University of Illinois streams its Parallel@Illinois seminars

Expanding on its role as CUDA Center of Excellence, University of Illinois in Urbana-Champaign is launching a 13-week seminar with focus on parallel computing. Well, GPU Computing, that is. Parallel@Illinois is the name for the whole project of GPU Computing, and this seminar was organized by prof. Sanjaj J. Patel and Wen-mei Hwu. Under a not-so-scientific moniker Need For Speed Seminar Series, this 13-week course will feature domestic alumni such as Mark Hasegawa-Johnson, Dan Roth, Narendra Ahuja, Stephen Boppart, John C. Hart, Tom Huang and Seth Hutchinson, and guests such as Keith Thulborn (UI Chicago),  Sam Blackman (Elemental), Nikola Bozinovic (MotionDSP), Mark Johns (Tapulous) and


3D, AMD, Companies, Graphics, Hardware, Intel, Software Programs

Badaboom’s CPU utilization issue explained

After the first look here, I managed to again speak with Sam and Mike of Elemental fame, who got back to me regarding my comments on high CPU utilization. I’ve experienced close to 100% load on AMD’s dual-core processor, while AMD’s quad-core worked normally. According to Elemental, CPU utilization can be high on a dual-core processor if you do low-resolution transcodes (which is kinda the natural purpose of this application). This is a natural latency between the CPU and the GPU that happens during moving frames between the GPU video memory and the CPU and its (system) memory. Guys haven’t experienced this on Intel platform,