Zobrazeno 1 - 10
of 1 015
pro vyhledávání: '"A. P. Dimitrakopoulos"'
Autor:
Tsintari, P., Dimitrakopoulos, N., Garg, R., Hermansen, K., Marshall, C., Montes, F., Perdikakis, G., Schatz, H., Setoodehnia, K., Arora, H., Berg, G. P. A., Bhandari, R., Blackmon, J. C., Brune, C. R., Chipps, K. A., Couder, M., Deibel, C., Hood, A., Gamage, M. Horana, Jain, R., Maher, C., Miskovitch, S., Pereira, J., Ruland, T., Smith, M. S., Smith, M., Sultana, I., Tinson, C., Tsantiri, A., Villari, A., Wagner, L., Zegers, R. G. T.
The synthesis of heavy elements in supernovae is affected by low-energy (n,p) and (p,n) reactions on unstable nuclei, yet experimental data on such reaction rates are scarce. The SECAR (SEparator for CApture Reactions) recoil separator at FRIB (Facil
Externí odkaz:
http://arxiv.org/abs/2411.03338
Multi-term floating-point addition appears in vector dot-product computations, matrix multiplications, and other forms of floating-point data aggregation. A critical step in multi-term floating point addition is the alignment of fractions of the floa
Externí odkaz:
http://arxiv.org/abs/2410.21959
The widespread adoption of machine learning algorithms necessitates hardware acceleration to ensure efficient performance. This acceleration relies on custom matrix engines that operate on full or reduced-precision floating-point arithmetic. However,
Externí odkaz:
http://arxiv.org/abs/2408.11997
Structured sparsity is an efficient way to prune the complexity of modern Machine Learning (ML) applications and to simplify the handling of sparse data in hardware. In such cases, the acceleration of structured-sparse ML models is handled by sparse
Externí odkaz:
http://arxiv.org/abs/2402.10850
Transformers have improved drastically the performance of natural language processing (NLP) and computer vision applications. The computation of transformers involves matrix multiplications and non-linear activation functions such as softmax and GELU
Externí odkaz:
http://arxiv.org/abs/2402.10118
Structured sparsity has been proposed as an efficient way to prune the complexity of modern Machine Learning (ML) applications and to simplify the handling of sparse data in hardware. The acceleration of ML models - for both training and inference -
Externí odkaz:
http://arxiv.org/abs/2311.07241
Autor:
Marshall, C., Meisel, Z., Montes, F., Wagner, L., Hermansen, K., Garg, R., Chipps, K. A., Tsintari, P., Dimitrakopoulos, N., Berg, G. P. A., Brune, C., Couder, M., Greife, U., Schatz, H., Smith, M. S.
Absolute cross sections measured using electromagnetic devices to separate and detect heavy recoiling ions need to be corrected for charge state fractions. Accurate prediction of charge state distributions using theoretical models is not always a pos
Externí odkaz:
http://arxiv.org/abs/2309.02991
The widespread proliferation of deep learning applications has triggered the need to accelerate them directly in hardware. General Matrix Multiplication (GEMM) kernels are elemental deep-learning constructs and they inherently map onto Systolic Array
Externí odkaz:
http://arxiv.org/abs/2309.02969
Systolic Array (SA) architectures are well suited for accelerating matrix multiplications through the use of a pipelined array of Processing Elements (PEs) communicating with local connections and pre-orchestrated data movements. Even though most of
Externí odkaz:
http://arxiv.org/abs/2304.12691
The acceleration of deep-learning kernels in hardware relies on matrix multiplications that are executed efficiently on Systolic Arrays (SA). To effectively trade off deep-learning training/inference quality with hardware cost, SA accelerators employ
Externí odkaz:
http://arxiv.org/abs/2304.01668