intel appup™ sdk suite 1.2 for meego

Software & Services Group

Developer Products Division Copyright© 2011, Intel Corporation. All rights reserved. *Other brands and names are the property of their respective owners.

Intel AppUp™ SDK Suite 1.2 for MeeGo*

Alexander Weggerle Uli DumschatIntel® SSG/Developer Products Division

July 2011

1



Developing Mobile Applications – What We Hear

I want to port my existing apps

I want to create new apps faster

I want to publish my app quicker

I want the coolest performance

I want less power consumption

I want fast responding technical support

2



Agenda

• Overview - Intel AppUp™ SDK Suite for MeeGo*

• Create

• Test

• Tune

• Publish

3


Developer Products Division Copyright© 2011, Intel Corporation. All rights reserved. *Other brands and names are the property of their respective owners. 4

Web-based SDK

All required tools at one place

Full technical support for ALL tools

What Do We Have TodayWhat Do We Have TodayWhat Do We Have TodayWhat Do We Have Today

http://appdeveloper.intel.com/meegoGo to SDK, Downloads and Tools tab



Intel AppUp™ SDK Suite 1.2 for MeeGo*Intel AppUp™ SDK Suite 1.2 for MeeGo*Intel AppUp™ SDK Suite 1.2 for MeeGo*Intel AppUp™ SDK Suite 1.2 for MeeGo*

Create, Test, Tune and Publish Apps To Intel AppUp Center

Start Your App Development For MeeGo* Today:

http://appdeveloper.intel.com/meego

SM



Qt* Development Environment

Qt development toolsQt development toolsQt development toolsQt development toolsQt modular class libraryQt modular class libraryQt modular class libraryQt modular class library

CoreGUIWebKitGraphics ViewScriptingOpenGL

XMLMultimediaDatabaseNetwork Unit TestsBenchmarking

Qt CreatorQt CreatorQt CreatorQt CreatorCross-platform IDE

Qt DesignerQt DesignerQt DesignerQt DesignerQt QuickQt QuickQt QuickQt QuickGUI Designer

Qt LinguistQt LinguistQt LinguistQt LinguistI18NToolset

Qt Qt Qt Qt AssistantAssistantAssistantAssistantHelp reader

Qt SimulatorQt SimulatorQt SimulatorQt SimulatorDevice Simulator

CrossCrossCrossCross----platform supportplatform supportplatform supportplatform support

ChipsetsChipsetsChipsetsChipsets

CreateCreateCreateCreate

http://qt.nokia.com/products

6



Qt* CreatorCreateCreateCreateCreate

• Windows*, Linux*, Mac OS*

• QML / Qt* Quick UI designer

• Sophisticated C++ and QML code editor (code completion, etc.)

• Native & Remote Debugging

• Qt* Simulator

• and many more...

• http://developer.qt.nokia.com/wiki/QtCreatorWhitepaper

QtQtQtQt QuickQuickQuickQuick

7



Qt* SimulatorQt* SimulatorQt* SimulatorQt* Simulator

Application Testing

8

TestTestTestTest

• Qt API Simulator

• Test appearance &functionality

• Include Qt apps/services

• Sensor emulation

QEMUQEMUQEMUQEMU

• MeeGo Emulator

• Test appearance &functionality

• Test against completeMeeGo stack

Real DeviceReal DeviceReal DeviceReal Device

• Real Device

• USB or TCP/IP

• Access to real H/W



Application Debugging

9

TestTestTestTest

• GDB integrated into Qt Creator

• Native & cross debugging

– Qt Sim, Real Device

• Qt classes/objects/container

Qt* Creator / DebuggerQt* Creator / DebuggerQt* Creator / DebuggerQt* Creator / Debugger

• Sophisticated GUI

• Native & cross debugging

− QEMU, Real Device

• MeeGo awareness – threaddebugging

• Execution trace support

Intel® Application Intel® Application Intel® Application Intel® Application Debugger for MeeGo*Debugger for MeeGo*Debugger for MeeGo*Debugger for MeeGo*

Linux host onlyLinux host onlyLinux host onlyLinux host only



Execution Trace Support

• Hardware feature of Intel® Atom™ Processor• Enables viewing of execution history• Identify the root cause for exceptions

Branch Trace BufferOn chip (Intel® JTAG Debugger)

Memory allocated (Intel® Application Debugger)

Executed

ApplicationKernel or

Application

Source Code

Send Branch

Trace Information

To DebuggerBranch

10



Localize Configuration Issueswith Instruction Trace

C/C++ Source Window

C/C++ Source Window

Stop at specific OS

signal

Stop at specific OS

signal

Assembler Window

Assembler Window

Trace WindowTrace

Window

11



Optimizing Applications

Performance

Power Consumption

Maturity & Stability

Intel AppUp™SDK Suite 1.2

for MeeGo*

Next GenerationSDK Suite

Performance maps to Power Consumption!Performance maps to Power Consumption!Performance maps to Power Consumption!Performance maps to Power Consumption!

