A page on LabLog, a review site (not the lab's official page)
Reconfigurable Systems Lab
Machine-translated · View original
The lab builds computers that run AI fast on reconfigurable LSIs such as FPGAs.

AboutAbout the lab
Speeding up AI computation with reconfigurable LSIs.
The Reconfigurable Systems Lab, at the Center for Unprecedented-Scale Data Analytics, researches and develops computer systems based on new reconfigurable LSIs.
In particular, the lab studies how to implement and apply AI on FPGAs (Field Programmable Gate Arrays), as well as high-performance computing with FPGAs.
The lab has joint research projects with many companies, and students can gain experience developing with the latest FPGAs.
The lab not only publishes its research results in papers but also works to put them to use in business through a Tohoku University startup.
Key terms
- FPGA
- An LSI whose circuit configuration the user can rewrite after manufacturing.
- Accelerator
- A dedicated circuit or device built to perform a specific kind of processing quickly.
- Deep learning
- A type of AI method that learns features of data using multi-layer neural networks.
- Moore's Law
- The empirical observation that the integration density of circuits on semiconductor chips doubles at regular intervals.
ResearchResearch themes
The lab studies reconfigurable systems, which are built on reconfigurable LSIs. Its main focus is how to implement and apply AI on FPGAs, and high-performance computing with FPGAs.
*Illustrative imageCircuits that run deep learning fast
The lab researches and develops methods for implementing AI accelerators on FPGAs to process deep learning at high speed. It has been a pioneer in producing results on lightweight AI models and dedicated hardware.
*Illustrative imageResearch and development of FPGAs with new architectures
As the end of Moore's Law is debated, it is predicted that progress in conventional FPGAs will come to an end. The lab researches and develops LSIs with new architectures such as Versal ACAP, and this includes work on open-source EDA (OpenEDA) tools such as OpenLANE.
*Illustrative imageHigh-performance computing with FPGAs
Data centers such as those in the cloud need to speed up computation, and opportunities to use programmable FPGAs are increasing. The lab studies training accelerators that speed up deep learning training, and cluster configurations built from them.
*Illustrative imageEfficient LSIs using multi-valued representation
Almost all VLSIs are designed with binary representation, but using multi-valued representation may make more efficient VLSIs possible. This is theoretical research with a lot of mathematical content, and it also covers deep learning using multi-valued logic and its implementation in hardware.
MembersFaculty
The members of the Reconfigurable Systems Lab are faculty, doctoral and master's students, and administrative assistants.As of 2024
- ProfessorHiroki Nakahara
VoicesStudent voices
Ratings and reviews reflect the experiences of individual current or former students, not the lab's official views. Whether a lab has reviews, or how many, says nothing about the lab itself.
Students who take part in an interview may receive a thank-you gift worth ¥1,000, regardless of what they say.
Student ratings (0 students)
--
--
--
--
--
--
Student voices answer questions like these
- What's great about this lab?
- What did you learn after joining?
- What's the vibe, and what is the professor like?
- Who is this lab for?
- Where do graduates go?
Your experience can help younger students choose their lab. Your name won't be shown.
Write a lab reviewAnonymous · Your draft is saved if you stopRelatedLabs similar to Reconfigurable Systems Lab
Intelligent Integrated Systems LabGraduate School of Information Sciences, Department of Computer and Mathematical SciencesHuman-friendly intelligent supercomputing; intelligent syste…
Communication Theory LabGraduate School of Information Sciences, Department of Computer and Mathematical SciencesInformation network architecture supporting the IoT society …Advanced Computing Systems Theory Lab (RIKEN)Graduate School of Information Sciences, Department of Computer and Mathematical SciencesAdvanced computing systems integrating HPC, AI, and quantum …
Wireless Networks LabGraduate School of Information Sciences, Department of Computer and Mathematical SciencesConnected spaces make society smarter; keywords: next-genera…The information on this page is compiled by the LabLog team from the lab's public information and interviews. For corrections or removal requests, please contact LabLog, not the lab.
Report an errorAbout the images
The top and research theme images are illustrative and were not taken at the lab. They are cropped from Wikimedia Commons images. Cropped CC BY-SA images are provided under the same CC BY-SA license as the original (version shown on each line).
- Top image: “TEI0001 Altera MAX 10 FPGA MAX1000 IoT Maker Board” Antti Lukats / CC0 (cropped)
- Circuits that run deep learning fast: “DARPA SyNAPSE 16 Chip Board” DARPA SyNAPSE / Public domain (cropped)
- Research and development of FPGAs with new architectures: “Plessey Semiconductor (Ferranti) ULA 2C200J Die Photograph” Revaldinho / CC BY 4.0 (cropped)
- High-performance computing with FPGAs: “Dutch national supercomputer "Huygens"” Dennis van Zuijlekom / CC BY-SA 2.0 (cropped)
- Efficient LSIs using multi-valued representation: “74LS08 AND Gate DIL Chip” RetroEditor / CC BY 4.0 (cropped)
- Related lab (知能集積システム学): “TEI0001 Altera MAX 10 FPGA MAX1000 IoT Maker Board top view” Antti Lukats / CC0 (cropped)
- Related lab (コミュニケーション論): “Google's First Production Server (1999) detail of networking - Computer History Museum ( by Carlo Nardone)” Carlo Nardone from Roma, Italy / CC BY-SA 2.0 (cropped)
- Related lab (ワイヤレスネットワーク学): “RouterBoard R52 miniPCI Wi-Fi card with U.FL-RSMA pigtail” Kozuch / CC BY-SA 4.0 (cropped)
About LabLog
LabLog is a lab review app for students only. Student members at each university interview students in labs and publish what they say. Student voices can only be read by students who sign up with a university email address. Operated by bestiee Inc.
Learn more about LabLog ↗Search engines and AI may reference the basic lab info and rating summaries on this page and the description of LabLog. Student voices are for student members only. Automated collection by programs (scraping, or input to or training of AI) is prohibited under Article 8 of the Terms of Service. If you need data for research or analysis, please contact us.