Sign up for our newsletter and get the latest HPC news and analysis.
Send me information from insideHPC:

Julia Computing and GPU Acceleration

Julia is a high-level programming language for mathematical computing that is as easy to use as Python, but as fast as C. The language has been created with performance in mind, and combines careful language design with a sophisticated LLVM-based compiler [Bezanson et al. 2017].

Julia is already well regarded for programming multicore CPUs and large parallel computing systems, but recent developments make the language suited for GPU computing as well. The performance possibilities of GPUs can be democratized by providing more high-level tools that are easy to use by a large community of applied mathematicians and machine learning programmers. In this blog post, I will focus on native GPU programming with a Julia package that enhances the Julia compiler with native PTX code generation capabilities: CUDAnative.jl.

The Julia package ecosystem already contains quite a few GPU-related packages, targeting different levels of abstraction. At the highest abstraction level, domain-specific packages like MXNet.jl and TensorFlow.jl can transparently use the GPUs in your system. More generic development is possible with ArrayFire.jl, and if you need a specialized CUDA implementation of a linear algebra or deep neural network algorithm you can use vendor-specific packages like cuBLAS.jl or cuDNN.jl. All these packages are essentially wrappers around native libraries, making use of Julia’s foreign function interfaces (FFI) to call into the library’s API with minimal overhead. For more information, check out the JuliaGPU GitHub organization which hosts many of these packages.

About Julia and Julia Computing

Julia is the fastest high-performance open source computing language for data, analytics, algorithmic trading, machine learning, artificial intelligence, and other scientific and numeric computing applications. Julia solves the two language problem by combining the ease of use of Python and R with the speed of C++. Julia provides parallel computing capabilities out of the box and unlimited scalability with minimal effort. Julia has been downloaded more than 11 million times and is used at more than 1,500 universities. Julia co-creators are the winners of the 2019 James H. Wilkinson Prize for Numerical Software and the 2019 Sidney Fernbach Award. Julia has run at petascale on 650,000 cores with 1.3 million threads to analyze over 56 terabytes of data using Cori, one of the ten largest and most powerful supercomputers in the world.

Julia Computing was founded in 2015 by all the creators of Julia to provide products including JuliaTeam, JuliaSure and JuliaRun to businesses and researchers using Julia.

Sign up for our insideHPC Newsletter

Leave a Comment


Resource Links: