Mais conteúdo relacionado
Semelhante a Intel Ultrabook Software Development Tools - Intel AppLab Berlin (20)
Mais de Intel Developer Zone Community (8)
Intel Ultrabook Software Development Tools - Intel AppLab Berlin
- 1. Intel® Software Development Tools
for Advanced Performance
Boost Performance. Scale Forward. Ensure Confidence.
Software & Services Group
Developer Products Division Copyright© 2011, Intel Corporation. All rights reserved.
*Other brands and names are the property of their respective owners.
- 2. Who I Am…
• Uli Dumschat
• Computer Science Degree
• Mobile Tools Product Marketing @ Intel
• Since 1998 in SW Tools business, Intel since 2001
DL2BAT
Software & Services Group
Developer Products Division Copyright© 2011, Intel Corporation. All rights reserved.
*Other brands and names are the property of their respective owners. 9/4/2012 2
- 3. Intel® SSG/Developer Products Division
Premium Class Tools For Intel® Architecture
http://www.intel.com/software/products
Software & Services Group
Developer Products Division Copyright© 2011, Intel Corporation. All rights reserved.
*Other brands and names are the property of their respective owners. 9/4/2012 3
- 4. Windows* 8 Compatibility
OS/Environment Development Intel® Software
Requirements Development
Tools
Let‘s talk about
Intel Tools
For Windows*
Desktop Apps
Software & Services Group
Developer Products Division Copyright© 2011, Intel Corporation. All rights reserved.
*Other brands and names are the property of their respective owners. 9/4/2012 4
- 5. Intel® Software Development Tools Overview
Libraries Bundled Suites Compilers Analysis/
Profiling Tools
Let‘s have a
closer look! ☺
Software & Services Group
Developer Products Division Copyright© 2011, Intel Corporation. All rights reserved.
*Other brands and names are the property of their respective owners. 9/4/2012 5
- 7. Intel® Parallel Studio XE
Windows and Linux
Value Proposition
Leading Software Development Tools for
What Optimized Application Performance, Scalable Parallelism, and
Confidence
What’s
Included? • Performance - Intel tools are key to utilizing processor performance
Why • Scale forward - Your application investment extends to tomorrow’s platforms
• Confidence - Trusted software tools you can count on for best results
• Leading C++ and Fortran performance optimizing compilers libraries,
performance libraries, and analysis tools
• Advanced parallel programming models to develop code for Intel® Xeon®
How
Processors today, easily extends to Intel® MIC architecture
• Trusted software correctness tools for application quality and ensured
confidence
Software & Services Group
Developer Products Division Copyright© 2011, Intel Corporation. All rights reserved.
*Other brands and names are the property of their respective owners. 9/4/2012 7
- 8. Intel® Parallel Studio XE 2011
A Complete SW Tools Solution Covering All Phases Of SW Development
Software & Services Group
Developer Products Division Copyright© 2011, Intel Corporation. All rights reserved.
*Other brands and names are the property of their respective owners. 9/4/2012 8
- 9. Intel® Parallel Studio XE
Powerful Tools Provide Comprehensive Coverage
Phase Productivity Tool Feature Benefit
Intel® Parallel • Simplifies, demystifies, and speeds
parallel application design
Advisor
Design Threading design assistant • Available for Intel® Parallel Studio XE
for C++ Windows and Intel® C++ Studio
Windows Windows (ESD)
C/C++ and Fortran compilers
and performance libraries • Enabling solution to achieve the
Build & Intel® • Intel® Parallel Building Blocks application performance and
Debug Composer XE • Intel® Integrated Performance scalability benefits of multicore and
Primitives forward scale to manycore
• Intel® Math Kernel Library
Memory & threading dynamic • Increased productivity, code quality,
Intel® analysis for code quality and lowers cost
Verify • Finds memory, threading , and security
Inspector XE Static Security Analysis for code
quality (Studio products only) defects before they happen
Performance Profiler for • Remove guesswork, saves time, makes
Intel® VTune™
Tune optimizing application it easier to find performance and
Amplifier XE performance and scalability scalability bottlenecks
Optimized Performance, Scalable Parallelism, Confidence
Software & Services Group
Developer Products Division Copyright© 2011, Intel Corporation. All rights reserved.
*Other brands and names are the property of their respective owners. 9/4/2012 9
- 11. ®
Intel Parallel Advisor - Overview
Threading Assistant for Windows*
Design Phase Simplifies and Speeds Threading Design
Best Results with Parallelism Design Insight and Analysis
Simplifies adding Parallelism
Shorter learning curve for parallelism by helping to identify and
experiment with parallel opportunities
Step-by-step threading guidance
From surveying code, finding the best implementation, to
checking correctness.
