5.6. Release notes - 08_05_00

5.6.1. Features


New features vs previous release are marked in bold Hardware support

  1. J721S2 Alpha EVM support with Leo and Hera PMIC processor board

  2. J721S2 ES1.0 support

  3. J721S2 HS support

  4. Fusion1 RevC daughter card with UB960 FPDLink deserializer

  5. IMX390 2MP CSI2 image sensor + UB953 FPDLink serializer

  6. AR0233 2.5MP CSI2 image sensor + UB953 FPDLink serializer

  7. AR0820 8MP CSI2 image sensor + UB953 FPDLink serializer

  8. GESI (Gateway/Ethernet Switch/Industrial) daughter card (for additional ethernet and CAN ports)

  9. Infotainment daughter card (for HDMI output) Software features


Below is a summary of key features. Refer individual SDK Components release notes for more details Vision Apps (ADAS, Vision, DL demos)

  • OpenVX based demos for ADAS, Vision, deep learning applications

    • FreeRTOS on C7x, R5F and Linux/QNX on A72

    • Integrates all major PSDK RTOS and PSDK LINUX SW components like TIDL, MMALIB, PDK, OpenVX, C7x algorithms, imaging/sensors, IPC, Linux, FreeRTOS, SPL/uboot.

    • Integrates all major HW components like CSI2 camera, eDP/HDMI display, UART, I2C, ethernet, SD card

  • Deep Learning demos

    • Image Classification demo

      • File based

      • Camera based

    • Standalone Semantic Segmentation application

      • File based

      • Camera based

    • Standalone Object Detection application

      • File based

      • Camera based

    • Auto valet parking (AVP) demo

      • semantic segmentation, Parking spot detect and Vehicle detect algorithms

      • 1 channel, 3 algo mode (AVP1 demo)

      • 3 channel, 3 algo mode - combined network for parking spot and vehicle detect (AVP2 demo)

      • 3 channel, 5 algo mode - combined network for parking spot and vehicle detect + Three task network for Semantic Segmentation, Motion Segmentation and Depth Estimation (AVP3 demo)

    • DKAZE-based Visual Localization application

    • Debug support for the ability to debug intermediate layer information from TIDL node

  • Surround view demos

    • 3D surround view using GPU on 4x 2MP 30fps live camera input

    • 3D surround view calibration application

  • ADAS/Vision demos

    • Dense optical flow (DOF) demo

    • Stereo disparity engine demo

    • Single and multi camera to display (CSI2RX + VISS + LDC + MSC + Display) demo

    • C7x algorithm offload demo (with DMA acceleration)

    • Multi channel codec demo utilizing CSI2RX + VISS + LDC + MSC + Display

  • CV Demos

    • Structure from motion

  • OpenVX target nodes

    • image pre-processing (YUV 2 RGB) nodes for DL demos

    • image post-processing and visualization nodes for deep learning, DOF, Stereo demos

    • lidar, radar, camera SFM nodes for PTK demos

    • OpenGL nodes for surround view

  • Profiling, logging and other utility APIs

  • All included MCU tasks are split between MCU2_0 (VPAC HWA) and MCU2_1 (DMPAC HWA), leaving MCU3_0 and MCU3_1 free on main domain Platform Development Kit (PDK)

  • RTOS device drivers running on R5F, C7x

  • Supported drivers and modules

    • ENET CPSW (2G) in MCU and Main domains, RGMII, lwIP

    • CSL-FL (Chip support library)

    • GPIO

    • I2C

    • IPC (inter processor communication)

    • MMCSD with FATFS

    • OSAL

    • SBL secondary bootloader

    • SCI Client (DMSC interface)

    • SPI driver (SPI, OSPI)

    • OSPI (NOR, NAND)

    • UART

    • UDMA and DRU

    • VPAC and DMAC (VHWA)

    • 2x CSI-Rx

    • CSI-Tx

    • DSS - DP

    • FreeRTOS Support on R5, DSPs

    • SafeRTOS Support on R5, DSPs

Refer to PDK release notes LINK for more details. MCU Software (MCUSW)

  • AutoSAR 4.3.1 MCAL driver and MCU1_0 example applications running on R5F (TI Arm Clang Compiler).

  • AutoSAR MCAL driver for Adc, Can, CDD IPC, Dio, Eth, Gpt, Pwm, Epwm Spi, Icu & Wdg

  • MCUSW ”boot app” TI Deep learning Product (TIDL) and MMALIB

  • TensorFlow Lite Runtime with Delegate API support for heterogeneous execution on ARM+C7x_MMA

  • ONNX Runtime with Execution Provider support for heterogeneous execution on ARM+C7x_MMA

  • NEO-AI-DLR support - TVM model compilation for heterogeneous execution on ARM+C7x_MMA

  • Upgraded to exercise MMA REV2 IP enhancement features - Limited support for hardware acceleration via on-the-fly padding of tensors - Limited support for asymmetric quantization for TF-Lite post training quantized models

  • TIDL deep learning inference engine library running on C7x/MMA

  • Supports Caffe, ONNX, TFlite network exchange formats

  • Supported layers: Convolution, Deconvolution, Pooling, ReLU, Elt-wise, Inner product, Soft-max, and many more, refer TIDL user guide (LINK)

  • TIDL network import tool and graph visualizer tool

  • Post Training Quantization options for 8-bit, 16-bit and mixed precision inference

  • Support of batch processing

  • Support for auto C7x code generation with TVM FFT Library for C7x/MMA (FFTLIB)

