CDSC/InTrans Project Annual Review Meeting
March 1 and 2, 2018
UCLA Faculty Center, Sequoia Room & Redwood Rooms on Day 1
Mong Learning Center, 180 Auditorium Eng VI on Day 2 (No Food & Drink Allowed)

March 1, 2018 UCLA Faculty Center, Sequoia & Redwood Rooms

8:00am-8:30am Breakfast

8:30am-8:40am Welcome Remarks, Jayathi Murthy, Dean (UCLA HSSEAS)

8:40am-9:00am Center Overview, Jason Cong (UCLA CS/ECE)

9:00am-10:05am Architectures for Customizable Computing

• Thrust overview:  Glenn Reinman, UCLA CS
• A Reconfigurable Accelerator for 5G Wireless using Pattern Lifting, Jian Weng, UCLA CS
• A Learning-based Design Space Exploration Framework for Customized Computing, Cody Yu, UCLA CS
• Near-Storage Acceleration of Content-Based Image Retrieval, Nazanin Farahpour, UCLA CS

10:05am-10:25am Break

10:25am-11:50pm Runtime and Compilation Support

• Thrust overview: Vivek Sarkar, Georgia Tech CS
• A New Scalable Approach to Exact Resource-Constrained Scheduling, Zhiru Zhang, Cornell ECE
• Automatic Systolic Array Architecture Compilation, Jie Wang, UCLA CS
• Enabling On-Chip Parameter Persistency for Training Dynamic Neural Networks, Farzad Khorasani, Georgia Tech CS
• Integration of Data Layout and Loop Transformations via Affine Scheduling, Vivek Sarkar, Georgia Tech CS

11:50am-1:00pm Lunch

1:00pm-1:45pm Keynote Speech 1:  Heterogeneous computing platforms for IoT applications. Dr. Yuichi Nakamura, head and general manager of System Platform Research Laboratories, NEC Corp.

1:45pm-3:10pm Application Drivers

• Thrust overview: Alex Bui, UCLA Radiology Sciences
• Lung cancer diagnosis using deep convolutional neural network in CT images, Shiwen Shen, UCLA Bioengineering
• Enhancing CT images using CNN-based super-resolution approach, Meng Li, UCLA & PKU
• SMEM++: A Pipelined and Time-Multiplexed SMEM Seeding Accelerator for Genome Sequencing on HARP2, Tianhe Yu, UCLA ECE
• A Few New Computational Challenges for Biomedical Applications, Alex Bui and William Hsu, UCLA Radiological Sciences

3:10pm-3:30pm Break

3:30pm-4:35pm Experimental Systems

• Thrust overview: Jason Cong, UCLA CS/ECE
• ST-Accel: A High-Level Programming Platform for Streaming Applications on FPGA, Zhenyuan Ruan, UCLA CS
• Accelerating high-quality lossless compression on HARP2: from serial processing to parallel processing, Weikang Qiao, UCLA ECE
• Predictive Compact LSTM in Neurofeedback and Optogenetics Applications, Zhe Chen, UCLA CS

4:35pm-5:05pm Posters Introduction

5:30pm-8:30pm Poster session at Faculty Center, Sequoia and Redwood Rooms
480 Charles E. Young Drive East, Los Angeles, CA 90095-1617
Tel: (310) 825-0877

March 2, 2018 Mong Learning Center, 180 Auditorium Eng VI (No Food & Drink Allowed)

8:00am-8:30am Breakfast (Alumni Suite 176 Eng VI)

8:30am-10:00am NSF/Intel Partnership on Computer Assisted Programming for Heterogeneous Architectures (CAPA) Session

• CAPA Vision — the Intel Perspective, Justin Gottschlich, Intel
• Raising the Level of Abstraction for Customizable Computing, Jason Cong, UCLA CS/ECE 
• Towards Multi-Paradigm Programming for Software-Defined FPGAs, Zhiru Zhang, Cornell ECE
• Dynamic Invariant Driven Synthesis and Performance Debugging for FPGA, Miryung Kim, UCLA CS
• Checking and Synthesizing the CPU–FPGA Interface in HeteroCL, Adrian Sampson, Cornell CS
• Programmatic Control of a Compiler of Generating High-Performance Spatial Hardware, Hongbo Rong, Intel

10:00am-10:30am Break (Alumni Suite 176 Eng VI)

10:30am-11:10am Keynote Speech 2: Integrative genomics in complex psychiatric disease. Dr. Dan Geschwind, Director of Institute of Precision Medicine (IPM), UCLA

