ENABLE REAL-TIME ANALYTICS AND TACKLE DATA-INTENSIVE HIGH-PERFORMANCE COMPUTING (HPC) WORKLOADS.
THE BIGGEST DATA MACHINE
Its in-memory design and unparalleled scale give you the ability to analyze the growing amount of data moving through your business in real time, keeping you a step ahead. Because the infrastructure is modular, it's the right fit for any business of any size.
Up to 896 CPU Cores
Proven 99.999% RAS
Up to 48 TB of Memory
ØGet the computing power you need for your most demanding in-memory workloads with groundbreaking performance at scale, ultra-low latency, and high bandwidth.
ØDesigned for the future based on Memory-Driven Computing design principles to boost analytics performance up to 100X, or more.
ØZetta-Data Server has a unique modular design that scales flexibly and seamlessly from 4 to 32 sockets in 4-socket increments.
ØZetta-Data Server delivers the highest levels of uptime on industry standards with proven RAS capabilities, not available on other standard platforms, resulting in five nines (99.999%) single-system availability.
ØReduces human error with best-in-class predictive fault handling Error Analysis Engine, which predicts hardware faults and initiates self-repair without operator assistance.
The DB-Turbo IO Zetta-Data configuration, as like all DB-Turbo IO systems, is identified as a “Data Processor Machine” engineered to deliver dramatically better performance, cost-effectiveness, and availability for databases and applications with intensive IO operations over data.
Zetta-Data is based on a modern architecture featuring scale-UP, with large CPU cores-count and built-in intelligent liquid-storage management.
Zetta-Data runs all types of database workloads, including Online Transaction Processing (OLTP), Data Warehousing, and a consolidation of mixed workloads. Zetta-Data powers and protects the most important databases.
Zetta-Data permits to deliver the unique power needed for the most demanding in-memory applications like DNA/RNA sequencing by providing up to 48 TByte of shared memory in a single node.