User Guide

Contents

batching

Emulate the execution of more than one instance simultaneously for a top-level offload.
GUI Equivalent
Project Properties
Analysis Target
Performance Modeling
Other parameters

Syntax

--batching
--no-batching
Default
Off (no-batching)
Actions Modified
collect
=projection
collect
=offload
Usage
Use the
batching
option to enable job batching for a top-level offload and emulate the execution of more than one instance simultaneously. This option is equivalent to
--threads=total_EU_count*threads_per_EU
.
Families of Intel® X
e
graphics products starting with Intel® Arc™ Alchemist (formerly DG2) and newer generations feature GPU architecture terminology that shifts from legacy terms. For more information on the terminology changes and to understand their mapping with legacy content, see GPU Architecture Terminology for Intel® X
e
Graphics
.
Example
  1. Run Survey Analysis.
  2. Run Trip Counts and FLOP analyses of the Characterization stage.
  3. Model your application performance on a target device and emulate the execution of several instances simultaneously for a top-level offload.
advisor --collect=survey --static-instruction-mix --project-dir=./advi_results -- ./myApplication
advisor --collect=tripcounts --flop --enable-data-transfer-analysis --project-dir=./advi_results -- ./myApplication
advisor --collect=projection --batching --project-dir=./advi_results

Product and Performance Information

1

Performance varies by use, configuration and other factors. Learn more at www.Intel.com/PerformanceIndex.