SK-AM62A-LP
AM62A starter kit for low-power Sitara™ processors
SK-AM62A-LP
Overview
The SK-AM62A-LP starter kit (SK) evaluation module (EVM) is built around our AM62A AI vision processor, which includes an image signal processor (ISP) supporting up to 5 MP at 60 fps, a 2 teraoperations per second (TOPS) AI accelerator, a quad-core 64-bit Arm® Cortex®-A53 microprocessor, a single-core Arm Cortex-R5F and an H.264/H.265 video encode/decode. SK-AM62A-LP is an ideal choice for those looking to develop low-power smart camera, dashcam, machine-vision camera and automotive front-camera applications.
SK-AM62A-LP also includes both a mobile industry processor interface (MIPI®) CSI-2 camera connector for a single camera and an additional expansion connector for up to four cameras, making it suitable for a variety of embedded vision and AI applications on the edge. For a variety of applications, our ISP can handle different lighting conditions in video streams by using high dynamic range (HDR) encoding and RGB-IR camera support. With edge AI, deep learning on video streams like image classification and object detection have greatly improved performance on the AM62A AI accelerator, therefore giving significant improvement in frame rate, latency and performance to allow offloading intensive processes from general-purpose cores.
Furthermore, the SK-AM62A-LP supports Linux® development with a feature-rich edge AI software development kit (SDK). On-chip emulation logic allows for emulation and debugging using standard development tools such as the Code Composer Studio™ integrated development environment (IDE) (CCSTUDIO) as well as an intuitive out-of-box user's guide to quickly start design evaluation.
During custom board design, customers tend to reuse the SK design files and make edits to the design file. Alternatively customers reuse some of the common implementations including the SOC, memory and communication interfaces. Since the SK is expected to have additional functionalities, customers optimize the SK implementation to suit their board design requirements. While optimizing the SK schematics, errors get introduced into the custom design that could cause functional, performance or reliability issues. When optimizing customers have queries regarding the SK implementation resulting in design errors. Many of the optimization and design errors are common across designs. Based on the learnings and data sheet pin connectivity recommendations, comprehensive Design Notes (D-Note:), Review Notes (R-Note:) and Cad Notes (Cad Note:) have been added near each section of the SK schematic that customers could review and follow to minimize errors. Additional files as part of the design downloads have been included to support customer evaluation.
Features
- Processing
- AM62A74 with four Arm Cortex-A53
- Cortex-R5F
- Deep-learning accelerator
- Display
- One HDMI connector over RGB888 with audio codec TLV320AIC3106
- M.2 key E interface support for Wi-Fi® and Bluetooth® modules, four-lane MIPI CSI-2 camera connector, up to two gigabit Ethernet
- Connectivity
- One USB Type-A 2.0
- One USB Type-C® dual-role device (DRD) 2.0 supports USB booting
- Onboard XDS110 Joint Test Action Group (JTAG) emulator
- Four universal asynchronous receiver-transmitters (UARTs) via USB Type-B 2.0
- Storage
- 4GB LPDDR4
- Bootable interfaces on SK
- Removable microSD
- USB
- Quad serial peripheral interface (QSPI)
- Ethernet
- UART
- Software
- TI processor SDK Linux
- RT-Linux
- SK design files
- Updated Downloadable files in the design files section Zip folder includes the following folders 1_SCHEMATIC, 2_BOM, 3_Board_File, 4_Gerber, 5_Gerber_PDF, 6_Assembly_Models_Package and 7_PCB_LAYER_STACKUP, and additional sub folders.
Not included:
- USB-C 5-V to 15-V and 3-A power supply and cable
- MicroSD card
- USB micro-B cable for UART serial communication
Arm-based processors
Order & start development
SK-AM62A-LP — AM62A starter kit for low-power Sitara™ processors
AM62A-ACADEMY — AM62Ax Academy
Products
Arm-based processors
Hardware development
Evaluation board
Release Infomation
AM62A-ACADEMY first release.
EDGE-AI-STUDIO — Edge AI Studio
EDGE-AI-STUDIO — Edge AI Studio
Products
Arm-based processors
Hardware development
Evaluation board
Development kit
Release Infomation
Edge AI studio is a collection of tools aimed to accelerate the development of edge AI application on TI embedded devices.
Model analyzer, formerly known as TI edge AI cloud, is a free online service that allows you to evaluate accelerated deep learning inference on remotely accessed development boards. With Model analyzer it only takes minutes to login, deploy a model and obtain a variety of performance benchmarks.
Model composer (coming soon) is a tool for training, compiling and deploying models on a local development board.
