Gabriel Weisz

Update 2/2024: I have joined AMD, where I am a Fellow Software Development Engineer, getting the latest and greatest neural network models working on our hardware.
Update 10/2022: I have joined MangoBoost as Director of Product Management.
Update 6/2017: I'm now at Micrsoft working on Project Catapult
Update 9/2015: I've completed my PhD at CMU and have joined the Reconfigurable Computing Group at the USC Information Sciences Institute.
My Email Address

My Resume


I currently work at MangoBoost, and am helping the company turn ten years of academic research into the world's best Data Processing Unit.
Previously, I worked at Microsoft, where developed the model compiler for Brainwave, an FPGA-accelerated deep learning inference system that is used for Bing search and other cloud-based searches.
I have a PhD from the Computer Science department at Carnegie Mellon University, where I worked with Dr. James Hoe on using FPGAs for computing.
Prior to going to CMU, I spent eleven years at Salar, Inc, where I was a co-founder, Vice President of Technology, and sat on the Board of Directors.
I managed the development team, and worked on a number of interesting projects, including:


My PhD thesis was about framework-level support for an accelerated data structure library for FPGAs.
I've also worked on compiling graph algorithms to FPGAs, and using the CoRAM FPGA computing framework as a high level synthesis target.

Select Publications

A configurable cloud-scale DNN processor for real-time AI.
Jeremy Fowers, Kalin Ovtcharov, Michael Papamichael, Todd Massengill, Ming Liu, Daniel Lo, Shlomi Alkalay, Michael Haselman, Logan Adams, Mahdi Ghandi, Stephen Heil, Prerak Patel, Adam Sapek, Gabriel Weisz, Lisa Woods, Sitaram Lanka, Steven K Reinhardt, Adrian M Caulfield, Eric S Chung, and Doug Burger.
2018 ACM/IEEE 45th Annual International Symposium on Computer Architecture (ISCA 2018).
Evaluating Rapid Application Development with Python for Heterogeneous Processor-based FPGAs.
Andrew G. Schmidt, Gabriel Weisz, and Matthew French. (Best Short Paper)
The 25th IEEE International Symposium on Field-Programmable Custom Computing Machines (FCCM 2017).
SpaceCubeX: A framework for evaluating hybrid multi-core CPU/FPGA/DSP architectures.
Andrew G. Schmidt, Gabriel Weisz, Matthew French, Thomas Flatley, Carlos Y Villalpando.
The 2017 IEEE Aerospace Conference.
A study of pointer-chasing performance on shared-memory processor-FPGA systems.
Gabriel Weisz, Joseph Melber, Yu Wang, Kermin Fleming, Eriko Nurvitadhi, James C. Hoe.
The 2016 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays (FPGA 2016).
High Performance Linkage Disequilibrium: FPGAs Hold the Key.
Nikolaos Alachiotis and Gabriel Weisz.
The 2016 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays (FPGA 2016).
CoRAM++: Supporting Data-Structure-Specific Memory Interfaces for FPGA Computing.
Gabriel Weisz and James C. Hoe. (Best Paper)
The 25th International Conference on Field Programmable Logic and Applications (FPL 2015).
GraphGen: An FPGA Framework for Vertex-Centric Graph Computation.
Eriko Nurvitadhi, Gabriel Weisz, Yu Wang, Skand Hurkat, Marie Nguyen, James C. Hoe, Josè F. Martìnez, and Carlos Guestrin.
The 22nd IEEE International Symposium on Field-Programmable Custom Computing Machines (FPL 2014).
C-To-CoRAM: Compiling Perfect Loop Nests to the Portable CoRAM Abstraction.
Gabriel Weisz and James C. Hoe.
The 2013 ACM International Symposium on Field-Programmable Gate Arrays (FPGA 2013).
Prototype and Evaluation of the CoRAM Memory Architecture for FPGA-Based Computing.
Eric S. Chung, Michael K. Papamichael, Gabriel Weisz, James C. Hoe and Ken Mai.
The 2012 ACM International Symposium on Field-Programmable Gate Arrays (FPGA 2012).


#11,556,762; Neural network processor based on application specific synthesis specialization parameters. Fowers, Ovtcharov, Chung, Massengill, Lie, & Weisz. January 17, 2023
#10,795,678; Matrix vector multiplier with a vector register file comprising a multi-port memory. Fowers, Ovtcharov, Chung, Massengill, Liu, & Weisz. October 6, 2020
#8,326,653; Method and apparatus for analyzing patient medical records; Gottlieb, Gottlieb, & Weisz. December 4, 2012

Other stuff