Intel® AVX Special German and United Kingdom Discussion 2010 (Archived)

AVX platform question

Dear all,
until now we were using only Westmere X5650 base machines. Now Ivy Bridge E5-2670V2 nodes arrived.

To get benefit from AVX I have to recompile the (commercial) codes with the new suitable options.

Is it necessary to compile the code directly on a AVX platform or is it possible to use older Westmere machines ? From my point of view it should no matter which platform until I use the latest Intel compiler version. Is it right ?

educational video on to-the-metal x86 optimization including avx

At the game developer conference I presented a session "Hotspots, Flops, and uOps" that talked about optimizing code for Intel's latest SandyBridge processors. The session is now publicly available on gdcvault.The link is: session dives deep into the processing and covers more than just AVX, since you need to ensure you are getting good throughput (instruction parallelism) in addition to SIMD (aka Vector) parallelism. stan melax

hi , i am optimize the compiler , and use more sse instruction , but i get result that sse instruction is slow than x87 instruction about 50%, can you have some commen!thanks.




is two attached file . one is generate form gcc with optimize option
-O2 (nbody.s.1), one is modify from nbody.s.1 (nbody.s) , i use sse
instruction to take place the x87 instruction .

I use the standard x86 instruction and sse instruction to do calc , i
use gcc with -O2 optimize option to accomplish same function .

Status of intel AVX meeting in MUC?

Michael Larabel has AVX benchmarks online for Linux:

he's in Munich 17th to 21st of Feb 2011:

@intel: Contact Michael or me if you're interested in a AVX related meeting in Munich in the above mentioned timeframe. I live in Munich.

AVX cloth Whitepaper : SOA Cloth Simulation with 256-bit Intel AVX

Im Basher Khan I know few AVX experts inside Intel so if you have any quarries you know who to ask!

You may find this article very useful, describes a code sample that uses the Intel Advanced Vector Extensions (Intel AVX) for computing mesh-based cloth simulation.

Visit AVX Cloth page (source code, binary, videos)

Nice AVX video demo

There's a nice demo showing pieces of cloth animated blowing in the wind, enabled using AVX, here:

I found it through the new site for Sandy Bridge here:

which has lots of white papers and developer guides for Sandy Bridge, for game and media development projects.

Widening availability to other programming languages

This post isn't really specific to AVX, but SIMD extensions in general. I'd like to see the availability of SIMD programming widen to more than just assembly and C/C++ intrinsics. By this I mean first class support, and not just via use of natively programmed modules. I think this is necessary if SIMD programming is ever to become more than just a niche, by widening availability to mobile device and web/smart client environments.


post AVX killer apps here

I was wondering which applications will profit most from AVX extensions. There are some AES, fp and integer math operations. Please post algorithms, academical papers, forum discussions, benchmarks.

Besides the newly integrated media content creation engine, I'm wondering in particular how much the word's best H.264 encoder
will profit from the AVX extension.

Subscribe to Intel® AVX Special German and United Kingdom Discussion 2010 (Archived)