HPC Architecture & Performance Student Assistant

📁
Students
💼
NE-NERSC
📅
89362 Requisition #

Berkeley Lab is seeking summer interns to work in the Advanced Technologies Group. Areas of interest span from performance analysis for next generation high-performance computing (HPC) architectures, power management and evaluating OpenMP on accelerators. The exact project will be determined with the supervisor or based on the intern’s research interests.


Project 1: Power management in high-performance computing (HPC)


The first of the Department of Energy's exascale systems will consume over 20 Megawatts in power. Power consumption in supercomputing is a growing area of concern that limits its size and scale. In this project, the summer intern will explore and evaluate the efficacy of power management methods in the context of hardware and applications of interest at the National Energy Research Supercomputing Center (NERSC). This work aims to help inform improvement in the design and operation of existing and future systems.

 

  1. Evaluate power controls and counters on general-purpose Graphics Processing Units (GPUs)


A growing amount of floating-point instructions per second (FLOPs) performance of HPC applications on the top supercomputers today is obtained from the GPUs in systems provisioned with CPUs and GPUs. It is necessary to understand the power consumption for representative HPC applications/benchmarks on the GPUs and how the controls in the hardware affect it along with the performance. This information can help the design of sophisticated power management schemes in the future. Besides, the goal of the project is also to understand the maturity in support and granularity of these power controls and counters in the GPUs.

 

  1. Understanding the opportunities for power-steering between CPUs and GPUs for NERSC applications


Given that a sizable portion of the FLOPs in GPU-enabled HPC applications come from the GPUs, CPUs tend to wait while dissipating power for the GPUs to complete. We want to evaluate the possibility of throttling CPU power in such scenarios in the context of NERSC applications. Further, we want to investigate if the saved power from the CPU throttling can be directed to the GPUs for additional performance gains. This will either entail power-performance analysis leading to a simulation/model or developing a prototype framework that allows CPU/GPU throttling and steering.


Qualifications for both project areas include:

  • Familiarity with Linux environments and programming in C/C++ or Python.

  • Familiarity with running HPC applications that use MPI, OpenMP or heterogeneous programming paradigms is strongly preferred.

  • Familiarity with performance modelling and analysis or framework development using hardware counters or controls is highly beneficial.

  • Senior undergraduate or graduate student in computer science or a related field.


Project 2: OpenMP on accelerators


The DOE uses OpenMP to improve application performance on modern supercomputers. There

is particular interest in newer OpenMP standards which support offloading of computations to

accelerators such as GPUs and FPGAs. In this project, the summer intern will evaluate OpenMP on accelerators to improve our understanding about how to use OpenMP efficiently on

Perlmutter and other supercomputers with accelerators. The exact project will be determined

with the supervisor but will likely involve one of the following two areas.

 

1. Porting an application to OpenMP 4.5/5.0


The intern will add OpenMP 4.5/5.0 directives to a pre-existing application and evaluate the performance on the NERSC GPU test-bed and other platforms. The target application will likely already have a CUDA, OpenACC or OpenCL GPU implementation. The goals are to evaluate the capability of OpenMP on GPUs and help NERSC staff come up with best practices to help NERSC users.

 

2. Evaluating OpenMP compiler performance


The intern will evaluate compiler performance by running a variety of OpenMP-4.5/5.0 micro-benchmarks, mini-apps and full applications written in C, C++ and Fortran on the NERSC GPU test-bed and other platforms. One possibility is for the intern to extract small kernels from the mini-apps and full applications to create a performance test-suite capturing DOE application requirements which would complement the SOLLVE V&V OpenMP correctness test-suite. The intent of the project is to compare the performance of several compilers, e.g. LLVM/Clang/Flang, GCC, Cray, to identify gaps in current compiler implementations, manage expectations among DOE users experimenting with OpenMP target offload, and show the OpenMP target offload code patterns which are robust and perform well across different compilers and platforms.

 

Qualifications for both project areas include:

  • Familiarity with Linux environments and programming in C, C++ or Fortran.

