Computational Storage
With the widespread adoption of high-speed storage and the increased performance requirement of data-intensive applications, traditional architectures have created CPU, memory, and storage bottlenecks.
Enabling Future Innovations in the Next-Generation of Data Centers
Xilinx makes it possible to reduce TCO and accelerate system level compute by moving information processing closer to where your data resides
Significant Performance Improvement
Lower Energy Consumption
Lower & Predictable Latency
Solution Advantages
By moving compute closer to the data, Xilinx significantly reduces system-level data bottlenecks, increases parallelism, and reduces overall power requirements.
Computational Storage Drive
- Move operations to SSD, bypassing system-level bottlenecks
- Performance scales with storage
- Partners measuring up to 5X lower latency and 10X performance improvement
Computational Storage Array
- Storage Consolidation – up to 50% cost reduction
- Shared Storage reduces the need for copies
- Storage Virtualization
- Increased infrastructure density & reduced power
Disaggregated Storage Acceleration
- Offload for NVMe over fabric, integrated target RNIC (RoCE v2 protocol)
- Accelerators: Erasure coding, RAID, compression, hashing / de-dupe
- Customer logic
Our Vision
The center of gravity is shifting from compute to data through computational storage and its implications on improved application performance and overall infrastructure efficiency.
Watch Now
Featured Applications
Xilinx FPGAs creates cutting edge applications for Big Data, Database, and HPC accelerators
Samsung SmartSSD
Samsung Electronics launches SmartSSD, a Xilinx-based (FPGA) SSD that enables high-performance accelerated computing closer to flash storage and bypasses CPU and memory limitations. Samsung’s SmartSSD, powered by Xilinx FPGAs, increases speed and efficiency and lowers operating costs by pushing intelligence to where data lives.
Learn More