We are thrilled to announce the official launch of Parallelware Analyzer 1.0, the first static code analyzer specializing in performance. During the last 2 years, over 200 early adopters have helped us shape Parallelware Analyzer thanks to their invaluable feedback through the Early Access Program. Appentra as an innovation company provides a revolutionary approach: Parallelware […]
HPC
How can Parallelware Analyzer advance the vectorization state-of-the-art?
Parallelware Analyzer can help advance the state-of-the-art of performance optimization. One representative example is vectorization. Compilers normally try to automatically vectorize as many loops as possible. However, in many cases they encounter code that is either not suitable for vectorization or too complex for them to handle. In these scenarios, invoking Parallelware Analyzer will identify […]
Parallelware Analyzer for large codes: GROMACS case study
Static code analysis is complex and thus, static analysis tools often struggle for large codes. One frequent question we get asked regarding Parallelware Analyzer is how well it behaves when analyzing large code bases. In order to answer it we have chosen the GROMACS project containing more than 340 thousand lines of code across more […]
Performance gains for classic computational examples with Parallelware Analyzer
Appentra’s performance-demos GitHub repository showcases the performance gains when parallelizing code with the help of Parallelware Analyzer. The following classic computational codes have been parallelized using CPU multi-threading and GPU offloading with Parallelware Analyzer: ATMUX: sparse matrix-vector multiplication. CANNY: image edge detection. COULOMB: computation of the electric potential created by a set of charges in […]
Parallelware Analyzer 0.19 released
We are pleased to announce a new public release of Parallelware Analyzer, the first static code analyzer specializing in performance. This version 0.19 introduces two new analyses, one comparing the vectorization capabilities of compilers present in the system and another one focused on functions, as well as significant filtering improvements to enhance the user experience. […]
Case Study: How we made Canny edge detector algorithm run faster? (part 1)
Canny edge detector algorithm is a famous algorithm in image processing. One of our customers was inquiring about the performance of that algorithm, so our performance engineers took a look. As always when dealing with unfamiliar codebases, we didn’t know what to expect. Some algorithms have a lot of room for performance improvements, others don’t. […]
Appentra at SC19 in Denver
Appentra will once again be participating in the International Conference for High Performance Computing, Networking, Storage, and Analysis (SC19), to be held between 17th and 21th of November. Appentra will take part as an Exhibitor in the Startup Café The Startup Café is the place for emerging companies to introduce their products and services to […]
Parallelware Trainer 1.3 released
We’re happy to announce the release of Parallelware Trainer 1.3 which now supports the detection of defects and recommendations for concurrency and parallelism. We expect this new feature to further improve the learning process by providing feedback about code issues right in the integrated editor. Parallelware Trainer provides an enhanced interactive learning environment, including provision […]
OpenACC programming: The OpenACC parallelization process (5/9)
This is the fifth video of our OpenACC programming course based on Appentra’s unique, productivity-oriented approach to learn best practices for parallel programming using OpenACC. Learning outcomes include how to decompose codes into parallel patterns and a practical step-by-step process based on patterns for parallelizing any code. In this video, we explain the incremental approach […]
OpenACC programming: Building and Running an OpenACC code (4/9)
This is the fourth video of our OpenACC programming course based on Appentra’s unique, productivity-oriented approach to learn best practices for parallel programming using OpenACC. Learning outcomes include how to decompose codes into parallel patterns and a practical step-by-step process based on patterns for parallelizing any code. In this video, we explain how to build […]