Intel Software Network articles Feed

Intel Architecture and Processor Identification With CPUID Model and Family Numbers

Tue, 04 Oct 2011 00:00:00 -0700

This article is intended to aid software developers in understanding the "big picture" of Intel®'s recent architecture and processor releases. The "tick tock" model adds predictability to Intel®'s architecture roadmap. However within each "tick" and "tock" architecture, multiple processors are launched to support the many diverse computing needs of consumers. While the general Instruction Set Architecture (ISA) and feature set within a given architecture are identical, certain model specific variations occur, and are generally enumerated through CPUID interrogation[1]. The CPUID model number is a convenient way of anticipating the model specific functionality that is available at runtime and subsequently designing the architecture specific parts of software (nevertheless, at runtime, the feature bits in the CPUID should always be verified before use).

The information in the table below is composed from the "Intel® Processor Identification and the CPUID Instruction" and the official Intel® product information source.

For identifying a particular processor, please use the Intel® Processor Identification Utility for Microsoft® Windows^TM operating systems or the bootable version for other operating systems[2].

Notes

The -EP suffix denotes a Dual Processor, meaning this processor is designed to operate in a Dual Processor platform (but can still operate in a Single Processor platform). The -EX suffix denotes a Multi-Processor (MP), meaning this processor is designed to operate in a Multiprocessor platform, but can still operate in a Single or Dual processor platform configuration.
The Family number is an 8-bit number derived from the processor signature by adding the Extended Family number (bits 27:20) and the Family number (bits 11:8). See section 5.1.2.2 of the "Intel Processor Identification and the CPUID Instruction".
The Model number is an 8 bit number derived from the processor signature by shifting the Extended Model number (bits 19:16) 4 bits to the left and adding the Model number (bits 7:4) . See section 5.1.2.2 of the "Intel Processor Identification and the CPUID Instruction".

Mainline Architectures and Processors

This table includes the mainline processors on 90nm and later process technology. Please read and understand these important disclaimers prior to use.

Process
Technology

Microarchitecture
Codename

Processor
Codename

Processor Signature

Family Number

Model Number

Intel® Brand
Name(s)

Intel® Brand
Processor Number

32 nm

SandyBridge

Sandy Bridge

0x206Ax

0x06

0x2A

Core™ i3
Core™ i5
Core™ i7
Celeron™ Desktop
Celeron™ Mobile
Pentium™ Desktop
Pentium™ Mobile
Xeon™ E3

i3-21xx/23xx-T/M/E/UE
i5-24xx/25xx-T/S/M/K
i7-2xxx-S/K/M/QM/LE/UE/QE
G4xx, G5xx
8xx, B8xx
350, G6xx, G6xxT, G8xx
9xx, B9xx
E3-12xx

Westmere

Arrandale

0x2065x

0x25

Celeron™ Mobile
Pentium™ Mobile
Core™ i3
Core™ i5
Core™ i7

P4xxx, U3xxx
P6xxx, U5xxx
i3-3xxE, i3-3xxM, i3-3xxUM
i5-4xxM/UM, i5-5xxE/M/UM
i7-6xxE/LE/UE/M/LM/UM

