Fraunhofer IIS offers JPEG XS plugin for NVIDIA´s Holoscan for Media Architecture
Erlangen, Germany/NAB, Las Vegas -- February 16, 2024 -- The Fraunhofer Institute for Integrated Circuits IIS today announces it has developed JPEG XS plugins and microservices especially designed for seamless data processing and exchange with NVIDIA Holoscan for Media Architecture, a software defined platform that enables developers to easily build and deploy live media applications. By combining Fraunhofer IIS´ JPEG XS SDKs (software development kit) with NVIDIA Holoscan for Media Architecture, developers can realize ubiquitous solutions for cloud and on-premises systems. Both companies combine their strength to allow a direct data transfer from network interface cards (NICs) to graphic cards and Fraunhofer IIS JPEG XS SDKs.
Fraunhofer IIS offers JPEG XS SDKs for various platforms, including x86, Arm and NVIDIA processors. Now, with the inclusion of their new JPEG XS plugins and microservices help expand the NVIDIA Holoscan for Media platform, facilitating seamless data processing and exchange. Holoscan for Media provides a platform for software-defined broadcasting by combining high-performance NICs with graphic cards and application-supporting SDKs. Together with the NVIDIA Rivermax SDK and CUDA toolkits, IP-based solutions including SMPTE ST 2110, AMWA NMOS, RIST and SRT can be built. While Holoscan for Media originally addressed both uncompressed and low-bit-rate streaming workflows, the integration of Fraunhofer´s JPEG XS SDKs provides a way to deliver an IP-based low-latency mezzanine video compression transport.
Developers profit from a ubiquitous solution
By combining these SDKs with NVIDIA Holoscan for Media Architecture, a ubiquitous solution for cloud and on-premises systems can be realized. The Fraunhofer IIS JPEG XS SDKs provide an interface and API that fit directly into the Holoscan for Media platform. If customers want to implement a cloud-based cluster system for ST2110-22 with JPEG XS processing, or an embedded solution using the NVIDIA Jetson platform, this is the ideal way to go.
“This optimized data processing pipeline combines NVIDIA’s expertise in high-data throughput IP interfaces and accelerated computing with the coding technologies of Fraunhofer IIS,” explains Siegfried Foessel, Head of the moving picture technology department at Fraunhofer IIS.
Nir Nitzani, Senior Director of Networking Media and Entertainment Product Marketing Management at NVIDIA, adds: “NVIDIA GPUDirect and Direct Packet Placing allow a direct data transfer from the NIC to the GPU. This is where the Fraunhofer JPEG XS plugin comes in, unpacking and decoding the JPEG XS RTP stream to eliminate time-consuming processing by the CPU and bottlenecks in workflows and data pipelines.” And by using a Docker container-based architecture, the processing and services can be used on many different platforms.
Visit us to get a demo of our SDKs at NAB, Las Vegas Convention Center,
Booth W2857, West Hall.
|
Fraunhofer IIS Hot IP
Related News
- Fraunhofer IIS and IHSE announce their partnership for new JPEG XS implementations at IBC 2023
- Fraunhofer IIS introduces Application Support Package to facilitate JPEG XS Integration
- Fraunhofer IIS and Astrodesign cooperate to offer JPEG XS solutions for video equipment manufacturer
- Fraunhofer IIS announces its JPEG XS SDK 5.0 solutions achieving 25% higher speed for en- and decoding
- Fraunhofer IIS introduces its JPEG XS ultra-low-latency software implementation at NAB 2022
Breaking News
- Breker RISC-V SystemVIP Deployed across 15 Commercial RISC-V Projects for Advanced Core and SoC Verification
- Veriest Solutions Strengthens North American Presence at DVCon US 2025
- Intel in advanced talks to sell Altera to Silverlake
- Logic Fruit Technologies to Showcase Innovations at Embedded World Europe 2025
- S2C Teams Up with Arm, Xylon, and ZC Technology to Drive Software-Defined Vehicle Evolution
Most Popular
- Intel in advanced talks to sell Altera to Silverlake
- Arteris Revolutionizes Semiconductor Design with FlexGen - Smart Network-on-Chip IP Delivering Unprecedented Productivity Improvements and Quality of Results
- RaiderChip NPU for LLM at the Edge supports DeepSeek-R1 reasoning models
- YorChip announces Low latency 100G ULTRA Ethernet ready MAC/PCS IP for Edge AI
- AccelerComm® announces 5G NR NTN Physical Layer Solution that delivers over 6Gbps, 128 beams and 4,096 user connections per chipset
![]() |
E-mail This Article | ![]() |
![]() |
Printer-Friendly Page |