  • C7x-only kernels

  • C7x+MMA kernels

  • Note: This is packaged as a stand-alone library component, and is not integrated into any SDK level demos DSP Library for C7x/MMA (DSPLIB)

  • C7x-only kernels

  • Note: This is packaged as a stand-alone library component, and is not integrated into any SDK level demos MATH Library for C7x/MMA (MATHLIB)

  • C7x-only kernels

  • Note: This is packaged as a stand-alone library component, and is not integrated into any SDK level demos TI OpenVX (TIOVX)

  • OpenVX v1.1 compliant implementation with graph pipelining and user data object extension support

  • OpenVX API on A72 running Linux/QNX

  • OpenVX target kernels on C7x, R5F, A72

  • OpenVX v1.1 C6x optimized kernels recompiled for C7x

  • OpenVX nodes for

    • TIDL (C7x-MMA)

    • VISS (R5F)

    • LDC (R5F)

    • MSC (multi-scalar) (R5F)

    • Pyramid (using MSC) (R5F)

    • Dense Optical Flow (R5F)

    • Stereo Disparity Engine (R5F)

    • BLNF (bilateral noise filter) (R5F)

    • CSI2-RX camera (R5F)

    • CSI2-TX (R5F)

    • Display (eDP) (R5F)

    • Display M2M (R5F)

  • OpenVX tutorials for getting started

  • PyTIOVX tools for target kernel code generation

  • Performance Analyzer tool for run time logging of OpenVX graphs

  • VISS node supports heterogeneous camera support Imaging

  • IMX390 2MP sensor driver (30/60fps) with IQ tuning

  • AR0233 2.5MP sensor driver with IQ tuning

  • AR0820 8MP sensor driver with IQ tuning

  • TI Auto-exposure and auto white-balance algorithms

  • Support for UB960 broadcast mode

  • Sensor framework supports heterogeneous camera support TI Autonomous Driving Algorithms (TIADALG)

  • Image pre-processing APIs for color plane conversion and separation YUV to RGB for DL applications (C6x optimized. recompiled for C7x)

  • Camera Pose estimation API using solve pnp technique (C6x optimized. recompiled for C7x)

  • Visual localization algorithm (C6x optimized. recompiled for C7x)

  • Structure from Motion algorithm FreeRTOS

  • FreeRTOS for R5F and C7x Code Gen Tools (CGT)

  • TI Compiler, assembler, linker for R5F, C7x

  • TI LLVM (CLANG) Compiler, assembler, linker for R5F

  • GCC compiler for A72 (needs to be downloaded separately)

5.6.2. Device Support and Validation Information


Build Host (OS)

Run Target (OS)

Test Plaform


x86_64 (Linux Ubuntu 18.04)

R5F, C7x running FreeRTOS

A72 running Linux or QNX

J721S2 EVM with daughter cards

PC emulation mode (1)

x86_64 (Linux Ubuntu 18.04)

x86_64 (Linux Ubuntu 18.04)

x86_64 (Linux Ubuntu 18.04)

(1) Requires download of addon package from mySecure Software

5.6.3. Upgrade and Compatibility

In this section, we only highlight a few significant changes in this SDK. For full list of upgrade and compatibility topics, please refer to individual components release notes SDK Components. Enet LLD

Support for scatter-gather in packet transmission has been added starting in 08.05.00 release. This feature requires a change in Enet LLD DMA API, so applications using Enet LLD APIs need to be ported to use the updated API. Developers should refer to the porting steps documented in Enet LLD User’s Guide (LINK). MCU Software (MCUSW) Ethernet

MCAL Ethernet (MCU CPSW_2G) and Virtual MAC (virtual client for CPSW9G) drivers have been signficantly refactored to remove most dependencies with other SDK components, such as Enet LLD and UDMA LLD. The only remaining SDK dependency is with SCI Client driver. The driver configuration has also moved to a static-oriented allocation approach for TX channel, RX channel, Ring Accs, and other resources. Please refer to the Ethernet User Guide (LINK) chapter in the MCUSW documentation for further information about Ethernet module configuration.

Additionally, MCAL Ethernet driver (MCU CPSW_2G) now has Global Time support (packet timestamping) as well as support for link time and post-build configuration, in addition to pre-compile variant already supported.

5.6.4. Known Issues

Refer to individual SDK Components release notes for known issues in each component

5.6.5. Change Requests


Head Line

Original Fix Version

New Fix Version



Ethernet: CPSW: Reduce scope of SG to TX for SDK 8.5





Device Manager shall support ACSPCIE mux clocking option





TIDL: Descope of 8.5 Requirements related to improving allowlisting and preprocessing





TIDL: Descope of 8.5 Requirements related to performance optimization





Expose imaging dcc source code in releases





TIDL: Descope of 8.5 Requirements related to high precision (asymmetric quantization) inference of floating point models





TIOVX safety moved out to 10.1





move Fusion2 board support with FPD Link 4 to 8.6





PDK 8.5 Scope Change





Remove PTK Demos from all SDKs





Boot App Migration to PDK





Ethernet: CPSW: MDIO errata i2329 workaround





Ethernet: CPSW: Scatter-Gather and Large Frame Support CR



ETHFW Errata workarounds


5.6.6. Additional Reports

For additional reports like test report, traceability refer [LINK] (or ${PSDK RTOS_PATH}/psdk_rtos/docs/additional_reports in package)