Subnormal floating-point numbers are expensive on Intel processors(lemire.me)

53 points by zdw 1 month ago | 41 comments

Prefix sums at gigabytes per second with ARM NEON(lemire.me)

55 points by mfiguiere 7 months ago | 8 comments

Ephemeral Testing(lemire.me)

71 points by ibobev 20 days ago | 25 comments

A blog post by Daniel Lemire on his blog titled "Ephemeral testing," a short essay about a software testing approach.

How fast can browsers process base64 data?(lemire.me)

35 points by mfiguiere 11 months ago | 20 comments

How much do amd64 microarchitecture levels help in Go?(lemire.me)

61 points by zdw 4 months ago | 39 comments

We see something that works, and then we understand it(lemire.me)

198 points by surprisetalk 5 months ago | 77 comments

AMD outsells Intel in the datacenter space(tomshardware.com)

426 points by baal80spam 1 year ago | 140 comments

Tom's Hardware news article reporting that AMD's datacenter sales surpassed Intel's for the first time, though both trail Nvidia's AI GPU sales.

AMD Ryzen AI Halo – $4k AI Dev Kit(lttlabs.com)

370 points by LabsLucas 3 months ago | 244 comments

LTT Labs article reviewing the AMD Ryzen AI Halo, a roughly $4,000 AI developer kit mini PC.

Ollama now supports AMD graphics cards(ollama.com)

578 points by tosh 2 years ago | 194 comments

Ollama blog post from March 14, 2024 announcing preview support for running models on AMD graphics cards.

Arm AGI CPU(newsroom.arm.com)

405 points by RealityVoid 7 months ago | 290 comments

Arm newsroom blog post announcing the Arm AGI CPU, a data center processor aimed at rack-level AI infrastructure for agentic AI cloud workloads.

Zenbleed(lock.cmpxchg8b.com)

1160 points by loeg 3 years ago | 327 comments

Tavis Ormandy's writeup of Zenbleed, an AMD Zen 2 CPU vulnerability that leaks data from vector registers, covering exploitation, discovery, and mitigation.

We were wrong about GPUs(fly.io)

834 points by mxstbr 1 year ago | 529 comments

Fly.io blog post reflecting on how the company's bet on offering GPU machines to developers did not pan out as expected.