<img height="1" width="1" style="display:none" src="https://www.facebook.com/tr?id=145304570664993&amp;ev=PageView&amp;noscript=1">


Our Poplar SDK accelerates machine learning training and inference with high-performance optimisations delivering world leading performance on IPUs across models such as  natural language processing,  probabilistic modelling, computer vision and more. We have provided a selection of the latest MK2 IPU performance benchmark charts on this page and will update it regularly. We also now provide detailed MK2 training and inference performance data in table format. You can reproduce all of these benchmarks using code in the examples repo on the Graphcore GitHub page. 

MK1 Benchmarks View Performance Results Table

BERT Large (Bidirectional Encoder Representations from Transformers) is one of the most well known NLP models in use today. The IPU accelerates both training and inference on BERT-Large, delivering faster time to train with significantly higher throughput at extremely low latency for inference. 

Bert-Large- Inference Click to Zoom
Get the code
Bert-Large- Training Click to Zoom
Get the code

IPU excels with models designed to leverage small group convolutions due to its fine grained architecture and unique Poplar features. We deliver unparalleled performance for both training and inference for newer computer vision models like EfficientNet and ResNeXt, which deliver higher accuracy and improved efficiency, as well as for traditional computer vision models such as ResNet-50.

Benchmark 081220 AI_EfficientNet-B0- Inference Click to Zoom
Benchmark 081220 AI_EfficientNet-B4- Training 10x Click to Zoom
Resnext-101- Inference Click to Zoom
Get the code
Resnext-101- Training Click to Zoom
Get the code
Resnet-50- Inference Click to Zoom
Resnet-50- Training Click to Zoom
Probabilistic Model- Training Click to Zoom
Get the code
LSTM- Inference Click to Zoom
Get the code

Deep Voice from Baidu is a prominent text-to-speech (TTS) model family for high-quality, end-to-end speech synthesis. The IPU’s capacity to rapidly accelerate fully convolutional TTS models like Deep Voice 3 with a notably higher throughput than a GPU opens up the opportunity to create entirely new classes of TTS models.

DeepVoice 3 TTS- Training Click to Zoom
Get the code

Female: "He likes the taste of worcestershire sauce"

Male: "She demonstrated great leadership on the field"

Download charts