Top Banner
How to Design Scalable HPC, Deep Learning and Cloud Middleware for Exascale Systems? Dhabaleswar K. (DK) Panda The Ohio State University E-mail: [email protected] http://www.cse.ohio-state.edu/~panda Keynote Talk at HPCAC Stanford Conference (Feb ‘19) by
61

How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

May 20, 2020

Download

Documents

dariahiddleston
Welcome message from author
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Page 1: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

How to Design Scalable HPC, Deep Learning and Cloud Middleware for Exascale Systems?

Dhabaleswar K. (DK) Panda

The Ohio State University

E-mail: [email protected]

http://www.cse.ohio-state.edu/~panda

Keynote Talk at HPCAC Stanford Conference (Feb ‘19)

by

Page 2: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

HPCAC-Stanford (Feb ‘19) 2Network Based Computing Laboratory

Big Data (Hadoop, Spark,

HBase, Memcached,

etc.)

Deep Learning(Caffe, TensorFlow, BigDL,

etc.)

HPC (MPI, RDMA, Lustre, etc.)

Increasing Usage of HPC, Big Data and Deep Learning

Convergence of HPC, Big Data, and Deep Learning!

Increasing Need to Run these applications on the Cloud!!

Page 3: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

HPCAC-Stanford (Feb ‘19) 3Network Based Computing Laboratory

Can We Run Big Data and Deep Learning Jobs on Existing HPC Infrastructure?

Physical Compute

Page 4: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

HPCAC-Stanford (Feb ‘19) 4Network Based Computing Laboratory

Can We Run Big Data and Deep Learning Jobs on Existing HPC Infrastructure?

Page 5: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

HPCAC-Stanford (Feb ‘19) 5Network Based Computing Laboratory

Can We Run Big Data and Deep Learning Jobs on Existing HPC Infrastructure?

Page 6: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

HPCAC-Stanford (Feb ‘19) 6Network Based Computing Laboratory

Can We Run Big Data and Deep Learning Jobs on Existing HPC Infrastructure?

Spark Job

Hadoop Job Deep LearningJob

Page 7: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

HPCAC-Stanford (Feb ‘19) 7Network Based Computing Laboratory

• Traditional HPC

– Message Passing Interface (MPI), including MPI + OpenMP

– Exploiting Accelerators

• Deep Learning

– Caffe, CNTK, TensorFlow, and many more

• Cloud for HPC

– Virtualization with SR-IOV and Containers

HPC, Deep Learning and Cloud

Page 8: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

HPCAC-Stanford (Feb ‘19) 8Network Based Computing Laboratory

Parallel Programming Models Overview

P1 P2 P3

Shared Memory

P1 P2 P3

Memory Memory Memory

P1 P2 P3

Memory Memory Memory

Logical shared memory

Shared Memory Model

SHMEM, DSM

Distributed Memory Model

MPI (Message Passing Interface)

Partitioned Global Address Space (PGAS)

Global Arrays, UPC, Chapel, X10, CAF, …

• Programming models provide abstract machine models

• Models can be mapped on different types of systems

– e.g. Distributed Shared Memory (DSM), MPI within a node, etc.

• PGAS models and Hybrid MPI+PGAS models are gradually receiving

importance

Page 9: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

HPCAC-Stanford (Feb ‘19) 9Network Based Computing Laboratory

Supporting Programming Models for Multi-Petaflop and Exaflop Systems: Challenges

Programming ModelsMPI, PGAS (UPC, Global Arrays, OpenSHMEM), CUDA, OpenMP,

OpenACC, Cilk, Hadoop (MapReduce), Spark (RDD, DAG), etc.

Application Kernels/Applications

Networking Technologies(InfiniBand, 40/100GigE,

Aries, and Omni-Path)

Multi-/Many-coreArchitectures

Accelerators(GPU and FPGA)

MiddlewareCo-Design

Opportunities

and

Challenges

across Various

Layers

Performance

Scalability

Resilience

Communication Library or Runtime for Programming Models

Point-to-point

Communication

Collective

Communication

Energy-

Awareness

Synchronization

and Locks

I/O and

File Systems

Fault

Tolerance

Page 10: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

HPCAC-Stanford (Feb ‘19) 10Network Based Computing Laboratory

• Scalability for million to billion processors– Support for highly-efficient inter-node and intra-node communication (both two-sided and one-sided)

– Scalable job start-up

– Low memory footprint

• Scalable Collective communication– Offload

– Non-blocking

– Topology-aware

• Balancing intra-node and inter-node communication for next generation nodes (128-1024 cores)– Multiple end-points per node

• Support for efficient multi-threading

• Integrated Support for Accelerators (GPGPUs and FPGAs)

• Fault-tolerance/resiliency

• QoS support for communication and I/O

• Support for Hybrid MPI+PGAS programming (MPI + OpenMP, MPI + UPC, MPI + OpenSHMEM, MPI+UPC++, CAF, …)

• Virtualization

• Energy-Awareness

Broad Challenges in Designing Runtimes for (MPI+X) at Exascale

Page 11: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

HPCAC-Stanford (Feb ‘19) 11Network Based Computing Laboratory

Overview of the MVAPICH2 Project• High Performance open-source MPI Library for InfiniBand, Omni-Path, Ethernet/iWARP, and RDMA over Converged Ethernet (RoCE)

– MVAPICH (MPI-1), MVAPICH2 (MPI-2.2 and MPI-3.1), Started in 2001, First version available in 2002

– MVAPICH2-X (MPI + PGAS), Available since 2011

– Support for GPGPUs (MVAPICH2-GDR) and MIC (MVAPICH2-MIC), Available since 2014

– Support for Virtualization (MVAPICH2-Virt), Available since 2015

– Support for Energy-Awareness (MVAPICH2-EA), Available since 2015

– Support for InfiniBand Network Analysis and Monitoring (OSU INAM) since 2015

– Used by more than 2,950 organizations in 86 countries

– More than 522,000 (> 0.5 million) downloads from the OSU site directly

– Empowering many TOP500 clusters (Nov ‘18 ranking)

• 3rd ranked 10,649,640-core cluster (Sunway TaihuLight) at NSC, Wuxi, China

• 14th, 556,104 cores (Oakforest-PACS) in Japan

• 17th, 367,024 cores (Stampede2) at TACC

• 27th, 241,108-core (Pleiades) at NASA and many others

– Available with software stacks of many vendors and Linux Distros (RedHat, SuSE, and OpenHPC)

– http://mvapich.cse.ohio-state.edu

• Empowering Top500 systems for over a decade

Partner in the upcoming TACC Frontera System

Page 12: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

HPCAC-Stanford (Feb ‘19) 12Network Based Computing Laboratory

0

100000

200000

300000

400000

500000

600000

Sep

-04

Feb

-05

Jul-

05

Dec

-05

May

-06

Oct

-06

Mar

-07

Au

g-0

7

Jan

-08

Jun

-08

No

v-0

8

Ap

r-0

9

Sep

-09

Feb

-10

Jul-

10

Dec

-10

May

-11

Oct

-11

Mar

-12

Au

g-1

2

Jan

-13

Jun

-13

No

v-1

3

Ap

r-1

4

Sep

-14

Feb

-15

Jul-

15

Dec

-15

May

-16

Oct

-16

Mar

-17

Au

g-1

7

Jan

-18

Jun

-18

No

v-1

8

Nu

mb

er o

f D

ow

nlo

ads

Timeline

MV

0.9

.4

MV

2 0

.9.0

MV

2 0

.9.8

MV

21

.0

MV

1.0

MV

21

.0.3

MV

1.1

MV

21

.4

MV

21

.5

MV

21

.6

MV

21

.7

MV

21

.8

MV

21

.9

MV

2-G

DR

2.0

b

MV

2-M

IC 2

.0

MV

2 2

.3M

V2

-X2

.3rc

1

MV

2V

irt

2.2

MV

2-G

DR

2.3

OSU

INA

M 0

.9.4

MVAPICH2 Release Timeline and Downloads

Page 13: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

HPCAC-Stanford (Feb ‘19) 13Network Based Computing Laboratory

Architecture of MVAPICH2 Software Family

High Performance Parallel Programming Models

Message Passing Interface(MPI)

