Please turn JavaScript on

hgpu

Want to stay in touch with the latest updates from Hgpu? That's easy! Just subscribe clicking the Follow button below, choose topics or keywords for filtering if you want to, and we send the news to your inbox, to your phone via push notifications or we put them on your personal page here on Specificfeeds.

Reading your RSS feed has never been easier!

Website title: High performance computing on graphics processing units | hgpu.org

Is this your feed? Claim it!

Publisher:  Unclaimed!
Message frequency:  0.64 / day

Message History

As deep learning (DL) models become increasingly complex and hardware architectures grow more heterogeneous, DL compilers play a critical role in optimizing computational efficiency and enabling scalable deployment. This paper presents a systematic analysis of DL compilers, covering their architectural evolution, compilation workflows, optimization techniques, and emerging re...


Read full story

Low latency is critical to user experience. As NVIDIA Blackwell and Rubin GPUs advance multi-die scaling, data placement and cross-die communication become increasingly important. However, the latency implications and underlying costs of cross-die communication and die-aware execution remain largely unexplored. In this report, we present a comprehensive evaluation of the Loca...


Read full story

Each new GPU generation is showcased by its peak instruction rates, yet users hardly ever run instructions directly: they reach the hardware's performance through vendor libraries, applications and devices shared with other jobs. How much of a theoretical speedup survives these layers is rarely measured, so a team deciding whether to move to a new generation, or to adopt FP8 ...


Read full story

High-resolution atmospheric modeling frameworks encounter severe memory bottlenecks when evaluating non-linear subgrid turbulence closures across global meshes (such as ERA5 with 103.8 million 3D points). Standard deep learning frameworks (PyTorch Eager) dispatch multiple disjoint kernels, causing effective throughput to drop below 50 GB/s. We present a register-fused, matrix...


Read full story

Large Language Models (LLMs) have shown strong capabilities in code generation and reasoning, motivating extensive benchmarks for evaluating functional correctness. However, performance optimization in High-Performance Computing (HPC) poses fundamentally different challenges that are not captured by existing evaluations: HPC performance depends on low-level code, intricate me...


Read full story