In a continuing commitment to enabling industry-leading data acceleration in heterogeneous compute environments, Achronix Semiconductor Corporation, the industry’s only independent supplier of high-end FPGAs and eFPGA IP solutions, today announced the production release of its AC7t1500 FPGA and the addition of the power-efficient AC7t800 FPGA to the Achronix Tool Suite.
“The Speedster®7t product family offers unprecedented FPGA-based performance for data acceleration applications,” said Steve Mensor, VP of Marketing and Business Development at Achronix. “The release of the AC7t1500 to production along with the addition of the AC7t800 in our ACE design tools gives customers multiple options from this industry-leading, high-performance family that offers FPGA programmability with ASIC-level performance. These advancements give customers confidence that they can design on a robust, validated FPGA product family that meets their high-performance and high-bandwidth needs.”
Speedster7t high-end FPGAs are built on TSMC’s 7nm process technology and deliver the industry’s highest performance for networking, storage and compute acceleration applications. The Speedster7t architecture includes a revolutionary 2D network on chip (2D NoC) that offers 20 Tbps of total bandwidth. The 2D NoC offers high-speed connectivity between the FPGA fabric and the high-speed interfaces including 400G Ethernet, PCIe Gen5, GDDR6 and DDR4/5. Additionally, Speedster7t FPGAs have machine learning processors (MLPs) distributed across the FPGA fabric. Each MLP is a highly configurable, compute-intensive block, with up to 32 multipliers, that support integer formats from 4 to 24 bits and various floating-point modes including direct support for Tensorflow’s bfloat16 format and block floating-point (BFP) format.
