News Press Release :: New Intel compilers pave the way for Hyper-threading technology

{param}


December 3, 2002 – Intel Corporation today introduced updated tools to help software developers optimize applications for Intel’s expanding family of architectures with key innovations such as Intel’s Hyper Threading Technology.

Version 7.0 of Intel® C++ and Intel® Fortran compilers for Windows* and Linux* can improve the performance of applications for Intel® Itanium® 2, Intel® Xeon and Intel® Pentium® 4 processor-based systems up to 40 percent when compared to compilers currently available from other vendors.**

Software developers use compilers to translate a programming language, such as C++ or Fortran, into the machine language understood by the processor. A more efficient compiler results in better application performance. Intel’s compilers are designed to help software developers deliver improved performance for their applications running on Intel-based computing and communication systems.

“Intel compilers enable software developers to make their applications more competitive with improved performance,” said Jon Khazam, director of Intel’s Software Products Division. “Intel’s high-performance tools are also compatible with leading development environments for Windows and Linux.”



Because of Intel’s expertise in processor architecture, its compilers have been highly optimized for the Intel Itanium 2, Intel Pentium 4 and the Intel Xeon processors, resulting in a better compiled application for faster operations. Types of applications that will achieve enhanced performance when built using Intel compilers include commercial, transaction-oriented computing, computationally intensive financial, engineering and scientific applications, digital media, gaming and special effects.

The new compilers support many features of Compaq* Visual Fortran, including command line compatibility and include extensive integration into Microsoft* Visual Studio. The Linux version provides GNU compatibility to C++ with the adoption of the C++ application binary interface. These compatibility features make it easier for application developers to start using Intel compilers to see how their applications might perform better on the Intel Architecture.

Intel’s compilers also help developers produce multi-threaded applications and take advantage of Intel’s Hyper-Threading technology. Threading is a software development technique that identifies tasks that can be done simultaneously. Intel’s Hyper-Threading technology enables a single physical processor to create a simulated logical processor to run multiple tasks at the same time.

The new version 7.0 Intel Compilers include an auto-parallelization option that automatically looks for opportunities in applications to create multiple execution threads and enhancements to OpenMP* support. OpenMP is the industry standard that enables the use of high-level directives that simplify the creation and management of multi-threaded application software.

“Our application is heavily used in very large and time consuming data mining applications, so it is of great importance to get the best performance possible,” said Dr. Fons Rademakers, senior scientist at CERN. “We ported 800,000 lines of C++ and 90,000 lines of C source code to the Intel compiler in one afternoon, an activity that previously took us about a week.”

Version 7.0 of the Intel C++ Compilers for Windows and Linux are now available for the suggested list prices of $399 each. Version 7.0 of the Intel Fortran Compilers for Windows and Linux are now available for the suggested list prices of $499 and $699 respectively. The compilers are available today from Intel and resellers worldwide for download and will be available on CDROMs by the end of the month. More information is available at www.intel.com/software/products <http://www.intel.com/software/products> .

Intel, the world’s largest chip maker, is also a leading manufacturer of computer, networking and communications products. Additional information about Intel is available at www.intel.com/pressroom.




Intel and Pentium are trademarks or registered trademarks of Intel Corporation or its subsidiaries in the United States and other countries.

* Other marks and brands may be claimed as the property of others.

** Performance will vary based on system configuration. For more information on the performance of Intel products, visit http://www.intel.com/performance/resources/limits.htm.

*** Hyper-Threading Technology requires a computer system with an Intel Pentium 4 processor at 3.06 GHz or higher, a chipset and BIOS that utilize this technology, and an operating system that includes optimizations for this technology. Performance will vary depending on the specific hardware and software you use. See www.intel.com/info/hyperthreading <http://www.intel.com/info/hyperthreading> for information

 

So far I'm not impressed... To wit a demo by PC Pro (June issue):

Lightwave 7 render on a dual Xeon 2.4 GHz system:

without hyperthreading: 10 mins. 56 sec.
with hyperthreading: 10 mins. 11 sec.

45 secs... I'm awestruck. OK, Lightwave 7 is not optimised for hyperthreading, but still.

For comparison: a dual Athlon 1900+ did the render in 12 mins. 28 sec. Note: that is with a much slower CPU... I think a dual Athlon 2400+ is likely to improve on that significantly. And still cost 2 grand less.

 

Yeah, or a P4 Xeon, as observed above.

Where's the COBOL compiler?

I dunno, given the choice of running an app compiled on a 1.0 compiler versus something done with a well-tested, thoroughly compiler, I think I'd forgo the performance bump in favor of the stability. That probably reflects my bias toward the server side of things.

 

So if you have the right CPU, and if you have the right BIOS, and if you have the right OS (and presumably an optimised program running on it) then you may see a performance improvement. Or not.

That's a lot of if's...

Too right!