Jekyll2026-11-07T19:00:28+00:00https://prashantnair.bitbucket.io/feed.xmlPrashant Nair | NewsPrashant J. Nair is an Associate Professor at the University of British Columbia (UBC), leading the Systems and Architectures (STAR) Lab. Welcome, James Chuang and Madhur Kumar2026-10-30T00:00:00+00:002026-10-30T00:00:00+00:00https://prashantnair.bitbucket.io/news/welcome-james-chuang-madhur-kumarTwo new Ph.D. students joined the STAR Lab in 2026:

  • James Chuang, a UBC Four-Year Fellowship holder, works on secure microarchitecture and architectural techniques for AI and next-generation workloads.
  • Madhur Kumar works on efficient compilation and architectures for the quantum computing stack.
]]>Junsu Kim wins the J.K. Zee Fellowship2026-10-30T00:00:00+00:002026-10-30T00:00:00+00:00https://prashantnair.bitbucket.io/news/junsu-kim-jk-zee-fellowshipCongratulations to Junsu Kim, who received the J.K. Zee Fellowship at UBC in October 2026. Junsu works on accelerating generative inference systems.

]]>ASPLOS 2027 acceptance: MagicFlow2026-10-29T00:00:00+00:002026-10-29T00:00:00+00:00https://prashantnair.bitbucket.io/news/asplos-2027-magicflowOur paper has been accepted to the ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS 2027).

Paper

  • MagicFlow: Breaking the Magic State Bottleneck for Scalable Fault-Tolerant Quantum Computing
    Meng Wang, Prashant J. Nair
]]>Keynote at the IBM AI Compute Symposium2026-10-28T00:00:00+00:002026-10-28T00:00:00+00:00https://prashantnair.bitbucket.io/news/ibm-ai-compute-symposium-keynoteI gave a keynote at the IBM IEEE CAS/EDS AI Compute Symposium at the IBM T. J. Watson Research Center: Scaling the Memory Wall: Towards 3D-DRAM-Based Accelerators for Efficient Generative Inference. I also joined the panel on Optimizing AI workloads across the stack.

Slides (PDF) · Event page

]]>Keynote at SACMAT 20262026-07-10T00:00:00+00:002026-07-10T00:00:00+00:00https://prashantnair.bitbucket.io/news/sacmat-2026-keynoteI gave the third keynote at the 31st ACM Symposium on Access Control Models and Technologies (SACMAT 2026) in Waterloo: The Memory Substrate of Tomorrow: Resilient DRAM for Secure and Intelligent Computing.

Slides (PDF)

]]>On Techquickie: Why PC Memory is Stuck in 19952026-07-09T00:00:00+00:002026-07-09T00:00:00+00:00https://prashantnair.bitbucket.io/news/techquickie-unified-memoryTechquickie and the Linus Media Group team interviewed me for Why PC Memory is Stuck in 1995 (Unified Memory Explained). The video looks at why PCs still keep CPU and GPU memory separate, and what a unified memory architecture would change.

Why PC Memory is Stuck in 1995 (Unified Memory Explained) Techquickie, Linus Media Group · July 9, 2026
]]>Service: General Co-Chair of ISCA 20272026-06-30T00:00:00+00:002026-06-30T00:00:00+00:00https://prashantnair.bitbucket.io/news/isca-2027-general-co-chairI am serving as General Co-Chair of the International Symposium on Computer Architecture (ISCA 2027).

]]>ISCA 2026 Distinguished Artifact Award2026-06-25T00:00:00+00:002026-06-25T00:00:00+00:00https://prashantnair.bitbucket.io/news/isca-2026-distinguished-artifactThe artifact for our ISCA 2026 paper “Transpiler-Architecture Co-Design to Curb Clifford Costs in Fault-Tolerant Quantum Computing”, led by my Ph.D. student Meng Wang, received one of the two Distinguished Artifact Awards at ISCA 2026. The award recognizes open-source research software that meets the highest standards of reproducibility, reusability, and engineering quality.

]]>ISCA 2026: Three papers, including the first silicon results for Raptor2026-06-20T00:00:00+00:002026-06-20T00:00:00+00:00https://prashantnair.bitbucket.io/news/isca-2026-three-papersWe presented three papers at the 53rd ACM/IEEE International Symposium on Computer Architecture (ISCA 2026) in Raleigh, NC.

Papers

  • Early Silicon of Raptor: The First 3D-DRAM Accelerator for Generative Inference
    Prashant J. Nair, Ramyad Hadidi, Subramani Ganesh, Sangamesh Kodge, Shubhankit Rathore, Neil Thanawala, Nikitha Reddy, Gyanesh Saharia, Vinayak Patankar, Arun Tiruvur, Nithesh Kurella, Sudeep Bhoja Talk slides (PDF) · How 3D-DRAM works
  • Transpiler-Architecture Co-Design to Curb Clifford Costs in Fault-Tolerant Quantum Computing
    Meng Wang, Chenxu Liu, Samuel Stein, Yufei Ding, Poulami Das, Prashant J. Nair, Ang Li
    Distinguished Artifact Award
  • Loaded Dice: Solving the Non-Selection Problem for Scalable Probabilistic RowHammer Defense
    Jeonghyun Woo, Junsu Kim, Aamer Jaleel, Prashant J. Nair
]]>Recorded talk at ETH Zürich: Scaling the Memory Wall2026-04-30T00:00:00+00:002026-04-30T00:00:00+00:00https://prashantnair.bitbucket.io/news/eth-zurich-safari-seminarI gave a SAFARI Live Seminar at ETH Zürich on Scaling the Memory Wall: Towards 3D-DRAM-Based Accelerators for Efficient Generative Inference. The recording is below; the talk starts at 2:59.

Scaling the Memory Wall: Towards 3D-DRAM-Based Accelerators for Efficient Generative Inference SAFARI Live Seminar, ETH Zürich · April 30, 2026
]]>