Clarksdale

Pentium™ Desktop
Core™ i3
Core™ i5
Xeon™ 3000

G69xx
i3-5xx
i5-6xx, i5-6xxK
L34xx

Gulftown

0x206Cx

0x2C

Core™ i7
Core™ i7 Extreme
Xeon™ 3000

i7-9xx
i7-9xxX
W36xx

Westmere-EP

Xeon™ 3000
Xeon™ 5000

W36xx
L56xx, E56xx, X56xx

Westmere-EX

0x206Fx

0x2F

Xeon™ E7

E7-2xxx, E7-48xx, E7-88xx

45 nm

Nehalem

Clarksfield

0x106Ex

0x1E

Core™ i7
Core™ i7 Extreme

i7-7xxQM, i7-8xxQM
i7-9xxXM

Lynnfield

Core™ i5
Core™ i7
Xeon™ 3000

i5-7xx, i5-7xxS
i7-8xx, i7-8xxS, i7-8xxK
X34xx

Jasper Forest

Xeon™ 5000
Celeron™ Desktop

LC55xx, EC55xx
P10xx

Bloomfield

0x106Ax

0x1A

Core™ i7 Extreme
Core™ i7
Xeon™ 3000

i7-965/975
i7-9x0
W35xx

Nehalem-EP

Xeon™ 5000

L55xx, E55xx, X55xx, W55xx

Nehalem-EX

0x206Ex

0x2E

Xeon™ 7000
Xeon™ 6000

L75xx, E75xx, X75xx
E65xx, X65xx

Penryn

Yorkfield

0x1067x

0x17

Core™ 2 Quad
Core™ 2 Extreme
Xeon™ 3000

Q9xxx, Q8xxx, !9xxxS
QX9xxx
L33xx, X3350

Wolfdale

Celeron™ Desktop
Core™ 2 Duo
Pentium™
Xeon™ 5000/3000

E3xxx
E7xxx, E8xxx
E5xxx, E6xxx, E6xxxK
L52xx, E31xx

Penryn

Core™ 2 Duo Mobile
Celeron™ M

P7xxx, P9xxx, SL9xxx
722

Harpertown (DP)

Xeon™ 5000

L54xx, E54xx, X54xx

Dunnington (MP)

0x106Dx

0x1D

Xeon™ 7000

L74xx, E74xx, Q7xx

65 nm

Merom

Clovertown

0x006Fx

0x0F

Xeon™ 5000

E53xx, L53xx, X53xx

Kentsfield

Xeon™ 3000
Core™ 2 Quad
Core™ 2 Extreme

X32xx
Q6600
QX6xxx

Conroe

Xeon™ 3000
Pentium™
Core™ 2 Duo
Core™ 2 Extreme
Celeron™ Desktop

30xx
E21xx
E43xx,E6xxx
X6800
E1600

Merom

Core™ 2 Duo M
Pentium™ Mobile
Core™ 2 Extreme M

L7xxx,T5xxx,T7xxx,U7xxx
T3200
X7xxx

Woodcrest

Xeon™ 5000

51xx

Merom
Conroe

0x1066x

0x16

Celeron™ Desktop
Celeron™ Mobile

4xx
5xx

Presler

Cedar Mill

0x0066x

0x0F

0x06

Pentium™ 4

3xx, 6xx

Presler

Pentium™ D

9xx

90 nm

Prescott

Nocona
Irwindale

0x0063x
0x0064x

0x03/
0x04

Xeon™

Prescott

Celeron™ D
Pentium™ 4

3xx
5xx

Dothan

Dothan

0x006Dx

0x06

0x0D

Celeron™ M
Pentium™ Mobile

3xx
7xx

Atom™ Architectures and Processors

This table includes the Atom™ processors on 45nm and later process technology. Please read and understand these important disclaimers prior to use.

Process
Technology

Architecture Codename

Processor Codename

Platform
Codename

Processor
Signature

Family
Number

Model
Number

Intel® Brand
Name(s)

Intel® Brand
Model Number

32 nm

Atom™

Cedarview

Cedar Trail

0x0366x

0x06

0x36

Atom™

N2000 series: N26xx, N28xx
D2000 Series: D25xx (no HT), D27xx

45 nm

Lincroft

Oak Trail

0x0266x

0x26

Z6xx (single core)

Pineview

Pine Trail

0x016Cx

0x1C

N4xx, D4xx (single core)
N5xx, D5xx (dual core)

Silverthorne

any

Z5xx

Disclaimers

Information in this article is intended as a convenient summary of the contents of the "Intel® Processor Identification and the CPUID Instruction" application note and the official Intel® product information source.

In case of discrepancy, the information in the original application note and product information source supersede the contents of this article. (Please notify the author of any such discrepancy).

Please consult Section 2: Usage Guidelines of the "Intel® Processor Identification and the CPUID Instruction" for the proper use of CPUID.

Intel® processor numbers are not a measure of performance. Processor numbers differentiate features within each processor family, not across different processor families. See http://www.intel.com/products/processor_number for details.

All information provided is subject to change at any time, without notice. Intel may make changes to manufacturing life cycle, specifications, and product descriptions at any time, without notice. The information herein is provided "as-is" and Intel does not make any representations or warranties whatsoever regarding accuracy of the information, nor on the product features, availability, functionality, or compatibility of the products listed. Please contact system vendor for more information on specific products or systems.

[1] For an example of interrogating CPUID to verify features please read Using CPUID to Detect the presence of SSE 4.1 and SSE 4.2 Instruction Sets

[2] In Linux based operating systems you can type ‘cat /proc/cpuinfo' to obtain the processor family and model numbers (note they are formatted in decimal, while the tables in this article containhexadecimal formatting of these numbers).