PGAS(UPC, OpenSHMEM, CAF, UPC++)

Hybrid --- MPI + X(MPI + PGAS + OpenMP/Cilk)

High Performance and Scalable Communication RuntimeDiverse APIs and Mechanisms

Point-to-

point

Primitives

Collectives

Algorithms

Energy-

Awareness

Remote

Memory

Access

I/O and

File Systems

Fault

ToleranceVirtualization

Active

MessagesJob Startup

Introspection

& Analysis

Support for Modern Networking Technology(InfiniBand, iWARP, RoCE, Omni-Path)

Support for Modern Multi-/Many-core Architectures(Intel-Xeon, OpenPower, Xeon-Phi, ARM, NVIDIA GPGPU)

Transport Protocols Modern Features

RC XRC UD DC UMR ODPSR-

IOV

Multi

Rail

Transport Mechanisms

Shared

MemoryCMA IVSHMEM

Modern Features

MCDRAM* NVLink* CAPI*

* Upcoming

XPMEM

Page 14: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

HPCAC-Stanford (Feb ‘19) 14Network Based Computing Laboratory

MVAPICH2 Software Family

Requirements Library

MPI with IB, iWARP, Omni-Path, and RoCE MVAPICH2

Advanced MPI Features/Support, OSU INAM, PGAS and MPI+PGAS with IB, Omni-Path, and RoCE

MVAPICH2-X

MPI with IB, RoCE & GPU and Support for Deep Learning MVAPICH2-GDR

HPC Cloud with MPI & IB MVAPICH2-Virt

Energy-aware MPI with IB, iWARP and RoCE MVAPICH2-EA

MPI Energy Monitoring Tool OEMT

InfiniBand Network Analysis and Monitoring OSU INAM

Microbenchmarks for Measuring MPI and PGAS Performance OMB

Page 15: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

HPCAC-Stanford (Feb ‘19) 15Network Based Computing Laboratory

• Scalability for million to billion processors– Support for highly-efficient inter-node and intra-node communication

– Scalable Start-up

– Optimized Collectives using SHArP and Multi-Leaders

– Optimized CMA-based and XPMEM-based Collectives

– Asynchronous Progress

• Exploiting Accelerators (NVIDIA GPGPUs)

• Optimized MVAPICH2 for OpenPower (with/ NVLink) and ARM

• Application Scalability and Best Practices

Overview of A Few Challenges being Addressed by the MVAPICH2 Project for Exascale

Page 16: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

HPCAC-Stanford (Feb ‘19) 16Network Based Computing Laboratory

One-way Latency: MPI over IB with MVAPICH2

0

0.2

0.4

0.6

0.8

1

1.2

1.4

1.6

1.8

2 Small Message Latency

Message Size (bytes)

Late

ncy

(u

s)

1.11

1.19

0.98

1.15

1.04

TrueScale-QDR - 3.1 GHz Deca-core (Haswell) Intel PCI Gen3 with IB switchConnectX-3-FDR - 2.8 GHz Deca-core (IvyBridge) Intel PCI Gen3 with IB switch

ConnectIB-Dual FDR - 3.1 GHz Deca-core (Haswell) Intel PCI Gen3 with IB switchConnectX-5-EDR - 3.1 GHz Deca-core (Haswell) Intel PCI Gen3 with IB Switch

Omni-Path - 3.1 GHz Deca-core (Haswell) Intel PCI Gen3 with Omni-Path switch

0

20

40

60

80

100

120TrueScale-QDRConnectX-3-FDRConnectIB-DualFDRConnectX-5-EDROmni-Path

Large Message Latency

Message Size (bytes)

Late

ncy

(u

s)

Page 17: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

HPCAC-Stanford (Feb ‘19) 17Network Based Computing Laboratory

TrueScale-QDR - 3.1 GHz Deca-core (Haswell) Intel PCI Gen3 with IB switchConnectX-3-FDR - 2.8 GHz Deca-core (IvyBridge) Intel PCI Gen3 with IB switch

ConnectIB-Dual FDR - 3.1 GHz Deca-core (Haswell) Intel PCI Gen3 with IB switchConnectX-5-EDR - 3.1 GHz Deca-core (Haswell) Intel PCI Gen3 IB switch

Omni-Path - 3.1 GHz Deca-core (Haswell) Intel PCI Gen3 with Omni-Path switch

Bandwidth: MPI over IB with MVAPICH2

0

5000

10000

15000

20000

25000TrueScale-QDR

ConnectX-3-FDR

ConnectIB-DualFDR

ConnectX-5-EDR

Omni-Path

Bidirectional Bandwidth

Ban

dw

idth

(M

Byt

es/

sec)

Message Size (bytes)

22,564

12,161

21,983

6,228

24,136

0

2000

4000

6000

8000

10000

12000

14000 Unidirectional Bandwidth

Ban

dw

idth

(M

Byt

es/

sec)

Message Size (bytes)

12,590

3,373

6,356

12,35812,366

Page 18: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

HPCAC-Stanford (Feb ‘19) 18Network Based Computing Laboratory

0

20

40

60

80

64

12

82

56

51

21

K2

K4

K8

K

16

K

32

K6

4K

12

8K

18

0K

23

0K

Tim

e (s

eco

nd

s)

Number of Processes

TACC Stampede2

MPI_Init Hello World

Startup Performance on KNL + Omni-Path

0

5

10

15

20

25

64

12

8

25

6

51

2

1K

2K

4K

8K

16

K

32

K

64

K

Tim

e (s

eco

nd

s)

Number of Processes

Oakforest-PACS

MPI_Init Hello World

22s

5.8s

21s

57s

• MPI_Init takes 22 seconds on 231,936 processes on 3,624 KNL nodes (Stampede2 – Full scale)• At 64K processes, MPI_Init and Hello World takes 5.8s and 21s respectively (Oakforest-PACS)• All numbers reported with 64 processes per node, MVAPICH2-2.3a• Designs integrated with mpirun_rsh, available for srun (SLURM launcher) as well

Page 19: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

HPCAC-Stanford (Feb ‘19) 19Network Based Computing Laboratory

Cooperative Rendezvous Protocols

Platform: 2x14 core Broadwell 2680 (2.4 GHz)

Mellanox EDR ConnectX-5 (100 GBps)

Baseline: MVAPICH2X-2.3rc1, Open MPI v3.1.0Cooperative Rendezvous Protocols for Improved Performance and Overlap

S. Chakraborty, M. Bayatpour,, J Hashmi, H. Subramoni, and DK Panda,

SC ‘18 (Best Student Paper Award Finalist)

19%16% 10%

• Use both sender and receiver CPUs to progress communication concurrently

• Dynamically select rendezvous protocol based on communication primitives and sender/receiver

availability (load balancing)

