Results 21 to 30 of about 46,646 (266)
Numerical behavior of NVIDIA tensor cores [PDF]
PeerJ Computer Science, 2021 We explore the floating-point arithmetic implemented in the NVIDIA tensor cores, which are hardware accelerators for mixed-precision matrix multiplication available on the Volta, Turing, and Ampere microarchitectures.
Massimiliano Fasi +3 more
doaj +2 more sources
LEGaTO: first steps towards energy-efficient toolset for heterogeneous computing [PDF]
, 2018 LEGaTO is a three-year EU H2020 project which started in December 2017. The LEGaTO project will leverage task-based programming models to provide a software ecosystem for Made-in-Europe heterogeneous hardware composed of CPUs, GPUs, FPGAs and dataflow ...
Alvarez, Carlos +38 more
core +1 more source
Special Section on Edge AI and Accelerators
IEEE Open Journal of Circuits and Systems, 2021 This special section presents seven state-of-the-art design techniques for AI hardware accelerators that lead to substantial improvements on energy efficiency, reconfigurability, and resource utilization.
Deepu John, Yongfu Li, Xinmiao Zhang
doaj +1 more source
On the Resilience of RTL NN Accelerators: Fault Characterization and Mitigation [PDF]
, 2018 Machine Learning (ML) is making a strong resurgence in tune with the massive generation of unstructured data which in turn requires massive computational resources.
Cristal, Adrian +2 more
core +2 more sources
Transactions on Cryptographic Hardware and Embedded Systems, 2020 This paper presents a set of efficient and parameterized hardware accelerators that target post-quantum lattice-based cryptographic schemes, including a versatile cSHAKE core, a binary-search CDT-based Gaussian sampler, and a pipelined NTT-based ...
Wen Wang +5 more
doaj +1 more source
Interstellar: Using Halide's Scheduling Language to Analyze DNN Accelerators
, 2020 We show that DNN accelerator micro-architectures and their program mappings represent specific choices of loop order and hardware parallelism for computing the seven nested loops of DNNs, which enables us to create a formal taxonomy of all existing dense
Bell, Steven Emberton +11 more
core +1 more source
Quick Boot of Trusted Execution Environment With Hardware Accelerators
IEEE Access, 2020 The Trusted Execution Environment (TEE) offers a software platform for secure applications. The TEE offers a memory isolation scheme and software authentication from a high privilege mode.
Trong-Thuc Hoang +6 more
doaj +1 more source
Adaptive embedded technologies: hardware acceleration [PDF]
, 2021 This thesis establishes the benefits of multi-architecture systems by using reconfigurable modules in conjunction with a case integration strategy to improve system performance. The modules and strategies discussed in this thesis provide opportunities to the improve system performance of processing units designed for the consumer market.
openaire +1 more source
Design Exploration of AES Accelerators on FPGAs and GPUs
Journal of Telecommunications and Information Technology, 2017 The embedded systems are increasingly becoming a key technological component of all kinds of complex technical systems and an exhaustive analysis of the state of the art of all current performance with respect to architectures, design methodologies ...
Vincenzo Conti, Salvatore Vitabile
doaj +1 more source
Implementation of the Lattice Boltzmann Method on Heterogeneous Hardware and Platforms using OpenCL
Advances in Electrical and Computer Engineering, 2012 The Lattice Boltzmann method (LBM) has become an alternative method for computational fluid dynamics with a wide range of applications. Besides its numerical stability and accuracy, one of the major advantages of LBM is its relatively easy ...
TEKIC, P. M. +2 more
doaj +1 more source