11:10am-12:10pm Industrial feedback session

12:10pm-1:10pm Lunch (Food set up in front of Mong Learning Center, 183 VIP suite available for guests to sit)

CDSC Advisory Board Meeting (CDSC industrial advisory board members only, 12:10pm-1:45pm over lunch)

 

LIST OF POSTERS

Architecture:

A Reconfigurable Accelerator for 5G Wireless using Pattern Lifting – Jian Weng, UCLA CS

A Learning-based Design Space Exploration Framework for Customized Computing – Hao Yu, UCLA CS

Near-Storage Acceleration of Content-Based Image Retrieval – Nazanin Farahpour, UCLA CS

Latte: Locality Aware Transformation for High-Level SynThEsis, Peipei Zhou, UCLA CS

Runtime and Compilation:

Automatic Systolic Array Architecture Compilation – Jie Wang, UCLA CS

A Fully Pipelined Communication Stack for JVM-FPGA Integration – Peng Wei, UCLA CS

Enabling On-Chip Parameter Persistency for Training Dynamic Neural Networks – Farzad Khorasani, Georgia Tech CS

Diagnosing Non-Deterministic Alignments in BWA-MEM – Max Grossman, Rice CS

Application:

Enhancing CT images using CNN-based super-resolution approach – Meng Li, UCLA & PKU

SMEM++: A Pipelined and Time-Multiplexed SMEM Seeding Accelerator for Genome Sequencing on HARP2 – Tianhe Yu, UCLA ECE

Exploring the Acceleration Potential of Irregular Machine Learning Workloads – Vidushi Dadu, UCLA CS

An Optimal Microarchitecture for Stencil Computation with Data Reuse and Fine-Grained Parallelism – Yuze Chi, UCLA CS

Experiment:

ST-Accel: A High-Level Programming Platform for Streaming Applications on FPGA – Zhenyuan Ruan, UCLA CS

Accelerating high-quality lossless compression on HARP2: from serial processing to parallel processing – Weikang Qiao, UCLA ECE

Predictive Compact LSTM in Neurofeedback and Optogenetics Applications – Zhe Chen, UCLA CS

Rapid Design Space Exploration of Applications with Dynamic Behavior – Young-kyu Choi, UCLA CS

 

KEYNOTE SPEAKERS

Yuichi Nakamura, PhD

Abstract

IoT(Internet of Things), which collects various data in real world and analyzes values from collected data is are good methods to help solve such serious problems and to construct efficient social systems.  Meanwhile, since it takes a long time to collect and analyze “Complicated Big data”, efficient network system and computer systems are required. Integration of heterogeneous computing and 5G network is the best platform to provide complex IoT systems. In this talk, a reason why complex IoT systems are require heater computing and high-speed communication systems is presented. In addition, some use cases of IoT infrastructures are also introduced.

Biography

Yuichi Nakamura is the head and general manager of System Platform Research Laboratories, NEC Corp.

He joined NEC Corp in 1988. He has more than 25 years of professional experience in R&D for VLSI CAD, software engineering, embedded system design and parallel systems. He contributed to develop NEC’s WDM, submarine optical system, main frames, various SoC design, and supercomputers, especially  “Earth Simulator” which achieved No1 fastest computer from 2002 to 2004.  He is author and co-author of more than 30 journal papers and more than 70 conference papers in embedded systems and received PhD. degree in 2007.

He is also a guest professor in National Institute of Informatics from 2009.

 

Dr. Dan Geschwind

Biography

Dr. Geschwind is the Gordon and Virginia MacDonald Distinguished Professor of Human Genetics, Neurology and Psychiatry at UCLA. In his capacity as Senior Associate Dean and Associate Vice Chancellor of Precision Health, he leads the Institute for Precision Health at UCLA. His laboratory has pioneered the application of systems biology methods in neurologic and psychiatric disease. Dr. Geschwind has put considerable effort into fostering large-scale collaborative patient resources for genetic research and data sharing in autism research. He has served on numerous scientific advisory boards, including the Faculty of 1000 Medicine, the Executive Committee of the American Neurological Association, the Scientific Advisory Board for the Allen Institute for Brain Science, the NIMH Advisory Council and the NIH Council of Councils. He has published over 400 papers and serves on the editorial boards of Cell, Neuron and Science. He has received several awards for his laboratory’s work and leadership including the Ruane Prize from the Brain and Behavior Foundation in 2013 and the Derek Denny-Brown Neurological Scholar Award from the American Neurological Association (ANA) in 2004. He is an elected Member of the American Association of Physicians and the National Academy of Medicine.