• Up to 2x improvement in large message latency and bandwidth

• Up to 19% improvement for Graph500 at 1536 processes

0

500

1000

1500

28 56 112 224 448 896 1536

Tim

e (S

eco

nd

s)

Number of Processes

Graph500MVAPICH2

Open MPI

Proposed

0

200

400

28 56 112 224 448 896 1536

Tim

e (S

eco

nd

s)

Number of Processes

CoMD

MVAPICH2

Open MPI

Proposed

0

50

100

28 56 112 224 448 896 1536

Tim

e (S

eco

nd

s)

Number of Processes

MiniGhost

MVAPICH2

Open MPI

Proposed

Will be available in upcoming MVAPICH2-X 2.3rc2

Page 20: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

HPCAC-Stanford (Feb ‘19) 20Network Based Computing Laboratory

0

0.1

0.2

0.3

0.4

(4,28) (8,28) (16,28)La

ten

cy (

seco

nd

s)

(Number of Nodes, PPN)

MVAPICH2

Benefits of SHARP Allreduce at Application Level

12%

Avg DDOT Allreduce time of HPCG

SHARP support available since MVAPICH2 2.3a

Parameter Description Default

MV2_ENABLE_SHARP=1 Enables SHARP-based collectives Disabled

--enable-sharp Configure flag to enable SHARP Disabled

• Refer to Running Collectives with Hardware based SHARP support section of MVAPICH2 user guide for more information

• http://mvapich.cse.ohio-state.edu/static/media/mvapich/mvapich2-2.3-userguide.html#x1-990006.26

Page 21: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

HPCAC-Stanford (Feb ‘19) 21Network Based Computing Laboratory

MPI_Allreduce on KNL + Omni-Path (10,240 Processes)

0

50

100

150

200

250

300

4 8 16 32 64 128 256 512 1024 2048 4096

Late

ncy

(u

s)

Message SizeMVAPICH2 MVAPICH2-OPT IMPI

0

200

400

600

800

1000

1200

1400

1600

1800

2000

8K 16K 32K 64K 128K 256K

Message SizeMVAPICH2 MVAPICH2-OPT IMPI

OSU Micro Benchmark 64 PPN

2.4X

• For MPI_Allreduce latency with 32K bytes, MVAPICH2-OPT can reduce the latency by 2.4X

M. Bayatpour, S. Chakraborty, H. Subramoni, X. Lu, and D. K. Panda, Scalable Reduction Collectives with Data Partitioning-based

Multi-Leader Design, SuperComputing '17. Available since MVAPICH2-X 2.3b

Page 22: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

HPCAC-Stanford (Feb ‘19) 22Network Based Computing Laboratory

Optimized CMA-based Collectives for Large Messages

1

10

100

1000

10000

100000

10000001K 2K 4K 8K

16K

32K

64K

128K

256K

512K 1M 2M 4M

Message Size

KNL (2 Nodes, 128 Procs)

MVAPICH2-2.3a

Intel MPI 2017

OpenMPI 2.1.0

Tuned CMA

Late

ncy

(u

s)

1

10

100

1000

10000

100000

1000000

1K 2K 4K 8K

16K

32K

64K

128K

256

K

512K 1M 2M

Message Size

KNL (4 Nodes, 256 Procs)

MVAPICH2-2.3a

Intel MPI 2017

OpenMPI 2.1.0

Tuned CMA1

10

100

1000

10000

100000

1000000

1K 2K 4K 8K

16K

32K

64K

128K

256K

512K 1M

Message Size

KNL (8 Nodes, 512 Procs)

MVAPICH2-2.3a

Intel MPI 2017

OpenMPI 2.1.0

Tuned CMA

• Significant improvement over existing implementation for Scatter/Gather with 1MB messages (up to 4x on KNL, 2x on Broadwell, 14x on OpenPower)

• New two-level algorithms for better scalability• Improved performance for other collectives (Bcast, Allgather, and Alltoall)

~ 2.5xBetter

~ 3.2xBetter

~ 4xBetter

~ 17xBetter

S. Chakraborty, H. Subramoni, and D. K. Panda, Contention Aware Kernel-Assisted MPI

Collectives for Multi/Many-core Systems, IEEE Cluster ’17, BEST Paper Finalist

Performance of MPI_Gather on KNL nodes (64PPN)

Available since MVAPICH2-X 2.3b

Page 23: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

HPCAC-Stanford (Feb ‘19) 23Network Based Computing Laboratory

Shared Address Space (XPMEM)-based Collectives Design

1

10

100

1000

10000

100000

16K 32K 64K 128K 256K 512K 1M 2M 4M

Late

ncy

(u

s)

Message Size

MVAPICH2-2.3bIMPI-2017v1.132MVAPICH2-X-2.3rc1

OSU_Allreduce (Broadwell 256 procs)

• “Shared Address Space”-based true zero-copy Reduction collective designs in MVAPICH2

• Offloaded computation/communication to peers ranks in reduction collective operation

• Up to 4X improvement for 4MB Reduce and up to 1.8X improvement for 4M AllReduce

73.2

1.8X

1

10

100

1000

10000

100000

16K 32K 64K 128K 256K 512K 1M 2M 4M

Message Size

MVAPICH2-2.3bIMPI-2017v1.132MVAPICH2-2.3rc1

OSU_Reduce (Broadwell 256 procs)

4X

36.1

37.9

16.8

J. Hashmi, S. Chakraborty, M. Bayatpour, H. Subramoni, and D. Panda, Designing Efficient Shared Address Space Reduction

Collectives for Multi-/Many-cores, International Parallel & Distributed Processing Symposium (IPDPS '18), May 2018.Available in MVAPICH2-X 2.3rc1

Page 24: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

HPCAC-Stanford (Feb ‘19) 24Network Based Computing Laboratory

Application-Level Benefits of XPMEM-Based Collectives

MiniAMR (Broadwell, ppn=16)

• Up to 20% benefits over IMPI for CNTK DNN training using AllReduce

• Up to 27% benefits over IMPI and up to 15% improvement over MVAPICH2 for MiniAMR application kernel

0

200

400

600

800

28 56 112 224

Exec

uti

on

Tim

e (s

)

No. of Processes

Intel MPIMVAPICH2MVAPICH2-XPMEM

CNTK AlexNet Training (Broadwell, B.S=default, iteration=50, ppn=28)

0

20

40

60

80

16 32 64 128 256

Exec

uti

on

Tim

e (s

)

No. of Processes

Intel MPI

MVAPICH2

MVAPICH2-XPMEM20%

9%

27%

15%

Page 25: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

HPCAC-Stanford (Feb ‘19) 25Network Based Computing Laboratory

Efficient Zero-copy MPI Datatypes for Emerging Architectures

• New designs for efficient zero-copy based MPI derived datatype processing

• Efficient schemes mitigate datatype translation, packing, and exchange overheads

• Demonstrated benefits over prevalent MPI libraries for various application kernels

• To be available in the upcoming MVAPICH2-X release

0.1

1

10

100

2 4 8 16 28

Lo

gsca

le L

ate

ncy

(mill

ise

co

nd

s)

No. of Processes

MVAPICH2X-2.3IMPI 2018IMPI 2019MVAPICH2X-Opt

5X

0.1

1

10

100

1000

Grid Dimensions (x, y, z, t)

MVAPICH2X-2.3

IMPI 2018

MVAPICH2X-Opt

19X

0.01

0.1

1

10

Grid Dimensions (x, y, z, t)

MVAPICH2X-2.3

IMPI 2018

MVAPICH2X-Opt3X

3D-Stencil Datatype Kernel on

Broadwell (2x14 core)

MILC Datatype Kernel on KNL 7250 in Flat-Quadrant Mode (64-core)

NAS-MG Datatype Kernel on OpenPOWER (20-core)

FALCON: Efficient Designs for Zero-copy MPI Datatype Processing on Emerging Architectures, J. Hashmi, S. Chakraborty, M. Bayatpour, H. Subramoni, D. K. (DK) Panda, 33rd IEEE International Parallel & Distributed Processing Symposium (IPDPS ’19), May 2019.

