🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Excited to announce that this work ended up getting both a distinguished paper and artifact award at ASPLOS! Looking forward to working on all the interesting research the techniques in this paper unlock.

Congrats to Reese Levine, Tim Guo, Mingun Cho, Alan Baker, Raph Levien, David Neto @[email protected], @AndrewRQuinn&@Tyler_UCSC, whose paper "MC Mutants: Evaluating and Improving Testing for Memory Consistency Specifications" received a Distinguished Paper Award ASPLOS '23. ...

Come see the presentation of our paper, GPUHarbor, at ISSTA Conference’s test optimizations session soon and see why it was awarded a distinguished artifact. Congrats to all my co-authors! Paper: dl.acm.org/doi/abs/10.114…

Some GPU humor from our group meeting today: Your warps when your code has uniform control flow: youtu.be/z0n6P5UJGxU?t=… Your warps when your code diverges: youtu.be/95Ds85ru77o?t=7

The fact that it was even necessary for a judge to decide this is sickening

According to Reese Levine at the FOWM workshop POPL 2026, memory models are just half of the problem. We need to start taking a closer look to forward progress models

IMHO, one of the most meaningful things AI developer tools can do, is help engineers use accelerators (GPU, TPU) more effectively – and flag when hardware is being underutilized so many companies are plagued with compute inefficiencies, and just leaving performance on the table

Just noticed the new sections on memory ordering/synchronization in MSL 3.2 (section 6.15 of developer.apple.com/metal/Metal-Sh…) Finally adding some useful primitives that open up the potential for a lot of interesting GPU compute algorithms on Apple silicon!

We’re looking for speakers for the upcoming year, spots are open for this fall quarter and beyond!

I can finally remove from my bucket list having Tyler Sorensen and Reese Levine as co-authors :D GPU Memory Consistency: Specifications, Testing, and Opportunities for Performance Tooling sigarch.org/gpu-memory-con…