Intel® Parallel Composer – supported versions

Tue, 21 Sep 2010 00:00:00 -0700

Intel® Parallel Composer - supported versions

Interactive support for Intel® Parallel Composer, a part of the larger Intel® Parallel Studio is provided via Intel® Premier Support or the Intel® Parallel Studio User Forum. Interactive support for older versions are only supported via the Intel® Parallel Studio User Forum.

If you have any questions on the above policy, please contact Intel® Premier Support or post on the Intel Parallel Studio User Forum. Refer to Intel® Premier support frequently asked questions link for useful information.

The following Composer versions are currently supported:

•· Current release: Intel® Parallel Composer 2011 Update 6

•· Previous release: Intel® Parallel Composer update 3 and above

Note: Older versions other than those indicated above are no longer supported.

Intel® FLEXlm* License Manager FAQ

Sun, 01 Aug 2010 00:00:00 -0700

Evaluation Guide Portal from Intel

Sun, 09 May 2010 00:00:00 -0700

Intel® Software Development Products: Quick Evaluation Guides for Serial and Parallel Apps

Boost performance and reliability today with Intel^® all-in-one tool suites

Intel^® Parallel Studio and Intel^® Parallel Studio XE deliver the compilers, libraries, and error-checking and profiling tools to create reliable, high-performance applications.

Intel Parallel Studio XE helps high-performance C/C++ and Fortran developers boost performance, code reliably, and scale forward. Intel Parallel Studio enables Microsoft Visual Studio* C/C++ developers to exploit multicore.

Download the step-by-step guides and see how quickly you can improve your code by addressing a range of issues including memory leaks, performance bottlenecks, parallelism, and more. Note that each guide requires the free 30-day trial of the software.

Intel® Parallel Studio: Download a free 30-day trial >

Intel® Parallel Studio XE: Download a free 30-day trial >

Boost Performance

In many cases, recompiling just one file can give you a major performance boost.

Get the guide now

For Intel®
Parallel Studio >

For Intel®
Parallel Studio XE >

Add Parallelism

Easily apply a parallel_for to a conforming for loop for a significant performance increase—even without further tuning.

Get the guide now

For Intel®
Parallel Studio >

For Intel®
Parallel Studio XE >

Eliminate Memory Errors

Find memory leaks and threading errors before they happen at any point in your development cycle.

Get the guide now

For Intel®
Parallel Studio >

For Intel®
Parallel Studio XE >

Eliminate Threading Errors

Find threading errors like data races and deadlocks which can cause crashes and application hangs.

For Intel®
Parallel Studio XE >

Resolve Resource Leaks

Identify, analyze, and resolve resource errors in serial or parallel programs.

Get the guide now

For Intel®
Parallel Studio >

For Intel®
Parallel Studio XE >

Improve C++ Code Quality
with Static Security Analysis (SSA)

Identify errors and security weaknesses through deep analysis of C++ source code.

Get the guide now

For Intel®
Parallel Studio XE >

Improve Fortran Code Quality
with Static Security Analysis (SSA)

Identify errors and security weaknesses through deep analysis of Fortran source code.

Get the guide now

For Intel®
Parallel Studio XE>

Intel^® Cilk™ Plus

Intel Cilk Plus adds simple language extensions to express data and task parallelism to the C and C++ language implemented by the Intel^® C++ Compiler, creating a simple path to parallelism.

Get the guide now

For Intel®
Parallel Studio >

Model Parallelism

Model the parallelization of your serial application using Intel^® Parallel Advisor.

Get the guide now

For Intel®
Parallel Studio >

Intel® Software Development Products – Events

Wed, 24 Feb 2010 21:00:00 -0800

Upcoming Events

Come and see Intel® Software Development Products in action at events!

Participate in technology and product demonstrations, training talks and sessions, network with our team on the floor, and learn more about our latest and greatest products!

Spring Webinar Series
Join James Reinders, Chief Software Evangelist and Director of Software Development Products at Intel Corporation, and fellow industry leaders and innovators for discussions focused on bringing threading to Windows* applications and optimizing for multicore.
Register now

What are the Intel Password Guidelines

Mon, 19 Oct 2009 00:00:00 -0700

The following password rules are for both the Registration Center and for Premier Support.