Page 26: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

HPCAC-Stanford (Feb ‘19) 26Network Based Computing Laboratory

0

5000

10000

15000

20000

25000

30000

224 448 896

Per

form

ance

in G

FLO

PS

Number of Processes

MVAPICH2 Async MVAPICH2 Default IMPI 2019 Default

0

1

2

3

4

5

6

7

8

9

112 224 448

Tim

e p

er

loo

p in

sec

on

ds

Number of Processes

MVAPICH2 Async MVAPICH2 Default IMPI 2019 Async

Benefits of the New Asynchronous Progress Design: Broadwell + InfiniBand

Up to 33% performance improvement in P3DFFT application with 448 processesUp to 29% performance improvement in HPL application with 896 processes

Memory Consumption = 69%

P3DFFT High Performance Linpack (HPL)

26%

27% Lower is better Higher is better

A. Ruhela, H. Subramoni, S. Chakraborty, M. Bayatpour, P. Kousha, and D.K. Panda, Efficient Asynchronous Communication Progress for MPI without Dedicated Resources, EuroMPI 2018 Available in MVAPICH2-X 2.3rc1

PPN=28

33%

29%

12%

PPN=28

8%

Page 27: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

HPCAC-Stanford (Feb ‘19) 27Network Based Computing Laboratory

• Scalability for million to billion processors

• Exploiting Accelerators (NVIDIA GPGPUs)

• Optimized MVAPICH2 for OpenPower (with/ NVLink) and ARM

• Application Scalability and Best Practices

Overview of A Few Challenges being Addressed by the MVAPICH2 Project for Exascale

Page 28: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

HPCAC-Stanford (Feb ‘19) 28Network Based Computing Laboratory

At Sender:

At Receiver:

MPI_Recv(r_devbuf, size, …);

inside

MVAPICH2

• Standard MPI interfaces used for unified data movement

• Takes advantage of Unified Virtual Addressing (>= CUDA 4.0)

• Overlaps data movement from GPU with RDMA transfers

High Performance and High Productivity

MPI_Send(s_devbuf, size, …);

GPU-Aware (CUDA-Aware) MPI Library: MVAPICH2-GPU

Page 29: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

HPCAC-Stanford (Feb ‘19) 29Network Based Computing Laboratory

CUDA-Aware MPI: MVAPICH2-GDR 1.8-2.3 Releases

• Support for MPI communication from NVIDIA GPU device memory

• High performance RDMA-based inter-node point-to-point communication (GPU-GPU, GPU-Host and Host-GPU)

• High performance intra-node point-to-point communication for multi-GPU adapters/node (GPU-GPU, GPU-Host and Host-GPU)

• Taking advantage of CUDA IPC (available since CUDA 4.1) in intra-node communication for multiple GPU adapters/node

• Optimized and tuned collectives for GPU device buffers

• MPI datatype support for point-to-point and collective communication from GPU device buffers

• Unified memory

Page 30: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

HPCAC-Stanford (Feb ‘19) 30Network Based Computing Laboratory

0

2000

4000

6000

1 2 4 8

16

32

64

12

8

25

6

51

2

1K

2K

4K

Ban

dw

idth

(M

B/s

)

Message Size (Bytes)

GPU-GPU Inter-node Bi-Bandwidth

MV2-(NO-GDR) MV2-GDR-2.3

0

1000

2000

3000

4000

1 2 4 8

16

32

64

12

8

25

6

51

2

1K

2K

4K

Ban

dw

idth

(M

B/s

)

Message Size (Bytes)

GPU-GPU Inter-node Bandwidth

MV2-(NO-GDR) MV2-GDR-2.3

0

10

20

300 1 2 4 8

16

32

64

12

8

25

6

51

2

1K

2K

4K

8K

Late

ncy

(u

s)

Message Size (Bytes)

GPU-GPU Inter-node Latency

MV2-(NO-GDR) MV2-GDR 2.3

MVAPICH2-GDR-2.3Intel Haswell (E5-2687W @ 3.10 GHz) node - 20 cores

NVIDIA Volta V100 GPUMellanox Connect-X4 EDR HCA

CUDA 9.0Mellanox OFED 4.0 with GPU-Direct-RDMA

10x

9x

Optimized MVAPICH2-GDR Design

1.85us11X

Page 31: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

HPCAC-Stanford (Feb ‘19) 31Network Based Computing Laboratory

• Platform: Wilkes (Intel Ivy Bridge + NVIDIA Tesla K20c + Mellanox Connect-IB)

• HoomdBlue Version 1.0.5

• GDRCOPY enabled: MV2_USE_CUDA=1 MV2_IBA_HCA=mlx5_0 MV2_IBA_EAGER_THRESHOLD=32768

MV2_VBUF_TOTAL_SIZE=32768 MV2_USE_GPUDIRECT_LOOPBACK_LIMIT=32768

MV2_USE_GPUDIRECT_GDRCOPY=1 MV2_USE_GPUDIRECT_GDRCOPY_LIMIT=16384

Application-Level Evaluation (HOOMD-blue)

0

500

1000

1500

2000

2500

4 8 16 32

Ave

rage

Tim

e St

eps

per

se

con

d (

TPS)

Number of Processes

MV2 MV2+GDR

0

500

1000

1500

2000

2500

3000

3500

4 8 16 32Ave

rage

Tim

e St

eps

pe

r se

con

d (

TPS)

Number of Processes

64K Particles 256K Particles

2X2X

Page 32: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

HPCAC-Stanford (Feb ‘19) 32Network Based Computing Laboratory

Application-Level Evaluation (Cosmo) and Weather Forecasting in Switzerland

0

0.2

0.4

0.6

0.8

1

1.2

16 32 64 96No

rmal

ized

Exe

cuti

on

Tim

e

Number of GPUs

CSCS GPU cluster

Default Callback-based Event-based

0

0.2

0.4

0.6

0.8

1

1.2

4 8 16 32

No

rmal

ized

Exe

cuti

on

Tim

e

Number of GPUs

Wilkes GPU Cluster

Default Callback-based Event-based

• 2X improvement on 32 GPUs nodes• 30% improvement on 96 GPU nodes (8 GPUs/node)

C. Chu, K. Hamidouche, A. Venkatesh, D. Banerjee , H. Subramoni, and D. K. Panda, Exploiting Maximal Overlap for Non-Contiguous Data

Movement Processing on Modern GPU-enabled Systems, IPDPS’16

On-going collaboration with CSCS and MeteoSwiss (Switzerland) in co-designing MV2-GDR and Cosmo Application

Cosmo model: http://www2.cosmo-model.org/content

/tasks/operational/meteoSwiss/

Page 33: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

HPCAC-Stanford (Feb ‘19) 33Network Based Computing Laboratory

MVAPICH2-GDR: Enhanced Derived Datatype Processing

• Kernel-based and GDRCOPY-based one-shot packing for inter-socket and inter-node communication

• Zero-copy (packing-free) for GPUs with peer-to-peer direct access over PCIe/NVLink