The faster an app is the earlier a system goes back into idle The faster an app is the earlier a system goes back into idle The faster an app is the earlier a system goes back into idle The faster an app is the earlier a system goes back into idle mode. Handheld systems ideally are “idle“ machines...mode. Handheld systems ideally are “idle“ machines...mode. Handheld systems ideally are “idle“ machines...mode. Handheld systems ideally are “idle“ machines...

maps tomaps tomaps tomaps tomaps tomaps tomaps tomaps to

TuneTuneTuneTune

12



Performance vs. Power Performance vs. Power Performance vs. Power Performance vs. Power

• Performance optimized

– Fast execution � earlier back to idle � less power consumption

• Power optimized– Technology driven � Silicon manufacturing process

– Optimized OS

– Efficient usage of SoC components during app execution

Today we can tune power consumption through better Today we can tune power consumption through better Today we can tune power consumption through better Today we can tune power consumption through better application performance. More to come...application performance. More to come...application performance. More to come...application performance. More to come...

Tools Tools Tools Tools ---- TodayTodayTodayTodayTools Tools Tools Tools ---- TodayTodayTodayToday

TechnologyTechnologyTechnologyTechnologyTechnologyTechnologyTechnologyTechnology

Power

time

OptimizedApp

Tools Tools Tools Tools ---- FutureFutureFutureFutureTools Tools Tools Tools ---- FutureFutureFutureFuture

TuneTuneTuneTune

13



Intel® VTune™ Amplifier XE for MeeGo*

• Identify performance bottlenecks in your app

• Time or event-based sampling

Less

eff

ort

s

Be

tte

r re

sult

s

TuneTuneTuneTune

C/C++

14

AnalyzeAnalyzeAnalyzeAnalyze

Performance Optimization Principles Performance Optimization Principles Performance Optimization Principles Performance Optimization Principles

C/C++

ReReReRe----compilecompilecompilecompile Intel® C++ Compiler for MeeGo*Intel® C++ Compiler for MeeGo*Intel® C++ Compiler for MeeGo*Intel® C++ Compiler for MeeGo*

• Optimized for Intel® Atom™ processor (in-order rescheduling)

• IPO (interprocedural optimization)

• PGO (program guided optimization)

C/C++

Use librariesUse librariesUse librariesUse libraries Intel® Integrated Performance PrimitivesIntel® Integrated Performance PrimitivesIntel® Integrated Performance PrimitivesIntel® Integrated Performance Primitives

• Highly optimized multimedia/math library functions

Intel® Threading Building Blocks Intel® Threading Building Blocks Intel® Threading Building Blocks Intel® Threading Building Blocks

• Threading libraries for parallelizing you applications withexcellent scaling to current and future processors

C/C++ASM

Modify sourcesModify sourcesModify sourcesModify sources Manual optimization Manual optimization Manual optimization Manual optimization

• Identify C and ASM – source spot optimization opportunities

• Analyse results – update sources, rebuild, analyze again

Inte

l Ap

pU

p™

SD

K S

uit

e f

or

Me

eG

o*



Intel® Intel® Intel® Intel® VTuneVTuneVTuneVTune™ ™ ™ ™ Amplifier XE for MeeGo*Amplifier XE for MeeGo*Amplifier XE for MeeGo*Amplifier XE for MeeGo*Identifies hard to find performance bottlenecksIdentifies hard to find performance bottlenecksIdentifies hard to find performance bottlenecksIdentifies hard to find performance bottlenecks

FeaturesFeaturesFeaturesFeatures• Statistic Analysis

• Stack based or Event-based Sampling

• Low overhead sampling

• No source/binary code instrumentation required

• Can monitor processor events like cache misses, etc.