The password must be at least eight characters long, and can contain
letters, numbers, and punctuation.
It must not exceed fourteen (14) characters.
It must contain at least one alpha character [a-z; A-Z], one numeric [0-9]
and one special character [`! @$%^&*()-_=+[];:'",<.>/?].
It cannot contain spaces.
The password cannot be the same as any of your previous eight (8) passwords.

It cannot contain your login id.
It may not contain any of the following special characters: Asterisk (*)
Comma (,) Backslash ( /) Forward Slash (\).
It must not:

Be a name (your own, family members, pets, or famous people)
Be your social security number, driver's license number, passport number or
some other identification number.
Be repeating numbers, letters or characters (111111, aaaaaa, !!!!!!)
Be a number or character combinations that are next to each other on the
keyboard (123456, asdfgh)
Be a dictionary word of any language
Begin with an exclamation point (!) or question mark (?)
Have the same first three characters.

How to find Host ID for Floating licenses

Thu, 13 Aug 2009 00:00:00 -0700

Identifying the Host Name and Host ID
The host name and host ID are system-level identifiers on supported platforms that are used in the license file to identify the node on which you plan to install the Intel License Manager for FLEXlm* and license file. To enable you to obtain a counted license, these unique values must be available when you register your product. For node-locked licenses, you will also need the host name and host id of the node from which your applications will run, if different from the node for the Intel License Manager for FLEXlm*. Follow the directions below to obtain the host name and host id for each supported platform.

For CoFluent products: Please refer to product documentation for instructions on how to find your composite host ID for node-locked and floating licenses.

Microsoft Windows*
1. From the Start menu, click Run...
2. Type cmd in the Open: field, then click OK.
3. Type ipconfig /all at the command prompt, and press Enter.

In the resulting output, host name is the value that corresponds to Host Name, and host id is the value that corresponds to Physical Address.

For example, if the output of ipconfig /all included the following:
Host Name . . . . . . . : mycomputer
. . .
Physical Address . . . . : 00-06-29-CF-74-AA
then host name is mycomputer and the host ID is 00-06-29-CF-74-AA.

Linux*
1. Run the hostname command to display the host name.
2. Run the command /sbin/ifconfig eth0 to display the hardware address.
For example, if the /sbin/ifconfig eth0 command returns
HWaddr 00:D0:B7:A8:80:AA, then the host ID is 00:D0:B7:A8:80:AA.
It is strongly recommended that users run the lmhostid utility to obtain the hostid value required to generate the counted licenses. The lmhostid utility can be found in the install location to which Intel License Manager for FLEXlm* is installed.

Mac OS* X on Intel® Architecture
1. Run the hostname command to display the host name.
2. Run the command /sbin/ifconfig en0 ether to display the hardware address.
The following is an example of an address that could be returned by this command:
en0: flags=8863 mtu 1500
ether 00:13:20:60:23:4f
It is strongly recommended that users run the lmhostid utility to obtain the hostid value required to generate the counted licenses. The lmhostid utility is installed to the same location as the Intel License Manager for FLEXlm*.

Intel® Thread Checker for Windows* - Instrumentation

Mon, 01 Dec 2008 00:00:00 -0800

Contents:

What is instrumentation?
Intel® Thread Checker instruments software before tracing it to find errors. Instrumentation adds benign Thread Checker library calls into the software to be traced. The Thread Checker library calls record information about threads, including memory accesses and APIs used, in order to find threading diagnostics including errors.

There are two different kinds of instrumentation: source and binary instrumentation.

What is source instrumentation?
Source instrumentation is added by the Intel® C++ or Fortran Compiler when C++ or Fortran source code is compiled with the -Qtcheck (Microsoft Windows*) .

What is binary instrumentation?
Binary instrumentation is added at run-time to an already built (made) binary module, including applications and dynamic or shared libraries. The instrumentation code isautomatically inserted when you run an Intel® Thread Checker activity in the VTune™ environment or the Microsoft .NET* Development Environment.Both Microsoft Windows* and Linux* executables can be instrumented for IA-32 processors, but not for Itanium® processors. Binary instrumentation can be used for software compiled with any of the supported compilers.

What system resources does instrumentation use?
The process of adding source or binary instrumentation to your software or takes time (CPU MIPs) and memory. Once the instrumentation has been added, your software will both run slower and use more memory that it usually does. This is because as your software runs, the Intel® Thread Checker library is recording the memory accesses and threading APIs that each thread uses.

