Category: servers
David Atienza presents SwissChips
Prof. David Atienza presents the national initiative SwissChips and the role of ESL in this massive collaboration. Video by Dr. Alex Levisse and Alex Widerski More on SwissChips: Alex Levisse explains SwissChips in detail ESL participates in three SwissChips projects X-HEEP and SwissChips Yuxuan Wang presents SwissChips project at maiden conference SwissChips official website
Optimising VEGA data with FPGA technology
There are thousands of courses on offer at EPFL, covering topics as far apart as socio-environmental learning, epilepsy monitoring and urban digital twins. We decided to have a closer look at a very special course, one which brings together the three fundamental principles of EPFL Institutes: education, research and industry. Field Programmable Gate Arrays (FPGAs) (…)
Collaboration with University of Bordeaux for structured pruning co-design
Our team collaborated with scientists from the University of Bordeaux to analyze how configuration choices across the stack affect performance metrics. Results demonstrate that structured pruning on systems featuring systolic array acceleration can effectively increase performance, while maintaining high QoS levels. Up to 44% system-wide speedups due to structured pruning and quantization were measured, with (…)
Accelerating the validation process of full systems without sacrificing accuracy
Introducing the first open-source RISC-V-based FS-validated simulation models with a complete and replicable methodology Full-System simulation is essential for performance evaluation of complete systems that execute complex applications on a complete software stack consisting of an operating system and user applications. Nevertheless, they require careful fine-tuning against real hardware to obtain reliable performance statistics, which (…)
Optimizing interconnects with amazing results
One of our teams has rolled out Gem5-AcceSys: an innovative framework for a system-level exploration of standard interconnects and configurable memory hierarchies. A series of tests using this new technology will be presented at the Design Automation Conference in San Francisco. In this study it has been shown that optimized interconnects can achieve up to (…)
ClearSpace will use Minority Report technology from ESL
Satellites are open to attack. All communications systems are vulnerable to hackers by definition, and are protected accordingly, with hardware and software. However, because they reside outside the protection of the Earth’s atmosphere, satellites are perhaps exposed to the mightiest and most unpredictable hacker of all: the Sun. “The Sun’s radiation can affect the data (…)
Innovations using analog in memory cores
A new article has been published showcasing exciting innovations, using AIMC (Analog in memory cores). Recent ESL alumnus Josh Klein, EPFL alumnus Irem Boybat, current ESL senior scientist Giovanni Ansaloni and ESL host professor Marina Zapater collaborated to prepare this exciting new paper, which is published in IEEE Transactions on Parallel and Distributed Systems. The (…)
Predicting the future with CloudProphet
If we are going to reduce the carbon footprint of data centers we need to use computing resources more efficiently. If processes always made use of data center facilities in a regular way, it would be an easy game. However, the resources of a data center are used by customers (more often customers of customers) (…)
Heating Bits – an EPFL collaboration
Five labs are collaborating on Heating Bits, an initiative to get ultimate levels of control over our data centers. Prof. Mario Paolone spoke to EcoCloud in detail about this exciting initiative.
Flavio Ponzina presents paper on edge AI acceleration at Embedded Systems Week
Dr Flavio Ponzina, who recently defended his PhD thesis on Hardware-Software co-design Methodologies for Edge AI Optimization, presented a paper entitled “Overflow-free compute memories for edge AI acceleration” at Embedded Systems Week, which took place in Hamburg. The video of his presentation is below: