DSN Member Profile: Myrtle Software

Myrtle Software


Myrtle accelerates performance critical workloads on FPGAs and has realized multiple proprietary deep learning networks as silicon designs, so that they execute at a latency and power point that makes them usable in real-world situations. Myrtle is currently targeting its automated design technology at inference workloads in data centers and is also involved in a major collaboration to address the safety and verification challenges for deep learning networks used in autonomous vehicles. Myrtle has significantly accelerated the time-to-market for FPGA designs by automating the translation of AI network designs using compiler technology targeting the Intel® Arria® 10 FPGA. Trained, high level algorithms, specified in a wide range of network descriptor formats – Torch, Caffe etc. are compiled and mathematically optimised, directly to VHDL to produce efficient, low latency designs. In cases where proprietary non-standard, deep learning layers are used these first need to be implemented.

Available Design Services

Design Services Device Family Country/Region Supported
Design Verification
Embedded Design: ARM Drivers, ARM Applications
Software Design: Software Drivers, Intel Xeon
Hardware Design: Specification Development, FPGA, Timing Closure
IP Integration
Contract Manufacturing
Arria 10 SoC, Arria 10 EMEA: Netherlands, Denmark, United Kingdom
Americas: United States

Additional Services and Features

‧    Low latency deep learning designs

‧    High level algorithm compilation direct to VHDL

‧    Accelerating datacenter workloads

‧    Fast turnaround for VHDL AI network designs

Contact Information

Second Floor
50 St Andrews Street
Cambridge, United Kingdom