A Performance Study of a Dual Xeon-Phi Cluster for the Forward Modelling of Gravitational Fields

Abstract

With at least 60 processing cores, the Xeon-Phi coprocessor is a truly multicore architecture, which consists of an interconnection speed among cores of 240 GB/s, two levels of cache memory, a theoretical performance of 1.01 Tflops, and programming flexibility, all making the Xeon-Phi an excellent coprocessor for parallelizing applications that seek to reduce computational times. The objective of this work is to migrate a geophysical application designed to directly calculate the gravimetric tensor components and their derivatives and in this way research the performance of one and two Xeon-Phi coprocessors integrated on the same node and distributed in various nodes. This application allows the analysis of the design factors that drive good performance and compare the results against a conventional multicore CPU. This research shows an efficient strategy based on nested parallelism using OpenMP, a design that in its outer structure acts as a controller of interconnected Xeon-Phi coprocessors while its interior is used for parallelyzing the loops. MPI is subsequently used to reduce the information among the nodes of the cluster.

OpenMP Implementation of a Novel Potential-Field-Data Source-Growth-Based Inversion Approach for 3D Salt Imaging in Deepwater Gulf of Mexico

“…With respect to the computing architecture, it is well known that a deep acquaintance of the architecture leads to a very efficient parallel solution to the problem, which in turn becomes complicated because it requires programming skills at low level and a large development (coding) time. This is the case of using CUDA C for Graphics Processing Units (GPU) or Message Passing Interface (MPI) for memory distributed architectures like clusters or Xeon Phi Co-processors [48,52,53]. As one of the goals of this paper is to make this research accessible to the greatest possible part of the geophysical and related communities, the acceleration of the herein presented algorithms are based on shared memory CPU-based architectures.…”

“…Thus, a deficient design of the parallel strategy is prone to a deficient performance. OpenMP has benefited several geophysical problems [48,52]. OpenMP also provides an implicit parallelism model which produces medium granularity tasks for MT applications, providing a higher computational abstraction than MPI.…”

“…A graphical representation can be observed in Figure 8. In this work, we only consider the large salt body emplaced in the center of the domain, with respect to other bodies in the zone [52]. For the magnetic properties of the model, we considered that there is no variation of the susceptibility with depth.…”

Analysis of Electromagnetic Propagation from MHz to THz with a Memory-Optimised CPML-FDTD Algorithm

“…An advantage of the usage of the presented CPML ABC consists in a drastic reduction of the number of memory arrays in the bidimensional algorithm [4], so it can be easily implemented for GPU processing, as those cards possess a limited amount of memory. The CPML ABC for the FDTD method requires to allocate the value of the time derivatives in a memory variable, which is implemented in two ways in this paper: the first, by allocating the memory variables for all the domain, and the second, by allocating them only in the absorption region (see Figure 2 [19,20].…”

Weakly Coupled Distributed Calculation of Lyapunov Exponents for Non-Linear Dynamical Systems

“…To divide tasks in a balanced way, we follow the procedure described by Couder-Castañeda et al [17], and Arroyo et al [18]. Let p n be the number of MPI processes and C n the number of problems to solve, then we define the problem number with which a process, p, must start and finish as p s and p e , respectively.…”