It was really fun doing this work over the summer at ToB! A huge thanks for all of their support and everyone who engaged with us over the last few months. It's an exciting time for GPUs, and I hope that security and privacy can start to be a bigger focus!

The deadline for CGO's SRC has been extended to Dec. 15! It will be in Australia, so it would be awesome to go, but there's a virtual track, because travel can be tough these days. It's a great way to get some feedback and meet other compiler folks! https://t.co/QtPXkTtMFc

Excited to be included on @TIME's list of the TIME100 AI of 2025! Grateful to the @AINowInstitute for supporting my work on addressing the safety revisionism of AI in defense and safety-critical contexts where safety has been obscured with little to no accountability. #TIME100AI

This year's PLDI student research competition was also a success, with several interesting projects presented by graduate and undergraduate students! Here are the three winners for each category (undergraduate and graduate) ⬇️

Not sure who is still here, but check out this post about GPU memory models: including testing, specs, and a cool case study! Lots of great co-authors, especially @h_poncedeleon + team, who are doing some awesome work on GPU model checking. https://t.co/hIAzl7wRWM

I am looking to hire interns for fall with experience in Triton and familiarity with gpu architecture. If you are a PhD student with these skillsets please DM me, I will send further details. RTs are appreciated🙏

I am looking to recruit a PhD student (fully funded at UK home tuition rate) to work on automated testing and verification of machine learning compilers and runtimes! Deadline: 30th April. Please spread the word! Details here:

With Reshabh K Sharma, Peli de Halleux, and Shraddha Barke, we just released "PromptPex: Automatic Test Generation for Language Model Prompts"( https://t.co/h3RJ9YEGiT). Repo: https://t.co/tiCLgQBEAG. PromptPex is a tool to generate and evaluate unit tests for an AI model prompt.

Join us on February 25 for a new episode of Microsoft Research Forum where we share the latest updates on multimodal generative AI for precision health, advances in drug discovery and agents, & delve into cutting-edge AI techniques for programming safety. https://t.co/zHzyNPGpcF

We, RiSE/MSR, are hiring for exciting and ambitious projects. https://t.co/fKAc4ChNSx (on the picture: lunch with colleagues)

I am looking for 1-2 PhD students interested broadly in computer systems, compilers, and/or PL! If you would like to do your PhD in a vibrant city with great weather, next to the sea 🌊, and the mountains 🏔️, make sure to apply to UCLA and mark my name as a potential advisor!

Just in time for halloween! Check out the scary things that can happen w.r.t. memory consistency when you link two binaries that were compiled using different atomic memory mappings 😱😱😱😱😱 It was a really fun project to be a part of and Luke did a great job leading!

New paper with @sarahbmyers & @mer__edith. We challenge the narrative emphasising AI bioweapons risks, and bring attention to the covert proliferation of military intelligence, surveillance, targeting, and reconnaissance (ISTAR) already occurring via foundation models. 1/5

Excited to announce that I’m now Chief AI Scientist at @AINowInstitute! Looking forward to sharing some upcoming work soon.

This was a really fun project to be involved in! @LukeGeeson did a great job finding a problem that is technically very interesting (memory models 😱) and also has some immediate and big impact (a new ABI for Arm binaries). Check it out!

Woohoo! @Cornell_CS PhD application deadline is December 15, 2024. I'm looking for students interested in high-performance parallel computing and systems for scientific discovery, to guide the design of the next generation of parallel computing systems and architectures! RT

Tomorrow, @aypan_17 from @UCBerkeley will share with the @buZZrobot community about the WMDP Benchmark, a dataset designed to measure whether LLMs could help malicious actors develop bio, cyber, and chemical weapons, and the state-of-the-art unlearning method to reduce harmful

Excited to finally share that I just started as a visiting researcher at Microsoft Research in the RiSE group! Looking forward to working on PL problems at such an impactful company at such an interesting time in tech! And I always love hacking on GPUs :)

“Thinking time” is now a luxury, one we seldom have because we are burdened with service, unrealistic research expectations, among many other time-sinks. I do think the quality of our overall science is decreasing due to the pace at which we have to “produce” 😣

I’ll be presenting my ML security work (@trailofbits) at @BSidesLV and @defcon! If you’re interested in attacks against ML systems, come learn all about incubated ML exploits.

🎉Congratulations to our Computational & Data Science Fellowship recipients!🎉 Jessica Dagostini (PhD, Computer Science) from @ucsantacruz Amina Diop (PhD, Astronomy) from @UVA Well deserved and well earned!