som

Posted on by Jean-Luc Aufranc (CNXSoft) - No Comments on AMD Versal AI Edge SoC FPGA system-on-module targets ADAS, robotics, medical imaging, and other AI applications

AMD Versal AI Edge SoC FPGA system-on-module targets ADAS, robotics, medical imaging, and other AI applications

AMD Xilinx Versal AI Edge System-on-Module

iWave Systems iW-Rainbow-G57M is a system-on-module (SoM) based on the AMD (Xilinx) Versal AI Edge series of Cortex-A72/R5 SoC FPGAs designed to deliver AI acceleration at relatively low power for demanding applications such as ADAS, robotics, and medical imaging. The module comes with up to 8GB 64-bit LPDDR4, 16GB eMMC Flash, 256MB QSPI Flash, delivers up to 45 TOPS of AI performance, and features eight transceivers that can be used for high-speed Ethernet, PCIe, MIPI DSI/CSI interfaces, and/or others as required by the customer’s specific project. iW-Rainbow-G57M specifications: FPGA SoC – AMD Xilinx Versal AI Edge/Prime SFVA784 package (VE2302, VE2202, VE2102,  or VE2002) with Dual Arm Cortex-A72 core processor @ up to 1.6 GHz Dual-core Arm Cortex-R5F Up to 328K Logic cells & 150K LUTs Programmable Network on Chip (NoC) Up to 45 TOPS (INT4) AI compute 8x GTYP Transceivers @ 28.21 Gbps (VE2302 & VE2202 only) Memory – Up […]

Posted on by Jean-Luc Aufranc (CNXSoft) - 6 Comments on $14+ Allwinner T113-S3 CPU module comes with 128MB RAM, 256MB NAND flash or 4GB eMMC flash

$14+ Allwinner T113-S3 CPU module comes with 128MB RAM, 256MB NAND flash or 4GB eMMC flash

Allwinner T113-S3 CPU module

MYiR MYC-YT113X is a low-cost solderable CPU module powered by an Allwinner T113-S3 dual-core Cortex-A7 processor with 128MB on-chip DDR3 RAM, and fitted with either a 256MB NAND flash or a 4GB eMMC flash for storage. The industrial temperature grade module provides a lower-end alternative to the company’s earlier MYC-YT507H Allwinner T507-H Cortex-A53 CPU module, and offers various display, camera, audio, Ethernet, USB, and low-speed I/Os through a 140-pin stamp hole design. It is designed for HMI, industrial automation, as well as display and control terminals. MYiR MYC-YT113X specifications: SoC – Allwinner T113-S3 CPU – Dual-core Arm Cortex-A7 @ 1.2 GHz with 32 KB L1 I-cache + 32 KB L1 D-cache per core, and 256 KB L2 cache DSP – Single-core HiFi4 VPU – H.265/H.264 video decoding up to 1080p60 and JPEG/MJPEG video encoding up to 1080p60 Memory – 128 MB DDR3 Storage – 4GB eMMC or 256MB NAND flash, […]

Posted on by Jean-Luc Aufranc (CNXSoft) - 4 Comments on Rongpin DR4-S905/DR4-A311D SoM features Amlogic S905D3 or A311D processor

Rongpin DR4-S905/DR4-A311D SoM features Amlogic S905D3 or A311D processor

DR4-A311D Amlogic A311D system-on-module

Shenzhen Rongpin Electronic Technology (Rongpin) DR4-S905 and DR4-A311D are SO-DIMM system-on-modules (SoM) respectively powered by Amlogic S905D3 quad-core Cortex-A55 processor and Amlogic A311D octa-core Cortex-A73/A53 processor. The modules come with 2GB LPDDR4 and 16GB eMMC flash by default, but can be ordered with up to 4GB RAM and 128GB storage, and the company offered a feature-rich carrier board to test all interfaces provided but the system-on-modules. DR4-S905 system-on-module specifications: SoC – Amlogic S905D3 quad-core Cortex-A55 processor @ 1.9GHz with Arm Mali-G31MP2 GPU up to 800MHz supporting OpenGL ES 3.2, Vulkan 1.0 and OpenCL 2.0, real-time Cortex-M4 core for always-on processing, and 1.2 TOPS NPU System Memory – 2GB LPDDR4 by default (1GB/4GB options) Storage – 16GB eMMC 5.1 flash by default (8GB, 32GB, 64GB, 128GB options) SO-DIMM edge connector for connection to a carrier board Power management – Discrete design Dimensions – 69.6 x 30mm Temperature Range – -25℃ to […]

Posted on by Jean-Luc Aufranc (CNXSoft) - 13 Comments on MediaTek Genio 1200 system-on-module powers Cortex-A78/A55 AIoT & robotics development kit

MediaTek Genio 1200 system-on-module powers Cortex-A78/A55 AIoT & robotics development kit

I-Pi SMARC 1200

ADLINK Technology’s SMARC 2.1 compliant LEC-MTK-I12000 system-on-module (SoM) features the MediaTek Genio 1200 octa-core Cortex-A78/A55 AIoT processor coupled with up to 8GB RAM and 256GB UFS storage, and powers the I-Pi SMARC 1200 development kit designed for robotics and AIoT applications. LEC-MTK-I1200 MediaTek Genio 1200 system-on-module LEC-MTK-I1200 SoM specifications: SoC – MediaTek Genio 1200 (MT8395) octa-core processor with 4x Cortex-A78 cores @ 2.2GHz, 4x Cortex-A55 cores @ 2.0GHz with penta-core Arm Mali-G57 GPU @ 880MHz with support for OpenGL ES 3.2/2.0/1.1, Vulkan 1.1/1.0, OpenCL 2.2, 5.0 TOPS NPU, HiFi 4 audio DSP, etc… System Memory – 4 or 8 GB LPDDR4X Storage – 32, 64, 128, or 256 GB UFS storage, compatible with UFS gear 2.1 Wireless – 802.11b/g/n/ac WiFi 5 2×2 MU-MIMO, Bluetooth 5.0 314-pin MXM connector with Storage – 1x SDIO (4-bit) compatible with SD/SDIO standard, up to version 3.0 Display HDMI 2.0b up to 4Kp60 Dual-channel LVDS […]