Can source and binary instrumentation be used together?
Yes. Some source files of one module (applications and dynamic or shared libraries) can be compiled with source instrumentation (/Qtcheck) while other files use binary instrumentation. Some modulesof a process may use source instrumentation while others use binary instrumentation.

Which is better, source or binary instrumentation?
In general, you will get more detailed diagnostics from Intel® Thread Checker by using source instrumentation; however, you should get similar diagnostics by using either instrumentation method.

When using Microsoft Windows* threads, should I use source or binary instrumentation?
Either source or binary instrumentation can be used. If you're using one of the Microsoft Visual* C++ compilers, then it is probably easiest to use binary instrumentation. If you're using an Intel® Compiler and it's easy to re-compile your source code, then consider making an Intel® Thread Checker build using the /Qtcheck option. This will provide you with the most detailed diagnostics from Thread Checker.

When using OpenMP* threads, should I use source or binary instrumentation?
On Microsoft Windows* systems, either source or binary instrumentation can usually be used. However, if your software uses thread-count dependant OpenMP*, and then binary instrumentation should be used with the Intel® Compilers v8.0, or higher.

Note: If binary instrumentation is used for OpenMP* software that is compiled and run with the Intel® Compilers any v7.0, then Intel® Thread Checker will produce incorrect results.

When using binary instrumentation, what level should I use?
Generally using the default instrumentation level of "All Functions" is recommended for User code (applications or dynamic or shared libraries). If you're concerned that Intel® Thread Checker might be missing some diagnostics and you can afford for Thread Checker to use more memory, then consider using the "Full Image" level. You should not reduce the instrumentation level below "All Functions" for your User code because then Thread Checker may not produce an accurate and complete diagnostic list.

How do I set the default instrumentation levels?

In the VTune™ environment, you can set the default instrumentation levels via the Configure " Options... " Intel® Thread Checker " Collector " Instrumentation Levels dialog.
In the Microsoft .NET* Development Environment, you can set the default instrumentation levels via the Tools " Options... " VTune™ Performance Tools " Intel® Thread Checker " Collector " Instrumentation Levels dialog.

Note: Setting the default levels in one environment, such as the VTune environment, does not propagate the changes to other environments, such as the Microsoft .NET* Development Environment.

The instrumentation level names have changed. How do these correspond to the old level names?
T his table lists the instrumentation level names used for Intel® Thread Checker by version number:

Version 2.x	Version 1.0
Full Image	All
Custom Image	All (selective)
All Functions	Partial
Custom Functions	Partial (selective)
API Imports	Not Applicable
Module Imports	Minimal

Intel® Thread Checker for Linux* - Instrumentation

Mon, 01 Dec 2008 00:00:00 -0800

Contents:

What is instrumentation?
Intel® Thread Checker instruments software before tracing it to find errors. Instrumentation adds benign Thread Checker library calls into the software to be traced. The Thread Checker library calls record information about threads, including memory accesses and APIs used, in order to find threading diagnostics including errors.

There are two different kinds of instrumentation: source and binary instrumentation.

What is source instrumentation?
Source instrumentation is added by the Intel® C++ or Fortran Compiler when C++ or Fortran source code is compiled with the -Qtcheck (Microsoft Windows*).

What is binary instrumentation?
Binary instrumentation is added at run-time to an already built (made) binary module, including applications and dynamic or shared libraries. The instrumentation code is automatically inserted when you run an Intel® Thread Checker activity in the VTune™ environment or the Microsoft .NET* Development Environment.

What system resources does instrumentation use?
The process of adding source or binary instrumentation to your software or takes time (CPU MIPs) and memory. Once the instrumentation has been added, your software will both run slower and use more memory that it usually does. This is because as your software runs, the Intel® Thread Checker library is recording the memory accesses and threading APIs that each thread uses.

Can source and binary instrumentation be used together?
Yes. Some source files of one module (applications and dynamic or shared libraries) can be compiled with source instrumentation (/Qtcheck) while other files use binary instrumentation. Some modules of a process may use source instrumentation while others use binary instrumentation.

W hich is better, source or binary instrumentation?
In general, you will get more detailed diagnostics from Intel® Thread Checker by using source instrumentation; however, you should get similar diagnostics by using either instrumentation method.

When using OpenMP* threads, should I use source or binary instrumentation?
On Microsoft Windows* systems, either source or binary instrumentation can usually be used. However, if your software uses thread-count dependant OpenMP*, and then binary instrumentation should be used with the Intel® Compilers 8.0, or higher.

