HANA, announced at SAP's annual Sapphire conference in May, provides a boost in performance by holding data to be processed in RAM instead of reading it from disks or flash storage.
The in-memory engine at the core of the appliance is an integrated database and calculation layer that allows the processing of massive quantities of real-time data in main memory to provide immediate results from analyses and transactions, SAP said.
The company claims the in-memory computing engine has delivered technical breakthroughs in trials with customers.
In speed tests, the SAP in-memory computing engine has the ability to scan 2 million records per millisecond per core with over 10 million complex aggregations calculated per second per core.
These results were attained with real customer data running on standard Intel processors, the company said.
SAP said HANA has been proven to scale performance linearly across cores, CPUS and servers because it has been designed ground-up around a multi-core architecture and implements adaptive, cache-aware algorithms. Current analyses indicate full parallelization at 1000 cores and beyond, the company said.
Lastly, the SAP in-memory computing engine employs advanced compression algorithms and data structures that minimise the memory footprint required to run the system while still maintaining full support for OLTP workloads, enabling a 450 billion record system to be implemented on less than three terabytes of physical memory.