Patrick Dreher

Moments of nucleon light cone quark distributions calculated in full lattice QCD

Moments of the quark density, helicity, and transversity distributions are calculated in unquenched lattice QCD. Calculations of proton matrix elements of operators corresponding to these moments through the operator product expansion have been performed on the 16{sup 3} x 32 lattices for Wilson fermions at Beta=5.6 using configurations from the SESAM collaboration and at Beta = 5.5 using configurations from SCRI. One-loop perturbative renormalization corrections are included. At quark masses accessible in present calculations, there is no statistically significant difference between quenched and full QCD results, indicating that the contributions of quark-antiquark excitations from the Dirac Sea are small. Close agreement between calculations with cooled configurations containing essentially only instantons and the full gluon configurations indicates that quark zero modes associated with instantons play a dominant role. Naive linear extrapolation of the full QCD calculation to the physical pion mass yields results inconsistent with experiment. Extrapolation to the chiral limit including the physics of the pion cloud can resolve this discrepancy and the requirements for a definitive chiral extrapolation are described.

Insight into nucleon structure from lattice calculations of moments of parton and generalized parton distributions

Abstract This talk presents recent calculations in full QCD of the lowest three moments of generalized parton distributions and the insight they provide into the behavior of nucleon electromagnetic form factors, the origin of the nucleon spin, and the transverse structure of the nucleon. In addition, new exploratory calculations in the chiral regime of full QCD are discussed.

Integration of High-Performance Computing into Cloud Computing Services

High-Performance Computing (HPC) projects span a spectrum of computer hardware implementations ranging from peta-flop supercomputers, high-end tera-flop facilities running a variety of operating systems and applications, to mid-range and smaller computational clusters used for HPC application development, pilot runs and prototype staging clusters. What they all have in common is that they operate as a stand-alone system rather than a scalable and shared user re-configurable resource. The advent of cloud computing has changed the traditional HPC implementation. In this article, we will discuss a very successful production-level architecture and policy framework for supporting HPC services within a more general cloud computing infrastructure. This integrated environment, called Virtual Computing Lab (VCL), has been operating at NC State since fall 2004. Nearly 8,500,000 HPC CPU-Hrs were delivered by this environment to NC State faculty and students during 2009. In addition, we present and discuss operational data that show that integration of HPC and non-HPC (or general VCL) services in a cloud can substantially reduce the cost of delivering cloud services (down to cents per CPU hour).

Moments of nucleon spin-dependent generalized parton distributions

Abstract We present a lattice measurement of the first two moments of the spin-dependent GPD H ∼~ (x, ξ, t) . From these we obtain the axial coupling constant and the second moment of the spin-dependent forward parton distribution. The measurements are done in full QCD using Wilson fermions. In addition, we also present results from a first exploratory study of full QCD using Asqtad sea and domain-wall valence fermions.

PageRank Pipeline Benchmark: Proposal for a Holistic System Benchmark for Big-Data Platforms

The rise of big data systems has created a need for benchmarks to measure and compare the capabilities of these systems. Big data benchmarks present unique scalability challenges. The supercomputing community has wrestled with these challenges for decades and developed methodologies for creating rigorous scalable benchmarks (e.g., HPC Challenge). The proposed PageRank pipeline benchmark employs supercomputing benchmarking methodologies to create a scalable benchmark that is reflective of many real-world big data processing systems. The PageRank pipeline benchmark builds on existing prior scalable benchmarks (Graph500, Sort, and PageRank) to create a holistic benchmark with multiple integrated kernels that can be run together or independently. Each kernel is well defined mathematically and can be implemented in any programming environment. The linear algebraic nature of PageRank makes it well suited to being implemented using the GraphBLAS standard. The computations are simple enough that performance predictions can be made based on simple computing hardware models. The surrounding kernels provide the context for each kernel that allows rigorous definition of both the input and the output for each kernel. Furthermore, since the proposed PageRank pipeline benchmark is scalable in both problem size and hardware, it can be used to measure and quantitatively compare a wide range of present day and future systems. Serial implementations in C++, Python, Python with Pandas, Matlab, Octave, and Julia have been implemented and their single threaded performance has been measured.

