Searcharxiv⌕ Search
Home/Archive/arXiv

arXiv · hep-lat/9509003

Performance of the Cray T3D and Emerging Architectures on Canopy QCD Applications

Mark Fischler·Mike Uchima
View original source ↗Read source document ↗Export metadata ↓

Abstract

The Cray T3D, an MIMD system with NUMA shared memory capabilities and in principle very low communications latency, can support the Canopy framework for grid-oriented applications. CANOPY has been ported to the T3D, with the intent of making it available to a spectrum of users. The performance of the T3D running Canopy has been benchmarked on five QCD applications extensively run on ACPMAPS at Fermilab, requiring a variety of data access patterns. The net performance and scaling behavior reveals an efficiency relative to peak Gflops almost identical to that achieved on ACPMAPS. Detailed studies of the major factors impacting performance are presented. Generalizations applying this analysis to the newly emerging crop of commercial systems reveal where their limitations will lie. On these applications, efficiencies of above 25\% are not to be expected; eliminating overheads due to Canopy will improve matters, but by less than a factor of two.

Explore related subjects

hep-lat

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Mark Fischler, Mike Uchima. 1995-09-01. Performance of the Cray T3D and Emerging Architectures on Canopy QCD Applications. https://doi.org/10.1016/0920-5632(96)00180-6

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Can multi-level Monte-Carlo address the sign problem in a finite-density Bose gas?

Numerical simulation of field theories with complex actions is frustrated by the sign problem, which causes an exponential growth in statistical sampling noise. A key example of such a theory is QCD at finite baryon chemical potential, which has important applications to the structure of atomic nuclei and neutron stars. Until now, the sign problem has precluded the possibility of first-principles numerical calculations that could provide key insight into these important physical systems. In this work, we propose an approach to avoiding this limitation by applying a reweighting procedure coupled with a multi-level Monte-Carlo sampling algorithm that offers an exponential enhancement of statistics to counteract the sign problem. We test the approach on a simpler model that displays the same sign problem at finite chemical potential. Our results demonstrate the promise of the proposed approach, significantly increasing the range over which precise calculations are possible, and providing improvements all the way up to the phase transition.

hep-lat↗
arXiv2026

A Note On Lattice Definition of Gauge Theories With Chiral Fermions

Because of the fermion doubling problem, it has been a longstanding challenge to describe a lattice algorithm for studying four-dimensional gauge theories coupled to chiral fermions. Recently, an algorithm to do so has been described by Craig, extending partial results in the previous literature. Here we describe a variant of this algorithm, based on interpolating a lattice gauge field over the continuum (as in Craig's work) and coupling the interpolated gauge field to continuum chiral fermions. The same variant was also proposed recently by Hsu. In any dimension and for any anomaly-free representation, this approach can be implemented on a computer in principle, but not in practice by Monte Carlo methods because the chiral fermion path integral is not positive.

hep-lat↗
arXiv2026

2+1 flavor light hadron spectrum with PACS10 configurations

We present the results for the hadron spectrum, the pseudoscalar meson decay constants, and the quark mass ratio in the continuum limit using the ``PACS10'' gauge configurations generated with the $O(a)$-improved Wilson quark action and the Iwasaki gauge action. Numerical simulations are carried out at three lattice spacings keeping the space-time volumes over (10 fm$)^4$ in 2+1 flavor QCD at the physical point. We calculate physical quantities with two choices of conventions to define pseudoexperimental values expected in the isosymmetric QCD. In order to investigate the finite size effects on the physical quantities we have additionally generated the (5.4 fm$)^4$ lattice at the coarsest lattice spacing of $a=0.08487(14)$~fm, which is a hypercube with half the length in each direction compared to the PACS10 configurations. While the finite size effect is hardly observed in comparison of the hadron effective masses on the (10.9 fm$)^4$ and (5.4 fm$)^4$ lattices, the results for the pseudoscalar meson decay constants show discrepancies beyond the error bars. The (5.4 fm$)^4$ lattice also serves for determining the expansion parameters of the pseudoscalar meson masses and decay constants, and the octet baryon masses in terms of the quark masses around the physical point with the aid of the mass reweighting technique. The expansion parameters are used for the fine-tuning of the physical point employing the pseudoexperimental masses of the $π$ meson, $K$ meson, and the $Ξ$ baryon as physical inputs in each convention. We compare the results for the octet baryon masses and the pseudoscalar decay constants in the continuum limit with the corresponding pseudoexperimental values in both conventions. We also discuss the deviation between two results with different conventions. As for the quark mass ratio the result is compared with the recent FLAG summary.

hep-lat↗