❌

Vue normale

Intel & AMD Now Collaborating On Software Optimizations With PyTorch/oneDNN

20 octobre 2026 à 16:50
Intel has long worked on tuning their oneDNN neural network library for their hardware and saw its adoption by PyTorch and other AI frameworks. AMD has maintained ZenDNN as their downstream fork that is oneDNN API compatible while catering to their Zen processor designs. As an interesting twist, AMD and Intel jointly announced today they will be collaborating around oneDNN for PyTorch and pushing the AMD Zen improvements into oneDNN...

Intel Core Ultra 9 Arrow Lake On Star Labs StarFighter Shows Nice Gains On Ubuntu 26.10

20 octobre 2026 à 14:25
For those running a Star Labs StarFighter Ultra or other Intel Core Ultra Arrow Lake laptop, the recent Ubuntu 26.10 release is providing some nice performance gains over the Ubuntu 26.04 LTS release. Here is a look at how Ubuntu 26.04 LTS vs. Ubuntu 26.10 performs with the Intel Core Ultra 9 285H over dozens of different benchmarks.

Linux Coredumps Via Sockets Can Be Much Smaller Now With Sparse Support

20 octobre 2026 à 13:11
Added to the Linux kernel last year was Coredump support via Unix domain sockets as an alternative to the pipe-based Coredumps. With code now merged for Linux 7.4, the core dumps via sockets has the potential of being much smaller thanks to sparse support. In extreme cases they can be 1% of the size without sparse support...

Linux 7.4 Adding New Emulation Function While Some Old CPUs May Soon Be Phased Out

20 octobre 2026 à 10:32
Linux 7.4 is seeing a new emulation function added for cmpxchg() for compare and exchange. This is being done so that two-byte cmpxchg() can be used in common Linux kernel code that is already natively supported on newer CPU architectures. The pull request notes though that some old systems might no longer be supported by the Linux kernel moving ahead...

Linus Torvalds' AI Code Improved: Huge Performance Wins With Reworked Code

19 octobre 2026 à 16:32
Last week I wrote about Linus Torvalds leveraging AI to come up with a hefty Linux kernel improvement using Claude Code. The code is for reading from the page cache without folio references to help workloads of small reads from a single file across many CPU threads. Meta engineer Kiryl Shutsemau has taken that code and reworked it and showing extremely promising performance results...
❌