Future microprocessors in the works from Intel and AMD will have new AVX instructions that will reportedly give you access to all kinds of performance gains. The question is, will you have to rewrite your code? AMD’s John Fruehe blogs that the answer is yes and no.
We have talked in the past about the AVX instructions, which provide a big benefit in terms of the ability to execute floating point code in 256-bit pieces. Development tools used by the HPC community have support for AVX in progress so you will be able be to recompile your code with AVX-supported compiler, like x86 Open64, PGI 2010, Visual Studio 2010, and GCC to gain AVX functionality. Keep in mind that AMD is implementing AVX in the same manner as our competitor. That means any application that supports AVX will work the same on both of our platforms. I am sure that you can appreciate that decision – more consistency in software code is always a good thing for the ecosystem.
Fruehe goes on to say that AMD expects few issues around software since many of these commands are being actively integrated into OSs and compilers. And after talking to the folks from PGI last week, I have to concur. The compiler people see this as opportunity. You’re going to need the latest software to get the greatest performance. It’s capitalism at its best, folks, so make sure you set aside some budget for compilers when you sign for that bulldozer cluster.