Note: If binary instrumentation is used for OpenMP* software that is compiled and run with the Intel® Compilers any v7.0, then Intel® Thread Checker will produce incorrect results.

When using binary instrumentation, what level should I use?
Generally using the default instrumentation level of "All Functions" is recommended for User code (applications or dynamic or shared libraries). If you're concerned that Intel® Thread Checker might be missing some diagnostics and you can afford for Thread Checker to use more memory, then consider using the "Full Image" level. You should not reduce the instrumentation level below "All Functions" for your User code because then Thread Checker may not produce an accurate and complete diagnostic list.

How do I set the default instrumentation levels?

In the VTune™ environment, you can set the default instrumentation levels via the Configure " Options... " Intel® Thread Checker " Collector " Instrumentation Levels dialog.
In the Microsoft .NET* Development Environment, you can set the default instrumentation levels via the Tools " Options... " VTune™ Performance Tools " Intel® Thread Checker " Collector " Instrumentation Levels dialog.

Note: Setting the default levels in one environment, such as the VTune environment, does not propagate the changes to other environments, such as the Microsoft .NET* Development Environment.

The instrumentation level names have changed. How do these correspond to the old level names?
This table lists the instrumentation level names used for Intel® Thread Checker by version number:

Version 2.x	Version 1.0
Full Image	All
Custom Image	All (selective)
All Functions	Partial
Custom Functions	Partial (selective)
API Imports	Not Applicable
Module Imports	Minimal

Intel® Thread Checker for Windows* - Tips and Techniques

Mon, 01 Dec 2008 00:00:00 -0800

Page Contents:

I don't have source code. Can I use Intel® Thread Checker?
Yes. For example: You are using an executable file from another vendor, so you don't have source code to it. But you are interested in diagnostics about a library (.dll or .so file) that is loaded by the vendor's executable file. You may not even have source code for the library that gets loaded. You can still use Thread Checker to see if any threading diagnostics are detected.Of course, if you really want to correct threading issues, you'll need source code.

DOS* Shell Redirection for Input (<) or Output (>)
My application uses DOS* command-shell redirection for input (<) or output (>). Can I still use Intel® Thread Checker? Yes. Use a .BAT file as the application. For example, create a myStart.bat file with this line:

myProgram.exe < myInputFile > myOutputFile

And then follow the steps:

Specify myProgram.exe as the Application to launch with the Intel® Thread Checker Wizard.
Enable (check) Modify default configuration when done with wizard.
Select Advanced Activity Configuration » Application/Module profiles.
Select your application, which would be myProgram in this example, and then press the Configure... button.
Disable (un-check) Add to Modules of Interest List, and then change the Application to Launch Filename: from myProgram.exe to myStart.bat.

Collecting Thread Checker Diagnostics Outside of the VTune™ Environment
To collect diagnostics outside of the VTune™ environment, follow this process:

Compile your software using an Intel® Compiler and the /Qtcheck (on Microsoft Windows*) or -tcheck (on Linux*) switch. This option enables source instrumentation.
Start your software as usual from the Windows*, DOS* or Linux* environment. For example, use Windows Explorer* to browse to your executable file and double-click on that file name.
Run your software until it terminates normally. Don't forget to reduce your workload. Also because your software is instrumented, expect that it will run slower than usual.
Exit (quit) your software, and a Thread Checker results ("*.thr") file is written to the working folder. If you are running on a Linux* system, transfer the .thr results file back to a Microsoft Windows* system (with Thread Checker installed) for viewing.
To view the results file with Windows* Explorer, simply double-click the file. Alternatively you can start the VTune environment and open it with the File » Open File ... (NOT Open Project...) dialog. Important: Don't forget to set the file type to *.thr when using this dialog.

Keep in mind that when collecting data outside of the VTune environment, only software that has been source instrumented will be analyzed by Thread Checker. Therefore, threading errors in the not instrumented software may be missed. To ensure that all run-time code is instrumented, you must run from within the VTune environment or Microsoft .NET* Developer Environment.

