Intel® Advisor 2017 Beta Update 1 - What’s new
We’re pleased to announce new version of the Vectorization Assistant tool - Intel® Advisor 2017 Beta Update 1.
Below are highlights of the new functionality in Intel Advisor 2017 Update 1.
Full support for all analysis types on the second generation Intel® Xeon™ Phi processor (code named Knights Landing)
FLOPS and mask utilization
Tech Preview feature! Accurate hardware independent FLOPS measurement tool. (AVX512 only) Mask aware . Unique capability to correlate FLOPS with performance data.
Improved MPI workflow allows you to create snapshots for MPI results, so you can collect data in CLI and transfer self-contained packed result to a workstation with GUI for analysis. We also fixed some GUI and CLI interoperability issues.
Project properties dialog was extended with command line configuration for MPI launcher.
Project properties dialog also extended to allow setting FLOPS analysis.
Memory Access Patterns
MAP analysis now detects Gather instruction usage, unveiling more complex access patterns. A SIMD loop with Gather instructions will work faster than scalar one, but slower, than SIMD loop without Gather operations. If a loop has “Gather stride” category, check new “Details” tab in Refinement report for information about strides and mask shape for the gather operation. One of possible solutions is to inform compiler about your data access patterns via OpenMP 4.x options – for cases, when gather instructions are not necessary actually.
In addition to Gather profiling, for AVX512 MAP analysis also detects Gather/scatter instruction usage, these instructions allow more code to vectorize but you can obtain greater performance by avoiding these types of instructions.
SMART MODE
New “Smart mode” for Survey results, which is an effective way to simplify data representation and to automatically select the loops that can be most impactful and/or suitable from a SIMD vector performance perspective.
NEW RECOMMENDATIONS
- Consider outer loop vectorization in appropriate cases
- Consider refactoring the code to avoid using single Gather or Scatter instructions if the pattern is regular
Get Intel Advisor and more information
Visit the product site, where you can find videos and tutorials. .