Looking for interns or permanent hires?

Visit ADA's directory of students and postdoc researchers available for both industry and academic opportunities.

 

 

 

 

ADA Center News

ADA Hosts Third Student Hackathon!


University of Washington PI Zachary Tatlock and his team led the effort this year, in collaboration with CRISP PI Luis Ceze and his students. The hackathon was centered on Domain Specific Languages and compilers. The hackathon framework of choice for this space was the TVM platform based on TVM. The goal was to work on open areas of the TVM stack. Students worked on seven different tasks, including improving benchmarking and profiling, creating datatypes, fuzzing (program testing), improving gradient coverage, improving training, uTVM (Minimize device communication overhead), TVM to FPCore Backend to run analysis. Overall, students reported that they found that working with their teams was effective and that the tasks were appropriately challenging. 

 

 
MilSpec

MilSpec, ADA's Defense- Inspired Benchmark Suite, has new releases. Check them out here: https://adacenter.org/milspec

ADA Develops New Tool for gem5 Simulations

ADA researchers at the University of Michigan have developed Lapidary, a new tool enabling more efficient gem5 simulations. Lapidary creates gem5 checkpoints on bare-metal to avoid the weeks of simulation usually required to create viable checkpoints. It takes core dumps of the program… Read more

JUMP Center Panel Featured at DAC 2019

"Electronics Innovation’s Great Leap Forward: An overview of the JUMP program" was one of the panels featured at the 2019 Design Automation Conference (DAC 2019), held in Las Vegas June 2-6. The panel, moderated by DARPA's Linton Salmon, discussed ADA and the other JUMP centers. ADA… Read more

 

Task Liaison Meetings

 

Calling All Task Liaisons

ADA Center students are presenting their research at online task liaison meetings each Wednesday. Task liaisons and other interested sponsors are invited to join. Registration is not necessary, but please visit our complete liaison meeting schedule for info on how to attend each meeting.




Eastern time

Efficient Notification Mechanisms for Software Data Planes

Mirhosseininiri

Amirhossein Mirhosseini University of Michigan

PhD Student

- An In-Memory Accelerator for Deep Learning
Charles Eckert, PhD Student (University of Michigan)
- Erie: Continuous Locality-Aware Program Optimizations
Tanvir Ahmed Khan, PhD Student (University of Michigan)

About ADA

 

 

Reimagining How Computers Are Designed

As the computing industry struggles to maintain its historically rapid pace of innovation, the ADA Center, based at the University of Michigan, aims to streamline and democratize the design and manufacturing of next-generation computing systems.

The Center for Applications Driving Architectures, or ADA, is developing a transformative, "plug-and-play" ecosystem to encourage a flood of fresh ideas in computing frontiers such as autonomous control, robotics and machine-learning.

Today, analysts worry that the industry is stagnating, caught between physical limits to the size of silicon transistors and the skyrocketing costs and complexity of system design.

"The electronic industry is facing many challenges going forward, and we stand a much better chance of solving these problems if we can make hardware design more accessible to a large pool of talent," said Valeria Bertacco, an Arthur F. Thurnau professor of computer science and engineering at U-M and director of the ADA Center. "We want to make it possible for anyone with motivation and a good idea to build novel high-performance computing systems."

The center is a five-year project that includes researchers from several leading universities.
 

 

University of Michigan
Carnegie Mellon University
Cornell University
Georgia Tech
Harvard University
Massachusetts Institute of Technology
Princeton University
Purdue University
University of Illinois at Urbana-Champaign
University of Washington

We Thank Our Sponsors For Their Support

SRC JUMP
DARPA
Analog Devices
ARM
EMD Performance Materials
IBM
Intel
Lockheed Martin
Micron
Northrup Grumman
Raytheon
Samsung
SK Hynix
TSMC