From Sensors to Supercomputers Eric Van Hensbergen Principal - - PowerPoint PPT Presentation

from sensors to supercomputers
SMART_READER_LITE
LIVE PREVIEW

From Sensors to Supercomputers Eric Van Hensbergen Principal - - PowerPoint PPT Presentation

From Sensors to Supercomputers Eric Van Hensbergen Principal Engineer HPC ARM Research Austin SYSTEMS RESEARCH & DEVELOPMENT ARM Primer SYSTEMS RESEARCH & DEVELOPMENT Terminology Architecture Processor Micro-Architecture


slide-1
SLIDE 1

SYSTEMS RESEARCH & DEVELOPMENT

From Sensors to Supercomputers

Eric Van Hensbergen Principal Engineer – HPC ARM Research Austin

slide-2
SLIDE 2

SYSTEMS RESEARCH & DEVELOPMENT

ARM Primer

slide-3
SLIDE 3

SYSTEMS RESEARCH & DEVELOPMENT

Terminology

Architecture “ARMv8” Processor Hard-Macro Implementation Processor Micro-Architecture “Cortex-A57”

slide-4
SLIDE 4

SYSTEMS RESEARCH & DEVELOPMENT

ARM Business Model

licence royalty IP chips ARM invests in ecosystem Ecosystem provides value chain with support & products based on ARM technology Processors GPUs Physical IP Interconnect

slide-5
SLIDE 5

SYSTEMS RESEARCH & DEVELOPMENT

Wide Choice of Partners

slide-6
SLIDE 6

SYSTEMS RESEARCH & DEVELOPMENT

Linaro – Distributed Software Organization

Working Groups Platform Engineering Landing T eams working under NDA Segment Groups T echnical Steering Committee (TSC) Kernel Consolidation Toolchain Power Management

:

Graphics LEG (15 companies) LAVA

Validation & Benchmarking

Builds & Baselines

OE/Yocto, Android, Fedora, Ubuntu

QA

Continuous Integration for Linaro output

Office of the CTO (OCTO) LNG (12 companies)

Optimization, consolidation and innovation SoC support and

  • ptimization

Validation, benchmarking and release management

slide-7
SLIDE 7

SYSTEMS RESEARCH & DEVELOPMENT

ARM: 21st Century Design

§ Focuses on Design & Licensing of IP Building

Blocks for SoCs (=LEGO’s)

§ Fosters an eco-system of standard pieces,

acting as COTS-on-Silicon

§ COTS-on-Silicon encourages multi-suppliers

through the eco-system

§ Allowing the eco-system the ability to deliver

cost effective solutions

§ Enforcing localized optimized end designs

§ Enabling circuit-boards to be miniaturized

  • nto a single chip

§ While retaining the technology DNA of

Energy-Efficiency

slide-8
SLIDE 8

SYSTEMS RESEARCH & DEVELOPMENT

Example

slide-9
SLIDE 9

SYSTEMS RESEARCH & DEVELOPMENT

ARM Spectrum

40G 4 uW/Mhz 0.01 mm2 12K Gates 28HPM 800+ MHz +FP +DSP 40LP 0.071mW/MHz 0.18 mm2 1+ GHz MP 40LP 0.12mW/MHz 0.68 mm2 2+ GHz 64-bit Fully OoO M4 M0 R4 R7 A5 A57

Cortex-M series (Microcontroller) Cortex-R series (Real Time) Cortex-A series (Application)

Note: the numbers may vary depending on specific implementation details x2 P O W E R E F F I C I E N C Y P E R F O R M A N C E

slide-10
SLIDE 10

SYSTEMS RESEARCH & DEVELOPMENT

Markets

H

  • m

e

Mobile

4.6bn

3%

in 2011

Embedded

2.3bn

25%

in 2011

Home

0.4bn

40%

in 2011

Enterprise

1.4bn

10%

in 2011

slide-11
SLIDE 11

SYSTEMS RESEARCH & DEVELOPMENT

10 Billion Cores Last Year, 50 Billion Overall

slide-12
SLIDE 12

SYSTEMS RESEARCH & DEVELOPMENT

Embedded HPC is not a new concept

slide-13
SLIDE 13

SYSTEMS RESEARCH & DEVELOPMENT

Top 500 Historical

slide-14
SLIDE 14

SYSTEMS RESEARCH & DEVELOPMENT

Why is ARM interested in HPC

1.E+05 1.E+06 1.E+07 1.E+08 1.E+09 1.E+10 1.E+11 1.E+12 1.E+13 1.E+14 1.E+15 1.E+16 1.E+17 1.E+18 1976 1978 1980 1982 1984 1986 1988 1990 1992 1994 1996 1998 2000 2002 2004 2006 2008 2010 2012 2014 2016 2018 2020

Supercomputing - #1 system on Top 500 iPad 2 == Cray 2*

* J. Dongarra & P . Luszczek HPEC 2012

Nexus 9

slide-15
SLIDE 15

SYSTEMS RESEARCH & DEVELOPMENT

Why ARM is interesting in HPC

5 10 15 20 25 30 35 6/1/1993 11/1/1993 4/1/1994 9/1/1994 2/1/1995 7/1/1995 12/1/1995 5/1/1996 10/1/1996 3/1/1997 8/1/1997 1/1/1998 6/1/1998 11/1/1998 4/1/1999 9/1/1999 2/1/2000 7/1/2000 12/1/2000 5/1/2001 10/1/2001 3/1/2002 8/1/2002 1/1/2003 6/1/2003 11/1/2003 4/1/2004 9/1/2004 2/1/2005 7/1/2005 12/1/2005 5/1/2006 10/1/2006 3/1/2007 8/1/2007 1/1/2008 6/1/2008 11/1/2008 4/1/2009 9/1/2009 2/1/2010 7/1/2010 12/1/2010 5/1/2011 10/1/2011 3/1/2012 8/1/2012 1/1/2013 6/1/2013 11/1/2013 4/1/2014 GFLOPS/Core

#1 on T

  • p 500
slide-16
SLIDE 16

SYSTEMS RESEARCH & DEVELOPMENT

System Design Space Exploration

HPC End Customers Workloads HPC Disk Image Performance Projection Design Sensitivity Studies Characterization Co-Design Centers RTL Simulation

slide-17
SLIDE 17

SYSTEMS RESEARCH & DEVELOPMENT

Research Themes

§ Co-Design

§ Workload optimizations and characterization for HPC & big data § Architectural & system design sensitivity sweeps § Simulation and modeling infrastructure

§ Software Ecosystem Enablement

§ Operating systems and runtimes targeted and optimized for ARM HPC § Math library enablement of ARM SIMD and architecture § Parallel and vector optimizing compilers and runtimes § Cross-stack optimizations for resiliency and energy efficiency

§ Acceleration

§ Compute Acceleration § IO Acceleration (Compute Near Memory, Compute Near Network, Compute Near Storage)

slide-18
SLIDE 18

SYSTEMS RESEARCH & DEVELOPMENT

Questions?