  • Familiarity with OpenMP or GPU programming is strongly preferred.

  • Senior undergraduate or graduate student in computer science or a related field hardware.


Project 3: Performance analysis for next generation HPC architectures


Understanding and predicting the performance of NERSC's workload on various processors and networks has been a fundamental step in the selection of every NERSC HPC system. However, hardware trends toward complex heterogeneous architectures with specialized accelerators now require more advanced modeling and analysis to produce accurate predictions. This project will improve NERSC's performance modeling capabilities through a combination of:

1) expanding the suite of runtime experiments

2) applying new and existing performance analyses to NERSC applications 

3) developing tools and procedures to measure specific performance properties

4) identifying ways to derive useful insights from system-wide monitoring (i.e. LDMS)


Qualifications for all project areas include:

  • Familiarity with Linux environments and programming in C/C++ or Python.

  • Familiarity with running HPC applications that use MPI.

  • Familiarity with basic concepts in performance profiling and performance models.

  • Senior undergraduate or graduate student in computer science or computational science.


Notes:

  • Student participation requires 40 hours per week commitment for Summer appointment, and 20 hours per week commitment for the Spring appointment. 

  • Salary will be predetermined based on student step rates.

  • This position may be subject to a background check. Any convictions will be evaluated to determine if they directly relate to the responsibilities and requirements of the position. Having a conviction history will not automatically disqualify an applicant from being considered for employment.

  • Work will be primarily performed at Lawrence Berkeley National Lab, 1 Cyclotron Road, Berkeley, CA.


Learn About Us: 


Berkeley Lab (LBNL) addresses the world’s most urgent scientific challenges by advancing sustainable energy, protecting human health, creating new materials, and revealing the origin and fate of the universe. Founded in 1931, Berkeley Lab’s scientific expertise has been recognized with 13 Nobel prizes. The University of California manages Berkeley Lab for the U.S. Department of Energy’s Office of Science.


Working at Berkeley Lab has many rewards including a competitive compensation program, excellent health and welfare programs, a retirement program that is second to none, and outstanding development opportunities. To view information about the many rewards that are offered at Berkeley Lab- Click Here.


Equal Employment Opportunity: Berkeley Lab is an Equal Opportunity/Affirmative Action Employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, disability, age, or protected veteran status. Berkeley Lab is in compliance with the Pay Transparency Nondiscrimination Provision under 41 CFR 60-1.4. Click here to view the poster and supplement: "Equal Employment Opportunity is the Law." Lawrence Berkeley National Laboratory encourages applications from women, minorities, veterans, and other underrepresented groups presently considering scientific research careers.


Previous Job Searches

My Profile

Create and manage profiles for future opportunities.

Go to Profile

My Submissions

Track your opportunities.

My Submissions

Similar Listings

CR-Computational Research

Bay Area, California, United States

📁 Students

Requisition #: 89592

EB-Environ Genomics & Systems Bio

Bay Area, California, United States

📁 Students

Requisition #: 88989

SN-Scientific Networking

Bay Area, California, United States

📁 Students

Requisition #: 88854

Equal Employment Opportunity: Berkeley Lab is an Equal Opportunity/Affirmative Action Employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, disability, age, or protected veteran status. Berkeley Lab is in compliance with the Pay Transparency Nondiscrimination Provision under 41 CFR 60-1.4. Click here to view the poster and supplement: "Equal Employment Opportunity is the Law."

 

Privacy & Security Notice | LBNL is an E-verify Employer | Contact Us


The Lawrence Berkeley National Laboratory provides accommodation to otherwise qualified internal and external applicants who are disabled or become disabled and need assistance with the application process. Internal and external applicants that need such assistance may contact the Lawrence Berkeley National Laboratory to request accommodation by telephone at 510-486-7635, by email to eeoaa@lbl.gov or by U.S. mail at EEO/AA Office, One Cyclotron Road, MS90R-2121, Berkeley, CA 94720. These methods of contact have been put in place ONLY to be used by those internal and external applicants requesting accommodation.