LV: Latency-Versatile Floating-Point Engine for High-Performance Deep Neural Networks.
Yun-Chen LoYu-Chih TsaiRen-Shuo LiuPublished in: IEEE Comput. Archit. Lett. (2023)
Keyphrases
- floating point
- neural network
- low latency
- fixed point
- graphics processing units
- square root
- memory bandwidth
- left ventricle
- deformable models
- instruction set
- floating point arithmetic
- sparse matrices
- interval arithmetic
- left ventricular
- prefetching
- data processing
- wall motion
- response time
- artificial neural networks
- fast fourier transform
- probabilistic model