Julia Computing and IBM present Julia for Deep Learning at SC16
18 Nov 2016 Salt Lake City - Julia Computing and IBM presented Julia for Deep Learning at SC16, the world's largest supercomputing conference held in Salt Lake City, Utah. This exciting new technology combines IBM's Power8 server platform and NVIDIA Tesla K80 GPU accelerators with the superior speed and performance of the Julia mathematical and scientific computing language.
Julia Computing and the IBM team used this powerful combination to apply deep learning to analyze medical images provided by Drishti Eye Hospitals to diagnose diabetic retinopathy, an eye disease that affects more than 126 million diabetics and accounts for more than 5% of blindness cases worldwide.
"India is home to 62 million diabetics", explained Kiran Anandampillai, founder and CEO of Drishti Eye Hospitals. "Many of whom live in rural areas with limited access to health facilities. Timely screening for changes in the retina can help get them to treatment and prevent vision loss. Julia Computing's work using deep learning makes retinal screening an activity that can be performed by a trained technician using a low cost fundus camera."
According to Julia Computing CEO Viral Shah, "Using IBM's Power platform with NVIDIA GPU accelerators increased processing speed by 57x - a dramatic improvement. IBM Power provides 2-3x more memory bandwidth combined with tight GPU accelerator integration to create a high performance environment for deep learning with Julia."
Julia has the following key advantages for scientific and mathematical computing:
- Julia is lightning fast. Julia provides speed improvements up to 1,000x for insurance model estimation, 225x for parallel supercomputing image analysis and 11x for macro-economic modelling.
- Julia is easy to learn. Julia's flexible syntax is familiar and comfortable for users of Python and R.
- Julia integrates well with existing code and platforms. Users of Python, R and other languages can easily integrate their existing code into Julia.
- Elegant code: Julia was built from the ground up for mathematical, scientific and statistical computing, and has advanced libraries that make coding simple and fast, and dramatically reduce the number of lines of code required - in some cases, by 90% or more.
- Julia solves the two language problem. Because Julia combines the ease of use and familiar syntax of Python and R with the speed of C, C++ or Java, programmers no longer need to estimate models in one language and reproduce them in a faster production language. This saves time and reduces error and cost.