ROCm

Winsage
October 15, 2026
Nvidia's CEO Jensen Huang introduced the RTX Spark platform at Computex 2026, which integrates the GB10 Superchip with a specialized version of Windows on Arm for local AI execution. Nvidia collaborates with Microsoft, Dell, HP, MSI, Lenovo, and Asus to create PCs that function as autonomous companions. The platform's local AI performance is assessed using a new benchmark called AgentPerf-local, focusing on completion time for AI tasks. The RTX Spark-powered Surface Laptop Ultra has shown good performance, though it comes with a high price of ,899 for 1TB of storage. The platform faces challenges due to rising DRAM and NAND prices and is still in development, with full software infrastructure yet to be established.
Winsage
July 27, 2026
The FreeBSD project released its Q2-2026 status report, highlighting several advancements, including the introduction of an AMD ROCm port and the development of a new NTSYNC driver. Enhancements for desktop and laptop users included porting the latest graphics driver code, transferring WiFi driver code from Linux, improving suspend and resume functionalities, enhancing support for the Framework Laptop, implementing suspend-to-disk capabilities, and refining the audio stack. An intern from the FreeBSD Foundation worked on porting AMD ROCm, and the NTSYNC driver is designed to be compatible with the Linux 7.0 interface. The unified system management platform, Sylve, received new features, and improvements were made in the scheduler, IPv6 support, and various software updates.
Winsage
March 8, 2025
AMD is working to expand its ROCm software stack support from Linux to Windows, with confirmation from Vice President of AI Software, Anush Elangovan, that the company is looking to broaden support for additional GPUs on Windows. Currently, ROCm support on Windows is limited to select AMD Instinct GPUs and a few Radeon GPUs, including the RX 7900 XT and XTX, leaving many users with newer RX 9000 series GPUs unsupported. The latest version for Windows is 6.2.4, but users have reported issues such as crashes and driver timeouts. AMD's potential support for RDNA 4 GPUs could benefit deep-learning tasks for Windows users. Additionally, tinygrad will receive two MI300X boxes from AMD to enhance its AI solutions.
Search