PARALLEL SESSION
C2L-C
Heterogeneous AI Systems and SoC Integration Session
SALA ALBENIZ
THURSDAY - 10 September | 14:10 - 15:50
CHAIRS
Kavya Sreedhar, Francesco Conti
SESSION PROGRAM
14:10 - 14:30
Zircon: A 16nm Heterogeneous CGRA SoC for Accelerating Dense and Sparse ML
Yuchen Mei, Michael Oduoza, Po-Han Chen, Maxwell Strange, Zhouhua Xie, Bo Wun Cheng, Kalhan Koul, Kartik Prabhu, Jeff...
14:30 - 14:50
HEMAIA: A 16 nm Heterogeneous Multi-Accelerator SoC with Accelerator-Centric Execution
Ryan Antonio, Xiaoling Yi, Jun Yin, Ce Ma, Yunhao Deng, Fanchen Kong, Abdelrahman Ayman, Joren Dumoulin, Josse Van De...
14:50 - 15:10
CHIMERA: A Flexible and Scalable 3.1 TOPS/W Ai-Mcu with Transformer Accelerator and 563 Gb/s Shared-L2 Memory Subsystem with QoS Guarantees
Lorenzo Leone, Philip Wiese, Gamze Islamoglu, Michael Rogenmoser, Davide Rossi, Francesco Conti, Luca Benini
15:10 - 15:30
LUCIA: A Scalable and Versatile 0.82 TOPS/W/mm² Chiplet Architecture for CNN in 22 nm FDSOI
Arturo Prieto, Kristoffer Westring, Alex Allfjord, Masoud Nouripayam, Sergio Castillo Mohedano, William Marnfeldt, Jo...
15:30 - 15:50
An AR/VR SoC with Dual-Mode Gaze Guided Perception and Few-Shot Keyword Spotting
Yuncheng Lu, Junyi Qian, Aobo Li, Chengshuo Yu, Zehao Li, Ruixin Mao, Yucen Shi, Tianyi Liu, Yujin Lee, Junying Li, C...