Search results

• Vector Processor for In-Memory Computing
  architectures has already been around for decades, but so far it has not been viable on an industrial scale. Recent developments in process technolo
  3 KB (443 words) - 13:10, 2 November 2015
• AMZ Driverless Competition Embedded Systems Projects
  ===Status: Available === (''not all need to be met'' by the single candidate)
  6 KB (895 words) - 16:27, 30 October 2020
• Accelerating Applications Relying on Matrix-Vector-Product-Like Operations
  ...ddressable Memory) [1] is a hardware accelerator that aims at accelerating not only matrix-vector products, but also other, similarly structured operation ...lement several more applications to be accelerated by PPAC, including (but not limited to) locality sensitive hashing, decoding using the recently propose
  7 KB (804 words) - 19:45, 21 November 2021
• CPS Software-Configurable State-Machine
  To save power, this unit will not be a conventional fully synchronously clocked design: the configurable stat ===Status: Available ===
  3 KB (418 words) - 11:24, 10 November 2017
• Efficient collective communications in FlooNoC (1M)
  ...would benefit from hardware support for collective communications but may not be able to afford separate, dedicated networks due to routing and area cost ...ect with a hierarchy of AXI XBARs is very limiting in scalability. AXI was not intended for large systems with a deep hierarchy, where master and slave co
  6 KB (897 words) - 19:52, 22 February 2024
• MCU Bus and Memory Generator: implementation of a Highly Configurable bus and memory subsystem for a RISC-V based microcontroller.
  Do not worry, the work it is not done twice, most of the IPs are actually the same. If you want to work on this project, but you think that you do not match some the required skills, we can give you some preliminary exercise t
  8 KB (1,304 words) - 14:44, 23 October 2023
• Smart Virtual Memory Sharing
  While heterogeneously shared virtual memory (SVM) is still not a high-end, high-performance GPGPUs, it is probably not affordable for PMCAs
  6 KB (865 words) - 12:16, 17 November 2017
• Learning Image Compression with Convolutional Networks
  ...ce aspect of this application is that the usually limited training data is not an issue, since randomly acquired images our the internet can be used to tr ===Status: {Available, Reserved, In Progress, Completed}===
  3 KB (362 words) - 16:25, 30 October 2020
• Optimal routing for 2D Mesh-based Analog Compute-In-Memory Accelerator Architecture (IBM-Zurich)
  ...tudies for decades and a wide variety of open-source libraries are already available. * Interest in FPGAs and/or digital synthesis flows (note that work will not be with FPGAs or digital synthesis, but applying applicable routing algorit
  3 KB (356 words) - 14:53, 11 October 2023
• Advanced 5G Repetition Combining
  ...y 20 dB. For the so-called PBCH this is especially difficult, since it has not been changed from legacy LTE. While it is transmitted continuously, the dat ===Status: Available ===
  3 KB (345 words) - 10:52, 5 April 2022
• Ultra-low power processor design
  ...ionality which will never be used in the target system and it is therefore not necessary to maintain all this functionality. Removing caches, IMMU, DMMU, ..., at least one processor will have to wait(stall) until the memory becomes available. To simulate such a miss in a single core structure, an acknowledge will be
  10 KB (1,669 words) - 19:01, 30 January 2014
• Heterogeneous SoCs
  ...r|Uniting many ICs in a single one: Heterogeneous integration has allowed (not only) Apple to get high computing performance under tight power constraints ==Available Projects==
  3 KB (421 words) - 18:41, 28 October 2020
• Noise Figure Measurement for Cryogenic System
  However, it is not trivial to set up cryogenic environment for high frequency (GHz) measuremen [[Category:Available]]
  2 KB (372 words) - 10:32, 14 February 2023
• Design study of tunneling transistors based on a core/shell nanowire structures
  ...eld-effect transistors (MOSFETs), the sub-threshold slope (SS) of TFETs is not limited to 60 mV/dec at room temperature, but could theoretically be reduce ===Status: Available ===
  3 KB (357 words) - 15:38, 4 September 2019
• LightProbe - Thermal-Power aware on-head Beamforming
  ...ct with human skin. Thus it must be able to throttle it's performance when not needed, e.g. , a 30 fps image is sufficient to find the right placement of ===Status: Available ===
  3 KB (374 words) - 20:50, 12 November 2020
• Computation of Phonon Bandstructure in III-V Nanostructures
  ...rm can be treated using Ewald's summation method in bulk structures, it is not clear how to handle it in nanostructures without too much increasing the co ===Status: Available ===
  3 KB (363 words) - 15:37, 4 September 2019
• Enhancing our DMA Engine with Vector Processing Capabilities (1-2S/B)
  ...lar multiplication, scalar addition, and logical operations (AND, OR, XOR, NOT)
  3 KB (384 words) - 12:13, 21 June 2022
• Graph neural networks for epileptic seizure detection
  ...ementary to this approach, efficient and robust algorithms are required to not only detect the seizure onset but also to identify the ictogenic (i.e. seiz ===Status: Currently Not Available ===
  10 KB (1,306 words) - 19:58, 10 March 2024
• Satellite Internet of Things
  ...verage features, truely world-wide coverage using those technologies would not be viable from an economical point of view. Satellite-borne communication s ===Status: Available ===
  3 KB (393 words) - 13:53, 13 November 2020
• Minimum Variance Beamforming for Wearable Ultrasound Probes
  ...f the acquired ultrasound images. Standard beamforming techniques are thus not well suited to obtain higher image qualities.
  3 KB (378 words) - 16:57, 16 September 2022

View (previous 20 | next 20) (20 | 50 | 100 | 250 | 500)