For highly demanding interactive and immersive graphics applications, developers need the best GPU accelerators at their disposal. To help artists, architects, and engineers create stunning scenes, Google just announced the availability of the NVIDIA Tesla P4 GPUs on the Google Cloud Platform. The GPUs are optimized for graphics-intensive applications and machine learning.
“The new P4 accelerators, now in beta, provide a good balance of price/performance for remote display applications and real-time machine learning inference,” said Ari Liberman, a Google Cloud Product Manager. “We now support virtual workstations with NVIDIA GRID on the P4 and P100, allowing you to turn any instance with one or more GPUs into a high-end workstation optimized for graphics-accelerated use cases,” he explained.
The Tesla P4 GPUs are an excellent fit for deep learning inference in cases such as visual search, interactive speech, and video recommendations. The GPUs offer up to 22 TOPs of INT8 performance on the Google Cloud virtual environment.
Developers can attach multiple P4 GPUs to any virtual machine.
“We support all our GPUs, including the P4, on Kubernetes Engine and Cloud Machine Learning Engine, zync render, and they can take advantage of sustained use discounts and pre-emptible pricing.”
The GPUs are available now in most of North America and Europe.