Viewing entries in
External FPGA


Xilinx demos the new VU37P FPGA with embedded HBM DRAM

Virtex UltraScale+ FPGA augmented with co-packaged HBM DRAM operating at full speed (460Gbytes/sec), error-free, on the very first day of silicon bringup
The 2-minute video below shows you an operational Xilinx Virtex UltraScale+ XCVU37P FPGA, which is enhanced with co-packaged HBM (high-bandwidth memory) DRAM using Xilinx’s well-proven, 3rd-generation 3D manufacturing process. (Xilinx started shipping 3D FPGAs way back in 2011, starting with the Virtex-7 2000T and we’ve been shipping these types of devices ever since.)
This video was made on the very first day of silicon bringup for the device and it is already operating at full speed (460Gbytes/sec), error-free, over 32 channels. The Virtex UltraScale+ XCVU37P is one big All Programmable device with:

  • 2852K System Logic Cells
  • 9Mbits of BRAM
  • 270Mbits of UltraRAM
  • 9024 DSP48E2 slices
  • 8Gbytes of integrated HBM DRAM
  • 96 32.75Gbps GTY SerDes transceivers

This will significantly reduce the system power and board size of a Cloud Video Transcoder. This video shows the world's largest and fastest HBM-enabled FPGA up and running error free within the first day of silicon bring up. This Virtex® UltraScale+™ HBM-enabled FPGA provides 460 GB/s integrated memory bandwidth and three million logic cells.



Xilinx FPGA-Powered Public Clouds

At SC17 Huawei unveiled Xilinx FPGA-Powered Cloud Server to North America. See the PR here.  We were part of a video transcoding and machine learning demo which was running on the Xilinx booth at SC17. We also took part in the Heterogeneous High Performance Reconfigurable Computing Workshop (H2RC) as well as the Xilinx Developer Lab: Accelerating Applications on AWS

Xilinx is clearly the market leader when it comes to public Clouds with FPGAs. See the picture below showing 6 public Clouds (source: Xilinx booth at SC17):

Xilinx Public Clouds.jpg





V-Nova & NGCodec Deliver real-time UHDp60 Perseus Plus HEVC encoding on a single FPGA

  • V-Nova PERSEUS™ 2 is the only next generation CODEC format that improves performance and reduces computational requirements
  • NGCodec RealityCodec™ delivers real-time HD HEVC encoding on a single FPGA, significantly reducing encoding cost for the best quality
  • Combined solution, to be showcased at IBC 2017, delivers best in class bitrate reduction & encoding costs to encode real-time UHDp60 on a single FPGA.

London, UK and Sunnyvale, CA, 7 September 2017V-Nova Ltd. & NGCodec® today announced the development of a joint FPGA encoding solution, which will deliver best-in-class UHD video bitrates and encoding cost reductions up to fifty times (50x) when compared against software HEVC - solution running on Amazon Web Services (AWS). The solution will enable broadcasters, operators and service providers to benefit from the most advanced video compression in a very cost effective form factor, reducing the encoding footprint and saving on appliance, power and cloud instances costs. The solution will be showcased for the first time at IBC 2017, on the NGCodec stand #5.B21 and V-Nova stand #11.B30u.

The award-winning V-Nova PERSEUS™ 2 codec addresses the real bottlenecks of IP video delivery, allowing for better viewing experiences across all data networks. Designed to provide enhanced platform support, the solution enables operators to quickly benefit from the core efficiencies of the encoding solution. This is particularly valuable for new broadcasters offering video-hungry services, from HD and UHD TV to social media applications, to benefit from its efficiencies. PERSEUS 2 extends support of H.264 environments to also cover HEVC and VP9 base layers, while maintaining full compatibility with the rest of the delivery workflows, including DRMs, streaming protocols like HLS and DASH, ad-insertion and other processes. Coupled with the Content Delivery Networks (CDN) savings associated with bandwidth and profile reduction, PERSEUS 2 is the most efficient and cost effective codec for next-generation service deployment today.

NGCodec RealityCodec HEVC/H.265 encoders run on FPGAs instead of CPUs in data centers. FPGAs are programmed at the hardware level and hence provide 10x more performance than CPUs. By leveraging FPGAs in public data centers like AWS, encoding costs can be significantly reduced whilst still providing very high compression efficiency.

