aiqbench takeChips & Infra

This release marks a significant expansion of NVIDIA's CUDA ecosystem by bringing GPU-accelerated computing to Windows on Arm, previously restricted to Linux environments. The update introduces early developer support for the Rubin architecture and enhances shared GPU management through Multi-Process Service V3, enabling more precise resource partitioning. These developments broaden the hardware landscape for AI model training and inference while improving efficiency in unified memory handling.

Source coveringQuantum Zeitgeist

What this isA model's reading of the article and related coverage, written for aiqbench. Not the publisher's words.

NVIDIA extends CUDA toolkit to Windows on Arm systems

Quantum ZeitgeistSeptember 13, 20266 min read

CUDA Toolkit 13.4 adds support for Windows on Arm, extending CUDA application support—previously available on Arm platforms through Linux—to the Windows on Arm platform. The release also introduces greater control over shared GPUs, with early developer support for the NVIDIA Rubin GPU architecture and enhanced GPU management capabilities.

NVIDIA has extended the reach of its CUDA Toolkit to Windows on Arm systems, bringing GPU-accelerated computing to a new environment previously limited to Linux. CUDA Toolkit 13.4 adds functional support for the NVIDIA Rubin architecture (compute capability 107) as a preview, enabling developers to begin porting applications before CUDA support for Rubin reaches general availability in a future release of the CUDA Toolkit, the company says. The update introduces Multi-Process Service V3, providing developers with a scriptable command line interface and namespaces for “precise GPU partitioning, where compute performance, memory boundaries, and execution priority are defined programmatically,” according to NVIDIA documentation. CUDA 13.4 Support for Windows on Arm Systems Expanding the CUDA ecosystem, NVIDIA now supports application development on Windows on Arm…

Excerpt shown under the publisher's RSS terms · 123 words · full text and figures are on the publisher's site

Read at Quantum Zeitgeist ↗Ask about this article