0

5

10

15

20

25

[6, 8,8,8,8] [6, 8,8,8,16] [6, 8,8,16,16] [6, 16,16,16,16]

MILC

Spee

du

p

Problem size

GPU-based DDTBench mimics MILC communication kernel

OpenMPI 4.0.0 MVAPICH2-GDR 2.3 MVAPICH2-GDR-Next

Platform: Nvidia DGX-2 system

(16 NVIDIA Volta GPUs connected with NVSwitch), CUDA 9.2

0

1

2

3

4

5

8 16 32 64

Exec

uti

on

Tim

e (s

)

Number of GPUs

Communication Kernel of COSMO Model

MVAPICH2-GDR 2.3 MVAPICH2-GDR-Next

Platform: Cray CS-Storm

(8 NVIDIA Tesla K80 GPUs per node), CUDA 8.0

Improved ~10X

Page 34: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

HPCAC-Stanford (Feb ‘19) 34Network Based Computing Laboratory

• Scalability for million to billion processors

• Exploiting Accelerators (NVIDIA GPGPUs)

• Optimized MVAPICH2 for OpenPower (with/ NVLink) and ARM

• Application Scalability and Best Practices

Overview of A Few Challenges being Addressed by the MVAPICH2 Project for Exascale

Page 35: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

HPCAC-Stanford (Feb ‘19) 35Network Based Computing Laboratory

0

0.5

1

1.5

0 1 2 4 8 16 32 64 128 256 512 1K 2K

Late

ncy

(u

s)

MVAPICH2-2.3

SpectrumMPI-10.1.0.2

OpenMPI-3.0.0

Intra-node Point-to-Point Performance on OpenPower

Platform: Two nodes of OpenPOWER (Power8-ppc64le) CPU using Mellanox EDR (MT4115) HCA

Intra-Socket Small Message Latency Intra-Socket Large Message Latency

Intra-Socket Bi-directional BandwidthIntra-Socket Bandwidth

0.30us0

20

40

60

80

4K 8K 16K 32K 64K 128K 256K 512K 1M 2M

Late

ncy

(u

s)

MVAPICH2-2.3

SpectrumMPI-10.1.0.2

OpenMPI-3.0.0

0

10000

20000

30000

40000

1 8 64 512 4K 32K 256K 2M

Ban

dw

idth

(M

B/s

)

MVAPICH2-2.3

SpectrumMPI-10.1.0.2

OpenMPI-3.0.0

0

20000

40000

60000

80000

1 8 64 512 4K 32K 256K 2M

Ban

dw

idth

(M

B/s

)

MVAPICH2-2.3

SpectrumMPI-10.1.0.2

OpenMPI-3.0.0

Page 36: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

HPCAC-Stanford (Feb ‘19) 36Network Based Computing Laboratory

0

5

10

15

20

1 2 4 8

16

32

64

12

8

25

6

51

2

1K

2K

4K

8K

Late

ncy

(u

s)

Message Size (Bytes)

INTRA-NODE LATENCY (SMALL)

Intra-Socket

Inter-Socket

MVAPICH2-GDR: Performance on OpenPOWER (NVLink + Volta)

05

1015202530

1 4

16

64

25

6

1K

4K

16

K

64

K

25

6K

1M

4MB

and

wid

th (

GB

/sec

)

Message Size (Bytes)

INTER-NODE BANDWIDTH

Platform: OpenPOWER (ppc64le) nodes equipped with a dual-socket CPU, 4 Volta V100-SXM2 GPUs, and 2port EDR InfiniBand Interconnect

0

100

200

300

400

500

16K 32K 64K 128K256K512K 1M 2M 4M

Late

ncy

(u

s)

Message Size (Bytes)

INTRA-NODE LATENCY (LARGE)

Intra-Socket

Inter-Socket

0

5

10

15

0 1 2 4 8

16

32

64

12

8

25

6

51

2

1K

2K

4K

8K

Late

ncy

(u

s)

Message Size (Bytes)

INTER-NODE LATENCY (SMALL)

0

100

200

300

400

Late

ncy

(u

s)

Message Size (Bytes)

INTER-NODE LATENCY (LARGE)

Intra-node Bandwidth: 63.7 GB/sec (NVLINK)Intra-node Latency: 5.77 us (without GDRCopy)

Inter-node Latency: 5.77 us (without GDRCopy) Inter-node Bandwidth: 23.7 GB/sec (2 port EDR)Available since MVAPICH2-GDR 2.3a

0

20

40

60

80

1 4

16

64

25

6

1K

4K

16

K

64

K

25

6K

1M

4MB

and

wid

th (

GB

/sec

)

Message Size (Bytes)

INTRA-NODE BANDWIDTH

Intra-Socket

Inter-Socket

Page 37: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

HPCAC-Stanford (Feb ‘19) 37Network Based Computing Laboratory

0

1000

2000

16K 32K 64K 128K 256K 512K 1M 2M

Late

ncy

(u

s)

MVAPICH2-GDR-Next

SpectrumMPI-10.1.0

OpenMPI-3.0.0

3X0

2000

4000

16K 32K 64K 128K 256K 512K 1M 2M

Late

ncy

(u

s)

Message Size

MVAPICH2-GDR-Next

SpectrumMPI-10.1.0

OpenMPI-3.0.0

34%

0

1000

2000

3000

4000

16K 32K 64K 128K 256K 512K 1M 2M

Late

ncy

(u

s)

Message Size

MVAPICH2-GDR-Next

SpectrumMPI-10.1.0

OpenMPI-3.0.0

0

1000

2000

16K 32K 64K 128K 256K 512K 1M 2M

Late

ncy

(u

s)MVAPICH2-GDR-Next

SpectrumMPI-10.1.0

OpenMPI-3.0.0

Optimized All-Reduce with XPMEM on OpenPOWER(N

od

es=1

, PP

N=2

0)

Optimized Runtime Parameters: MV2_CPU_BINDING_POLICY=hybrid MV2_HYBRID_BINDING_POLICY=bunch

• Optimized MPI All-Reduce Design in MVAPICH2– Up to 2X performance improvement over Spectrum MPI and 4X over OpenMPI for intra-node

2X

(No

des

=2, P

PN

=20

)

4X48%

3.3X

2X

2X

Page 38: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

HPCAC-Stanford (Feb ‘19) 38Network Based Computing Laboratory

0

0.5

1

1.5

0 1 2 4 8 16 32 64 128256512 1K 2K 4K

Late

ncy

(u

s)

MVAPICH2-2.3

Intra-node Point-to-point Performance on ARM Cortex-A72

0

2000

4000

6000

8000

10000

Ban

dw

idth

(M

B/s

)

MVAPICH2-2.3

0

5000

10000

15000

20000

Bid

irec

tio

nal

Ban

dw

idth MVAPICH2-2.3

Platform: ARM Cortex A72 (aarch64) processor with 64 cores dual-socket CPU. Each socket contains 32 cores.

