SubsidieMeestersFast Matrix Multiplication for AI
Developing patented methods for faster and energy-efficient matrix multiplication in software and hardware to enhance AI applications and capitalize on business opportunities.
Projectdetails
Introduction
Matrix multiplication consumes a huge amount of resources: computing time and energy, primarily in AI applications. The industry has recognized the need for faster and more energy-efficient matrix multiplication with state-of-the-art solutions in software and hardware.
Current Solutions
-
Software Solutions:
- DGEMM of Intel's math kernel library (MKL) for CPU
- NVIDIA's CUDA for GPU
-
Hardware Solutions:
- Google's TPU
- Intel / Habana Labs Gaudi accelerator
Limitations of Existing Solutions
Unfortunately, all present solutions employ a wasteful cubic-time algorithm.
Our Innovations
We have developed methods that provide speedup for matrix multiplication in both software and hardware. The novel developments of Prof. Oded Schwartz and his strong team are based on years of research and are protected by several patents.
Funding Request
The funds are requested to pursue this business opportunity.
Financiële details & Tijdlijn
Financiële details
| Subsidiebedrag | € 150.000 |
| Totale projectbegroting | € 150.000 |
Tijdlijn
| Startdatum | 1-4-2023 |
| Einddatum | 30-9-2024 |
| Subsidiejaar | 2023 |
Partners & Locaties
Projectpartners
- THE HEBREW UNIVERSITY OF JERUSALEMpenvoerder
Land(en)
Vergelijkbare projecten binnen European Research Council
| Project | Regeling | Bedrag | Jaar | Actie |
|---|---|---|---|---|
Reducing Carbon Footprint for Generative AIThe project aims to reduce the energy consumption and carbon footprint of generative AI systems by implementing more efficient matrix multiplication algorithms, potentially saving 40-50% energy while maintaining performance. | ERC Proof of... | € 150.000 | 2023 | Details |
The Complexity of Dynamic Matrix ProblemsThis project aims to enhance dynamic data structures for efficient matrix operations, optimizing algorithms in both convex and non-convex settings, particularly for deep neural networks and AI applications. | ERC Starting... | € 1.439.413 | 2022 | Details |
Outplaying the hardware lottery for embedded AIThe BINGO project aims to revolutionize embedded AI by enabling rapid customization of heterogeneous compute platforms using prefabricated chiplets, achieving 100x efficiency gains in days. | ERC Consolid... | € 1.995.750 | 2023 | Details |
ANalogue In-Memory computing with Advanced device TEchnologyThe project aims to develop closed-loop in-memory computing (CL-IMC) technology to significantly reduce energy consumption in data processing while maintaining high computational efficiency. | ERC Advanced... | € 2.498.868 | 2023 | Details |
Analyzing and Exploiting Inexactness in Exascale Matrix ComputationsThis project aims to develop a holistic framework for analyzing and exploiting multiple sources of inexactness in matrix computations to enhance algorithm performance and accuracy for exascale applications. | ERC Starting... | € 1.496.085 | 2023 | Details |
Reducing Carbon Footprint for Generative AI
The project aims to reduce the energy consumption and carbon footprint of generative AI systems by implementing more efficient matrix multiplication algorithms, potentially saving 40-50% energy while maintaining performance.
The Complexity of Dynamic Matrix Problems
This project aims to enhance dynamic data structures for efficient matrix operations, optimizing algorithms in both convex and non-convex settings, particularly for deep neural networks and AI applications.
Outplaying the hardware lottery for embedded AI
The BINGO project aims to revolutionize embedded AI by enabling rapid customization of heterogeneous compute platforms using prefabricated chiplets, achieving 100x efficiency gains in days.
ANalogue In-Memory computing with Advanced device TEchnology
The project aims to develop closed-loop in-memory computing (CL-IMC) technology to significantly reduce energy consumption in data processing while maintaining high computational efficiency.
Analyzing and Exploiting Inexactness in Exascale Matrix Computations
This project aims to develop a holistic framework for analyzing and exploiting multiple sources of inexactness in matrix computations to enhance algorithm performance and accuracy for exascale applications.
Vergelijkbare projecten uit andere regelingen
| Project | Regeling | Bedrag | Jaar | Actie |
|---|---|---|---|---|
n-ary spintronics-based edge computing co-processor for artificial intelligenceMultiSpin.AI aims to revolutionize edge computing by developing a neuromorphic AI co-processor that enhances energy efficiency and processing speed, enabling transformative applications while reducing CO2 emissions. | EIC Pathfinder | € 3.143.276 | 2024 | Details |
Ontwikkeling driefasen-matrix converteri2Motion onderzoekt de ontwikkeling van een driefasen-matrix converter voor efficiënte energiebeheer en aansturing van elektrische aandrijvingen. | Mkb-innovati... | € 20.000 | 2020 | Details |
A novel hardware & software platform to revolutionise artificial intelligence at the edgeDeveloping a scalable hardware and software platform for efficient edge AI inference, targeting computer vision and NLP, to drive adoption with reduced costs and power consumption. | EIC Accelerator | € 2.499.999 | 2024 | Details |
Scalable Unified Processor Enhancing Revolutionary Computing, Harnessing Integrated Performance for Edge AI, Autonomous Driving, Generative AI, and Decentralized AIoT ApplicationsDeveloping the Tyr chip to enable real-time, efficient processing for Level 4/5 autonomous driving, addressing current data and processing limitations in the industry. | EIC Accelerator | € 2.499.999 | 2023 | Details |
Evolutionary Machine Engineering powered by AIAtlas ontwikkelt een SaaS-applicatie die engineers ondersteunt bij het selecteren en doorrekenen van machinecomponenten, wat leidt tot efficiënter ontwerp en duurzaamheid in de maakindustrie. | Mkb-innovati... | € 350.000 | 2023 | Details |
n-ary spintronics-based edge computing co-processor for artificial intelligence
MultiSpin.AI aims to revolutionize edge computing by developing a neuromorphic AI co-processor that enhances energy efficiency and processing speed, enabling transformative applications while reducing CO2 emissions.
Ontwikkeling driefasen-matrix converter
i2Motion onderzoekt de ontwikkeling van een driefasen-matrix converter voor efficiënte energiebeheer en aansturing van elektrische aandrijvingen.
A novel hardware & software platform to revolutionise artificial intelligence at the edge
Developing a scalable hardware and software platform for efficient edge AI inference, targeting computer vision and NLP, to drive adoption with reduced costs and power consumption.
Scalable Unified Processor Enhancing Revolutionary Computing, Harnessing Integrated Performance for Edge AI, Autonomous Driving, Generative AI, and Decentralized AIoT Applications
Developing the Tyr chip to enable real-time, efficient processing for Level 4/5 autonomous driving, addressing current data and processing limitations in the industry.
Evolutionary Machine Engineering powered by AI
Atlas ontwikkelt een SaaS-applicatie die engineers ondersteunt bij het selecteren en doorrekenen van machinecomponenten, wat leidt tot efficiënter ontwerp en duurzaamheid in de maakindustrie.