Note: Many third-party libraries, such as MFC* (Microsoft Foundation Class*) libraries, create and use threads. Therefore, software that uses MFC should always be run from within the VTune environment or Microsoft .NET* Developer Environment

Analyze Multiple Processes or Executables
Intel® Thread Checker only supports one process (executable) when run from within either the VTune™ environment or Microsoft .NET* Developer Environment. Furthermore, Thread Checker only supports finding diagnostics within one process; that is it will not produce diagnostics for synchronization objects shared between processes. However if your software launches another process, Thread Checker can still be used to find threading diagnostics within either process. To use Thread Checker for either process, use source instrumentation and run your software outside of the VTune™ environment.

Using Intel® Thread Checker with Applications That Have to be started Outside of VTune

Start VTune™ Performance Analyzer.
Start Intel® Thread Checker Wizard to create a new project.
Uncheck (de-select) Launch an Application.
Check (select) Modify default configuration when done with wizard, and then click Next.
Fill in your Modules of Interest. This should be your application and the DLLs (that you have symbols for) that your application depends on as it runs.
Click Finish.
Click Configure button to setup the Thread Checker data collector, and the select the Module Instrumentation tab.
In the row with YourApp.exe, set the Force Instrumentation column to Yes. If you click No in this column, a drop down menu will appear to let you set it to Yes.

Note: If you don't see the Force Instrumentation column, then you didn't Uncheck Launch an Application as described in step 3 above.
Click OK for each of the two dialog boxes. Thread Checker will begin to instrument your software. Please be patient as this will take a while (usually several minutes).
When Instrumentation has completed, Thread Checker will bring up a message box saying "It is time to run your application...". Click OK.
Start your software in the usual manner from the Windows* desktop. Wait patiently for your software to complete and/or run your software until you have executed the code path(s) of interest. Execution speed will be much slower than normal as Thread Checker needs to collect a lot of data as it monitors all threads in your software; so don't forget to reduce your workload.

Please Note: If you must abnormally terminate your software, you should use Windows Task Manager* and not the VTune environment Activity » Stop menu.
When your software has terminated, go to the VTune environment and use the Activity » Stop menu (or Shift-F5) to stop Thread Checker data collection. Thread Checker results will be loaded and displayed in the VTune environment.

