FAQS: Compilers, Libraries, Performance, Profiling and Optimization.

In the period prior to the launch of Intel® Xeon Phi™ coprocessor, Intel collected questions from developers who had been involved in pilot testing. This document contains some of the most common questions asked. Additional information and Best-Known-Methods for the Intel Xeon Phi coprocessor can be found here.

The Intel® Compiler reference guides can be found at:

Оптимизировали, оптимизировали, да не выоптимизировали!

Оптимизация? Конечно, каждый сталкивался с данной задачей при разработке своих, сколь-нибудь значительных, требующих определённых вычислений, приложений. При этом способов оптимизировать код существует огромное множество, и, как следствие, различных путей сделать это в автоматическом режиме с помощью опций компилятора. Вот здесь и возникает проблема – как выбрать то, что нужно нам и не запутаться?

Links to instruction documentation

Slides from May 4th Webinar on Cilk

Hi all,

We did a webinar this morning at 8am Pacific time on changes and new updates in Cilk in the Intel Parallel Composer beta. I am posting the slides here. Let me know if there's any interest to do another webinar on this around 5pm or so Pacific time - I want to see if there's anyone that couldn't attend due to the time that would have liked to attend. Thanks everyone, and I really enjoyed the questions in today's session.

Why MIC requires strict data alignment? How about auto vectorize of unaligned data?

MIC requires strict 64Byte data alignment to utilize vpu, but why? I found Sparc also have such an requirement. But other multi-core CPU can handle unaligned data.

As MIC can automatically vectorize a for loop of data(with compiler optimization), what if the data is unaligned in this case? will the auto optimization still work?  if yes, how?

Help Using Lapack for Getting Least Squares Fit Polynomial Coefficients

Hello all,

I am a first time MKL user trying to use the library to fit a 3rd-order 2-d polynomial function to f(x,y). This algorithm works using pretty much the same exact approach in Python so I believe it to be conceptually sound.

I'm trying to use LAPACKE_dgelsy but my program dies whenever it's called, and I'm sure my function arguments are incorrect.

Intel MKL 11.3 IFFT bug?


There seems to be a bug in the Intel MKL library version 11.3 with IFFT. The test program below (sorry the attach feature doesn't work) performs the FFT on an input buffer and then the IFFT on the returned buffer. The results of the IFFT is completely different from the original input buffer. The problem was not present in the Intel MKL library version 10.3. The problem is present on both Linux and Mac OS X and the same code works fine on other FFTW3 implementations. Is this a known problem? I am missing something?

Knight's Landing + Java

Dear Intel Staff,

I just got to know some details of your great presentation of Knight's Landing (KNL) at Hot Chips this year. Information about KNL on the website is still sparse. From your slides I understand that there will be a version of KNL that is socked and can be used as a primary CPU in a rack. However, this raises quite some questions that I cannot find satisfying answers.

Suscribirse a Vectorización