CLOCKTREE-AM62AX — Clock tree configuration for AM62Ax
CLOCKTREE-AM62AX — Clock tree configuration for AM62Ax
Products
Arm-based processors
Hardware development
Evaluation board
Release Infomation
Clock tree configuration tool for AM62AX
PROCESSOR-SDK-QNX-AM62AX — QNX software development kit for AM62A Sitara™ processors
MCU-PLUS-SDK-AM62A — MCU+ SDK for AM62A – RTOS, No-RTOS
MCU-PLUS-SDK-AM62A — MCU+ SDK for AM62A – RTOS, No-RTOS
MCU PLUS SDK Linux Installer
MCU PLUS SDK Windows Installer
Products
Arm-based processors
Hardware development
Evaluation board
Documentation
MCU PLUS SDK online documentation
Performance measurement datasheet
Documentation only package
Code Composer Studio™ integrated development environment (IDE)
TI ARM CLANG compiler
Tool to configure SOC pimux and MCU PLUS SDK driver parameters
Buildsheet of supported features
Release Infomation
Thank you for your interest in the AM62A MCU PLUS Software Development Kit (SDK). This software accelerates application development schedules by eliminating the need to create basic system software functions from scratch.
- The SDK includes a real-time multitasking kernel, examples and drivers.
- The exact content of the SDK depends on the capabilities of the device, but all devices share common APIs and build on existing proven software components to ensure reliability and quality.
- The software components are fully tested to ensure that they work together with TI’s Code Composer Studio integrated development environment.
What's new
- SBL: Image authentication from DDR when in-place authentication fails from OSPI NOR
- SBL: Software version check with RPRC image format
- SBL: Switch off bootable cores in case of boot failure
PROCESSOR-SDK-LINUX-RT-AM62A — RT-Linux SDK for edge AI applications on AM62A
PROCESSOR-SDK-LINUX-RT-AM62A — RT-Linux SDK for edge AI applications on AM62A
Get access to latest bug fixes and feature enhancements with Yocto build environment
Linux Installer for sources, pre-built binaries and file system images with edge AI and robotics stack
Products
Arm-based processors
Hardware development
Evaluation board
Documentation
Quick Start Guide for the AM62A Starter Kit (SK) board
Online edge AI SDK user manual
Online robotics SDK user manual
Online LINUX SDK user manual
Learn how to build embedded Linux systems using AM62A processors
Explore a selection of self-paced lessons for edge AI development. Follow along with free cloud tools.
Download Linux SDK user manual for offline view
Build Sheet of supported features for AM62A
Release Infomation
Thank you for your interest in PROCESSOR SDK LINUX RT AM62A Software Development Kit (SDK) for edge AI applications.
The Yocto build environment based RT-Linux SDK for edge AI provides
- Upstream RT-Linux LTS Kernel with peripheral drivers, U-Boot bootloader.
- Pre-integrated firmware for hardware accelerated deep learning and camera ISP
- GStreamer plugins and edge AI application stack
The SDK documentation provides simple steps to build, develop and run high performance deep learning applications using a live camera and display.
TI Linux CI/CD Snapshot
In order to improve access to the very latest bug fixes and feature enhancements, TI is enabling Continuous Integration and Continuous Deployment (CI/CD) for AM62A processors. The patches for these changes have always been available on public repositories hosted on git.ti.com, and these source repositories could be built using the Yocto build environment on a daily basis. The new TI Linux CI/CD Snapshot makes it even easier to consume these changes with pre-built binaries of Linux boot images to try out on TI Evaluation Modules (EVMs and SKs) before migrating or picking the patches. A detailed test report is also published to help users understand the status of the build and features being validated. The Linux boot images from a snapshot can be regenerated using sources by following the build instructions provided on the snapshot page.
The daily snapshot is not a replacement for the official Processors SDK releases which have full documentation, training and support. The snapshot is a new easy way to try bug fixes and feature enhancements planned for the next SDK while enabling much more tighter integration with customizations and application development. This improved integration should allow users to release their customized code built on the SDKs more quickly and confidently.
What's new
- Linux Kernel LTS migration from 6.1 to 6.6
- ATF 2.10 and OPTEE 4.2.0
- Supports Docker based Ubuntu 24.04 on top of Yocto-Scarthgap
DDR-CONFIG-AM62A — DDR Configuration Tool
DDR-CONFIG-AM62A — DDR Configuration Tool
Products
Arm-based processors
Hardware development
Evaluation board
Documentation
Release Infomation
This tool is intended to simplify the process of configuring the DDR Subsystem Controller and PHY to interface with DRAM memory devices.
What's new
- fixed CA VREF range1 training search for LPDDR4
- added flexibility in choosing operating frequencies
- changed WDQS Extension to enabled by default for LPDDR4. This enables WDQS Read Based Control.
- added periodic ZQ calibration selection for LPDDR4
- added REGION_IDX parameter to properly set Subsystem register
PROCESSOR-SDK-LINUX-AM62A — Linux SDK for edge AI applications on AM62A
PROCESSOR-SDK-LINUX-AM62A — Linux SDK for edge AI applications on AM62A
Linux Installer for sources, pre-built binaries and file system images with edge AI and robotics stack
SD card image
Get access to latest bug fixes and feature enhancements with Yocto build environment
Products
Arm-based processors
Hardware development
Evaluation board
Documentation
Quick Start Guide for the AM62A Starter Kit (SK) board
Online edge AI SDK user manual
Online LINUX SDK user manual
Online robotics SDK user manual
Learn how to build embedded Linux systems using AM62A processors
Explore a selection of self-paced lessons for edge AI development. Follow along with free cloud tools.
