K
Kazimierz Wiatr
Researcher at AGH University of Science and Technology
Publications - 130
Citations - 612
Kazimierz Wiatr is an academic researcher from AGH University of Science and Technology. The author has contributed to research in topics: Field-programmable gate array & Reconfigurable computing. The author has an hindex of 13, co-authored 126 publications receiving 574 citations. Previous affiliations of Kazimierz Wiatr include University of Science and Technology & Atlantic General Hospital.
Papers
More filters
Proceedings ArticleDOI
Constant coefficient multiplication in FPGA structures
Kazimierz Wiatr,Ernest Jamro +1 more
TL;DR: Investigates different architectures implementing bit-parallel constant-coefficient multiplication in FPGA structures, and a novel algorithm for the conversion from two's-complement to CSD representation is presented.
BookDOI
Building a National Distributed e-Infrastructure–PL-Grid
TL;DR: A comparison of two Designed Approaches with Regard toComputational Infrastructures A Toolkit for Storage QoS Provisioning for Data-Intensive Applications Implementation of Service Level Management in PL-Grid Infrastructure.
Journal ArticleDOI
Numerical simulations of elastic wave propagation using graphical processing units—Comparative study of high-performance computing capabilities
Pawel Packo,T. Bielak,A. B. Spencer,Tadeusz Uhl,W. J. Staszewski,Keith Worden,Tomasz Barszcz,P. Russek,Kazimierz Wiatr +8 more
TL;DR: It is demonstrated how graphical processing units can be used efficiently for large models of elastic wave propagation in complex media using a domain decomposition approach based on the local interaction simulation approach and a parallel algorithm architecture.
Proceedings ArticleDOI
FPGA Implementation of 64-Bit Exponential Function for HPC
TL;DR: The presented novel architecture employs three independent Look-Up Tables (LUTs) together with a short Taylor expansion exp(x)ap1+times to achieve huge performance with satisfactory accuracy, latency and FPGA area consumption.
Book ChapterDOI
Highly Efficient Structure of 64-Bit Exponential Function Implemented in FPGAs
TL;DR: This paper presents implementation of the double precision exponential function with novel table-based architecture which provides low latency (30 clock cycles) which is comparable to 32-bit implementations and aims primarily to meet quantum chemistry's huge and strict requirements of precision and speed.