Small Message Latency Large Message Latency

Bi-directional BandwidthBandwidth

0.27 micro-second

(1 bytes)

0

200

400

600

800

8K 16K 32K 64K 128K 256K 512K 1M 2M 4M

Late

ncy

(u

s)

MVAPICH2-2.3

Page 39: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

HPCAC-Stanford (Feb ‘19) 39Network Based Computing Laboratory

• Scalability for million to billion processors

• Exploiting Accelerators (NVIDIA GPGPUs)

• Optimized MVAPICH2 for OpenPower (with/ NVLink) and ARM

• Application Scalability and Best Practices

Overview of A Few Challenges being Addressed by the MVAPICH2 Project for Exascale

Page 40: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

HPCAC-Stanford (Feb ‘19) 40Network Based Computing Laboratory

0

20

40

60

80

100

120

140

160

MILC Leslie3D POP2 LAMMPS WRF2 LU

Exe

cuti

on

Tim

e in

(s)

Intel MPI 18.1.163

MVAPICH2-X-2.3rc1

31%

SPEC MPI 2007 Benchmarks: Broadwell + InfiniBand

MVAPICH2-X outperforms Intel MPI by up to 31%

Configuration: 448 processes on 16 Intel E5-2680v4 (Broadwell) nodes having 28 PPN and interconnected

with 100Gbps Mellanox MT4115 EDR ConnectX-4 HCA

29% 5%

-12%1%

11%

Page 41: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

HPCAC-Stanford (Feb ‘19) 41Network Based Computing Laboratory

Application Scalability on Skylake and KNL (Stamepede2)

MiniFE (1300x1300x1300 ~ 910 GB)

Runtime parameters: MV2_SMPI_LENGTH_QUEUE=524288 PSM2_MQ_RNDV_SHM_THRESH=128K PSM2_MQ_RNDV_HFI_THRESH=128K

0

50

100

150

2048 4096 8192

Exec

uti

on

Tim

e (s

)

No. of Processes (KNL: 64ppn)

MVAPICH2

0

20

40

60

2048 4096 8192

Exec

uti

on

Tim

e (s

)

No. of Processes (Skylake: 48ppn)

MVAPICH2

0

500

1000

1500

48 96 192 384 768No. of Processes (Skylake: 48ppn)

MVAPICH2

NEURON (YuEtAl2012)

Courtesy: Mahidhar Tatineni @SDSC, Dong Ju (DJ) Choi@SDSC, and Samuel Khuvis@OSC ---- Testbed: TACC Stampede2 using MVAPICH2-2.3b

0

1000

2000

3000

4000

64 128 256 512 1024 2048 4096

No. of Processes (KNL: 64ppn)

MVAPICH2

0

500

1000

1500

68 136 272 544 1088 2176 4352

No. of Processes (KNL: 68ppn)

MVAPICH2

0

500

1000

1500

2000

48 96 192 384 768 1536 3072No. of Processes (Skylake: 48ppn)

MVAPICH2

Cloverleaf (bm64) MPI+OpenMP, NUM_OMP_THREADS = 2

Page 42: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

HPCAC-Stanford (Feb ‘19) 42Network Based Computing Laboratory

• MPI runtime has many parameters

• Tuning a set of parameters can help you to extract higher performance

• Compiled a list of such contributions through the MVAPICH Website– http://mvapich.cse.ohio-state.edu/best_practices/

• Initial list of applications– Amber

– HoomDBlue

– HPCG

– Lulesh

– MILC

– Neuron

– SMG2000

– Cloverleaf

– SPEC (LAMMPS, POP2, TERA_TF, WRF2)

• Soliciting additional contributions, send your results to mvapich-help at cse.ohio-state.edu.

• We will link these results with credits to you.

Applications-Level Tuning: Compilation of Best Practices

Page 43: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

HPCAC-Stanford (Feb ‘19) 43Network Based Computing Laboratory

• Traditional HPC

– Message Passing Interface (MPI), including MPI + OpenMP

– Exploiting Accelerators

• Deep Learning

– Caffe, CNTK, TensorFlow, and many more

• Cloud for HPC and BigData

– Virtualization with SR-IOV and Containers

HPC, Deep Learning and Cloud

Page 44: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

HPCAC-Stanford (Feb ‘19) 44Network Based Computing Laboratory

• Deep Learning frameworks are a different game

altogether

– Unusually large message sizes (order of megabytes)

– Most communication based on GPU buffers

• Existing State-of-the-art

– cuDNN, cuBLAS, NCCL --> scale-up performance

– NCCL2, CUDA-Aware MPI --> scale-out performance

• For small and medium message sizes only!

• Proposed: Can we co-design the MPI runtime (MVAPICH2-

GDR) and the DL framework (Caffe) to achieve both?

– Efficient Overlap of Computation and Communication

– Efficient Large-Message Communication (Reductions)

– What application co-designs are needed to exploit

communication-runtime co-designs?

Deep Learning: New Challenges for MPI Runtimes

Scal

e-u

p P

erf

orm

ance

Scale-out PerformanceA. A. Awan, K. Hamidouche, J. M. Hashmi, and D. K. Panda, S-Caffe: Co-designing MPI Runtimes and Caffe for Scalable Deep Learning on Modern GPU Clusters. In Proceedings of the 22nd ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming (PPoPP '17)

cuDNN

gRPC

Hadoop

MPIMKL-DNN

DesiredNCCL1NCCL2

Page 45: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

HPCAC-Stanford (Feb ‘19) 45Network Based Computing Laboratory

• MVAPICH2-GDR offers

excellent performance via

advanced designs for

MPI_Allreduce.

• Up to 11% better

performance on the RI2

cluster (16 GPUs)

• Near-ideal – 98% scaling

efficiency

Exploiting CUDA-Aware MPI for TensorFlow (Horovod)

0

100

200

300

400

500

600

700

800

900

1000

1 2 4 8 16

Imag

es/s

eco

nd

(H

igh

er is

bet

ter)

No. of GPUs

Horovod-MPI Horovod-NCCL2 Horovod-MPI-Opt (Proposed) Ideal

MVAPICH2-GDR 2.3 (MPI-Opt) is up to 11% faster than MVAPICH2

2.3 (Basic CUDA support)

A. A. Awan et al., “Scalable Distributed DNN Training using TensorFlow and CUDA-Aware MPI: Characterization, Designs, and Performance Evaluation”, Under Review, https://arxiv.org/abs/1810.11112

Page 46: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

HPCAC-Stanford (Feb ‘19) 46Network Based Computing Laboratory

0

10000

20000

30000

40000

50000

512K 1M 2M 4M

Late

ncy

(u

s)

Message Size (Bytes)

MVAPICH2 BAIDU OPENMPI

0

1000000

2000000

3000000

4000000

5000000

6000000

83

88

608

16

77

721

6

33

55

443

2

67

10

886

4

13

42

177

28

26

84

354

56

53

68

709

12

Late

ncy

(u

s)

Message Size (Bytes)

MVAPICH2 BAIDU OPENMPI

1

10

100

1000

10000

100000

4

16

64

25

6

10

24

40

96

16

38

4

65

53

6

26

21

44

Late

ncy

(u

s)

Message Size (Bytes)

MVAPICH2 BAIDU OPENMPI

• 16 GPUs (4 nodes) MVAPICH2-GDR vs. Baidu-Allreduce and OpenMPI 3.0

MVAPICH2-GDR: Allreduce Comparison with Baidu and OpenMPI

*Available since MVAPICH2-GDR 2.3a

~30X betterMV2 is ~2X better

than Baidu

~10X better OpenMPI is ~5X slower

than Baidu

~4X better

Page 47: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

HPCAC-Stanford (Feb ‘19) 47Network Based Computing Laboratory

MVAPICH2-GDR vs. NCCL2 – Allreduce Operation

• Optimized designs in MVAPICH2-GDR 2.3 offer better/comparable performance for most cases

• MPI_Allreduce (MVAPICH2-GDR) vs. ncclAllreduce (NCCL2) on 16 GPUs

1

10

100

1000

10000

100000

Late

ncy

(u

s)

Message Size (Bytes)