• View results with corresponding source / assembly code

Intel® VTune™ Amplifier XE

*.TB5 result file

Sampling Collector

Host

Usage ModelUsage ModelUsage ModelUsage Model• Two components

− Intel® VTune™ Amplifier XE on host

− Sampling Collector on the target

• Collect data on target and analyze it on the host

The Intel® The Intel® The Intel® The Intel® VTuneVTuneVTuneVTune™ ™ ™ ™ AmplfierAmplfierAmplfierAmplfier XE tells you which module, function or XE tells you which module, function or XE tells you which module, function or XE tells you which module, function or routine could use some improvementroutine could use some improvementroutine could use some improvementroutine could use some improvement

TuneTuneTuneTune

15



Sampling - How To Find Hotspots“Hotspot Analysis“

TuneTuneTuneTune

16

StackBasedSampling

MeeGo*

Logging

file

Sampling Routine

Makes A Snapshot

Program Counter

Proc/Thread ID

Exec. module

Linux*Linux*Linux*Linux*kernelkernelkernelkernel

File For Offline Analysis

Intel®Atom™

Processor

• OS-timer-based sampling

• Time-based hotspot analysis – easy to use

• For concurrency & wait sampling

• No specific drivers required



Sampling - How To Find Hotspots“Lightweight Hotspot Analysis“

PerformanceMonitoring Unit Sampling Routine

Makes A Snapshot

Program Counter

Proc/Thread ID

Exec. module

PMUPMUPMUPMU

EventBasedSampling

File For Offline Analysis

TuneTuneTuneTune

Intel®Atom™

Processor

17

• Event-based sampling – uses PMU processor hardware feature

• Lightweight-hotspot only collect: instructions retired, clock ticks and reference clock tick. More in-depth analysis, e.g. Cache misses, branch-mispredictions, dependency/pipeline stalls

• Requires kernel driver

Logging

file



Intel® VTune™ Amplifier XE Performance Profiler

18

Where is my application…

Spending Time? Wasting Time? Waiting Too Long?

• Focus tuning on functions taking time

• See call stacks• See time on source

• See cache misses on your source

• See functions sorted by # of cache misses

• See locks by wait time

• Red/Green for CPU utilization during wait

Focus your application optimization efforts where it counts Focus your application optimization efforts where it counts Focus your application optimization efforts where it counts Focus your application optimization efforts where it counts –––– Intel® Intel® Intel® Intel® VTuneVTuneVTuneVTune™ Amplifier XE for MeeGo* ™ Amplifier XE for MeeGo* ™ Amplifier XE for MeeGo* ™ Amplifier XE for MeeGo* helps to analyze applications without helps to analyze applications without helps to analyze applications without helps to analyze applications without

source and binary instrumentationsource and binary instrumentationsource and binary instrumentationsource and binary instrumentation

TuneTuneTuneTune



Intel® C++ Compiler Advantages

19

• -xSSE3_ATOM• In-order scheduling• SIMD support• And more…

For (i=0; i<=MAX; i++)c[i] = a[i] + b[i];

+ + + +

a[3]

b[3]

c[3]

a[2]

b[2]

c[2]

a[1]

b[1]

c[1]

a[0]

b[0]

c[0]

ArchitecturalArchitecturalArchitecturalArchitectural

OptimizationsOptimizationsOptimizationsOptimizations VectorizerVectorizerVectorizerVectorizer

InterInterInterInter----ProceduralProceduralProceduralProcedural

OptimizationOptimizationOptimizationOptimization

Program GuidedProgram GuidedProgram GuidedProgram Guided

OptimizationOptimizationOptimizationOptimization

• SIMD Parallelism• Key to loop

performance• Great for multi-

media processing• And more…

• In-lining• Passing arguments

in registers• Dead-code

elimination• And more…

• Execution time feedback

• Iterative optimization process

• Use case driven• Better cache

behavior, etc.• And more…

PGOPGOIPOIPO

Use Intel® C++ Compiler for MeeGo* for higher Use Intel® C++ Compiler for MeeGo* for higher Use Intel® C++ Compiler for MeeGo* for higher Use Intel® C++ Compiler for MeeGo* for higher performance on Intel® Atom™ processorsperformance on Intel® Atom™ processorsperformance on Intel® Atom™ processorsperformance on Intel® Atom™ processors

TuneTuneTuneTune



0

0,2

0,4

0,6

0,8

1

1,2

1,4

1,6

"-O2" "Advanced" "-O2" "Advanced"

C/C++ Compiler Benchmark – Geometric Mean

GCC 4.5.0 Intel® Compiler 11.1 for Linux*

Estim

ate

d R

ela

tive P

erf

orm

ance

To G

CC 4

.5.0

(G

CC 4

.5.0

= 1

.0)

For more information on the compiler’s optimization approach, please refer to the Optimization Notice: http://software.intel.com/en-us/articles/optimization-notice/Performance tests and ratings are measured using specific computer systems and/or components and reflect the approximate performance of Intel products as measured by those tests. Any difference in system hardware or software design or configuration may affect actual performance. Buyers should consult other sources of information to evaluate the performance of systems or components they are considering purchasing. For more information on performance tests and on the performance of Intel products, reference www.intel.com/software/products or call (U.S.) 1-800-628-8686 or 1-916-356-3104

Intel does not control or audit the design or implementation of third party benchmarks or Web sites referenced in this document. Intel encourages all of its customers to visit the referenced Web sites or others where similar performance benchmarks are reported and confirm whether the referenced benchmarks are accurate and reflect performance of systems available for purchase.

