SC 2019 - Denver, CO, USA
(Nov 17 - 22, 2019)

Time Location Event Speaker(s)

Friday, November 15

8:45AM - 9:45AM Courtyard by Marriott Denver Airport

Benchmarks and Middleware for Designing Convergent HPC, Big Data and Deep Learning Software Stacks for Exascale Systems at Bench '19

[Keynote Talk]

DK Panda

Saturday, November 16

12:30PM - 1:00PM Galvanize Inc.

Accelerating HPC, Big Data and Deep Learning on OpenPOWER Platforms at OpenPOWER Summit

[Talk]

DK Panda

Sunday, November 17

8:30AM - 12:00PM 207

High Performance Distributed Deep Learning: A Beginner's Guide

[Tutorial]

DK Panda
A. Awan
H. Subramoni
C. Chu
2:00PM - 2:20PM Space Gallery

Full Stack View of AI Influence on HPC Hardware Systems at HPC Day

[Talk]

DK Panda
4:30PM - 5:00PM 502-503-504

Scaling TensorFlow, PyTorch, and MXNet using MVAPICH2 for High-Performance Deep Learning on Frontera

[Paper Presentation]

A. Jain

Monday, November 18

8:30AM - 12:00PM 201

InfiniBand, Omni-Path, and High-Speed Ethernet for Beginners

[Tutorial]

DK Panda
H. Subramoni
M. Bayatpour
1:30PM - 5:00PM 201

InfiniBand, Omni-Path, and High-Speed Ethernet: Advanced Features, Challenges in Designing HEC Systems and Usage

[Tutorial]

DK Panda
H. Subramoni
J. Hashmi
3:00PM - 3:20PM Curtis Hotel - Marco Polo Ballroom

Talk at ARM HPC User Group

[Talk]

DK Panda
3:30PM - 4:00PM 603

OMB-UM: Design, Implementation, and Evaluation of CUDA Unified Memory Aware MPI Benchmarks

[Paper Presentation]

K. Vadambacheri Manian

Tuesday, November 19

10:00AM - 10:30AM OSU Booth (#2094)

Scalable and Reliable Broadcast using InifiniBand and NVIDIA GPUDirect Technology in MVAPICH2-GDR

[Presentation-Demo-Discussion]

C. Chu
10:30AM - 11:00AM OSU Booth (#2094)

Performance Study of CUDA-Aware MPI libraries for GPU-enabled OpenPOWER Systems

[Presentation-Demo-Discussion]

K. Shafie Khorassani
11:00AM - 11:30AM Mellanox Booth 601

Mellanox Booth Talk

[Talk]

DK Panda
11:00AM - 11:30AM OSU Booth (#2094)

MVAPICH Touches the Cloud New Frontiers for MPI in High Performance Clouds

[Presentation-Demo-Discussion]

S. Xu
11:30AM - 12:00PM OSU Booth (#2094)

Performance Characterization of Distributed DNN Training: CPU vs GPU

[Presentation-Demo-Discussion]

A. Jain
12:00PM - 12:30PM OSU Booth (#2094)

Scalable and Distributed Deep Learning (DL): Co-design MPI Runtimes and DL Frameworks

[Presentation-Demo-Discussion]

A. Awan
12:15PM - 1:15PM Room #605

Talk at UCX BoF

[Talk]

DK Panda
12:30PM - 1:00PM OSU Booth (#2094)

Performance Study of CUDA-Aware MPI libraries for GPU-enabled OpenPOWER Systems

[Presentation-Demo-Discussion]

K. Shafie Khorassani
1:00PM - 1:30PM OSU Booth (#2094)

Characterizing CUDA UM-Aware MPI libraries on Modern GPUs

[Presentation-Demo-Discussion]

K. Vadambacheri Manian
1:30PM - 2:00PM OSU Booth (#2094)

Accelerating MPI Message Matching and Reduction Collectives For Multi-/Many-core Architectures

[Presentation-Demo-Discussion]

M. Bayatpour
2:00PM - 2:30PM OSU Booth (#2094)

Efficient Designs for Distributed MPI Neighborhood Collectives

[Presentation-Demo-Discussion]

