Home > Authorities > Grants > Record #341824 > print

001     341824
005     20230827173327.0
024 7 _ |a G:(EU-Grant)101113120
|d 101113120
|2 CORDIS
024 7 _ |a G:(EU-Call)ERC-2022-POC2
|d ERC-2022-POC2
|2 CORDIS
024 7 _ |a corda_____he::101113120
|2 originalID
035 _ _ |a G:(EU-Grant)101113120
150 _ _ |a Fast Matrix Multiplication for AI
|y 2023-04-01 - 2024-09-30
372 _ _ |a ERC-2022-POC2
|s 2023-04-01
|t 2024-09-30
450 _ _ |a FMMF-AI
|w d
|y 2023-04-01 - 2024-09-30
510 1 _ |0 I:(DE-588b)5098525-5
|a European Union
|2 CORDIS
680 _ _ |a Matrix multiplication consumes 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 (e.g., DGEMM of Intel's math kernel library (MKL) for CPU and NVIDIA's CUDA for GPU) and hardware (e.g., Google's TPU and Intel / Habana labs Gaudi accelerator). Unfortunately, all present solutions employ a wasteful cubic-time algorithm. We have developed methods that provide speedup for matrix multiplication in SW and in HW. The novel developments of Prof. Oded Schwartz and his strong team are based on years of research, and are protected by several patents. The funds are requested to pursue business opportunity.
909 C O |o oai:juser.fz-juelich.de:1011183
|p authority:GRANT
|p authority
909 C O |o oai:juser.fz-juelich.de:1011183
980 _ _ |a G
980 _ _ |a CORDIS
980 _ _ |a AUTHORITY

LibraryCollectionCLSMajorCLSMinorLanguageAuthor
Marc 21