A 7-nm Four-Core Mixed-Precision AI Chip With 26.2-TFLOPS Hybrid-FP8 Training, 104.9-TOPS INT4 Inference, and Workload-Aware Throttling.

Kerstin Schelm

Sae Kyu Lee Ankur Agrawal Joel Silberman Matthew M. Ziegler Mingu Kang Swagath Venkataramani Nianzheng Cao Bruce M. Fleischer Michael Guillorn Matthew Cohen Silvia M. Mueller Jinwook Oh Martin Lutz Jinwook Jung Siyu Koswatta Ching Zhou Vidhi Zalani Monodeep Kar James Bonanno Robert Casatuta Chia-Yu Chen Jungwook Choi Howard Haynie Alyssa Herbert Radhika Jain Kyu-Hyoun Kim Yulong Li Zhibin Ren Scot Rider Marcel Schaal Kerstin Schelm Michael Scheuermann Xiao Sun 0013 Hung Tran Naigang Wang Wei Wang 0333 Xin Zhang 0025 Vinay Shah Brian W. Curran Vijayalakshmi Srinivasan Pong-Fei Lu Sunil Shukla Kailash Gopalakrishnan Leland Chang A 7-nm Four-Core Mixed-Precision AI Chip With 26.2-TFLOPS Hybrid-FP8 Training, 104.9-TOPS INT4 Inference, and Workload-Aware Throttling. 182-197 2022 57 IEEE J. Solid State Circuits 1 https://doi.org/10.1109/JSSC.2021.3120113 db/journals/jssc/jssc57.html#LeeASZKVCFGCMOL22

Swagath Venkataramani Vijayalakshmi Srinivasan Wei Wang 0333 Sanchari Sen Jintao Zhang Ankur Agrawal Monodeep Kar Shubham Jain 0004 Alberto Mannari Hoang Tran Yulong Li Eri Ogawa Kazuaki Ishizaki Hiroshi Inoue Marcel Schaal Mauricio J. Serrano Jungwook Choi Xiao Sun 0013 Naigang Wang Chia-Yu Chen Allison Allain James Bonanno Nianzheng Cao Robert Casatuta Matthew Cohen Bruce M. Fleischer Michael Guillorn Howard Haynie Jinwook Jung Mingu Kang Kyu-Hyoun Kim Siyu Koswatta Sae Kyu Lee Martin Lutz Silvia M. Mueller Jinwook Oh Ashish Ranjan 0001 Zhibin Ren Scot Rider Kerstin Schelm Michael Scheuermann Joel Silberman Jie Yang Vidhi Zalani Xin Zhang 0025 Ching Zhou Matthew M. Ziegler Vinay Shah Moriyoshi Ohara Pong-Fei Lu Brian W. Curran Sunil Shukla Leland Chang Kailash Gopalakrishnan RaPiD: AI Accelerator for Ultra-low Precision Training and Inference. 153-166 2021 ISCA https://doi.org/10.1109/ISCA52012.2021.00021 conf/isca/2021 db/conf/isca/isca2021.html#VenkataramaniSW21 Ankur Agrawal Sae Kyu Lee Joel Silberman Matthew M. Ziegler Mingu Kang Swagath Venkataramani Nianzheng Cao Bruce M. Fleischer Michael Guillorn Matt Cohen Silvia M. Mueller Jinwook Oh Martin Lutz Jinwook Jung Siyu Koswatta Ching Zhou Vidhi Zalani James Bonanno Robert Casatuta Chia-Yu Chen Jungwook Choi Howard Haynie Alyssa Herbert Radhika Jain Monodeep Kar Kyu-Hyoun Kim Yulong Li Zhibin Ren Scot Rider Marcel Schaal Kerstin Schelm Michael Scheuermann Xiao Sun 0013 Hung Tran Naigang Wang Wei Wang 0333 Xin Zhang 0025 Vinay Shah Brian W. Curran Vijayalakshmi Srinivasan Pong-Fei Lu Sunil Shukla Leland Chang Kailash Gopalakrishnan A 7nm 4-Core AI Chip with 25.6TFLOPS Hybrid FP8 Training, 102.4TOPS INT4 Inference and Workload-Aware Throttling. 144-146 2021 ISSCC https://doi.org/10.1109/ISSCC42613.2021.9365791 conf/isscc/2021 db/conf/isscc/isscc2021.html#AgrawalLSZKVCFG21 Stefan Payer Cédric Lichtenau Michael Klein Kerstin Schelm Petra Leber Nicol Hofmann Tina Babinsky SIMD Multi Format Floating-Point Unit on the IBM z15(TM). 125-128 2020 ARITH https://doi.org/10.1109/ARITH48897.2020.00027 conf/arith/2020 db/conf/arith/arith2020.html#PayerLKSLHB20 Maarten Boersma Michael Kroener Christophe Layer Petra Leber Silvia M. Müller Kerstin Schelm The POWER7 Binary Floating-Point Unit. 87-91 2011 IEEE Symposium on Computer Arithmetic https://doi.org/10.1109/ARITH.2011.21 https://doi.ieeecomputersociety.org/10.1109/ARITH.2011.21 conf/arith/2010 db/conf/arith/arith2010.html#BoersmaKLLMS10 Ankur Agrawal Allison Allain Tina Babinsky Maarten Boersma James Bonanno Nianzheng Cao Robert Casatuta Leland Chang Chia-Yu Chen Jungwook Choi Matt Cohen Matthew Cohen Brian W. Curran Bruce M. Fleischer Kailash Gopalakrishnan Michael Guillorn Howard Haynie Alyssa Herbert Nicol Hofmann Hiroshi Inoue Kazuaki Ishizaki Radhika Jain Shubham Jain 0004 Jinwook Jung Mingu Kang Monodeep Kar Kyu-Hyoun Kim Michael Klein Siyu Koswatta Michael Kroener Christophe Layer Petra Leber Sae Kyu Lee Yulong Li Cédric Lichtenau Pong-Fei Lu Martin Lutz Alberto Mannari Silvia M. MüllerSilvia M. Mueller Eri Ogawa Jinwook Oh Moriyoshi Ohara Stefan Payer Ashish Ranjan 0001 Zhibin Ren Scot Rider Marcel Schaal Michael Scheuermann Sanchari Sen Mauricio J. Serrano Vinay Shah Sunil Shukla Joel Silberman Vijayalakshmi Srinivasan Xiao Sun 0013 Hoang Tran Hung Tran Swagath Venkataramani Naigang Wang Wei Wang 0333 Jie Yang Vidhi Zalani Jintao Zhang Xin Zhang 0025 Ching Zhou Matthew M. Ziegler