Download Linux SDK user manual for offline view
Build Sheet of supported features for AM62A
Software manifest
Release Infomation
Thank you for your interest in PROCESSOR SDK LINUX AM62A Software Development Kit (SDK) for edge AI applications.
The Yocto build environment based Linux SDK for edge AI provides
- Upstream Linux LTS Kernel with peripheral drivers, U-Boot bootloader.
- Pre-integrated firmware for hardware accelerated deep learning and camera ISP
- GStreamer plugins and edge AI application stack
The SDK documentation provides simple steps to build, develop and run high performance deep learning applications using a live camera and display.
TI Linux CI/CD Snapshot
In order to improve access to the very latest bug fixes and feature enhancements, TI is enabling Continuous Integration and Continuous Deployment (CI/CD) for AM62A processors. The patches for these changes have always been available on public repositories hosted on git.ti.com, and these source repositories could be built using the Yocto build environment on a daily basis. The new TI Linux CI/CD Snapshot makes it even easier to consume these changes with pre-built binaries of Linux boot images to try out on TI Evaluation Modules (EVMs and SKs) before migrating or picking the patches. A detailed test report is also published to help users understand the status of the build and features being validated. The Linux boot images from a snapshot can be regenerated using sources by following the build instructions provided on the snapshot page.
The daily snapshot is not a replacement for the official Processors SDK releases which have full documentation, training and support. The snapshot is a new easy way to try bug fixes and feature enhancements planned for the next SDK while enabling much more tighter integration with customizations and application development. This improved integration should allow users to release their customized code built on the SDKs more quickly and confidently.
What's new
- Linux Kernel LTS migration from 6.1 to 6.6
- ATF 2.10 and OPTEE 4.2.0
- Supports Docker based Ubuntu 24.04 on top of Yocto-Scarthgap
- Robotics SDK Docker build process is now independent of the host Linux file system
- TIDL: Support for Centernet model architecture : Added/optimized new operators : Object detection layer for Centernet
- TIDL: Optimization of TIDLRT-Create for boot time performance improvement
- TIDL: Robustness improvement for compiler (parser, graph partition and optimizer modules)
CCSTUDIO — Code Composer Studio™ integrated development environment (IDE)
CCSTUDIO — Code Composer Studio™ integrated development environment (IDE)
This design resource supports most products in these categories.
Check the product details page to verify support.
- Digital signal processors (DSPs)
- Arm-based processors
- MSP430 microcontrollers
- C2000 real-time microcontrollers
- Arm-based microcontrollers
- Signal conditioners
- mmWave radar sensors
- Wi-Fi products
- Sub-1 GHz products
- Digital power isolated controllers
Products
Arm Cortex-M0+ MCUs
Arm Cortex-M4 MCUs
Arm Cortex-R MCUs
Automotive mmWave radar sensors
Industrial mmWave radar sensors
Sub-1 GHz wireless MCUs
Hardware development
Evaluation board
Development kit
Release Infomation
The Code Composer Studio™ IDE is a complete integrated suite that enables developers to create and debug applications of all Texas Instruments Embedded Processors (Sitara, DSP, Automotive, Keystone), Microcontrollers (SimpleLink™, C2000 Digital Control, MSP430, TM4C, Hercules), as well as Digital Power (UCD) and Programmable Gain Amplifier (PGA) devices.
CCS v20 is TI’s next generation Integrated Development Environment (IDE) based on Theia IDE framework. CCS v20.0.1 uses a modified version of the Theia-IDE framework and offers a user experience similar to Visual Studio Code™.
- Installation instructions and User's Guide
- Windows 32bit is not supported with CCSv20.
- XDS510 class debug probes are not supported with CCSv20.
What's new
- v20.0.1 is a maintenance release based on v20.0.0, with the following updates:
- Updated C29 device support to support flash programming on the M4 core, as well as enhancements and bug fixes.
- Added support for Stellaris In-Circuit Debug Interface debug probe
- Added support for MSP432 MCU device family
- Fixed version of bundled C2000 and C6000 Compiler
- Various debug enhancements and bug fixes
Design files
Technical documentation
Type | Title | Date | ||
---|---|---|---|---|
Product overview | SK-AM62A-LP Design Package Folder and Files List | PDF | HTML | 24 Jul 2024 | |
EVM User's guide | SK-AM62A-LP AM62A Low-Power SK EVM User’s Guide (Rev. A) | PDF | HTML | 13 Dec 2023 | |
Certificate | SK-AM62A-LP EU Declaration of Conformity (DoC) (Rev. B) | 11 Dec 2023 |
Related design resources
Hardware development
EVALUATION BOARD
Support & training
TI E2E™ forums with technical support from TI engineers
Content is provided "as is" by TI and community contributors and does not constitute TI specifications. See terms of use.
If you have questions about quality, packaging or ordering TI products, see TI support.