Evaluate return on investment
Performance benefit vs. the cost of transitioning to parallelism
Software & Services Group
Developer Products Division Copyright© 2011, Intel Corporation. All rights reserved.
*Other brands and names are the property of their respective owners. 9/4/2012 11
- 12. Intel® Parallel Advisor – Overview
Design Phase Discover, Analyze, Check, Add Parallelism
Analyzes the executing serial program as developers work
through the methodology
Survey Target
Focuses effort where it will pay off and targets coarse-grain parallelism
Annotate Sources
Inserts annotations to sources to describe parallel experiments
Check Suitability
Evaluates performance impact and implication of the parallel experiments
Check Correctness
Finds and resolves conflicts before parallelism is applied. Reduces
debugging problems by defining safe and solid paths to parallelism
Models Intel® Threading Building Blocks, Intel® Cilk™
Plus, Microsoft*PPL, Windows* Threads, OpenMP*
Software & Services Group
Developer Products Division Copyright© 2011, Intel Corporation. All rights reserved.
*Other brands and names are the property of their respective owners. 9/4/2012 12
- 13. Intel Composer XE - Overview
Compilers, Performance Libraries, Debugging Tools
• Leading Performance Optimizing
Compilers
Intel® C++ - Intel C++ and Fortran Compilers
Composer XE
- Intel® Integrated Performance Primitives, Intel®
• Intel® C++ Compiler XE 12.1
• Intel® Parallel Building Blocks Math Kernel Library libraries
- Intel® Threading Building Blocks - Profile-Guided Optimization (PGO)
- Intel® Cilk™ Plus
• Intel® Math Kernel Library - Interprocedural Optimization (IPO)
• Intel® Integrated Performance - Guided-auto parallelism (GAP)
Primitives
- High-Performance Parallel Optimizer (HPO)
- SIMD Pragma
Intel® Fortran - C++ Array Notations
Composer XE • Standard Support
• Intel® Fortran Compiler XE 12.1 - OpenMP*
• Intel® Math Kernel Library - C++0x
• Intel® Integrated Performance
Primitives
- Support for key parts of the latest Fortran and
C++ standards, Visual Studio* 2010 Shell for
Visual Fortran*
• Compatibility – Mix and Match
Windows*, Linux*, Mac OS* - Binary and source compatible with
Microsoft* Visual Studio* C++ and GCC*
32-bit & 64-bit multicore processor support Supported Environments
Intel® AVX support Microsoft Visual Studio* 2005, 2008, 2010 Eclipse CDT and Mac XCode*
Software & Services Group
Developer Products Division Copyright© 2011, Intel Corporation. All rights reserved.
*Other brands and names are the property of their respective owners. 9/4/2012 13
- 14. Updated Compilers and Libraries
Produce Industry Leading Performance
• Intel v12.1 compilers improve
performance compared with:
– Competitive compilers
– Previous version Intel compilers
Intel v12.1 Intel v12.1 Intel v12.1 Intel v12.1
Compiler on Compiler on Compiler on Compiler on
Windows* vs. Linux* vs. Windows vs. Linux vs.
nearest nearest v12.0 v12.0
competitor competitor
C/C++
47% faster 12% faster 11% faster 6% faster
Integer1
C/C++
Floating 21% faster 9% faster 3% faster 1% faster
Point1
Fortran2 24% faster 17% faster 22% faster 27% faster
Notes:
1C/C++ performance measured using SPECint®_base2006 estimated
RATE benchmark running on a 64 bit operating system
2 Fortran performance measured using Polyhedron* benchmark running
on a 64 bit operating system. In this performance measurement,
“faster” refers to percent reduction in time-to-completion.
Software & Services Group
Developer Products Division Copyright© 2011, Intel Corporation. All rights reserved.
*Other brands and names are the property of their respective owners. 9/4/2012 14
- 15. A Family of Parallel Programming Models
Developer Choice
Intel® Cilk™ Plus Intel® Threading Domain-
Domain-Specific Established Research and
Building Blocks Libraries Standards Development
C/C++ language Widely used C++ Intel® Integrated Message Passing Intel® Concurrent
extensions to simplify template library for Performance Interface (MPI) Collections
parallelism parallelism Primitives
OpenMP* Offload Extensions
Intel® Math Kernel
Library Intel® Array Building
Coarray Fortran Blocks
Open sourced Open sourced Intel® SPMD Parallel
OpenCL*
Also an Intel product Also an Intel product Compiler
Choice of high-performance parallel programming models
• Libraries for pre-optimized and parallelized functionality
• Intel® Cilk™ Plus and Intel® Threading Building Blocks supports composable
parallelization of a wide variety of applications.
