Quantcast
Channel: Intel Developer Zone Articles
Viewing all articles
Browse latest Browse all 3384

Intel® Advisor XE 2016 Update 3 What’s new

$
0
0
We’re pleased to announce new version of the Vectorization Assistant tool - Intel® Advisor XE 2016 Update 3. Below are highlights of the new functionality and improvements.

 

Support for Intel® Xeon Phi™ processor (codename: Knights Landing)

You can run the Survey analysis on the Intel® Xeon Phi™ processors (codename Knights Landing), see Intel AVX-512 ISA metrics and new Intel AVX-512-specific traits, e.g. Scatter, Compress/Expand, masking manipulations, etc.

Other analysis types are not available for Intel® Xeon Phi™ processors yet. We will extend the platform support in future updates.

 

Analysis of non-Executed code paths

Using the Intel Advisor XE, you can get your code ready for the next generation CPUs and Intel® Xeon Phi™ coprocessors even if you don’t have access to the hardware yet. Enable this functionality by generating code for multiple vector instruction sets (including Intel AVX-512) using the Intel Compiler
–ax option, and then analyze the resulting binary with Vectorization Advisor.

Read the detailed article about using the feature with some examples: https://software.intel.com/en-us/blogs/2016/02/02/explore-intel-avx-512-code-paths-while-not-having-compatible-hardware.

 

New tab “Loop Analytics”

“Loop Analytics” combines several loop metrics in single place, with easy-to-read visualization. The tab contains brand new metric “Instruction mix” - percentage of Memory, Compute and other instructions with distribution to vector/scalar instruction types. Other metrics are ISA, Traits and Efficiency. In future updates we plan to extend this tab with even more information, such as detailed instruction mix break-downs,  explanation and performance impact break-down for various sophisticated vectorization notions (multi-pumping, vectorized remainder) and more.

 

Filter results data by thread

You can now filter data by thread in the Survey report view, to narrow down performance metrics:

 

New recommendations

We have updated recommendation for Fortran "contiguous" attribute and added two new recommendations:

  1. “Indirect function calls” recommendation, that is useful for vectorizing C++ codes with virtual methods/functions.

  1. Recommendation for better utilization of FMA instructions:

 

Extended CLI snapshot

You can now pack your Advisor results with caching of sources and binaries from command line. So, you can make self-contained packed result snapshot on a remote server or a cluster node, which then can be easily copied to your workstation for investigation in GUI. This option is also handy for keeping historical results:

advixe-cl --snapshot --project-dir ./my_proj --pack --cache-sources --cache-binaries -- /tmp/my_proj_snapshot

 

Get Intel Advisor and more information

Visit the product site, where you can download free evaluation and find videos and tutorials.


Viewing all articles
Browse latest Browse all 3384

Trending Articles