How Oracle Exadata aims to accelerate machine learning
The new Oracle Exadata Database Machine X8 features hardware and software enhancements, as well as unique machine learning capabilities.
Delivering performance and availability, Oracle Exadata is the foundation for Oracle Autonomous Database, the world’s first self-driving database, and Oracle Cloud Applications.
In the fiscal year 2018, Exadata set all-time product sales records with continued adoption across multiple workloads such as OLTP, Analytics, and IoT, and multiple verticals, including finance, retail, electronics, and telecommunications.
“For the past 10 years, Exadata has been running the most critical workloads for thousands of customers around the world. Exadata now powers Oracle Autonomous Database and Oracle Cloud Applications,” said Oracle VP Juan Loaiza.
“Today, we are improving the performance and capacity of the platform, and adding a broad range of capabilities based on artificial intelligence and machine learning to further increase Exadata’s advantages.”
With Exadata X8, Oracle introduces unique machine-learning capabilities, including Automatic Indexing, which continuously learns and tunes the database as usage patterns change.
Based on technology from Oracle Autonomous Database, the entire process is automatic and improves database performance while eliminating manual tuning.
Exadata X8 also includes new automated performance monitoring, which combines artificial intelligence, years of real-world performance triaging experience, and best practices to automatically detect performance issues and determine the root cause without human intervention.
Exadata X8 Platform Innovations and Improved Cost Effectiveness
Exadata X8 hardware enhancements include the latest Intel Xeon processors and PCIe NVME flash technology to drive performance improvements -- a 60 per cent increase in I/O throughput for all-Flash storage and a 25 per cent increase in IOPS per storage server compared to Exadata X7.
Each Exadata X8 storage server now features 60 per cent more cores to offload Oracle Database processing and 40 per cent higher capacity disk drives to support massive data growth and database consolidation strategies.
These improvements come with no price increase, further improving the cost-effectiveness of the Exadata platform.
Additionally, a new extended storage server is available for storing infrequently accessed, older, or regulatory data.
At Hadoop/object storage prices, all customer data now receives the benefits of the Exadata scale-out architecture and Oracle Database storage, including application transparency, consistency of operational models, hybrid columnar compression (HCC) and the same security model with encryption across all tiers.