Výsledky vyhledávání - Mathematics of computing Mathematical analysis Numerical analysis Computation of transforms

Design of an energy-efficient accelerator for training of convolutional neural networks using frequency-domain computation Autor Jong Hwan Ko, Mudassar, Burhan, Na, Taesik, Mukhopadhyay, Saibal

“…Convolutional neural networks (CNNs) require high computation and memory demand for training…”
Získat plný text

Accelerating Fourier and Number Theoretic Transforms using Tensor Cores and Warp Shuffles Autor Durrani, Sultan, Chughtai, Muhammad Saad, Hidayetoglu, Mert, Tahir, Rashid, Dakkak, Abdul, Rauchwerger, Lawrence, Zaffar, Fareed, Hwu, Wen-mei

“… To speed things up, fast Fourier transform (FFT) algorithms, which are reduced-complexity formulations for computing the DFT of a sequence, have been proposed and implemented for traditional processors and their corresponding instruction sets…”
Získat plný text

A High-Precision and Low-Cost Approximate Transform Accelerator for Video Coding Autor Hao, Zhijian, Liu, Jiaming, He, Chenlong, Zheng, Qi, Chen, Shushi, Xu, Jinchang, Hao, Yue, Yan, Xiao, Ma, Xiaohua

“…The introduction of multiple transform types in the Versatile Video Coding (VVC) standard has yielded notable encoding gains but also imposed considerable computational burdens…”
Získat plný text

Bitwidth-Optimized Energy-Efficient FFT Design via Scaling Information Propagation Autor Liu, Xinzhe, Chen, Fupeng, Muhamad, Raees Kizhakkumkara, Blinder, David, Nikolova, Dessislava, Schelkens, Peter, Catthoor, Francky, Ha, Yajun

“…The Fast Fourier Transform (FFT) is an efficient algorithm widely used in digital signal processing to transform between the time domain and the frequency domain…”
Získat plný text

A high performance split-radix FFT with constant geometry architecture Autor Kwong, Joyce, Goel, Manish

“…High performance hardware FFTs have numerous applications in instrumentation and communication systems. This paper describes a new parallel FFT architecture…”
Získat plný text

A flexible and fast software implementation of the FFT on the BPE platform Autor Cupaiuolo, Teo, Iacono, Daniele Lo

“…The importance of having an efficient Fast Fourier Transform (FFT) implementation is universally recognized as one of the key enablers for the development of new and more powerful signal processing algorithms…”
Získat plný text

Auto-tuning 3-D FFT library for CUDA GPUs Autor Nukada, Akira, Matsuoka, Satoshi

“…Existing implementations of FFTs on GPUs are optimized for specific transform sizes like powers of two, and exhibit unstable and peaky performance i.e…”
Získat plný text

Interconnection Networks for Scalable Quantum Computers Autor Isailovic, Nemanja, Patel, Yatish, Whitney, Mark, Kubiatowicz, John

“… We also explore the control requirements for such a network. Finally, we propose a specific routing architecture and simulate the Quantum Fourier Transform…”
Získat plný text

Exploring irregular time series through non-uniform fast Fourier transform Autor Song, Jung Heon, de Prado, Marcos López, Simon, Horst D., Wu, Kesheng

“…Most popular analysis tools on time series require the data to be taken at uniform time intervals…”
Získat plný text

Standby power optimization via transistor sizing and dual threshold voltage assignment Autor Ketkar, Mahesh, Sapatnekar, Sachin S.

“… Based on an analysis of the effects of these two transforms on the delay and leakage, we justify a two-step procedure for performing this optimization…”
Získat plný text

FFT program generation for shared memory: SMP and multicore Autor Franchetti, Franz, Voronenko, Yevgen, Püschel, Markus

“… transforms such as the discrete Fourier transform (DFT). We present a shared memory extension of Spiral…”
Získat plný text

A 32x32x32, spatially distributed 3D FFT in four microseconds on Anton Autor Young, Cliff, Bank, Joseph A., Dror, Ron O., Grossman, J. P., Salmon, John K., Shaw, David E.

“… are aware. Achieving this FFT performance requires a coordinated combination of computation and communication techniques that leverage Anton's underlying hardware mechanisms…”
Získat plný text

Tera-Scalable Algorithms for Variable-Density Elliptic Hydrodynamics with Spectral Accuracy Autor Cook, Andrew W., Cabot, William H., Williams, Peter L., Miller, Brian J., Supinski, Bronis R. de, Yates, Robert K., Welcome, Michael L.

“…We describe Miranda, a massively parallel spectral/compact solver for variabledensity incompressible flow, including viscosity and species diffusivity effects…”
Získat plný text

Energy-optimized image communication on resource-constrained sensor platforms Autor Lee, Dong-U, Kim, Hyungjin, Tu, Steven, Rahimi, Mohammad, Estrin, Deborah, Villasenor, John D.

“… JPEG compression computations are mapped onto various resource-constrained sensor platforms using a design environment that allows computation using the minimum integer and fractional bit-widths…”
Získat plný text

Architectures and APIs: assessing requirements for delivering FPGA performance to applications Autor Underwood, Keith D., Hemmert, K. Scott, Ulmer, Craig

“…Reconfigurable computing leveraging field programmable gate arrays (FPGAs) is one of many accelerator technologies that are being investigated for application to high performance computing (HPC…”
Získat plný text

High performance discrete Fourier transforms on graphics processors Autor Govindaraju, Naga K., Lloyd, Brandon, Dotsenko, Yuri, Smith, Burton, Manferdelli, John

“…We present novel algorithms for computing discrete Fourier transforms with high performance on GPUs…”
Získat plný text

Using Wavelets to Classify Documents Autor Xexéo, Geraldo, Souza, Jano de, Castro, Patrícia F., Pinheiro, Wallace A.

“…Currently, Fourier and cosine discrete transformations are used to classify documents. This article proposes a new strategy that uses wavelets in the…”
Získat plný text

Spatial correlation extraction via random field simulation and production chip performance regression Autor Liu, Bao

“…Statistical timing analysis needs a priori knowledge of process variations. Lack of such a priori knowledge of process variations prevents accurate statistical…”
Získat plný text

Bandwidth intensive 3-D FFT kernel for GPUs using CUDA Autor Nukada, Akira, Ogata, Yasuhiko, Endo, Toshio, Matsuoka, Satoshi

“…Most GPU performance "hypes" have focused around tightly-coupled applications with small memory bandwidth requirements e.g., N-body, but GPUs are also…”
Získat plný text

Methods for Efficient, High Quality Volume Resampling in the Frequency Domain Autor Li, Aili, Mueller, Klaus, Ernst, Thomas

“…Resampling is a frequent task in visualization and medical imaging. It occurs whenever images or volumes are magnified, rotated, translated, or warped…”
Získat plný text