*Other brands and names are the property of their respective owners

Estimated by measurement on internal systems based on the

following configuration assumptions:

• Source: Intel estimates as of July 30th, 2010

• Basis of comparison: Intel estimates of Intel and GCC compilers as of July 30th, 2010

Compilers:

• Intel® C++ Compiler 11.1 for Linux* (ICC)

• GCC 4.5.0

Hardware:

• Intel® Desk Top Board D945GCLF2 with Intel® Atom™ processor 330, 1x1.60GHz, 2GB, 512 KB, 533MHz system bus

• Form factor: Mini-ITX / micro-ATX compatible

• Chipset: Intel® 945GC and ICH7

• Audio: Realtek ALC662 audio codec (5.1 channel HD audio)

• Video: Intel® Graphics Media Accelerator 950 & S-video output support

• I/O Control: SMSC LPC47M997 based Legacy I/O controller for serial, parallel, and PS/2 ports

• LAN control: 10/100/1000 Mbits/sec LAN subsystem using the Realtek LAN adapter device

Operating System:

• Red Hat* Enterprise Linux Server release 5 (Tikanga)

SPECint*_base2000 and SPECfp*_base2000 from SPEC CPU2000 V1.3

• SPEC and SPECint, SPECfp are trademarks of the Standard Performance Evaluation Corporation. For more information see www.spec.org

• SPEC has retired SPEC CPU2000 and is no longer publishing results on its website

Compiler switches used for estimates:

“-O2“

• ICC: -O2

• GCC: -O2

“Advanced“

• ICC: -O3 -ipo -no-prec-div -xSSE3_Atom -prof_gen -prof_use

• GCC: -O3 -ffast-math -funroll-all-loops -m32 -mtune=atom -msse2 –fprofile-generate –fprofile-use

Note:

• Floating point geometric means are based on the C/C++ workloads from the SPEC CPU2000 floating point suite (177.mesa, 179.art, 183.equake, 188.ammp)

C/C++ Compiler BenchmarkIntel® C++ Compiler 11.1 for Linux* VS. GCC 4.5.0based on SPEC* CPU2000 estimated results – July 30th, 2010

46%faster 35%

faster18%faster10%

faster

TuneTuneTuneTune

20



• Highly optimized multimedia functions

– Images & video– Communication & signal

processing– Data processing

• Fully utilizing– Intel® MMX™ technology– SSE2, SSE3

• Rapid application development

• Cross-platform compatibility& code re-use

• Outstanding performance

Intel® Integrated Performance Primitives (Intel® IPP) Library

Use Use Use Use Intel IPP Intel IPP Intel IPP Intel IPP libraries to concentrate on new features rather than libraries to concentrate on new features rather than libraries to concentrate on new features rather than libraries to concentrate on new features rather than optimizing application performanceoptimizing application performanceoptimizing application performanceoptimizing application performance

Optimized for Intel® Atom™ Processor

TuneTuneTuneTune

21



“TBB helped KnowledgeMinerachieve speeds 8x faster on an 8 core system. In addition, a strict redesign of KnowledgeMiner for parallel computing is giving a total speedup over the previous version 400x. This astonishing change in speed allows KnowledgeMiner to operate in almost real time, something we didn’t previously think was possible.”

Frank LemkeFounder and President

KnowledgeMiner Software

Intel® Threading Building Blocks

• Scalable performance

• Make multi-threaded application development practical

– A C++ template library that uses familiar task patterns, not threads

– A high level abstraction requiring less code for threading without sacrificing performance

• Maximize application performance

– Appropriately scales to the number of cores available

• Works with Intel® Hyper-Threading technology enabled Intel® Atom™ processors, as well as dual-core processors

• Available as open source at opentbb.org

Book available from O’Reilly publishing

22

TuneTuneTuneTune



Publishing to Intel AppUp SM Center

• MeeGo* AppUpSM SDK for Windows*

• Tools framework for app publishing

• App licensing

• Update mechanism

• Offers C and C++ API

• Contains:

• API Libraries

• Documentation

• Qt* Creator setup

• Auto RPM packaging

• Intel AppUpTM Software Debugger

• Requires: Intel AppUp™ SDK Suite for MeeGo* or open source MeeGo* SDK

PublishPublishPublishPublish

23



Vision

• Ease-of-use

• Full MeeGo* integration

–Complete Solution

–Qt* Creator integration

• Power Analysis Tools

• Porting Tools

• ... and more!