Posted on by Jean-Luc Aufranc (CNXSoft) - 38 Comments on Lichee Pi 4A RISC-V SBC takes on Raspberry Pi 4 with TH1520 processor

Lichee Pi 4A RISC-V SBC takes on Raspberry Pi 4 with TH1520 processor

Lichee Pi 4A RISC V SBC

Lichee Pi 4A is a single board computer (SBC) powered by Alibaba T-Head TH1520 quad-core RISC-V Xuantie C910  processor @ 2.0 GHz with an Imagination GPU and a 4 TOPS NPU for AI that can compete against the Raspberry Pi 4 in terms of performance and features. We previously mentioned the Lichee Pi 4A (LPi4A) in our article about the Sipeed LM4A RISC-V system-on-module, but at the time we only had some benchmarks for the board and no photos and specifications about the SBC. Sipeed has now released photos, published detailed specifications, and is taking orders for the board. So let’s have a closer look. Lichee Pi 4A specifications against the ones for Raspberry Pi 4.   The TH1520 used to be advertised at up to 2.5 GHz, but it seems to have now come down to 2.0 GHz. Software support will include Debian, OpenWrt, and Android which should then […]

Posted on by Jean-Luc Aufranc (CNXSoft) - 7 Comments on Banana Pi BPI-W3 SBC features Rockchip RK3588 SoM, M.2 NVMe socket, 2.5GbE, HDMI output and input

Banana Pi BPI-W3 SBC features Rockchip RK3588 SoM, M.2 NVMe socket, 2.5GbE, HDMI output and input

Banana Pi BPI-W3

Banana Pi BPI-W3 is another Rockchip RK3588 SBC (single board computer) with 8GB RAM, 32GB eMMC flash, an M.2 NVMe socket, 2.5GbE networking, two HDMI 2.1 output ports, one HDMI 2.0 input port, and other features. We first recovered the board last summer, but at the time the RK3588 SBC came with a PCIe x4 slot and dual Gigabit Ethernet, and the company has now redesigned the board without either using instead a Rockchip RK3588 system-on-module as part of the design and implemented 2.5GbE and M.2 NVMe SSD support with the available PCIe interfaces. Banana Pi BPI-W3 specifications: SoM – BPI-RK3588 core board SoC- Rockchip RK3588 octa-core processor with 4x Cortex-A76 cores @ up to 2.4 GHz, 4x Cortex-A55 cores @ 1.8 GHz, an Arm Mali G610MC4 GPU, a 6 TOPS NPU, 8Kp60 H.265/VP9/AVS2 10-bit decoder, 8Kp30 H.265/H.264 encoder System Memory – 8GB LPDDR4 (options for 4GB to 32GB) Storage […]

Posted on by Jean-Luc Aufranc (CNXSoft) - 5 Comments on Mixtile Core 3588E Rockchip RK3588 system-on-module works with NVIDIA Jetson TX2 NX carrier boards

Mixtile Core 3588E Rockchip RK3588 system-on-module works with NVIDIA Jetson TX2 NX carrier boards

Rockchip RK3588 SoM NVIDIA Jetson TX2 NX alternative

Mixtile Core 3588E is a system-on-module powered by a Rockchip RK3588 SoC and equipped with the 260-pin SO-DIMM connector found in the NVIDIA Jetson TX2 NX (and Jetson Nano, Xavier NX, Orin Nano modules). We’ve seen several companies make Raspberry Pi CM4 alternatives such as Radxa CM3 or Pine64 SoQuartz, and Mixtile even has its own Core 3568M SoM that can be used as a drop-in replacement for the Raspberry Pi CM4. But I had not seen companies try to make system-on-modules based on NVIDIA Jetson’s 260-pin SO-DIMM edge connector, and that’s exactly what the Mixtile Core 3588E has to offer. Mixtile Core 3588E specifications: SoC – Rockchip RK3588 CPU – Octa-core processor with 4x Arm Cortex-A76 cores @ up to 2.4 GHz, 4x Arm Cortex-A55 cores GPU – Arm Mali-G610 MP4 GPU with support for OpenGL ES3.2, OpenCL 2.2, Vulkan1.1 AI accelerator – 6 TOPS NPU with support for […]

Posted on by Leo Zachary - No Comments on 100ASK-V853-Pro – A feature-rich Allwinner V853 board designed for AI vision applications

100ASK-V853-Pro – A feature-rich Allwinner V853 board designed for AI vision applications

100ASK V853 Pro

The 100ASK-V853-Pro board is a development kit consisting of an Allwinner V853 system-on-module board (SoM) and a feature-rich carrier board with a large number of interfaces. Allwinner V853 supports up to 1TOPS of NPU computing power and is mainly for AI vision application development. The core board contains a DDR and eMMC as well as a PMU chip (AXP2101) and is connected to the carrier board through a board-to-board connector. All the functional resources of the V853 are drawn out through the carrier board. The carrier board comes with 2-channels CSI camera interfaces as well as RGB and MIPI DSI display interfaces. Although 1 TOPS of AI computing power is not outstanding, the NPU can still be used to accelerate AI vision applications at the edge. The board also comes with four USB 2.0 ports (two Type-A, two Type-C), an 100Mbps Ethernet port, a 22-pin header for expansion, and five […]

Exit mobile version