Publications

Results 101–125 of 266
Skip to search filters

Fast linear algebra-based triangle counting with KokkosKernels

2017 IEEE High Performance Extreme Computing Conference, HPEC 2017

Wolf, Michael W.; Deveci, Mehmet D.; Berry, Jonathan W.; Hammond, Simon D.; Rajamanickam, Sivasankaran R.

Triangle counting serves as a key building block for a set of important graph algorithms in network science. In this paper, we address the IEEE HPEC Static Graph Challenge problem of triangle counting, focusing on obtaining the best parallel performance on a single multicore node. Our implementation uses a linear algebra-based approach to triangle counting that has grown out of work related to our miniTri data analytics miniapplication [1] and our efforts to pose graph algorithms in the language of linear algebra. We leverage KokkosKernels to implement this approach efficiently on multicore architectures. Our performance results are competitive with the fastest known graph traversal-based approaches and are significantly faster than the Graph Challenge reference implementations, up to 670,000 times faster than the C++ reference and 10,000 times faster than the Python reference on a single Intel Haswell node.

More Details
TYPE Conference Poster YEAR 2017
ScopusOSTI

Performance analysis for using non-volatile memory DIMMs: Opportunities and challenges

ACM International Conference Proceeding Series

Awad, Amro A.; Hammond, Simon D.; Hughes, Clayton H.; Rodrigues, Arun; Hemmert, Karl S.; Hoekstra, Robert J.

DRAM scalability is becoming more challenging, pushing the focus of the research community towards alternative memory technologies. Many emerging non-volatile memory (NVM) devices are proving themselves to be good candidates to replace DRAM in the coming years. For example, the recently announced 3D-XPoint memory by Intel/Micron promises latencies that are comparable to DRAM, while being non-volatile and much more dense. While emerging NVMs can be fabricated in different form factors, the most promising (from a performance perspective) are NVM-based DIMMs. Unfortunately, there is a shortage of studies that explore the design options for NVM-based DIMMs. Because of the read and write asymmetries in both power consumption and latency, as well as limited write endurance, which often requires wear-leveling techniques, NVMs require a specialized controller. The fact that future on-die memory controllers are expected to handle different memory technologies pushes future hardware towards on-DIMM controllers. In this paper, we propose an architectural model for NVM-based DIMMs with internal controllers, explore their design space, evaluate different optimizations and reach out to several architectural suggestions. Finally, we make our model publicly available and integrate it with a widely used architectural simulator.

More Details
TYPE Conference Poster YEAR 2017
ScopusOSTIDOI

Final Review of FY17 ASC CSSE L2 Milestone #6018 entitled "Analyzing Power Usage Characteristics of Workloads Running on Trinity"

Hoekstra, Robert J.; Hammond, Simon D.; Hemmert, Karl S.; Gentile, Ann C.; Oldfield, Ron A.; Lang, Mike L.; Martin, Steve M.

The presentation documented the technical approach of the team and summary of the results with sufficient detail to demonstrate both the value and the completion of the milestone. A separate SAND report was also generated with more detail to supplement the presentation.

More Details
TYPE Other Report YEAR 2017
OSTIDOI

Tri-Lab Co-Design Milestone: In-Depth Performance Portability Analysis of Improved Integrated Codes on Advanced Architecture

Hoekstra, Robert J.; Hammond, Simon D.; Richards, David F.; Bergen, Ben B.

This milestone is a tri-lab deliverable supporting ongoing Co-Design efforts impacting applications in the Integrated Codes (IC) program element Advanced Technology Development and Mitigation (ATDM) program element. In FY14, the trilabs looked at porting proxy application to technologies of interest for ATS procurements. In FY15, a milestone was completed evaluating proxy applications in multiple programming models and in FY16, a milestone was completed focusing on the migration of lessons learned back into production code development. This year, the co-design milestone focuses on extracting the knowledge gained and/or code revisions back into production applications.

More Details
TYPE Other Report YEAR 2017
OSTIDOI
Results 101–125 of 266
Results 101–125 of 266