
Assistant Professor @UBC improving cloud computing systems. @UBC_CIRRUS_Lab
Vancouver, BC
Joined March 2016
- Tweets864
- Following605
- Followers1.7K
- Likes9.3K
Mohammad Shahrad retweeted
New #serverless traces just released: github.com/ubc-cirrus-lab/ib…
- 1.9B+ invocations over two months
- Characterizing an open-source platform (Knative) in production
📄 Accompanying paper to appear at ACM EuroSys ’26 in April.
Mohammad Shahrad retweeted
I wrote a short post on some etiquette for a seemingly mundane task: declining an offer (for a job, internship, grad school, etc). Link in next tweet. 1/2
It's exciting to witness the evolution of serverless! What was just running simple code a few years ago (FaaS), is now a lot broader. The addition of GPUs to serverless infrastructure over the past year or two makes a lot of sense and has enabled more diverse applications.
🎉 @nvidia GPU support for Cloud Run is now generally available!
Now, you can enjoy the following benefits across both GPUs and CPUs:
- Pay-per-second billing
- Scale to zero
- Rapid startup and scaling
- Full streaming support
Learn more ↓ goo.gle/43Iw6pI
Mohammad Shahrad retweeted
RT appreciated! We're assembling the Artifact Evaluation Committee (AEC) for @usenix OSDI+ATC 2025.
JOIN US!
It'll be fun, useful (help understand research artifacts of accepted papers), with a manageable load (1-2 papers per AEC member based on research interests).
We are seeking members to join the Artifact Evaluation Committee for #OSDI25 & #USENIXATC25.
Help promote reproducibility, and engage with cutting-edge systems research!
Please apply by April 17th via forms.gle/187NkvkWyNtBHDsu5.
#SystemsResearch #Reproducibility #OSDI #ATC
Many in my field have migrated to other platforms, including Bluesky, for good reasons. While I'll continue limited use of X for now, I'm also joining Bluesky to better connect with my community. If you're there, let's reconnect: bsky.app/profile/mshahrad.bs…
Thanks dear reviewer for:
- praising our paper
- saying "this is a strong paper"
- providing no weakness except for small font sizes in some figures
... then giving an overall merit of "weak" accept (3/5)!!! 😑
IMHO, lukewarm reviews are worse than well-founded negatives.
Mohammad Shahrad retweeted
I'm on the faculty market and at #NeurIPS!👩🏫
homes.cs.washington.edu/~nil…
I work on privacy, memorization, and emerging challenges in data use for AI.
Privacy isn't about PII removal but about controlling the flow of information contextually, & LLMs are still really bad at this!
Mohammad Shahrad retweeted
Don’t choose PhD programs by rankings—they may not be a good fit for you (& everyone applies there!)
Instead, focus on potential advisors. How to find them?
1. Pick your top 20-40 favorite papers
2. Find the authors in academic positions
3. Apply to their schools
Good luck!🍀
This year, @ACMSoCC had a record high submitted and accepted paper count. Great job to PC chairs, @NeerajaJY and Peter Alvaro, and the entire PC for the hard work.
SoCC'24 is underway, with our PC Chairs (@NeerajaJY and Peter Alvaro) kicking things off! We are so excited to learn from all our speakers and authors this week!
Mohammad Shahrad retweeted
Replying to @ASPLOSConf
@ASPLOSConf Steering Committee solicits community input on the multi-deadline review model first implemented in 2023. As our community continues to grow, we seek guidance on how to scale conference review.
Please read the @sigarch blog post for more info: sigarch.org/evaluating-the-n…
Mohammad Shahrad retweeted
SoCC'24 promises to be great. It will be held at the Microsoft campus in Redmond, *Nov 20-22*, and has an amazing program with 63 papers (most ever!), single track over 3 days. Did I mention it is also the cheapest ever? $150 registration for students! Hope to see you there!
Hey folks, the SoCC’24 program is out! Thanks to the hard work of our PC chairs (@NeerajaJY and Peter Alvaro) and PC members, we have an exciting program this year! Congratulations to all the authors, we look forward to learning more about your work at the conference!
Now that things have settled, I can share more. This system (Caribou) pushes the boundaries of geospatial shifting for cloud systems for greenhouse gas reduction. 💚🌎
Paper available here: cirrus.ece.ubc.ca/papers/sos…
And the system is open sourced: github.com/ubc-cirrus-lab/ca…
Proud of Arshia (@amoghimi98). He led building a serverless autoconfiguration tool (Parrotfish, SoCC '23, github.com/ubc-cirrus-lab/pa…), and significantly contributed to a serverless compliance tool (IEEE S&P '25). He was also with @CICUBC doing notable work with @awscloud on campus.
Congrats to Arshia Moghimi (@amoghimi98) for successfully defending his MASC thesis yesterday! His thesis focused on building tools to automate resource and security configuration of serverless applications. Arshia was advised by @MShahrad and @aasthakm.
Mohammad Shahrad retweeted
IISWC 2024 is at the Robert H. Lee Alumni Centre, UBC Vancouver, 15-17 Sept. Learn from experts on workload characterization and its role in future tech. Register here: bit.ly/4g9XjY3
#IISWC2024 #TechInnovation #Computing #Networking
The tentative program for the 2024 IEEE International Symposium on Workload Characterization (IISWC) is out: iiswc.org/iiswc2024/program.…
Excited to welcome you all to UBC soon (Sep 15-17).
Remember to register by the 8/31 early deadline: iiswc.org/iiswc2024/reg.html
So proud of my team for an accepted SOSP paper. Special thanks to our champion reviewer, and those two open-minded reviewers who increased their grade post rebuttal. (contrary to popular belief, rebuttal is not always futile.)
Mohammad Shahrad retweeted
Join the artifact evaluation committee for IISWC'24! Experiencing the AE process behind the scenes is very valuable for your own submissions!
The review period is July 24 - Aug 6.
Interested? Email Sagar: [email protected]
Indeed, a great program with an exciting lineup of papers!
My lab's first sustainability paper is here too, and we have multiple ongoing sustainability projects. Cannot wait to learn from others active in the sustainable computing area and share ideas.
This Post is from an account that no longer exists. Learn more
I often wish systems papers had titles like biology papers: clear, descriptive sentences that highlight the core novelty. It's frustrating when a paper title has broad promises (e.g., sustainable cloud systems) but turns out to focus on a specific service when you get to page 3.
Mohammad Shahrad retweeted
I will be giving a talk on Wednesday, June 19 at #woscx on our tool "Parrotfish: An Advanced Multi-Objective Serverless Rightsizing Tool". Join me to discover how Parrotfish can optimize your serverless functions! 🐠
🔗 Program: serverlesscomputing.org/wosc…
🎟️ Registration is FREE!






















