ARM Extends OpenCL to the ARM Cortex-A Processor Family
September 30, 2014 -- Today ARM® announced OpenCL™ for ARM NEON™ technology. This enables the use of the OpenCL framework on ARM Cortex®-A processors. Alongside the already supported ARM Mali™ GPUs, OpenCL for NEON now enables heterogeneous multiprocessing on any Cortex-A based device. Heterogeneous multiprocessing enables compute-intensive workloads to be tasked to the most appropriate CPU or GPU resource improving both end-user experience and battery life.
Why:
As demand for mobile computing resources continues to grow, programmers face the challenge of finding smarter ways of running advanced applications without using too much battery power. The OpenCL framework enables efficient general purpose parallel compute on heterogeneous multiprocessor platforms. OpenCL enables the most efficient processor for the appropriate task. Modern platforms typically include a CPU and a GPU, it is therefore important to support OpenCL for NEON technology and Mali GPUs.
When used in conjunction with ARM DS-5 Development Studio Streamline, OpenCL for NEON enables programmers to effortlessly identify the right processor for task execution and utilize their resources in an improved manner. Examples of workloads that will benefit from heterogeneous multiprocessing include:
- Mobile
- Image stabilization, editing, correction and enhancement
- Face, smile and landmark recognition
- Computer vision, augmented reality
- Digital TV
- Upscaling, conversion from 2D to Stereo 3D
- Support for emerging codec standards
- Pre and Post-processing (stabilize, transcode, color-conversion)
- User interfaces, multi-viewer gesture-based UI and speech
- Automotive
- Advanced Driver Assistance Systems (ADAS)
- Lane departure, collision warning and pedestrian detection
When:
OpenCL for NEON is available for licensing today.
Click here to find out more about ARM OpenCL for NEON.
Who:
ARM is at the heart of the world's most advanced digital products. Our technology enables the creation of new markets and transformation of industries and society. We design scalable, energy efficient-processors and related technologies to deliver the intelligence in applications ranging from sensors to servers, including smartphones, tablets, enterprise infrastructure and the Internet of Things.
Our innovative technology is licensed by ARM Partners who have shipped more than 50 billion System on Chip (SoCs) containing our intellectual property since the company began in 1990. Together with our Connected Community, we are breaking down barriers to innovation for developers, designers and engineers, ensuring a fast, reliable route to market for leading electronics companies. Learn more and join the conversation at http://community.arm.com.
|
Arm Ltd Hot IP
Related News
- Mindspeed Announces High-Performance, Multi-Core ARM Cortex-A CPU-Based Communications Processor Family
- The most versatile and high-performing RTOS yet by Enea for ARM-based architectures
- PathPartner Technology Announces HEVC (H.265) Decoder on ARM Cortex-A Family Processors
- Latest Linaro GCC Toolchain Release Supports Full Range of ARM Cortex-A Processors
- TI announced as the first licensee of the next generation ARM Cortex-A series processor core
Breaking News
- RISC-V International Promotes Andrea Gallo to CEO
- See the 2025 Best Edge AI Processor IP at the Embedded Vision Summit
- Andes Technology Showcases RISC-V AI Leadership at RISC-V Summit Europe 2025
- RISC-V Royalty-Driven Revenue to Exceed License Revenue by 2027
- Keysom Unveils Keysom Core Explorer V1.0
Most Popular
- RISC-V Royalty-Driven Revenue to Exceed License Revenue by 2027
- SiFive and Kinara Partner to Offer Bare Metal Access to RISC-V Vector Processors
- Imagination Announces E-Series: A New Era of On-Device AI and Graphics
- Siemens to accelerate customer time to market with advanced silicon IP through new Alphawave Semi partnership
- Cadence Unveils Millennium M2000 Supercomputer with NVIDIA Blackwell Systems to Transform AI-Driven Silicon, Systems and Drug Design
![]() |
E-mail This Article | ![]() |
![]() |
Printer-Friendly Page |