• OpenCL* addresses the needs of customers in specific segments, and
provides developers an additional choice to maximize their app performance
• MPI supports distributed computation, combines with other models on nodes
Software & Services Group
Developer Products Division Copyright© 2011, Intel Corporation. All rights reserved.
*Other brands and names are the property of their respective owners.
- 16. Advanced Tools to Develop Code for Intel® Xeon®
Processors Today, Easily Extends to Intel® MIC
Architecture
“SGI understands the significance of inter-
“By just utilizing standard programming
processor communications, power, density and
on both Intel® Xeon processor and Intel®
usability when architecting for exascale. Intel
MIC architecture based platforms, the
has made the leap towards exaflop computing
performance met multi-threading
with the introduction of Intel® Many Integrated
scalability expectations and we
Core (MIC) architecture. Future Intel® MIC
observed near-theoretical linear
products will satisfy all four of these priorities,
performance scaling with the number
especially with their expected ten times
of threads.” – Hongsuk Yi,
increase in compute density coupled with their
Heterogeneous Computing Team
familiar X86 programming environment.” –
Leader, KISTI Supercomputing Center
Dr. Eng Lim Goh, SGI CTO
Software & Services Group
Developer Products Division Copyright© 2011, Intel Corporation. All rights reserved.
*Other brands and names are the property of their respective owners. 9/4/2012 16
- 17. What’s New: Intel® Cilk™ Plus v1.1
Implemented with Commercial Support; Simplifies Going
Parallel
• Enhanced performance and
utilization of future Intel CPU cilk_for (int i=0; i<n; ++i) {
Foo(a[i]);
features
}
• SIMD pragma loops, vector length, Parallel loops made easy
and elemental functions support
• Mac OS* support
}int fib (int n) }int fib (int n)
{ {
if (n <= 2) if (n <= 2)
return n; return n;
else { else {
int x,y; int x,y;
x = fib(n-1); x = _cilk_spawn fib(n-1);
y = fib(n-2); y = fib(n-2);
return x+y; _cilk_sync;
} return x+y;
} }
Turn serial code } Into parallel code
Open spec at: cilkplus.org
Software & Services Group
Developer Products Division Copyright© 2011, Intel Corporation. All rights reserved.
*Other brands and names are the property of their respective owners. 9/4/2012 17
- 18. Intel® Inspector XE - Dynamic Analysis
Detects memory and threading errors
• Memory errors
• Invalid Memory Accesses
• Memory Leaks
• Uninitialized Memory Accesses
• Improper usage of Memory API(s)
• Resource Leaks (Windows only)
• Threading Errors
• Data Races
• Deadlock/Lock Hierarchy Violation
• Cross Stack Memory Accesses
No special compiles
(dynamic binary instrumentation)
Analyze DLLs (source optional)
Runs threaded
32 and 64-bit OSs
(e.g., Windows 7, RHEL 6)
Easy user interface
Software & Services Group
Developer Products Division Copyright© 2011, Intel Corporation. All rights reserved.
*Other brands and names are the property of their respective owners. 9/4/2012 18
- 19. Intel® Parallel Studio XE - Static Analysis
Detects over 250 different kinds of errors & security risks
Coding Errors (partial list)
• Memory and resource leaks
• Incorrect OpenMP* and Cilk directives
• Pointer and array errors
Security Errors (partial list)
• Buffer overflows and underflows
• Uninitialized variables and objects
• Incorrect pointer usage
• Misuse of string, memory formatting
library routines
No compiler change required
− Existing compiler for code generation
− Intel compiler front end for static
analysis
No workload required
Fast ~1.5X time of an optimizing
compile†
Easy user interface
Static Analysis is included in all Studio XE products.
It is not sold separately.
† Estimate. Your results may vary.
Software & Services Group
Developer Products Division Copyright© 2011, Intel Corporation. All rights reserved.
*Other brands and names are the property of their respective owners. 9/4/2012 19
- 20. Intel® VTune™ Amplifier XE
Performance Profiler
Where is my application…
Spending Time? Wasting Time? Waiting Too Long?
• Focus tuning on • See cache misses on • See locks by wait time
functions taking time your source • Red/Green for CPU
• See call stacks • See functions sorted by utilization during wait
• See time on source # of cache misses
• Windows & Linux We improved the performance of the
latest run 3 fold. We wouldn't have
• Low overhead found the problem without something
• No special recompiles like Intel® VTune™ Amplifier XE.
Claire Cates
Principal Developer, SAS Institute Inc.
Advanced Profiling For Scalable Multicore Performance
Software & Services Group
Developer Products Division Copyright© 2011, Intel Corporation. All rights reserved.
