Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
hardware_acceleration [2018/03/23 11:26]
admin
hardware_acceleration [2018/08/10 02:39] (current)
admin
Line 69: Line 69:
 of a logistic regression classi€er in 1.53 minutes, a 46x improvement of a logistic regression classi€er in 1.53 minutes, a 46x improvement
 over the fastest reported performance. over the fastest reported performance.
 +
 +https://​arxiv.org/​abs/​1808.02513 Rethinking Numerical Representations for Deep Neural Networks
 +
 + We show that inference using these custom numeric representations on production-grade DNNs, including GoogLeNet and VGG, achieves an average speedup of 7.6x with less than 1% degradation in inference accuracy relative to a state-of-the-art baseline platform representing the most sophisticated hardware using single-precision floating point.