|
Intel® Array Building Blocks (Intel® ArBB) provides a generalized vector parallel programming solution that frees application developers from dependencies on particular low-level parallelism mechanisms or hardware architectures. It is comprised of a combination of standard C++ library interface and powerful runtime. It produces scalable, portable, and deterministic parallel implementations from a single high-level source description. It is ideal for applications that require data-intensive mathematical computations such as those found in medical imaging, digital content creation, financial analytics, energy, data mining, science and engineering. Intel® ArBB is a component of Intel® Parallel Building Blocks, and complements other Intel developer and parallel programming tools. Intel Array Building Blocks is the combination of Intel’s Ct Technology and RapidMind technology.
Intel Array Building Blocks provides several key benefits for developers:
-
Performance: Programs written with Intel ArBB are scalable and efficient across all cores and vector units (SIMD) allowing them to fully harness available CPU resources. Intel ArBB can offer many times the performance of straight C++ compilation, depending on the algorithm.
-
Productive: Intel ArBB uses C++ language extensions for compatibility with all standard compilers and IDEs, allowing it to easily fit into existing development environments. It offers powerful, compact language constructs to quickly express complex large data structures for vector parallel workloads
-
Forward Scaling: Intel ArBB lets a single-source application work consistently on multiple multicore and manycore processors with different Intel compatible architectures, instruction sets, cache architectures, core counts, and vector widths without requiring developers to rewrite programs over and over. Since code modification or recompilation is not required to take advantage of future architectures, programs written with Intel ArBB are future proofed.
-
Safety: By default, Intel ArBB prevents parallel programming bugs such as data races and deadlocks.
-
Compatibility: Intel ArBB runs on Windows* and Linux*, and supports all standard C++ compilers including Intel, Microsoft Visual C++ and GCC C++ compilers.
Intel ArBB beta is included in Intel® Parallel Building Blocks which is supported by:
|
 |
Beta Program
Intel® Array Building Blocks Beta is now available to download
Steps to participate in the Intel ArBB Beta:
- Complete the required beta questionnaire (click on "Sign up for Beta" button)
- Register, download and install the beta product
- Participate in discussions or submit your questions through the Intel ArBB User Forum
- Provide feedback via the beta survey
Beta support and feedback
Submit problem reports, usage questions and general feedback to the Intel ArBB User Forum. This forum exclusively discusses Intel ArBB related information with other developers and Intel engineers. At the end of beta program a survey will be sent out to all participants. Your feedback and comments are critical to the success of our product and will help drive the future direction of Intel ArBB.
Learn
In-depth Tutorial material delivered at SC'10
Overview video
Product Brief
Product Documentation
Product Support
Article - A Flexible Parallel Programming Model for Multicore and Manycore Architectures
Webinar - Intel ArBB Introduction and Q&A
Webinar – Intel ArBB Code Tips
Case Studies
RTT software calls on Intel's Ct Technology to help transform how automotive manufacturers develop the next generation of cars. Learn more>
Intel’s Ct Technology’s ability to provide near real-time processing algorithms for large data sets will be increasingly important to meet the demands as medical imaging advances. Learn more>
|
“Intel® Array Building Blocks will help us take full advantage of the power of vector parallelism, and Ct’s forward-scaling capability will help us quickly scale our applications into the future.” Xia Zhang, Neusoft CTO
“We believe Intel® Array Building Blocks, including its versatile programming models and capabilities to handle irregular problems, is an exciting new technology that is very promising for data-intensive computing environments such as seismic imaging.”
Laurent Clerc, VP Technology Services , CGGVeritas
“Intel® Array Building Blocks is a breakthrough capability. As the underlying hardware platform evolves, we would like to take advantage of Intel ArBB's ability to scale, so we can build high-performance financial algorithms that protect our investment." Jeffrey M. Birnbaum , Bank of America
“Advances in medical imaging are accompanied by significant increases in the amount of data to be analyzed and processed, both in terms of image resolution and multiple imaging sources. Intel® Array Building Blocks’ ability to provide near real-time processing algorithms for large data sets will be increasingly important to meet these demands." Gal Sela, Chief Technology Officer, Sentinelle Medical
|
|