*Other brands and names are the property of their respective owners. 9/4/2012 20
- 21. Intel® VTune™ Amplifier XE
Tune Applications for Scalable Multicore Performance
• Fast, Accurate Performance Profiles
– Hotspot (Statistical call tree)
– Hardware-Event Based Sampling
• Thread Profiling
– Visualize thread interactions on timeline
– Balance workloads
• Easy set-up
– Pre-defined performance profiles
– Use a normal production build
• Compatible
– Microsoft, GCC, Intel compilers
– C/C++, Fortran, Assembly, .NET
– Latest Intel® processors
and compatible processors1
• Find Answers Fast
– Filter extraneous data
– View results on the source / assembly
– Event multiplexing
• Windows or Linux
– Visual Studio Integration (Windows)
– Standalone user i/f and command line 1 IA32 and Intel® 64 architectures.
– 32 and 64-bit Many features work with compatible processors.
Event based sampling requires a genuine Intel® Processor.
Software & Services Group
Developer Products Division Copyright© 2011, Intel Corporation. All rights reserved.
*Other brands and names are the property of their respective owners. 9/4/2012 21
- 23. Intel® Parallel Studio XE
Performance, Quality, and Scalable Parallelism Solutions
• Performance - Intel tools are key to
utilizing processor performance
• Scale forward - Your application
investment extends to tomorrow’s
platforms
• Confidence - Trusted software tools
you can count on
software.intel.com
Software & Services Group
Developer Products Division Copyright© 2011, Intel Corporation. All rights reserved.
*Other brands and names are the property of their respective owners. 9/4/2012 23
- 24. Intel® Parallel Studio XE Intel®
Parallel
Intel®
C++
Intel®
Fortran
Family Suites Studio XE Studio XE Studio XE
Intel® Inspector XE
Memory and Thread Checker
Analysis
Intel® Static Security Analysis
Intel® VTune™ Amplifier XE
Performance Profiler
Compilers
Intel® C++ Compiler x
Intel® Fortran Compiler x
Intel® Integrated Performance Primitives x
Libraries
Intel® x
Threading Building Blocks
Intel® Math Kernel Library
Tool
Intel® Parallel Advisor C++ Windows available x
(separate download)
Windows MSRP $1,899 $1,499 $1,599
Windows SSR $759 $599 $639
Linux MSRP $2,249 $1,499 $1,799
Linux SSR $899 $599 $719
Intel Confidential - Internal Use Only
Software & Services Group
Developer Products Division Copyright© 2011, Intel Corporation. All rights reserved.
*Other brands and names are the property of their respective owners. 9/4/2012 24
- 25. Software & Services Group
Developer Products Division Copyright© 2011, Intel Corporation. All rights reserved.
*Other brands and names are the property of their respective owners. 9/4/2012
- 26. Optimization Notice
Optimization Notice
Intel’s compilers 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 SSE2®, SSE3, and 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. Certain optimizations not specific to Intel microarchitecture are reserved for
Intel microprocessors. Please refer to the applicable product User and Reference Guides for more information
regarding the specific instruction sets covered by this notice.
Notice revision #20110804
Software & Services Group
Developer Products Division Copyright© 2011, Intel Corporation. All rights reserved.
*Other brands and names are the property of their respective owners. 9/4/2012
- 27. Legal Disclaimer
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
Software & Services Group
Developer Products Division Copyright© 2011, Intel Corporation. All rights reserved.
*Other brands and names are the property of their respective owners. 9/4/2012
- 28. Backup
Software & Services Group
Developer Products Division Copyright© 2011, Intel Corporation. All rights reserved.
*Other brands and names are the property of their respective owners.
- 29. ISV Guidance: Tools for Parallelism
App Tool Description
Distributed MPI • Multi-fabric message passing library used for making applications
perform better on IA-based clusters.
Fortran OpenMP • Need high level abstractions (instead of low level native threads)
• Look to use traditional execution patterns and utilize standards
C Intel CilkTM • Language extensions for task and data parallelism
Plus • Simple yet powerful compiler based solution with a lower overhead
OpenMP • Need high level abstractions (instead of low level native threads)
• Look to use traditional execution patterns and utilize standards
OpenCL • Use specifically when heterogeneous support is required
(CPU+GEN/NVIDIA/ATI support)
• Need low level control/API and interoperability w/ OpenGL and DX
• Requires deep expertise and advanced knowledge
C++ Intel CilkTM • Language extensions for task and data parallelism.
Plus • Simple yet powerful compiler based solution with a lower overhead
PBB (TBB) • Widely used C++ template library for task parallelism.
• Contains a rich feature set for general purpose parallelism
OpenCL • Can be used in API level, but kernel needs to be implemented in C
Select from a variety of powerful tools to aid parallelism
Although most tools can be used for multiple languages, Intel recommendations are listed above.
Software & Services Group
Developer Products Division Copyright© 2011, Intel Corporation. All rights reserved.
*Other brands and names are the property of their respective owners.