Academic on Academic

Improving Productivity and Sustainability for Parallel Computing Software

Wed, 12 Feb 2020 00:00:00 -0500

CAAR-ORNL-HZDR Collaborative Project

Sun, 01 Sep 2019 00:00:00 -0400

Applying directives to port MURaM code to heterogeneous systems

Sat, 29 Jun 2019 00:00:00 -0400

Talk Title: Applying directives to port MURaM code to heterogeneous systems This talk will discuss the computational aspects of Max Planck/University of Chicago Radiative MHD code (MURaM), the primary model for simulating the sun's upper convection zone, its surface, and the corona. Accelerating MURaM allows physicists to interpret high-resolution solar observations. The talk will describe the programmatic challenges and optimization techniques that we have employed while using the OpenACC programming model to accelerate MURaM on GPUs and multicore architectures. The talk will also examine lessons learned and how it could be broadly applied to atmospheric and astrophysical applications.

ECP SOLLVE: OpenMP Validation and Verification Testsuite Project

Sat, 01 Jun 2019 00:00:00 -0400

Accelerating a Biophysics Problem: 14 hours to 46 seconds

Thu, 30 May 2019 00:00:00 -0400

Using the Parallel Programming Model, OpenACC, to do More Science and Less Programming

Tue, 30 Oct 2018 00:00:00 -0400

Accelerating a Nuclear Physics problem on GPUs

Fri, 30 Mar 2018 00:00:00 -0400

HPC-as-a-Service to Domain Scientists

Thu, 14 Dec 2017 00:00:00 -0500

Opportunities and Challenges Migrating Scientific Code to Accelerators

Wed, 13 Dec 2017 00:00:00 -0500

Talk Title: Opportunities and Challenges Migrating Scientific Code to Accelerators Hardware architectures are rapidly evolving and High performance computing nodes are becoming increasingly heterogeneous. Such diverse architectures require their own code optimization strategies, while the application developers prefer a “write-once” code development strategy in which a single code will execute efficiently on all targeted architectures. This talk will focus on 1-2 scientific applications and discuss challenges faced as a scientific developer to port these applications to large-scale systems using directive-based programming models.

Path forward for softwarization to tackle evolving hardware

Wed, 13 Dec 2017 00:00:00 -0500

Talk Title: Path forward for softwarization to tackle evolving hardware Even though legacy scientific code bases have long lifetimes and not going away anytime soon, by 2030, disruptive technologies would have dramatically changed softwarization. Are we ready to tackle tomorrow’s hardware? Relying on traditional programming paradigms will no longer suffice. We need to explore software abstractions and advanced smart techniques in compiler and runtime systems to effectively exploit tomorrow’s hardware. With the advent of neuromorphic chips and quantum computers as effective accelerators to which traditional X86 systems could offload relevant computations, we need to rethink the impact of these disruptive technologies on today’s software and fundamental programming abstractions.

Adapting Minisweep, a Proxy Application, on Heterogeneous Systems Using OpenACC Directives

Tue, 12 Dec 2017 00:00:00 -0500

Learn about how the high-level directive-based, widely popular, programming model, OpenACC can help port radiation transport scientific codes to large scale heterogeneous systems consisting of state-of-the-art accelerators such as GPUs. Architectures are rapidly evolving and the exascale machines are expected to offer billion-way concurrency. We need to rethink algorithms, languages, programming models among other components in order to increase parallelism from a programming standpoint to be able to migrate large scale applications to these massively powerful platforms. This talk will discuss programming challenges and its corresponding solutions for porting a wavefront based miniapplication for Denovo, which is a production code for nuclear reactor modeling, using OpenACC. Our OpenACC implementation running on NVIDIA’s next-generation Volta GPU boasts a 85.06x speedup over serial code, which is larger than CUDA’s 83.72x speedup over the same serial implementation.

Achieving Performance While Preserving Portability for NGS Application

Mon, 11 Dec 2017 00:00:00 -0500

Talk Title: Achieving Performance While Preserving Portability for NGS Application DNA damage is a major source of mutation. Patient samples contain natural genetic variations created by mutations such as indels, or single nucleotide polymorphisms (SNPs). We need sophisticated sequence alignment tools to accelerate identification of mutations of various types such as substitution, insertion, deletion (indels) or frameshift. Alignment is computationally intensive and expensive. State-of-the-art alignment algorithms BWA, bowtie, BarraCUDA and nvbowtie do not take advantage of the rich resources of novel hardware. The same concern holds good for assembly algorithms. Why? These algorithms are either closely tied to a particular programming language or hardware causing extensive intervention from the programmer to massively restructure the code. Such interventions can slow tool’s productivity and can be erroneous too. These limit tool’s usage by biologists who would rather spend quality time on science and not on programming and debugging. Our research plan aims to produce a fast, accurate, reliable, reproducible and portable tool. A tool that will help us be ready to tackle an unexpected event that anticipates a quick response and treatment. Our software tool will use high-level programming models and also use docker container, a major requirement to address reproducible research and minimize the IT support requirement in any clinical lab setting thus easing the deployment and portability aspect of usability.

New Book Released: OpenACC for Programmers

Tue, 14 Nov 2017 00:00:00 -0500

Video: OpenACC Eases GPU Programming for HPC at SC17

Mon, 13 Nov 2017 00:00:00 -0500

Training: Programming Hackathons

Sun, 12 Nov 2017 00:00:00 -0500