Package Content

The hl_qual tools package contains the applications (plugins) listed in the below table:

Module

Description

Type

Device

hl_qual

Glue logic application that runs all test plugins located in /opt/habanalabs/qual/gaudi. See hl_qual Design.

Application

First-gen Gaudi/ Gaudi2

runner

A generic test plugin loader and runner application. The runner image is loaded by hl_qual and is responsible for loading the test plugins and running the selected plugin on the tested device (one instance of a runner process per tested device). The application is located in /opt/habanalabs/qual/gaudi. See hl_qual Design.

Application

First-gen Gaudi/ Gaudi2

monitor

A standalone monitoring application to monitor multiple device execution metric measurement (device power usage, Device clock and Device temperature). See hl_qual Monitor Textual UI.

Application

First-gen Gaudi/ Gaudi2

libfunctional2 _test_plugin.so

Dynamically linked library implementing the functional test 2 plugin. See Functional Test 2 Plugin Design Consideration and Responsibilities.

Dynamically linked lib

First-gen Gaudi/ Gaudi2

libNIC_basetest _plugin.so

Dynamically linked library implementing the NIC base tests plugin. See Serdes Base Test Design Consideration and Responsibilities.

Dynamically linked lib

First-gen Gaudi/ Gaudi2

libpci_bw_plugin.so

Dynamically linked library implementing the PCI bandwidth test plugin. See PCI Bandwidth Design

Dynamically linked lib

First-gen Gaudi/ Gaudi2

libpower_stress_plugin.so

Dynamically linked library implementing the Power stress and EDP test plugin. See First-gen Gaudi Power Stress Plugin Design Consideration and Responsibilities.

Dynamically linked lib

First-gen Gaudi

libconcurrency_powertest.so

Dynamically linked library implementing the Power stress. See Gaudi2 Power Stress Plugin Design Consideration and Responsibilities.

Dynamically linked lib

Gaudi2

libmemory_bw_plugin.so

Dynamically linked library implementing the Memory bandwidth plugin. See Memory Bandwidth Plugin Design Consideration and Responsibilities.

Dynamically linked lib

First-gen Gaudi/ Gaudi2

libhbm_stress_plugin.so

Dynamically linked library implementing a HBM stress plugin. See First-gen Gaudi HBM Stress Plugin Design Consideration and Responsibilities

Dynamically linked lib

First-gen Gaudi

libhbm_plugin_gaudi2.so

Dynamically linked library implementing a HBM stress plugin. the plugin supports 3 sub tests HBM_DMA_STRESS, HBM_TPC_STRESS and HBM_FULL_DATA_CHECK See Gaudi2 HBM Stress Plugin Design Consideration and Responsibilities

Dynamically linked lib

Gaudi2

libe2e_hlthunk_based.so

Dynamically linked library implementing the E2E serdes test. See First-gen Gaudi E2E Serdes Test Plugin Design Consideration and Responsibilities

Dynamically linked lib

First-gen Gaudi

libe2e_concurrency.so

Dynamically linked library implementing the E2E concurrency test. See Gaudi2 E2E Concurrency Test Plugin Design Consideration and Responsibilities

Dynamically linked lib

Gaudi2

libber_plugin.so

Dynamically linked library implementing the Ber test. See Gaudi2 BER Test Plugin Design Consideration and Responsibilities

Dynamically linked lib

Gaudi2

E2E_create_configuration_files.py

E2E test python ports and link configuration scripts.

Python configuration file

First-gen Gaudi/ Gaudi2

lspci_parser.py

PCI tree reader and BW estimator

Python configuration

First-gen Gaudi/ Gaudi2

hard_reset.sh

Reset control bash script

bash script

First-gen Gaudi/ Gaudi2

prepare.sh

ImageNet images preprocessing script

bash script

First-gen Gaudi/ Gaudi2

nic_information.sh

Habana device NIC information reader

bash script

First-gen Gaudi/ Gaudi2

pcie_aer_detector

PCIe error detector

APP

First-gen Gaudi/ Gaudi2

training64.json training256.json validation64.json validation256.json

ResNet-50 training stress test plugin configuration JSON file for Aeon library data loader.

Aeon config file

First-gen Gaudi/ Gaudi2

hbm_stress_test.json tpc_hbm_stress.json dma_full_compare_cfg_prod.json full_mem_compare_test.json dma_cfg_prod.json

Hbm_stress concurrency based plugin configuration JSON file for different plugin modes.

Hbm_stress concurrency config files

Gaudi2

gaudi2_dma.ini

INI general configuration file for all HBM stress test modes.

INI format config file Gaudi2

Gaudi2

hl_qual.ini

INI hl_qual configuration file which defines which test plugin will be loaded and the basic behavior of the monitor sampling.

INI format config file

First-gen Gaudi/ Gaudi2

config.ini

Test plugin configuration INI file. This file is brought as a usage example. Users may customize this file or generate a new one.

INI format config file

First-gen Gaudi

monitor.ini

INI configuration file to control the sampling Of the standalone monitor application and the hl_qual monitor add-on.

INI format config file

First-gen Gaudi/ Gaudi2

device.ini

INI configuration file to control Habanalabs device setup.

INI format config file

First-gen Gaudi/ Gaudi2

hlthunk_tests.ini

HBM BE hlthunk test configuration file. This file should not be edited.

INI format config file

First-gen Gaudi/ Gaudi2
../../_images/Qualification_Package_Content_gaudi.JPG

Figure 24 Qualification Package Content

Note

The installation folder of the hl_qual package can be found under /opt/habanalabs/qual/gaudi/