LAB LOGA page on LabLog, a review site (not the lab's official page)
Endo Lab
Machine-translated · View original
The lab builds software that unlocks the full power of supercomputers.
AboutAbout the lab
Supercomputers, easier to use and faster
The Endo Lab studies software and algorithms for high-performance computing systems, including supercomputers.
Using supercomputers such as the on-campus TSUBAME4.0, the lab has recently also been working on scaling up and accelerating deep learning with GPUs.
Supercomputer designs keep changing year after year, with growing parallelism and increasingly complex memory hierarchies.
Software that makes these machines easier to use is in demand, and the lab carries out joint research with closely related labs as well as labs in other fields.
Key terms
- High-performance computing
- Using large computers such as supercomputers together to carry out large-scale calculations quickly
- GPU
- A processor originally built for image processing. It excels at performing large numbers of identical calculations side by side, and is also used for machine learning
- Memory hierarchy
- The way a computer organizes its memory by combining storage devices ranging from fast ones with small capacity to slow ones with large capacity
NewsLab news
View More ↗ResearchResearch themes
The lab studies software for supercomputers and high-performance computing systems. It aims to advance system software that bridges application domains, where theories and models are becoming more complex, and supercomputers, whose configurations are becoming more complex and larger in scale.
*Illustrative imageReducing supercomputer wait times
In collaboration with Fujitsu, the lab studies job scheduling technology aimed at greatly reducing, or even eliminating, the wait times caused by supercomputer congestion. The goal is high-performance computing that can be used interactively and in real time.
*Illustrative imageGoing beyond GPU memory limits
The lab developed HHRT, system software that lets parallel applications running on multiple GPUs run beyond the limited capacity of GPU memory. It makes the capacity of the entire memory hierarchy available, including main memory and flash SSDs.
*Illustrative imageBringing out the performance of GPU supercomputers
In 2008, the lab developed the first Linpack benchmark software for a GPU supercomputer, on TSUBAME1.2, and it appeared in the Top500 supercomputer ranking. This was joint research with the Matsuoka Lab and various vendors.
*Illustrative imageSupercomputers cooled by oil immersion
With TSUBAME-KFC, a supercomputer that uses oil-immersion cooling, the lab achieved the world's top energy efficiency in 2013. This too was a joint effort with the Matsuoka Lab and various vendors.
MembersFaculty
The members of the Endo Lab consist of faculty, administrative staff, technical support staff, and doctoral, master's, and undergraduate students.As of 2026
- ProfessorToshio EndoPublications ↗
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 Endo Lab
Takabe LabSchool of Computing, Department of Mathematical and Computing ScienceStatistical physics; information processing by machine learn…
Yamashita LabSchool of Computing, Department of Mathematical and Computing ScienceDeriving Optimal Solutions to Real-World Problems through Ma…
Miyoshi LabSchool of Computing, Department of Mathematical and Computing ScienceAnalysis of irregularity and uncertainty using probability
Fujisawa LabSchool of Computing, Department of Mathematical and Computing ScienceRealization of a super-smart society through AI and mathemat…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: “Amalka Supercomputing facility” Davidpodhola / CC BY-SA 3.0 (cropped)
- Reducing supercomputer wait times: “TSUBAME 3.0 PA075088” Kestrel / CC BY-SA 4.0 (cropped)
- Going beyond GPU memory limits: “Sapphire-Radeon-HD-5570-Video-Card” Evan-Amos / Public domain (cropped)
- Bringing out the performance of GPU supercomputers: “TSUBAME 3.0 PA075096” Kestrel / CC BY-SA 4.0 (cropped)
- Supercomputers cooled by oil immersion: “Submer Immersion Cooling SmartPodX” Submer Immersion Cooling / CC BY-SA 4.0 (cropped)
- Related lab (高邉賢史研究室): “Ising-tartan” Linas / CC BY-SA 3.0 (cropped)
- Related lab (山下真研究室): “Rosenbrock function 2” RokerHRO / Public domain (cropped)
- Related lab (三好直人研究室): “Voronoi AAAAA14” SmallJarsWithGreenLabels / CC0 (cropped)
- Related lab (藤澤克樹研究室): “Automated Storage and Retrieval System” QmcBeQ3G7DZCmY84uPgT / CC BY 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.