Search NASA⌕ Search

Engineering topics

Joo, Balint

Publications and source records attributed to Joo, Balint.

25 records · Page 2

Automatic Offloading C++ Expression Templates to CUDA Enabled GPUs

In the last few years, many scientific applications have been developed for powerful graphics processing units (GPUs) and have achieved remarkable speedups. This success can be partially attributed to high performance host callable GPU library routines that are offloaded to GPUs at runtime. These library routines are based on C/C++-like programming toolkits such as CUDA from NVIDIA and have the same calling signatures as their CPU counterparts. Recently, with the sufficient support of C++ templates from CUDA, the emergence of template libraries have enabled further advancement in code reusability and rapid software development for GPUs. However, Expression Templates (ET), which have been very popular for implementing data parallel scientific software for host CPUs because of their intuitive and mathematics-like syntax, have been underutilized by GPU development libraries. The lack of ET usage is caused by the difficulty of offloading expression templates from hosts to GPUs due to the inability to pass instantiated expressions to GPU kernels as well as the absence of the exact form of the expressions for the templates at the time of coding. This paper presents a general approach that enables automatic offloading of C++ expression templates to CUDA enabled GPUs by using the C++ metaprogramming technique and Just-In-Time (JIT) compilation methodology to generate and compile CUDA kernels for corresponding expression templates followed by executing the kernels with appropriate arguments. This approach allows developers to port applications to run on GPUs with virtually no code modifications. More specifically, this paper uses a large ET based data parallel physics library called QDP++ as an example to illustrate many aspects of the approach to offload expression templates automatically and to demonstrate very good speedups for typical QDP++ applications running on GPUs against running on CPUs using this method of offloading. In addition, this approach of automatic offlo- ding expression templates could be applied to other many-core accelerators that provide C++ programming toolkits with the support of C++ template.

97 MATHEMATICS AND COMPUTING↗

Lattice QCD and Graphical Processing Units

New heavy vector bosons, also known as ``heavy photons'', ``dark photons'', or ``hidden sector photons'', are expected on very general theoretical grounds. Recent astrophysical evidence motivates the direct search for a heavy photon $A'$ in the mass range $m_{A'} \sim 20$ to 1000 MeV/c$^{2}$, with coupling to ordinary photons {\it via} a kinetic mixing term $\propto\epsilon$, expected around $10^{-5}$ to $10^{-2}$. Such a new dark force gauge boson below the GeV range would naturally mediate TeV range dark matter annihilation, and interaction with ordinary matter. Existing constraints from collider searches and beam dump experiments leave much of this preferred $(m_{A'},\epsilon)$ phase space unexplored. The detection of electroproduced $A'$ on a heavy target from their decay into $e^{+}e^{-}$ pairs comes with a copious QED trident background. Using the high luminosity and precision beam available from Jlab, and combining a silicon microstrip vertex tracker with a lead-tungstate calorimeter for triggering, the HPS experiment will hunt for the $A'$ in a large $\epsilon$ range, with unique sensitivity in the lower coupling range using vertexing to suppress the trident background. In this talk, the experimental setup and goals of the HPS experiment will be presented.

Joo, Balint↗

Lattice QCD on GPU Clusters, using the QUDA Library and the Chroma Software System

The QUDA library for optimized lattice quantum chromodynamics using GPUs, combined with a high-level application framework such as the Chroma software system, provides a powerful tool for computing quark propagators, a key step in current calculations of hadron spectroscopy, nuclear structure, and nuclear forces. In this contribution we will discuss our experiences, including performance and strong scaling of the QUDA library and Chroma on the Edge Cluster at Lawrence Livermore National Laboratory and on various clusters at Jefferson Lab. We highlight some scientific successes and consider future directions for graphics processing units in lattice QCD calculations.

Joo, Balint↗

Nucleon, $\Delta$ and $\Omega$ excited states in $N_f=2+1$ lattice QCD

The energies of the excited states of the Nucleon, $\Delta$ and $\Omega$ are computed in lattice QCD, using two light quarks and one strange quark on anisotropic lattices. The calculation is performed at three values of the light quark mass, corresponding to pion masses $m_{\pi}$ = 392(4), 438(3) and 521(3) MeV. We employ the variational method with a large basis of interpolating operators enabling six energies in each irreducible representation of the lattice to be distinguished clearly. We compare our calculation with the low-lying experimental spectrum, with which we find reasonable agreement in the pattern of states. In addition, the need to include operators that couple to the expected multi-hadron states in the spectrum is clearly identified.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Excited-Nucleon Spectroscopy with 2+1 Fermion Flavors

We present progress made by the Hadron Spectrum Collaboration (HSC) in determining the tower of excited nucleon states using 2+1-flavor anisotropic clover lattices. The HSC has been investigating interpolating operators projected into irreducible representations of the cubic group in order to better calculate two-point correlators for nucleon spectroscopy; results are published for quenched and 2-flavor anisotropic Wilson lattices. In this work, we present the latest results using a new technique, distillation, which allows us to reach higher statistics than before. Future directions will be outlined at the end.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