Intel® Advisor User Guide

ID 766448
Date 3/22/2024
Public

A newer version of this document is available. Customers should click here to go to the newest version.

Document Table of Contents

target-device

Specify a device configuration to model cache for during Trip Counts collection.

GUI Equivalent

Analysis Workflow > Offload Modeling > Target Platform Model

Syntax

--target-device=<string>

Arguments

<string> is one of the following device configurations:

Argument

Description

pvc_xt_448xve

Intel® Data Center GPU Max 448

pvc_xt_512xve

Intel® Data Center GPU Max 512

xehpg_256xve

Intel® Arc™ graphics with 256 vector engines

xehpg_512xve

Intel® Arc™ graphics with 512 vector engines

gen12_tgl

Intel® Iris® Xe graphics

gen12_dg1

Intel® Iris® Xe MAX graphics

Default

No default

Actions Modified

collect=tripcounts --enable-cache-simulation

collect=offload

Usage

IMPORTANT:

Make sure to specify the same configuration argument as for the config option during Performance Modeling (collect=projection).

Do not confuse the target gpu option with the target-device option. The target-device option modifies only the --collect=tripcounts action and is used to simulate memory cache of a specific GPU platform for Offload Modeling. The --target-gpu modifies the --collect=roofline, --collect=survey, and --collect=tripcounts and is used to select a target GPU to collect data and plot a GPU Roofline for if you have several GPUs.

Example

  1. Run Survey Analysis.

  2. Run Trip Counts and FLOP analyses of the Characterization stage.

  3. Model your application performance for the gen9_gt2 configuration.

advisor --collect=survey --static-instruction-mix --project-dir=./advi_results -- ./myApplication
advisor --collect=tripcounts --flop --enable-cache-simulation --target-device=gen9_gt2 --project-dir=./advi_results -- ./myApplication
advisor --collect=projection --config=gen9_gt2 --project-dir=./advi_results

See Also