LONDON – Vector Fabrics BV has announced the availability of its vfThreaded-x86 cloud-based software tool to help with the parallelization and optimization of applications for multi-core x86 architectures.
The tool is aimed at software developers that write performance-centric code such as for high-performance computing, scientific, industrial, video or imaging applications and is available for just 175 euro ($250) for one month's access.
Vector Fabrics (Eindhoven, The Netherlands) claimed the tool reduces development time and risks but did not say what it was comparing against or what risks it was measuring. Nor did the company indicate whether there are any limitations within the x86 family or whether vfThreaded can support any and all x86 chips from suppliers such as Advanced Micro Devices as well as Intel.
Vector Fabrics did say that the vfTheaded-x86 tool uses both dynamic and static code analysis to make partitioning choices and assign code to separate cores. This includes examining cache hit/miss effects, data bandwidth to memories and bandwidth between individual code sections. The tool comes with a graphical user interface that provides code visualizations and highlights code hotspots and dependencies that might require partitioning trade-offs.
The tool is able to model and predict code performance improvements prior to altering the code. A dependency analysis function avoids data races and promotes a correct-by-construction approach to multi-core development.
The vfThreaded-x86 tool is available as a cloud-based software service and is accessed through the Vector Fabrics website using a standard web browser. The software development tool runs in the Amazon EC2 cloud. This cloud runs under Windows, Linux and Apple. Pricing is based on a subscription fee that includes technical support. License fees start from 175 euro (about $250) for one month's use.
"Our tools make it easy to speed up a program using multiple threads, something programmers often shy away from since they find it difficult to split up code and to avoid hard-to-find bugs. Our tools largely automate this otherwise error-prone and lengthy manual parallelization process," said Mike Beunder, CEO of Vector Fabrics, in a statement.