Comment Comment by p1esk Here are some details about their upcoming chip: http://www.nextplatform.com/2016/08/08/deep-learning-chip-up...Summary:- 28nm- looks similar to P100 (interposer with HBM)- 55 teraops/s performance- custom number format (variable length fixed point?)- simplified memory architecture (no cache?)- no info about power consumption parent p1esk 10 years ago
Summary:
- 28nm
- looks similar to P100 (interposer with HBM)
- 55 teraops/s performance
- custom number format (variable length fixed point?)
- simplified memory architecture (no cache?)
- no info about power consumption