System on Chip Design
System on Chip (SoC) vereint Mikroprozessoren, funktionsspezifische Peripherie- oder Codec-Bausteine sowie meistens auch frei programmierbare Logik (FPGA) auf einem gemeinsamen Silizium-Chip. Damit lassen sich äusserst leistungsfähige, flexible und zudem kostengünstige Systeme mit schneller Datenverarbeitung und Datenübertragung herstellen. Das InES fokussiert in diesem Schwerpunkt auf das Zusammenspiel von Hardware und Software innerhalb von SoCs, insbesondere auf die Architektur, den Entwurf und die Programmierung von SoCs mit frei programmierbarer Logik.

Programmierbare Logik hat heutzutage weitgehend applikationsspezifische integrierte Schaltungen sowie Gate Arrays ersetzt. Grund dafür sind die geringen «Non-recurring Expenses» und die Möglichkeit, Hardware und Software im Feld zu aktualisieren.
Wegen der hohen Umsatzzahlen konnten die führenden Hersteller von programmierbarer Logik ausgedehnte Forschung betreiben und ihre Produkte ausbauen. So sind neben zahlreicher, in Makrozellen konfigurierbarer IPs, so genannte Softcore-Prozessoren und viele fest eingebaute Hochleistungsfunktionen standardmässig integriert. Beispiele sind GBit-Chip-zu-Chip-Kommunikation, Dual-Core-RISC-Prozessoren und Speichercontroller. Die Architekturen und Entwicklungswerkzeuge dazu werden immer anspruchsvoller. Somit werden Ingenieure, die FPGA-Schaltungen formal entwerfen und verifizieren können, zu Spezialisten. Das InES forscht an netzwerkorientierten Geräten, bei denen der Einsatz von FPGAs ein zentraler Bestandteil ist. Typische InES-Projekte, bei denen FPGAs eingesetzt werden, sind ein redundantes Kommunikationssystem entlang Bahngleisen, Audio/Video Switching über Wide Area Networks und Bildwiedergabe in medizinischen Geräten.
Embedded High Performance Multimedia Blog
-
BLOG
Running Artificial Intelligence Algorithms Directly on Jetson Nano and Microcontrollers
Running artificial intelligence (AI) algorithms, such as neural networks, directly on embedded devices has many advantages compared to running them in the cloud: One can save significant amounts of ...
gelk
-
BLOG
USBC2: USB-C Two Port Card
USBC2: USB-C Two Port Card Technical Data: USB Type-C V1.0Uses Xavier AGX USB MACs Availability: In stock, request quote
gelk
-
BLOG
NWG1: 1Gbit Ethernet Card
Technical Data: GbE transceiver1000BASE-T, 100BASE-TX and 10BASE-TBased on Marvel 88E1512 Availability: In Stock, request a quote
gelk
-
BLOG
FPDI4: FPD-Link III four Input Card
FPDI4: FPD-Link III four Input Card Technical Data: CSI-2 data rate scalable to 400/800 Mbps/1.5 Gbps/1.6 GbpsAllows connection of four active sensorsPower over coaxSupports single ended coaxial ...
gelk
-
BLOG
HDMI4KO2: 4k HDMI two Output Card
HDMI4KO2: 4k HDMI two Output Card Technical Data: 2 x HDMI Type A HDMI2.04k@60fps Availability: In stock, request a quote
gelk
-
BLOG
AGXC512: Modular Carrier Board for NVIDIA Jetson AGX
AGXC512:Modular Carrier Board for NVIDIA Jetson AGX(Jetson AGX and carrier boards not included) Technical Data: Power 12V1 x HDMI2.0 Output1 x USB 3.01 x USB 2.01 x USB-C1 x PCIe E-Key slot2 x ...