MVAPICH2-GDR NCCL2

~1.2X better

Platform: Intel Xeon (Broadwell) nodes equipped with a dual-socket CPU, 1 K-80 GPUs, and EDR InfiniBand Inter-connect

1

10

100

1000

4 8

16

32

64

12

8

25

6

51

2

1K

2K

4K

8K

16

K

32

K

64

K

Late

ncy

(u

s)

Message Size (Bytes)

MVAPICH2-GDR NCCL2

~3X better

Page 48: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

HPCAC-Stanford (Feb ‘19) 48Network Based Computing Laboratory

MVAPICH2-GDR vs. NCCL2 – Allreduce Operation (DGX-2)

• Optimized designs in upcoming MVAPICH2-GDR offer better/comparable performance for most cases

• MPI_Allreduce (MVAPICH2-GDR) vs. ncclAllreduce (NCCL2) on 1 DGX-2 node (16 Volta GPUs)

1

10

100

1000

10000

Late

ncy

(u

s)

Message Size (Bytes)

MVAPICH2-GDR-Next NCCL-2.3

~1.7X better

Platform: Nvidia DGX-2 system (16 Nvidia Volta GPUs connected with NVSwitch), CUDA 9.2

0

10

20

30

40

50

60

8

16

32

64

12

8

25

6

51

2

1K

2K

4K

8K

16

K

32

K

64

K

12

8K

Late

ncy

(u

s)

Message Size (Bytes)

MVAPICH2-GDR-Next NCCL-2.3

~2.5X better

Page 49: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

HPCAC-Stanford (Feb ‘19) 49Network Based Computing Laboratory

MVAPICH2-GDR vs. NCCL2 – ResNet-50 Training

• ResNet-50 Training using TensorFlow benchmark on 1 DGX-2 node (8 Volta GPUs)

0

500

1000

1500

2000

2500

3000

1 2 4 8

Imag

e p

er s

eco

nd

Number of GPUs

NCCL-2.3 MVAPICH2-GDR-Next

7.5% higher

Platform: Nvidia DGX-2 system (16 Nvidia Volta GPUs connected with NVSwitch), CUDA 9.2

75

80

85

90

95

100

1 2 4 8

Scal

ing

Effi

cien

cy (

%)

Number of GPUs

NCCL-2.3 MVAPICH2-GDR-Next

Scaling Efficiency =Actual throughput

Ideal throughput at scale× 100%

Page 50: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

HPCAC-Stanford (Feb ‘19) 50Network Based Computing Laboratory

• Caffe : A flexible and layered Deep Learning framework.

• Benefits and Weaknesses

– Multi-GPU Training within a single node

– Performance degradation for GPUs across different

sockets

– Limited Scale-out

• OSU-Caffe: MPI-based Parallel Training

– Enable Scale-up (within a node) and Scale-out (across

multi-GPU nodes)

– Scale-out on 64 GPUs for training CIFAR-10 network on

CIFAR-10 dataset

– Scale-out on 128 GPUs for training GoogLeNet network on

ImageNet dataset

OSU-Caffe: Scalable Deep Learning

0

50

100

150

200

250

8 16 32 64 128

Trai

nin

g Ti

me

(sec

on

ds)

No. of GPUs

GoogLeNet (ImageNet) on 128 GPUs

Caffe OSU-Caffe (1024) OSU-Caffe (2048)

Invalid use caseOSU-Caffe publicly available from

http://hidl.cse.ohio-state.edu/

Page 51: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

HPCAC-Stanford (Feb ‘19) 51Network Based Computing Laboratory

• High-Performance Design of TensorFlow over RDMA-enabled Interconnects

– High performance RDMA-enhanced design with native InfiniBand support at the verbs-level for gRPC and TensorFlow

– RDMA-based data communication

– Adaptive communication protocols

– Dynamic message chunking and accumulation

– Support for RDMA device selection

– Easily configurable for different protocols (native InfiniBand and IPoIB)

• Current release: 0.9.1

– Based on Google TensorFlow 1.3.0

– Tested with

• Mellanox InfiniBand adapters (e.g., EDR)

• NVIDIA GPGPU K80

• Tested with CUDA 8.0 and CUDNN 5.0

– http://hidl.cse.ohio-state.edu

RDMA-TensorFlow Distribution

Page 52: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

HPCAC-Stanford (Feb ‘19) 52Network Based Computing Laboratory

0

50

100

150

200

16 32 64

Imag

es /

Sec

on

d

Batch Size

gRPPC (IPoIB-100Gbps)

Verbs (RDMA-100Gbps)

MPI (RDMA-100Gbps)

AR-gRPC (RDMA-100Gbps)

Performance Benefit for RDMA-TensorFlow (Inception3)

• TensorFlow Inception3 performance evaluation on an IB EDR cluster

– Up to 20% performance speedup over Default gRPC (IPoIB) for 8 GPUs

– Up to 34% performance speedup over Default gRPC (IPoIB) for 16 GPUs

– Up to 37% performance speedup over Default gRPC (IPoIB) for 24 GPUs

4 Nodes (8 GPUS) 8 Nodes (16 GPUS) 12 Nodes (24 GPUS)

0

200

400

600

16 32 64

Imag

es /

Sec

on

d

Batch Size

gRPPC (IPoIB-100Gbps)Verbs (RDMA-100Gbps)MPI (RDMA-100Gbps)AR-gRPC (RDMA-100Gbps)

0

100

200

300

400

16 32 64Im

ages

/ S

eco

nd

Batch Size

gRPPC (IPoIB-100Gbps)

Verbs (RDMA-100Gbps)

MPI (RDMA-100Gbps)

AR-gRPC (RDMA-100Gbps)

Page 53: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

HPCAC-Stanford (Feb ‘19) 53Network Based Computing Laboratory

• Traditional HPC

– Message Passing Interface (MPI), including MPI + OpenMP

– Exploiting Accelerators

• Deep Learning

– Caffe, CNTK, TensorFlow, and many more

• Cloud for HPC and BigData

– Virtualization with SR-IOV and Containers

HPC, Deep Learning and Cloud

Page 54: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

HPCAC-Stanford (Feb ‘19) 54Network Based Computing Laboratory

• Virtualization has many benefits– Fault-tolerance

– Job migration

– Compaction

• Have not been very popular in HPC due to overhead associated with Virtualization

• New SR-IOV (Single Root – IO Virtualization) support available with Mellanox InfiniBand adapters changes the field

• Enhanced MVAPICH2 support for SR-IOV

• MVAPICH2-Virt 2.2 supports:– OpenStack, Docker, and singularity

Can HPC and Virtualization be Combined?