• BETA 1 – July 18th

– CNDA required!

24



Thank You!

25



Optimization Notice

27

Optimization Notice

Intel compilers, associated libraries and associated development tools may include or utilize options that optimize for instruction sets that are available in both Intel and non-Intel microprocessors (for example SIMD instruction sets), but do not optimize equally for non-Intel microprocessors. In addition, certain compiler options for Intel compilers, including some that are not specific to Intel micro-architecture, are reserved for Intel microprocessors. For a detailed description of Intel compiler options, including the instruction sets and specific microprocessors they implicate, please refer to the “Intel Compiler User and Reference Guides” under “Compiler Options." Many library routines that are part of Intel compiler products are more highly optimized for Intel microprocessors than for other microprocessors. While the compilers and libraries in Intel compiler products offer optimizations for both Intel and Intel-compatible microprocessors, depending on the options you select, your code and other factors, you likely will get extra performance on Intel microprocessors.

Intel compilers, associated libraries and associated development tools may or may not optimize to the same degree for non-Intel microprocessors for optimizations that are not unique to Intel microprocessors. These optimizations include Intel® Streaming SIMD Extensions 2 (Intel® SSE2), Intel® Streaming SIMD Extensions 3 (Intel® SSE3), and Supplemental Streaming SIMD Extensions 3 (Intel SSSE3) instruction sets and other optimizations. Intel does not guarantee the availability, functionality, or effectiveness of any optimization on microprocessors not manufactured by Intel. Microprocessor-dependent optimizations in this product are intended for use with Intel microprocessors.

While Intel believes our compilers and libraries are excellent choices to assist in obtaining the best performance on Intel and non-Intel microprocessors, Intel recommends that you evaluate other compilers and libraries to determine which best meet your requirements. We hope to win your business by striving to offer the best performance of any compiler or library; please let us know if you find we do not.

Notice revision #20110307



Legal Disclaimer

28

INFORMATION IN THIS DOCUMENT IS PROVIDED “AS IS”. NO LICENSE, EXPRESS OR IMPLIED, BY ESTOPPEL OR OTHERWISE, TO ANY INTELLECTUAL PROPERTY RIGHTS IS GRANTED BY THIS DOCUMENT. INTEL ASSUMES NO LIABILITY WHATSOEVER AND INTEL DISCLAIMS ANY EXPRESS OR IMPLIED WARRANTY, RELATING TO THIS INFORMATION INCLUDING LIABILITY OR WARRANTIES RELATING TO FITNESS FOR A PARTICULAR PURPOSE, MERCHANTABILITY, OR INFRINGEMENT OF ANY PATENT, COPYRIGHT OR OTHER INTELLECTUAL PROPERTY RIGHT.

Performance tests and ratings are measured using specific computer systems and/or components and reflect the approximate performance of Intel products as measured by those tests. Any difference in system hardware or software design or configuration may affect actual performance. Buyers should consult other sources of information to evaluate the performance of systems or components they are considering purchasing. For more information on performance tests and on the performance of Intel products, reference www.intel.com/software/products.

BunnyPeople, Celeron, Celeron Inside, Centrino, Centrino Atom, Centrino Atom Inside, Centrino Inside, Centrino logo, Cilk, Core Inside, FlashFile, i960, InstantIP, Intel, the Intel logo, Intel386, Intel486, IntelDX2, IntelDX4, IntelSX2, Intel Atom, Intel Atom Inside, Intel Core, Intel Inside, Intel Inside logo, Intel. Leap ahead., Intel. Leap ahead. logo, Intel NetBurst, Intel NetMerge, Intel NetStructure, Intel SingleDriver, Intel SpeedStep, Intel StrataFlash, Intel Viiv, Intel vPro, Intel XScale, Itanium, Itanium Inside, MCS, MMX, Oplus, OverDrive, PDCharm, Pentium, Pentium Inside, skoool, Sound Mark, The Journey Inside, Viiv Inside, vPro Inside, VTune, Xeon, and Xeon Inside are trademarks of Intel Corporation in the U.S. and other countries.*Other names and brands may be claimed as the property of others.

Copyright © 2011. Intel Corporation.

http://intel.com/software/products

intel appup™ sdk suite 1.2 for meego

Technology

intel corporation

intel application qt

respective owners

intel appupsm centerstart

qml qt

qt appsservices test

native remote debugging

sdk suitefor meego