Process Technology	Microarchitecture Codename	Processor Codename	Processor Signature	Family Number	Model Number	Intel® Brand Name(s)	Intel® Brand Processor Number
32 nm	SandyBridge	Sandy Bridge	0x206Ax	0x06	0x2A	Core™ i3 Core™ i5 Core™ i7 Celeron™ Desktop Celeron™ Mobile Pentium™ Desktop Pentium™ Mobile Xeon™ E3	i3-21xx/23xx-T/M/E/UE i5-24xx/25xx-T/S/M/K i7-2xxx-S/K/M/QM/LE/UE/QE G4xx, G5xx 8xx, B8xx 350, G6xx, G6xxT, G8xx 9xx, B9xx E3-12xx
	Westmere	Arrandale	0x2065x		0x25	Celeron™ Mobile Pentium™ Mobile Core™ i3 Core™ i5 Core™ i7	P4xxx, U3xxx P6xxx, U5xxx i3-3xxE, i3-3xxM, i3-3xxUM i5-4xxM/UM, i5-5xxE/M/UM i7-6xxE/LE/UE/M/LM/UM
		Clarksdale	0x2065x		0x25	Pentium™ Desktop Core™ i3 Core™ i5 Xeon™ 3000	G69xx i3-5xx i5-6xx, i5-6xxK L34xx
		Gulftown	0x206Cx		0x2C	Core™ i7 Core™ i7 Extreme Xeon™ 3000	i7-9xx i7-9xxX W36xx
		Westmere-EP	0x206Cx		0x2C	Xeon™ 3000 Xeon™ 5000	W36xx L56xx, E56xx, X56xx
		Westmere-EX	0x206Fx		0x2F	Xeon™ E7	E7-2xxx, E7-48xx, E7-88xx
45 nm	Nehalem	Clarksfield	0x106Ex		0x1E	Core™ i7 Core™ i7 Extreme	i7-7xxQM, i7-8xxQM i7-9xxXM
		Lynnfield				Core™ i5 Core™ i7 Xeon™ 3000	i5-7xx, i5-7xxS i7-8xx, i7-8xxS, i7-8xxK X34xx
		Jasper Forest				Xeon™ 5000 Celeron™ Desktop	LC55xx, EC55xx P10xx
		Bloomfield	0x106Ax		0x1A	Core™ i7 Extreme Core™ i7 Xeon™ 3000	i7-965/975 i7-9x0 W35xx
		Nehalem-EP	0x106Ax		0x1A	Xeon™ 5000	L55xx, E55xx, X55xx, W55xx
		Nehalem-EX	0x206Ex		0x2E	Xeon™ 7000 Xeon™ 6000	L75xx, E75xx, X75xx E65xx, X65xx
	Penryn	Yorkfield	0x1067x		0x17	Core™ 2 Quad Core™ 2 Extreme Xeon™ 3000	Q9xxx, Q8xxx, !9xxxS QX9xxx L33xx, X3350
		Wolfdale				Celeron™ Desktop Core™ 2 Duo Pentium™ Xeon™ 5000/3000	E3xxx E7xxx, E8xxx E5xxx, E6xxx, E6xxxK L52xx, E31xx
		Penryn				Core™ 2 Duo Mobile Celeron™ M	P7xxx, P9xxx, SL9xxx 722
		Harpertown (DP)				Xeon™ 5000	L54xx, E54xx, X54xx
		Dunnington (MP)	0x106Dx		0x1D	Xeon™ 7000	L74xx, E74xx, Q7xx
65 nm	Merom	Clovertown	0x006Fx		0x0F	Xeon™ 5000	E53xx, L53xx, X53xx
		Kentsfield				Xeon™ 3000 Core™ 2 Quad Core™ 2 Extreme	X32xx Q6600 QX6xxx
		Conroe				Xeon™ 3000 Pentium™ Core™ 2 Duo Core™ 2 Extreme Celeron™ Desktop	30xx E21xx E43xx,E6xxx X6800 E1600
		Merom				Core™ 2 Duo M Pentium™ Mobile Core™ 2 Extreme M	L7xxx,T5xxx,T7xxx,U7xxx T3200 X7xxx
		Woodcrest				Xeon™ 5000	51xx
		Merom Conroe	0x1066x		0x16	Celeron™ Desktop Celeron™ Mobile	4xx 5xx
	Presler	Cedar Mill	0x0066x	0x0F	0x06	Pentium™ 4	3xx, 6xx
	Presler	Presler	0x0066x		0x06	Pentium™ D	9xx
90 nm	Prescott	Nocona Irwindale	0x0063x 0x0064x		0x03/ 0x04	Xeon™
	Prescott	Prescott	0x0063x 0x0064x		0x03/ 0x04	Celeron™ D Pentium™ 4	3xx 5xx
	Dothan	Dothan	0x006Dx	0x06	0x0D	Celeron™ M Pentium™ Mobile	3xx 7xx

Process Technology	Architecture Codename	Processor Codename	Platform Codename	Processor Signature	Family Number	Model Number	Intel® Brand Name(s)	Intel® Brand Model Number
32 nm	Atom™	Cedarview	Cedar Trail	0x0366x	0x06	0x36	Atom™	N2000 series: N26xx, N28xx D2000 Series: D25xx (no HT), D27xx
45 nm		Lincroft	Oak Trail	0x0266x		0x26		Z6xx (single core)
		Pineview	Pine Trail	0x016Cx		0x1C		N4xx, D4xx (single core) N5xx, D5xx (dual core)
		Silverthorne	any	0x016Cx		0x1C		Z5xx

Intel Software Network articles Feed

Intel Architecture and Processor Identification With CPUID Model and Family Numbers

Intel® Parallel Composer – supported versions

Intel® FLEXlm* License Manager FAQ

Evaluation Guide Portal from Intel

Intel® Software Development Products: Quick Evaluation Guides for Serial and Parallel Apps

Boost performance and reliability today with Intel® all-in-one tool suites

Boost Performance

Add Parallelism

Eliminate Memory Errors

Eliminate Threading Errors

Resolve Resource Leaks

Improve C++ Code Quality with Static Security Analysis (SSA)

Improve Fortran Code Quality with Static Security Analysis (SSA)

Intel® Cilk™ Plus

Model Parallelism

Intel® Software Development Products – Events

What are the Intel Password Guidelines

How to find Host ID for Floating licenses

Intel® Thread Checker for Windows* - Instrumentation

Intel® Thread Checker for Linux* - Instrumentation

Intel® Thread Checker for Windows* - Tips and Techniques

Boost performance and reliability today with Intel^® all-in-one tool suites

Improve C++ Code Quality
with Static Security Analysis (SSA)

Improve Fortran Code Quality
with Static Security Analysis (SSA)

Intel^® Cilk™ Plus