Aller Is an Artix-7 FPGA Board with an M.2 Interface

The Numato Lab team has just launched an FPGA development board, based on the Xilinx Artix-7, in an M.2 form factor that can easily be…

Hackster Staff
5 years ago

The Numato Lab team has just launched an FPGA development board, based on the Xilinx Artix-7, in an M.2 form factor that can easily be inserted into any laptop, mini PC or server with a standard 2280 M-key slot.

The Aller is aimed at developers who want to experiment with PCI Express-based FPGA designs leveraging simple and cost-effective hardware, although it can be employed for a variety of PCIe acceleration applications as well.

“Aller was designed to help users with easier access to flexible and reconfigurable PCI Express infrastructure. With the decline of standard PCs and proliferation of M.2 connectors in laptops, servers and desktop PCs, Aller breaks the barrier to PCI Express designs. Aller can also be used with standard PCI Express slots using M.2-to-PCI Express Adapter without any loss of functionality.” — Rohit Sigh, Head of Development at the FPGA Division

As for its hardware, the Aller is equipped a Xilinx Artix-7 100T FPGA — featuring ~101K LUTs, ~126K flip-flops, ~600KiB Block RAM and 240 DSP slices — and packs 2Gb DDR3 SDRAM and 1Gb QSPI Flash memory. Additionally, an onboard Trusted Platform Module (TPM) IC enables users to completely offload their security sensitive computations to the FPGA.

With a compact M.2 footprint, the Aller can be hosted by a wide range of motherboards and laptops. Since most new systems these days ship with an M.2 M-key slot meant for SSDs, the board can directly take advantage of the huge ecosystem of the motherboards. As opposed to A, B or E-keys, the M-key is more common thanks to the popularity of SSDs and even sports four more PCI Express lanes. Because the M.2 M-key form factor supports PCI Express x4, it results in maximum theoretical bandwidth of 1GB/s between Aller and its host system.

Aller is a perfect match for several applications such as hardware accelerators, machine learning, and neural network engines, high hash-rate calculations for blockchain technologies, PCI Express kernel driver training, digital signal processing, as well as the development and testing of embedded processors.

The board is now available for purchase at a price of $399.95— with volume discounts available upon request.

Hackster Staff
Projects and articles from the Hackster Staff!
Latest articles
Sponsored articles
Related articles
Latest articles
Read more
Related articles