Implementing Domain-Specific Languages for Heterogeneous Parallel Computing von HyoukJoong Lee, Brown, Kevin J., Sujeeth, Arvind K., Chafi, H., Olukotun, K., Rompf, Tiark, Odersky, Martin

Volltext

Building-Blocks for Performance Oriented DSLs von Rompf, Tiark, Sujeeth, Arvind K., Lee, HyoukJoong, Brown, Kevin J., Chafi, Hassan, Odersky, Martin, Olukotun, Kunle

Volltext

Delite: A Compiler Architecture for Performance-Oriented Embedded Domain-Specific Languages von Sujeeth, Arvind K., Brown, Kevin J., Lee, Hyoukjoong, Rompf, Tiark, Chafi, Hassan, Odersky, Martin, Olukotun, Kunle

Volltext

Generating Configurable Hardware from Parallel Patterns von Prabhakar, Raghu, Koeplinger, David, Brown, Kevin J., Lee, HyoukJoong, De Sa, Christopher, Kozyrakis, Christos, Olukotun, Kunle

Volltext

Multi-codec variable length decoder design with configurable processor von HyoukJoong Lee, Kiyoung Choi

Volltext bestellen

Generating Configurable Hardware from Parallel Patterns von Prabhakar, Raghu, Koeplinger, David, Brown, Kevin J., Lee, HyoukJoong, De Sa, Christopher, Kozyrakis, Christos, Olukotun, Kunle

Volltext

Composition and Reuse with Compiled Domain-Specific Languages von Sujeeth, Arvind K., Rompf, Tiark, Brown, Kevin J., Lee, HyoukJoong, Chafi, Hassan, Popic, Victoria, Wu, Michael, Prokopec, Aleksandar, Jovanovic, Vojin, Odersky, Martin, Olukotun, Kunle

Volltext

A domain-specific approach to heterogeneous parallelism von Chafi, Hassan, Sujeeth, Arvind K., Brown, Kevin J., Lee, HyoukJoong, Atreya, Anand R., Olukotun, Kunle

Volltext

Automatic Cross-Replica Sharding of Weight Update in Data-Parallel Training von Xu, Yuanzhong, Lee, HyoukJoong, Chen, Dehao, Choi, Hongjun, Hechtman, Blake, Wang, Shibo

Volltext bestellen

Optimizing data structures in high-level programs: new directions for extensible compilers based on staging von Rompf, Tiark, Sujeeth, Arvind K., Amin, Nada, Brown, Kevin J., Jovanovic, Vojin, Lee, HyoukJoong, Jonnalagedda, Manohar, Olukotun, Kunle, Odersky, Martin

Volltext

GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding von Lepikhin, Dmitry, Lee, HyoukJoong, Xu, Yuanzhong, Chen, Dehao, Firat, Orhan, Huang, Yanping, Krikun, Maxim, Shazeer, Noam, Chen, Zhifeng

Volltext bestellen

GSPMD: General and Scalable Parallelization for ML Computation Graphs von Xu, Yuanzhong, Lee, HyoukJoong, Chen, Dehao, Hechtman, Blake, Huang, Yanping, Joshi, Rahul, Krikun, Maxim, Lepikhin, Dmitry, Ly, Andy, Maggioni, Marcello, Pang, Ruoming, Shazeer, Noam, Wang, Shibo, Wang, Tao, Wu, Yonghui, Chen, Zhifeng

Volltext bestellen

ATTENTION NEURAL NETWORKS WITH CONDITIONAL COMPUTATION von Lepikhin, Dmitry, Krikun, Maxim, Xu, Yuanzhong, Huang, Yanping, Shazeer, Noam M, Firat, Orhan, Lee, HyoukJoong, Chen, Dehao, Chen, Zhifeng

Volltext bestellen

TRAINING GIANT NEURAL NETWORKS USING PIPELINE PARALLELISM von Ngiam, Jiquan, Huang, Yanping, Cheng, Youlong, Lee, HyoukJoong, Chen, Dehao, Chen, Zhifeng

Volltext bestellen

Exploring the limits of Concurrency in ML Training on Google TPUs von Kumar, Sameer, Bradbury, James, Young, Cliff, Wang, Yu Emma, Levskaya, Anselm, Hechtman, Blake, Chen, Dehao, Lee, HyoukJoong, Deveci, Mehmet, Kumar, Naveen, Kanwar, Pankaj, Wang, Shibo, Wanderman-Milne, Skye, Lacy, Steve, Wang, Tao, Oguntebi, Tayo, Zu, Yazhou, Xu, Yuanzhong, Swing, Andy

Volltext bestellen

Training giant neural networks using pipeline parallelism von Ngiam, Jiquan, Huang, Yanping, Cheng, Youlong, Lee, HyoukJoong, Chen, Dehao, Chen, Zhifeng

Volltext bestellen

Scale MLPerf-0.6 models on Google TPU-v3 Pods von Kumar, Sameer, Bitorff, Victor, Chen, Dehao, Chou, Chiachen, Hechtman, Blake, Lee, HyoukJoong, Kumar, Naveen, Mattson, Peter, Wang, Shibo, Wang, Tao, Xu, Yuanzhong, Zhou, Zongwei

Volltext bestellen

Surgical precision JIT compilers von Rompf, Tiark, Sujeeth, Arvind K., Brown, Kevin J., Lee, HyoukJoong, Chafi, Hassan, Olukotun, Kunle

Volltext

ATTENTION NEURAL NETWORKS WITH CONDITIONAL COMPUTATION von LEPIKHIN, Dmitry, LEE, HyoukJoong, KRIKUN, Maxim, XU, Yuanzhong, HUANG, Yanping, CHEN, Zhifeng, CHEN, Dehao, FIRAT, Orhan, SHAZEER, Noam M

Volltext bestellen

TRAINING GIANT NEURAL NETWORKS USING PIPELINE PARALLELISM von Ngiam, Jiquan, Huang, Yanping, Cheng, Youlong, Lee, HyoukJoong, Chen, Dehao, Chen, Zhifeng

Volltext bestellen