Beat each preceding STAC-M3 submission in over 50% of the baseline benchmarks in 1:1 comparisons
First STAC benchmarks of a container/orchestration framework
New records in all performance benchmarks and the energy efficiency benchmark
Servers with Skylake processors and Optane drives set multiple STAC-M3 records
Worst-case absolute accuracy of -0.5 +/5.5 nanoseconds for timestamps from any port on a single device
Unaudited benchmark results for a combined compute/storage architecture
Another successful round of STAC Summits has concluded. These events in three cities focused on artificial intelligence; C++ optimization; time sync measurement standards; new ways to scale up Python analytics; architectures for strategy backtesting; realities of public and private cloud with high-performance workloads; the future of low-latency, long-distance communication; low-latency FPGA solutions; and much more.
To see the agendas and slides from the events, click on the appropriate link below:
(Slides are for members only.)
The STAC-TS Working Group has poured a lot of effort into developing standards and software for demonstrating timestamp accuracy to the satisfaction of European regulators concerned with RTS 25 of MiFID 2. Much of that effort has concerned software-application timestamps. App timestamping is central to many firm's plans but is one of the most misunderstood issues with RTS 25.