Soft-core processors implemented in SRAM-based FPGAs are an attractive option for applications to be employed in radiation environments due to their flexibility, relatively-low application development costs, and reconfigurability features enabling them to adapt to the evolving mission needs. Despite the advantages soft-core processors possess, they are seldom used in critical applications because they are more sensitive to radiation than their hard-core counterparts. For instance, both the logic and signal routing circuitry of a soft-core processor as well as its user memory are susceptible to radiation-induced faults. Therefore, soft-core processors must be appropriately hardened against ionizing-radiation to become a feasible design choice for harsh environments and thus to reap all their benefits. This survey henceforth discusses various techniques to protect the configuration and user memories of an LEON3 soft processor, which is one of the most widely used soft-core processors in radiation environments, as reported in the stateof-the-art literature, with the objective of facilitating the choice of right fault-mitigation solution for any given soft-core processor.
<p class="ABSTRACT">The design and implementation of an FPGA core that parallelises all the necessary operations to compute the non-bonded interactions in a MD simulation with the purpose of accelarating the LAMMPS MD software is presented in this paper. Our MD processor core comprised of 4 identical pipelines working independently in parallel to evaluate the non-bonded potentials, forces and virials was implemented on the nodes of a FPGA-based supercomputer named Maxwell. Implementing our FPGA core on multiple nodes of Maxwell allowed us to produce a special-purpose parallel machine for the hardware acceleration of MD simulations. The timing performance figures of this machine for the pairwise LJ and short-range Coulombic (via PPPM) interaction computations in the MD simulations of the solvated Rhodopsin protein systems with various numbers of atom show performance gains over the pure software implementation by factors of up to 13 on two nodes of the Maxwell machine. Furthermore, our MD machine is highly scalable, yielding higher computational power with the additional Maxwell nodes. To our knowledge, this is the first attempt to port an existing production-grade MD software to a FPGA-based parallel computer.</p>
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.