industry news
Subscribe Now

Impulse and Convey Enable C-to-FPGA Programming for Hybrid-Core Computing

Bellevue, WA – April 8, 2011 – Impulse Accelerated Technologies today announced the availability of a new C-to-FPGA Platform Support Package (PSP) enabling software programming of Convey computing platforms, including the Convey HC-1ex hybrid-core server. The new PSP allows Convey platform developers with a new, more efficient path from C-language algorithms to FPGA accelerators.

Convey hybrid-core systems, which combine high-performance Intel® processors with closely coupled Xilinx® FPGA devices, provide hybrid, FPGA-accelerated computing. The Convey systems employ “personalities”—application-specific instruction sets that accelerate performance-critical segments of applications. Convey provides turnkey personalities, or users can develop their own using a “Personality Development Kit” in a traditional HDL-based FPGA design flow. With the addition of C-to-FPGA support from Impulse, application developers now have an alternative method of programming the FPGAs, using familiar C-language programming methods and tools.

The Impulse C-to-FPGA tools, when combined with an Impulse PSP, allow application developers to quickly move legacy or newly developed C code into FPGA hardware, through a process of iterative development and optimization. The Impulse compiler helps speed such conversions by performing automatic parallelizing and pipelining of C code, and by enabling parallel application development using an API-driven communicating process programming mode.

“Our research groups have experience with both the Convey HC-1 platform and the Impulse C-to-FPGA tools,” said Professor Peter Athanas of Virginia Tech. “I believe the combination of a datacenter-ready FPGA platform with a C-to-FPGA compiler is an enabler for large-scale, hybrid-core reconfigurable computing.”

According to Brian Durwood, Impulse CEO, “Convey has taken FPGA/processor integration to new levels with its hybrid-core processing systems, combining both processor types in a tightly-integrated server that can scale up from single process acceleration to FPGA-based supercomputing. This new platform support package enables faster, more efficient development of complex applications and algorithms for Convey servers.”

The Impulse C-to-FPGA compiler increases algorithm throughput and lowers power consumption. The integrated solution for Convey platforms combines Impulse compiler-generated hardware kernel functions with C-language access to Convey’s proprietary shared memory accelerator architecture. The Impulse C compiler generates hardware in standard formats, allowing the hardware code to be simulated and mapped to Convey hardware personalities with minimal effort. Applications for the combined platform and compiler include bioinformatics, financial computing, image processing and other data intensive and process intensive computing.

“We like working with Impulse to make the Convey FPGA-accelerated platforms easier to program,” said Bob Masson, Marketing Director at Convey. “The Impulse compiler has an excellent reputation across a number of application domains, and is a perfect complement to our hybrid computing systems.”

Impulse C is the most widely used high level synthesis tool for moving software applications to FPGA coprocessors. Research at the University of Washington benchmarked a 30% reduction in development time in designing in C rather than VHDL. More significantly, the team benchmarked an 80% reduction in iteration time.

About Impulse Accelerated Technologies

Founded in 2002, Impulse C-to-FPGA tools enable developers to quickly offload processing logic to FPGAs. Impulse also provides training and custom solutions. Impulse C has been used to design vision systems, financial feed handlers, and database grid accelerators. Impulse C is used by most federal agencies, most major car manufacturers, Wall Street banks, Japanese image processing firms, most top government contractors, and hundreds of R&D labs worldwide. www.ImpulseAccelerated.com  

About Convey Computer Corporation

Based in Richardson, Texas, Convey Computer breaks power, performance and programmability barriers with the world’s first hybrid-core computer—a system that marries the low cost and simple programming model of a commodity system with the performance of a customized hardware architecture.www.conveycomputer.com 

Leave a Reply

featured blogs
Dec 19, 2024
Explore Concurrent Multiprotocol and examine the distinctions between CMP single channel, CMP with concurrent listening, and CMP with BLE Dynamic Multiprotocol....
Dec 24, 2024
Going to the supermarket? If so, you need to watch this video on 'Why the Other Line is Likely to Move Faster' (a.k.a. 'Queuing Theory for the Holiday Season')....

Libby's Lab

Libby's Lab - Scopes Out Silicon Labs EFRxG22 Development Tools

Sponsored by Mouser Electronics and Silicon Labs

Join Libby in this episode of ā€œLibbyā€™s Labā€ as she explores the Silicon Labs EFR32xG22 Development Tools, available at Mouser.com! These versatile tools are perfect for engineers developing wireless applications with BluetoothĀ®, ZigbeeĀ®, or proprietary protocols. Designed for energy efficiency and ease of use, the starter kit simplifies development for IoT, smart home, and industrial devices. From low-power IoT projects to fitness trackers and medical devices, these tools offer multi-protocol support, reliable performance, and hassle-free setup. Watch as Libby and Demo dive into how these tools can bring wireless projects to life. Keep your circuits charged and your ideas sparking!

Click here for more information about Silicon Labs xG22 Development Tools

featured chalk talk

Machine Learning on the Edge
Sponsored by Mouser Electronics and Infineon
Edge machine learning is a great way to allow embedded devices to run applications that can collect sensor data and locally process that data. In this episode of Chalk Talk, Amelia Dalton and Clark Jarvis from Infineon explore how the IMAGIMOB Studio, ModusToolboxā„¢ Software, and PSoC and AURIXā„¢ microcontrollers can help you develop a custom machine learning on the edge application from scratch. They also investigate how the IMAGIMOB Studio can help you easily develop and deploy AI/ML models and the benefits that the PSoCā„¢ 6 Artificial Intelligence Evaluation Kit will bring to your next machine learning on the edge application design process.
Aug 12, 2024
56,208 views