Integration of high-performance computing into a VCL cloud

High-Performance Computing (HPC) services can range from those on peta-flop supercomputers down to smaller computational clusters used for HPC application development, pilot runs and staging. What they all have in common is that traditionally HPC facilities tend to be isolated from the more general scientific computing services. Advent of the cloud computing has started changing that. In this paper we discuss a very successful production-level architecture and policy framework for supporting HPC services within a more general cloud computing infrastructure called VCL. This integrated environment has been operating at NC State since fall 2004. It typically delivers over 14 million HPC CPU hours per year to NC State faculty and students. Our experience is that integration of HPC and non-HPC services in a cloud can substantially reduce the cost of both services.

Physics development of web-based tools for use in hardware clusters doing lattice physics

Jefferson Lab and MIT are developing a set of web-based tools within the Lattice Hadron Physics Collaboration to allow lattice QCD theorists to treat the computational facilities located at the two sites as a single meta-facility. The prototype Lattice Portal provides researchers the ability to submit jobs to the cluster, browse data caches, and transfer files between cache and off-line storage. The user can view the configuration of the PBS servers and to monitor both the status of all batch queues as well as the jobs in each queue. Work is starting on expanding the present system to include job submissions at the meta-facility level (shared queue), as well as multi-site file transfers and enhanced policy-based data management capabilities.

Cost Analysis Comparing HPC Public Versus Private Cloud Computing

The past several years have seen a rapid increase in the number and type of public cloud computing hardware configurations and pricing options offered to customers. In addition public cloud providers have also expanded the number and type of storage options and established incremental price points for storage and network transmission of outbound data from the cloud facility. This has greatly complicated the analysis to determine the most economical option for moving general purpose applications to the cloud. This paper investigates whether this economic analysis for moving general purpose applications to the public cloud can be extended to more computationally intensive HPC type computations. Using an HPC baseline hardware configuration for comparison, the total cost of operations for several HPC private and public cloud providers are analyzed. The analysis shows under what operational conditions the public cloud option may be a more cost effective alternative for HPC type applications.

Toward a Proof of Concept Cloud Framework for Physics Applications on Blue Gene Supercomputers

Traditional high performance supercomputers are capable of delivering large sustained state-of-the-art computational resources to physics applications over extended periods of time using batch processing mode operating environments. However, today there is an increasing demand for more complex workflows that involve large fluctuations in the levels of HPC physics computational requirements during the simulations. Some of the workflow components may also require a richer set of operating system features and schedulers than normally found in a batch oriented HPC environment. This paper reports on progress toward a proof of concept design that implements a cloud framework onto BG/P and BG/Q platforms at the Argonne Leadership Computing Facility. The BG/P implementation utilizes the Kittyhawk utility and the BG/Q platform uses an experimental heterogeneous FusedOS operating system environment. Both platforms use the Virtual Computing Laboratory as the cloud computing system embedded within the supercomputer. This proof of concept design allows a cloud to be configured so that it can capitalize on the specialized infrastructure capabilities of a supercomputer and the flexible cloud configurations without resorting to virtualization. Initial testing of the proof of concept system is done using the lattice QCD MILC code. These types of user reconfigurable environments have the potential to deliver experimental schedulers and operating systems within a working HPC environment for physics computations that may be different from the native OS and schedulers on production HPC supercomputers.

Large scale commodity clusters for lattice QCD

We describe the construction of large scale clusters for lattice QCD computing being developed under the umbrella of the U.S. DoE SciDAC initiative. We discuss the study of floating point and network performance that drove the design of the cluster, and present our plans for future multi-Terascale facilities.