Leveraging PERSEUS 2’s ability to drastically reduce video encoding requirements alongside the highly performing NGCodec’s RealityCodec, the joint solution will enable broadcasters, operators and service providers to uniquely run a high frame rate UHD encode (UHDp60) in real-time on a single FPGA. This translates into real operational savings, reaching up to fifty times (50x) for an encoding instance in the cloud for an equivalent broadcast-quality result.

“V-Nova PERSEUS 2 has been designed to be the cross-media codec; it consistently delivers best in class performance, regardless of the source file, network or end device,” said Guido Meardi, CEO and co-founder, V-Nova Ltd. “The next generation of PERSEUS supports more platforms than ever, including FPGAs, making it perfectly suited for NGCodec’s RealityCodec encoders. NGCodec RealityCodec is outperforming software encoders at the highest quality settings. The combination of our technologies is able to encode UHD in real-time at 60fps on a single AWS F1 instance, providing dramatic operational savings to help the industry maximize today’s infrastructure and making a business case for new services.”

“V-Nova PERSEUS 2 provides impressive bitrate reductions compared to standard codecs in any given environment,” said Oliver Gunasekara, CEO & Co-founder, NGCodec. “Collaborating with V-Nova means that our joint solution can deliver the best performance at a fraction of the standard costs – a groundbreaking development for the industry. For example, a combined PERSEUS 2 + RealityCodec solution running in a single AWS FPGA instance will provide adaptive bitrate 4K encoding at game-changing low costs and bitrates.”

To book a meeting with NGCodec at IBC Hall 5.B21, please go to

To book a meeting with V-Nova at IBC Hall 11.B30u, please contact


About V-Nova

V-Nova Ltd. is a London-headquartered technology company providing next generation compression solutions to address the ever-growing media processing and delivery challenges. V-Nova provides solutions spanning the entire media delivery chain, including content production, contribution, storage and distribution to end users.

V-Nova’s award-winning PERSEUS™ is the only cross-media codec format and delivers on the promises of next-generation image and video compression, today. Using PERSEUS technology, media and entertainment companies can now monetise unmet consumer demand for higher definition video everywhere, on existing devices and infrastructure, by a simple software upgrade.

PERSEUS is available in multiple formats. PERSEUS Pro, for mathematically lossless and visually lossless professional production and contribution applications. PERSEUS Plus, for high compression efficiency in content distribution to end users, web publishing and cloud applications.

V-Nova’s shareholding comprises of a diversified group of strategic partners in TV & Media, including the satellite operator Eutelsat and leading entertainment company Sky plc. For more information please visit


About NGCodec:

NGCodec® has been in passionate pursuit of next generation video compression since 2012. With the support of investors including Xilinx, NGCodec’s agile startup team has created Reality Codec™, a compressor-decompressor technology optimized for ultra-low latency, high-quality applications. Headquartered in Sunnyvale, California. Learn more at @NGCodec.




Image Matters ORIGAMI Module B20 Video Interview

Image Matters develops innovative, high-performance platforms for extreme imaging applications. The ORIGAMI Module B20 is a future-proof video production solution, designed to provide extreme connectivity and processing power to advanced video applications, with the flexibility to scale to meet future interface requirements.
Video presentation of the Origami B20 module @NAB 2016



Video of AWS CEO announcing the new F1 FPGA Instance

Amazon EC2 F1 is a compute instance with field programmable gate arrays (FPGAs) that you can program to create custom hardware accelerations for your application. F1 instances are easy to program and come with everything you need to develop, simulate, debug, and compile your hardware acceleration code, including an FPGA Developer AMI and Hardware Developer Kit (HDK).



NGCodec Quote in Amazon Press Release on the new F1 instance announcement

“Cloud video encoding is exploding, but traditional software approaches need massive CPU resources and cannot deliver the video quality and latency necessitated by new applications. We have developed a next generation video encoder that, using FPGA hardware acceleration, offers low latency and low cost while maximizing video quality to keep up with today’s broadcasting standards,” said Oliver Gunasekara, Chief Executive Officer and co-founder, NGCodec. “AWS is the first cloud provider to add FPGA instances, which provide massive acceleration. In just three weeks, we ported our RealityCodec™ H.265/HEVC encoder to the new F1 instance type to enable AWS Cloud customers to leverage the benefits of higher video quality, lower latency, and lower cost for live H.265/HEVC video encoding. Updating our install base globally will be as simple as publishing a new Amazon FPGA image and re-launching F1 instances.”

The full Amazon Press Release is here: AWS Announces Seven New Compute Services and Capabilities to Support an Even Wider Range of Workloads