search slide
search slide
pages bottom
Currently Browsing: Results for Tag "inference"

Google's dedicated TensorFlow processor, or TPU, crushes Intel, Nvidia in inference workloads

Google's dedicated TensorFlow processor, or TPU, crushes Intel, Nvidia in inference workloads Several years ago, Google began working on its own custom software for machine learning and artificial intelligence workloads, dubbed TensorFlow.Now, Google has released some performance data for their TPU and how it compares to Intel’s Haswell CPUs and Nvidia’s K80 (Kepler-based) data center dual GPU.

Nvidia claims Pascal GPUs would challenge Google's TensorFlow TPU in updated benchmarks

Nvidia claims Pascal GPUs would challenge Google's TensorFlow TPU in updated benchmarks Here’s Nvidia: Nvidia’s claim that the TPU has 13x the performance of K80 is provisionally true, but there’s a snag.The net result of these improvements, according to Nvidia, is that the P40 offers 26x more inference performance than one die of a K80.