M. Ghazimirsaeed
2:30PM - 3:00PM OSU Booth (#2094)

Designing Next-Generation Communication Middlewares for Many-Core Architectures

[Presentation-Demo-Discussion]

J. Hashmi
3:00PM - 3:30PM OSU Booth (#2094)

Efficient Design for MPI asynchronous progress without dedicated resources

[Presentation-Demo-Discussion]

A. Ruhela
3:30PM - 4:00PM OSU Booth (#2094)

Efficient Non-contiguous Data Transfer using MVAPICH2-GDR for GPU-enabled HPC Applications

[Presentation-Demo-Discussion]

C. Chu
4:00PM - 4:30PM OSU Booth (#2094)

Performance Engineering using MVAPICH and TAU

[Talk]

Sameer Shende (University of Oregon)
4:30PM - 5:00PM OSU Booth (#2094)

Exploiting Network-level parallelism with Multiple Process-Endpoints for MPI Broadcast

[Presentation-Demo-Discussion]

A. Ruhela
5:00PM - 5:30PM OSU Booth (#2094)

Design, Implementation and Evaluation of CUDA Unified Memory Aware MPI Benchmarks

[Presentation-Demo-Discussion]

K. Vadambacheri Manian
5:30PM - 6:00PM OSU Booth (#2094)

Accelerating MPI Message Matching and Reduction Collectives For Multi-/Many-core Architectures

[Presentation-Demo-Discussion]

M. Bayatpour

Wednesday, November 20

10:00AM - 10:30AM OSU Booth (#2094)

Efficient Design for MPI asynchronous progress without dedicated resources.

[Presentation-Demo-Discussion]

A. Ruhela
10:30AM - 11:00AM OSU Booth (#2094)

MVAPICH Touches the Cloud New Frontiers for MPI in High Performance Clouds

[Presentation-Demo-Discussion]

S. Xu
11:00AM - 11:30AM OSU Booth (#2094)

Efficient Designs for Distributed MPI Neighborhood Collectives

[Presentation-Demo-Discussion]

M. Ghazimirsaeed
11:30AM - 12:00PM OSU Booth (#2094)

Accelerating MPI Message Matching and Reduction Collectives For Multi-/Many-core Architectures

[Presentation-Demo-Discussion]

M. Bayatpour
12:00PM - 12:30PM OSU Booth (#2094)

Designing Next-Generation Communication Middlewares for Many-Core Architectures

[Presentation-Demo-Discussion]

J. Hashmi
12:30PM - 1:00PM OSU Booth (#2094)

Accelerating MPI Message Matching and Reduction Collectives For Multi-/Many-core Architectures

[Presentation-Demo-Discussion]

M. Bayatpour
1:00PM - 1:30PM OSU Booth (#2094)

Characterizing CUDA UM-Aware MPI libraries on Modern GPUs

[Presentation-Demo-Discussion]

K. Vadambacheri Manian
1:30PM - 2:00PM Mellanox Booth 601

Mellanox Booth Talk 2

[Talk]

DK Panda
1:30PM - 2:00PM OSU Booth (#2094)

OSU INAM: A Profiling and Visualization Tool for Scalable and In-Depth Analysis of High-Performance HPC Clusters

[Presentation-Demo-Discussion]

P. Kousha
2:00PM - 2:30PM OSU Booth (#2094)

Scalable and Distributed Deep Learning (DL): Co-design MPI Runtimes and DL Frameworks

[Presentation-Demo-Discussion]

A. Awan
2:30PM - 3:00PM OSU Booth (#2094)

The latest MVAPICH2 performance results on ABCI

[Talk]

Shinichiro Takizawa AIST, Japan
3:00PM - 3:30PM OSU Booth (#2094)

Faster Deep Learning Training with MVAPICH2-GDR on NVLink-enabled GPU Clusters

[Presentation-Demo-Discussion]

C. Chu
3:30PM - 4:00PM OSU Booth (#2094)

Designing Next-Generation Communication Middlewares for Many-Core Architectures

[Presentation-Demo-Discussion]

