CPU, GPU or FPGA: Performance evaluation of cloud computing platforms for Machine Learning training

FPGAs on the cloud (f1.2xlarge on this case with InAccel ML suite) achieves the best combination in terms of performance-accuracy and cost.

Read more

Accelerating data science and HPC applications with FPGAs using Jupyter Hub, instantly

InAccel, a world-leader in application acceleration through the use of adaptive acceleration platforms (ACAP, FPGA) has integrated JupyterHub in its technology. InAccel provides an FPGA resource manager that allows the instant deployment, scaling and virtualization of FPGAs making easier than ever the utilization of FPGA clusters for applications like machine learning, data processing, data analytics and many more HPC workloads.

Read more

Automated deployment, scaling and management of FPGA clusters: the easy way

Coral is a scalable, reliable and fault-tolerant distributed acceleration system responsible for monitoring, virtualizing and orchestrating clusters of FPGAs. Coral also introduces high-level abstractions by exposing FPGAs as a single pool of accelerators to any application developer that she can easily invoke through simple API calls. Finally, Coral runs as a microservice and is able to run on top of other state-of-the-art resource managers like Hadoop YARN and Kubernetes.

Read more

InAccel’s Accelerated ML suite boosts Spark ML as much as 7x using Intel’s® Arria® FPGAs

The IP cores for logistic regression and K-means clustering leverage the processing power of the Intel FPGAs to speedup the training of these algorithms. The IP core is optimized for the Intel® FPGAs (e.g. Arria® 10) available as instances on Alibaba cloud.

Read more

InAccel Accelerates XGboost and releases the IP core for FPGAs

InAccel has released today as open-source the FPGA IP core for the training of XGboost. The FPGA accelerated solution for the XGBoost algorithm is based on the Exact (Greedy) algorithm for tree creation. It can provide up to 26x speedup compared to a single threaded execution and up to 5x compared to an 8 threaded CPU execution respectively

Read more

Subscribe to get updates!

Error, please retry.