industry news
Subscribe Now

InAccel releases open-source Logistic Regression IP core for FPGAs

Machine learning algorithms are extremely computationally intensive and time consuming when they must be trained on large amounts of data. Typical processors are not optimized for machine learning applications and therefore offer limited performance. Therefore, both academia an industry is focused on the development of specialized architectures for the efficient acceleration of machine learning applications. 

FPGAs are programmable chips that can be configured with tailored-made architectures optimized for specific applications. As FPGAs are optimized for specific tasks, they offer higher performance and lower energy consumption compared with general purpose CPUs or GPUs. FPGAs are widely used in applications like image processing, telecommunications, networking, automotive and machine learning applications. 

Recently major cloud and HPC providers like Amazon, Alibaba, Huawei and Nimbix have started deploying FPGAs in their data centers. However, currently there are limited cases of wide utilization of FPGAs in the domain of machine learning. 

Towards this end, InAccel has released today as open-source the FPGA IP core for the training of logistic regression algorithms. The accelerated FPGA IP core offers up to 70x speedup compared to a single threaded execution and up to 12x compared to an 8-core general purpose CPU execution respectively.

The IP core for logistic regression leverage the processing power of the Xilinx FPGAs. The IP core is optimized for the Xilinx FPGAs like Alveo U200 and U250 cards and the FPGAs available as instances on the cloud providers (f1 on AWS and f3 on Alibaba cloud).

The release of the Logistic Regression IP core will help demonstrate the advantages of the FPGAs in the domain of machine learning and it will offer to the data science community the chance to experiment, deploy and utilize FPGAs in order to speedup their machine learning applications. 

The logistic regression IP core can be used as an add-on library that overload the functions for the logistic regression training. InAccel offers all the required APIs for seamless integration with Python, Java and Scala. That means that data scientist and data engineers do not need to change their code at all. 

The IP core is available on https://github.com/inaccel/logisticregression 

Leave a Reply

featured blogs
Nov 20, 2019
During ICCAD earlier in the month, there was the 2nd WOSET, which stands for Workshop on Open-Source EDA Technology. I wasn't there but Anton Klotz, who runs the Cadence Academic Network in... [[ Click on the title to access the full blog on the Cadence Community site. ...
Nov 18, 2019
By Srinivas Velivala – Mentor, A Siemens Business MaxLinear implemented the Calibre RealTime Digital interface for fast, iterative signoff DRC during P&R, and shaved weeks off tapeout schedules while meeting PPA targets. Learn how they did it… At the 2019 TSM...
Nov 18, 2019
Dangers of 5G. Thousands of satellites. Radio controlled birds. Smartphones spying on us. And much, much more....
Nov 15, 2019
As we seek to go faster and faster in our systems, heat grows as does the noise from the cooling fans. It is because of this heat and noise, many companies are investigating or switching to submersible cooling (liquid immersion cooling) options. Over the last few years, subme...
Nov 15, 2019
[From the last episode: we looked at how intellectual property helps designers reuse circuits.] Last week we saw that, instead of creating a new CPU, most chip designers will buy a CPU design '€“ like a blueprint of the CPU '€“ and then use that in a chip that they'€™re...