J. Hashmi
4:00PM - 4:30PM OSU Booth (#2094)

Performance Characterization of Distributed DNN Training: CPU vs GPU

[Presentation-Demo-Discussion]

A. Jain
4:30PM - 5:00PM OSU Booth (#2094)

Efficient Designs for Distributed MPI Neighborhood Collectives

[Presentation-Demo-Discussion]

M. Ghazimirsaeed
5:00PM - 5:30PM OSU Booth (#2094)

Design, Implementation and Evaluation of CUDA Unified Memory Aware MPI Benchmarks

[Presentation-Demo-Discussion]

K. Vadambacheri Manian
5:15PM - 6:45PM 702

MPICH BoF at SC'19

[BoF]

H. Subramoni
5:30PM - 6:00PM OSU Booth (#2094)

Scalable and Distributed Deep Learning (DL): Co-design MPI Runtimes and DL Frameworks

[Presentation-Demo-Discussion]

A. Awan

Thursday, November 21

10:00AM - 10:30AM OSU Booth (#2094)

MVAPICH Touches the Cloud New Frontiers for MPI in High Performance Clouds

[Presentation-Demo-Discussion]

S. Xu
10:30AM - 11:00AM OSU Booth (#2094)

Accelerating MPI Message Matching and Reduction Collectives For Multi-/Many-core Architectures

[Presentation-Demo-Discussion]

M. Bayatpour
11:00AM - 11:30AM OSU Booth (#2094)

Scalable and Distributed Deep Learning (DL): Co-design MPI Runtimes and DL Frameworks

[Presentation-Demo-Discussion]

A. Awan
11:30AM - 11:50AM 210-212

Designing Next-Generation Communication Middlewares for Many-Core Architectures

[Doctoral Showcase]

J. Hashmi
11:30AM - 12:00PM OSU Booth (#2094)

Experiences with OSU INAM in a Production HPC Environment

[Talk]

Karen Tomko, OSC
12:00PM - 12:30PM OSU Booth (#2094)

Faster Deep Learning Training with MVAPICH2-GDR on NVLink-enabled GPU Clusters

[Presentation-Demo-Discussion]

C. Chu
12:30PM - 1:00PM OSU Booth (#2094)

Performance Study of CUDA-Aware MPI libraries for GPU-enabled OpenPOWER Systems

[Presentation-Demo-Discussion]

K. Shafie Khorassani
1:00PM - 1:30PM OSU Booth (#2094)

Characterizing CUDA UM-Aware MPI libraries on Modern GPUs

[Presentation-Demo-Discussion]

K. Vadambacheri Manian
1:30PM - 1:50PM 210-212

Co-Designing Communication Middleware and Deep Learning Frameworks for High-Performance DNN Training on HPC Systems

[Doctoral Showcase]

A. Awan
1:30PM - 2:00PM OSU Booth (#2094)

OSU INAM: A Profiling and Visualization Tool for Scalable and In-Depth Analysis of High-Performance HPC Clusters

[Presentation-Demo-Discussion]

P. Kousha
2:00PM - 2:30PM OSU Booth (#2094)

Exploiting Network-level parallelism with Multiple Process-Endpoints for MPI Broadcast

[Presentation-Demo-Discussion]

A. Ruhela
2:10PM - 2:30PM 210-212

Efficient and Scalable Communication Middleware for Emerging Dense-GPU Clusters

[Doctoral Showcase]

C. Chu
2:30PM - 3:00PM OSU Booth (#2094)

Performance Characterization of Distributed DNN Training: CPU vs GPU

[Presentation-Demo-Discussion]

A. Jain

Friday, November 22

9:59AM - 10:19AM 405-406-407

Design and Evaluation of Shared Memory CommunicationBenchmarks on Emerging Architectures using MVAPICH2

[Paper Presentation]

S. Xu
9:59AM - 10:19AM 709

Leveraging Network-level parallelism with Multiple Process-Endpoints for MPI Broadcast

[Paper Presentation]

A. Ruhela