No compromise between
Speed Only Hardware Can Deliver
Compare to traditional off-the-shelves software solutions, NovaSparks feed-handlers can process market data feeds 5 to 10 times faster on average and 50 to 100 times during peak times. NovaSparks expects those acceleration factors to be maintained, and even increased in the future, given the power wall preventing CPUs to be used with higher operational frequencies. By comparison, FPGAs are still using moderate operational frequencies and thus should outperform CPUs even more in the future. In addition, NovaSparks constantly works at lowering the latency its solutions as demonstrated the diagram below showing the average historical wire to wire latency for the processing of Nasdaq TotalView ITCH feed, including book building.
Scale Only Software Could Deliver
Processing speed is not very useful if a feed handler can only process a limited number of instruments. Historically, FPGA have suffered from heavy restrictions in term of configurable instrument count because of the inherent memory limitations imposed by FPGA technology. NovaSparks is different. NovaSparks does not rely on off-the shelves FPGA cards. Instead, it designs its own FPGA modules with both speed and scale in mind. NovaSparks is constantly working to increase symbol count. With NovaTick 4th generation platform, instrument count can now scale up to 262,000 per FPGA module and growing. The diagram below shows the historical instrument scaling capability for one FPGA module.