gelk
-
BLOG
HDMI4KI2: 4k HDMI two Input Card
Technical Data: HDMI2.0b, HDMI1.4compliant with HDCP2.24k@30fps2k@ 60fpsYcBCr4:2:2, 16/20/24-bitRGB, 16/20/24-bitBased on Lontium LT6911UXCNVIDIA Jetson driver available Availability: In Stock, ...
gelk
-
BLOG
Jamulus-Direct low latency music performance application for RaspberryPi 4
The Institute of Embedded Systems (InES) High Performance Multimedia group generated a low latency version of the classic Jamulus music rehearsal application for the Raspberry Pi 4 The classic ...
gelk
-
BLOG
Nvidia Xavier-AGX Multimedia Prototyping System
The Institute of Embedded Systems (InES) at ZHAW, with great experience in hardware development for NVIDIA computing modules, developed a rapid prototyping system for the NVIDIA Xavier AGX. To ...
gelk
-
BLOG
Linux Driver for the LT6911UXC HDMI to MIPI CSI-2 Converter
The ZHAW Institute of Embedded Systems (InES), High Performance Multimedia Group, developed a 4k video for Linux driver for the Lontium LT6911UXC HDMI to MIPI CSI-2 converter IC.The driver was written ...
gelk
-
BLOG
Secure Boot Concept for the Zynq Ultrascale+ MPSoC
The complexity of today’s multiprocessor System-on-Chip (MPSoC) can lead to major security risks in embedded designs, as the available security functions are often not or insufficiently utilized. ...
gelk
-
BLOG
Linux Driver for TI DS90UB95x FPD-Link III serializer and deserializer
The Institute of Embedded Systems at ZHAW developed a driver for the deserializer DS90UB954 and serializer DS90UB953 from Texas Instruments. The driver was tested on the RaspberryPi 4, NVIDIA Nano ...
gelk
-
BLOG
Power over Coax FPD-Link III Link Streaming Adapter for Raspberry PI CSI-Interface
The Institute of Embedded Systems at ZHAW has developed an open source adapter which allows streaming of a CSI-2 Camera interface to a Raspberry Pi. This allows connecting cameras with CSI interface ...
gelk
-
BLOG
Deep Learning for Classifying Food Waste
Amin MazloumianHans-Joachim GelkeMatthias Rosenthal Institute of Embedded Systems Zurich University of Applied Sciences Zurich, Switzerland amin.mazloumian@zhaw.ch One third of food produced in ...
gelk
-
BLOG
Artificial Intelligence on Microcontrollers
Using artificial intelligence algorithms, specifically neural networks on microcontrollers offers several possibilities but reveals challenges: limited memory, low computing power and no operating ...
rosn
-
BLOG
ZNNN the Framework to Port Neural Networks to FPGA
BY TOBIAS WELTI AND HANS-JOACHIM GELKE Due to their hardware architecture, Field Programmable Gate Arrays (FPGAs) are optimally suited for the execution of machine learning algorithms. These ...
gelk
-
BLOG
Interfacing FPD-Link III to a x86-PC via PCI Express
FPD-Link III tp PCIe Interface A computer with a GPU combined with an FPGA is a powerful tool for high speed video processing. An FPGA can preprocess multiple video streams in realtime and then ...
gelk
-
BLOG
Direct communication between FPGA and GPU using Frame Based DMA (FDMA)
By Philipp Huber, Hans-Joachim Gelke, Matthias Rosenthal GPUs with their immense parallelization are best fitted for real-time video and signal processing. However, in a real-time system, the ...
gelk
-
BLOG
IntEdgPerf: A new AI benchmark for embedded processors
IntEdgPerf is a new benchmark for running machine learning algorithms on embedded devices. It was developed at the Institute of Embedded Systems (InES) at the Zürich University of Applied Sciences. ...
rosn
-
BLOG
Machine learning on Cortex-M4 using Keras and ARM-CMSIS-NN
We have developed a simple software to show how a custom keras model can be automatically translated into c-code. The generated c-code can, in combination with the ARM-CMSIS-NN functions, be used to ...
rosn