implements and evaluates Whisper dot-product kernel offloading on a programmable Coarse-Grained Linear Arrays (CGLAs) architecture to reduce power consumption.
This paper presents a framework called MEERKAT to mitigate inefficiencies in heterogeneous systems-on-chip by migrating Linux OS support from software to hardware.