Language Selection

English French German Italian Portuguese Spanish

Speeding Up The Linux Kernel With Your GPU

Filed under
Linux
Hardware

Sponsored in part by NVIDIA, at the University of Utah they are exploring speeding up the Linux kernel by using GPU acceleration. Rather than just allowing user-space applications to utilize the immense power offered by modern graphics processors, they are looking to speed up parts of the Linux kernel by running it directly on the GPU.

From the project page: "The idea behind KGPU is to treat the GPU as a computing co-processor for the operating system, enabling data-parallel computation inside the Linux kernel. This allows us to use SIMD (or SIMT in CUDA) style code to accelerate Linux kernel functionality, and to bring new functionality formerly considered too compute intensive into the kernel. Simply put, KGPU enables vector computing for the kernel."

Additionally, "it makes the Linux kernel really parallelized: it is not only processing multiple requests concurrently, but can also partition a single large requested computation into tiles and spread them across the large number of cores on a GPU."

rest here




More in Tux Machines

Forget Google's robot cars, now it's on to ANDROID cars

Google is planning a big push into in-car infotainment systems with an upcoming version of Android, sources claim. "Android M" – the version to come after the current Android 5.0 "Lollipop" – will be available in a formulation designed specifically to run cars' built-in screens, Reuters reports, citing anonymous insiders with knowledge of the plan. Google made its first advances toward the automotive world at its I/O developer conference earlier this year, when it unveiled its Android Auto software. The first Android Auto–compatible cars are expected to arrive early next year. Read more

today's howtos