Cyceera Intelligent Multithreading
Cyceera Limited, incorporated in England and Wales, registered number: 07230474,
Registered office 1 – 3 St. Mary’s Place, Bury, Lancashire BL9 0DZ, UK.
© Cyceera
Limited 2012
Welcome to Cyceera
Reconfigurable Heterogeneous Manycore Platforms For High Performance Computing, Signal Processing Systems & Machine Learning.
Based on our patented scalable heterogeneous manycore technology, Cyceera is developing
related parallel processing technologies in the field of Intelligent Systems that
exploit the advantages of our manycore technology. More specifically, we are targeting
real time autonomous decision support systems requiring a high degree of situational
awareness and cognitive style processing. Our technology is realised through a novel
learning Inference Engine. The Inference Engine can be employed in diverse and complex
environments that require experience based multi-
Ever greater convergence, increased autonomy and a demand for systems that provide more intelligent feedback and interaction requires an adaptable, flexible and parallel approach.
Our manycore technology is poised to address these needs and revolutionise multithreading
designs through novel system partitioning, self synchronising threads and optimising
core resource utilisation (dark silicon). Our technology enables the creation of
powerful parallel processing devices that address the constantly increasing demands
of reduced size, reduced power dissipation and greater throughput. Our technology
implements various levels of parallelism, including Instruction, Data, Logic, Thread,
Task, Storage and IO. Our manycore technology will offer a complete framework of
building blocks that provides flexible configurable hardware and targeted performance.
Not only are the components field programmable they offer partial and runtime reconfiguration
enabling the sharing of valuable processing resources. This will enable Cyceera to
provide innovative custom design solutions for organisations that may need assistance
with complex parallel processing applications through consultancy and or co-
