flâneur

Your RAM Has a 60 Year Old Design Flaw. I Bypassed It. - YouTube

youtube.com · 9,663 words · saved by 1 readers

Explore how hidden, periodic freezes in computer memory impact performance. Discover techniques to measure these tiny disruptions and learn to engineer solutions that bypass them for faster data access. Follow along using the transcript. Explore how hidden, periodic freezes in computer memory impact performance. Discover techniques to measure these tiny disruptions and learn to engineer solutions that bypass them for faster data access. Follow along using the transcript.

Modern DRAM is based on a brilliant design from IBM. But, we're still paying for a latency penalty that's existed since the 60s! In this video, I'm introducing my personal research project (Tailslayer) that immensely reduces p99.99 latency on traditional RAM! By implementing a hedged read strategy taking advantage of (undocumented!) channel scrambling offsets, I've gotten as much as 15x reductions in tail latency. The technique works across Intel, AMD, Graviton, DDR4, DDR5, x86, ARM, you name it. Check out the C++ lib I wrote, watch the video, and try it yourself! --- Timestamps:…

saved by

related reading