J. Zhang, X. Lu, J. Jose, R. Shi and D. K. Panda, Can Inter-VM Shmem Benefit MPI Applications on SR-IOV based

Virtualized InfiniBand Clusters? EuroPar'14

J. Zhang, X. Lu, J. Jose, M. Li, R. Shi and D.K. Panda, High Performance MPI Library over SR-IOV enabled InfiniBand

Clusters, HiPC’14 J. Zhang, X .Lu, M. Arnold and D. K. Panda, MVAPICH2 Over OpenStack with SR-IOV: an Efficient Approach to build

HPC Clouds, CCGrid’15

Page 55: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

HPCAC-Stanford (Feb ‘19) 55Network Based Computing Laboratory

0

50

100

150

200

250

300

350

400

milc leslie3d pop2 GAPgeofem zeusmp2 lu

Exe

cuti

on

Tim

e (

s)

MV2-SR-IOV-Def

MV2-SR-IOV-Opt

MV2-Native

1%9.5%

0

1000

2000

3000

4000

5000

6000

22,20 24,10 24,16 24,20 26,10 26,16

Exe

cuti

on

Tim

e (

ms)

Problem Size (Scale, Edgefactor)

MV2-SR-IOV-Def

MV2-SR-IOV-Opt

MV2-Native2%

• 32 VMs, 6 Core/VM

• Compared to Native, 2-5% overhead for Graph500 with 128 Procs

• Compared to Native, 1-9.5% overhead for SPEC MPI2007 with 128 Procs

Application-Level Performance on Chameleon

SPEC MPI2007Graph500

5%

A Release for Azure Coming Soon

Page 56: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

HPCAC-Stanford (Feb ‘19) 56Network Based Computing Laboratory

0

500

1000

1500

2000

2500

3000

22,16 22,20 24,16 24,20 26,16 26,20

BFS

Exe

cuti

on

Tim

e (

ms)

Problem Size (Scale, Edgefactor)

Graph500

Singularity

Native

0

50

100

150

200

250

300

CG EP FT IS LU MG

Exec

uti

on

Tim

e (

s)

NPB Class D

Singularity

Native

• 512 Processes across 32 nodes

• Less than 7% and 6% overhead for NPB and Graph500, respectively

Application-Level Performance on Singularity with MVAPICH2

7%

6%

J. Zhang, X .Lu and D. K. Panda, Is Singularity-based Container Technology Ready for Running MPI Applications on HPC Clouds?,

UCC ’17, Best Student Paper Award

Page 57: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

HPCAC-Stanford (Feb ‘19) 57Network Based Computing Laboratory

0

5000

10000

15000

20000

Ban

dw

idth

(M

B/s

)

Message Size (Bytes)

GPU-GPU Inter-node Bi-Bandwidth

Docker Native

02000400060008000

1000012000

Ban

dw

idth

(M

B/s

)

Message Size (Bytes)

GPU-GPU Inter-node Bandwidth

Docker Native

1

10

100

1000

1 4 16 64 256 1K 4K 16K 64K 256K 1M 4M

Late

ncy

(u

s)

Message Size (Bytes)

GPU-GPU Inter-node Latency

Docker Native

MVAPICH2-GDR-2.3aIntel Haswell (E5-2687W @ 3.10 GHz) node - 20 cores

NVIDIA Volta V100 GPUMellanox Connect-X4 EDR HCA

CUDA 9.0Mellanox OFED 4.0 with GPU-Direct-RDMA

MVAPICH2-GDR on Container with Negligible Overhead

Works with NVIDIA HPC Container Makerhttps://github.com/NVIDIA/hpc-container-maker/blob/master/recipes/hpcbase-pgi-mvapich2.py

Page 58: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

HPCAC-Stanford (Feb ‘19) 58Network Based Computing Laboratory

• Supported through X-ScaleSolutions (http://x-scalesolutions.com)

• Benefits:

– Help and guidance with installation of the library

– Platform-specific optimizations and tuning

– Timely support for operational issues encountered with the library

– Web portal interface to submit issues and tracking their progress

– Advanced debugging techniques

– Application-specific optimizations and tuning

– Obtaining guidelines on best practices

– Periodic information on major fixes and updates

– Information on major releases

– Help with upgrading to the latest release

– Flexible Service Level Agreements

• Support provided to Lawrence Livermore National Laboratory (LLNL) for the last two years

Commercial Support for MVAPICH2, HiBD, and HiDL Libraries

Page 59: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

HPCAC-Stanford (Feb ‘19) 59Network Based Computing Laboratory

Funding Acknowledgments

Funding Support by

Equipment Support by

Page 60: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

HPCAC-Stanford (Feb ‘19) 60Network Based Computing Laboratory

Personnel AcknowledgmentsCurrent Students (Graduate)

– A. Awan (Ph.D.)

– M. Bayatpour (Ph.D.)

– S. Chakraborthy (Ph.D.)

– C.-H. Chu (Ph.D.)

– S. Guganani (Ph.D.)

Past Students

– A. Augustine (M.S.)

– P. Balaji (Ph.D.)

– R. Biswas (M.S.)

– S. Bhagvat (M.S.)

– A. Bhat (M.S.)

– D. Buntinas (Ph.D.)

– L. Chai (Ph.D.)

– B. Chandrasekharan (M.S.)

– N. Dandapanthula (M.S.)

– V. Dhanraj (M.S.)

– T. Gangadharappa (M.S.)

– K. Gopalakrishnan (M.S.)

– R. Rajachandrasekar (Ph.D.)

– G. Santhanaraman (Ph.D.)

– A. Singh (Ph.D.)

– J. Sridhar (M.S.)

– S. Sur (Ph.D.)

– H. Subramoni (Ph.D.)

– K. Vaidyanathan (Ph.D.)

– A. Vishnu (Ph.D.)

– J. Wu (Ph.D.)

– W. Yu (Ph.D.)

– J. Zhang (Ph.D.)

Past Research Scientist

– K. Hamidouche

– S. Sur

Past Post-Docs

– D. Banerjee

– X. Besseron

– H.-W. Jin

– W. Huang (Ph.D.)

– W. Jiang (M.S.)

– J. Jose (Ph.D.)

– S. Kini (M.S.)

– M. Koop (Ph.D.)

– K. Kulkarni (M.S.)

– R. Kumar (M.S.)

– S. Krishnamoorthy (M.S.)

– K. Kandalla (Ph.D.)

– M. Li (Ph.D.)

– P. Lai (M.S.)

– J. Liu (Ph.D.)

– M. Luo (Ph.D.)

– A. Mamidala (Ph.D.)

– G. Marsh (M.S.)

– V. Meshram (M.S.)

– A. Moody (M.S.)

– S. Naravula (Ph.D.)

– R. Noronha (Ph.D.)

– X. Ouyang (Ph.D.)

– S. Pai (M.S.)

– S. Potluri (Ph.D.)

– J. Hashmi (Ph.D.)

– A. Jain (Ph.D.)

– K. S. Khorassani (Ph.D.)

– P. Kousha (Ph.D.)

– D. Shankar (Ph.D.)

– J. Lin

– M. Luo

– E. Mancini

Current Research Asst. Professor

– X. Lu

Past Programmers

– D. Bureddy

– J. Perkins

Current Research Specialist

– J. Smith

– S. Marcarelli

– J. Vienne

– H. Wang

Current Post-doc

– A. Ruhela

– K. Manian

Current Students (Undergraduate)

– V. Gangal (B.S.)

– M. Haupt (B.S.)

– N. Sarkauskas (B.S.)

– A. Yeretzian (B.S.)

Past Research Specialist

– M. Arnold

Current Research Scientist

– H. Subramoni

Page 61: How to Design Scalable HPC, Deep Learning and Cloud ...€¦ · (Hadoop, Spark, HBase, Memcached, etc.) Deep Learning (Caffe, TensorFlow, BigDL, etc.) HPC (MPI, RDMA, Lustre, etc.)

HPCAC-Stanford (Feb ‘19) 61Network Based Computing Laboratory

Thank You!

Network-Based Computing Laboratoryhttp://nowlab.cse.ohio-state.edu/

[email protected]

The High-Performance MPI/PGAS Projecthttp://mvapich.cse.ohio-state.edu/

The High-Performance Deep Learning Projecthttp://hidl.cse.ohio-state.edu/

The High-Performance Big Data Projecthttp://hibd.cse.ohio-state.edu/