Computational Storage

Computational Storage shifts the compute-storage paradigm, processing data on the storage device. It operates on data in-flight directly on storage, and can also drastically reduce the volume of data that moves to the CPU.

Samsung, with its SmartSSD, is leading computational storage innovation.

SmartSSD eBook

Hyperacceleration = Hardware innovation + Zero code change

Hyperacceleration improves performance of data platforms like Apache Spark by automatically optimizing them with compute hardware. The flexible approach gives access to cutting-edge hardware like the SmartSSD with no impact on user Spark code.

How it Works

Bigstream Hyperacceleration enables the Samsung SmartSSD to execute Spark stages like filtering and decompression in storage, sending a small fraction of data to the CPU. The result is dramatic overall acceleration.

Technical Advantages

  • Computations are routed to the SmartSSD FPGA and execute more efficiently than if on the CPU.
  • SmartSSD executes expensive computations, freeing up CPU for more useful work.
  • Performing operations such as filter and project on the SmartSSD results in smaller data volumes sent to CPU, minimizing
CPU-storage bandwidth usage.

Deliver Results

Fast Insights

Jobs run up to 10X faster without changing your Apache Spark code, increasing data science productivity and the ability to meet tight SLAs

Enriched Analytics

Incorporate fuller data sets and more data sources by eliminating the bottlenecks forcing you to make compromises

Lower TCO

Instead of scale-out and scale-up, optimize your existing Spark environment with Bigstream, lowering hardware and operating expenses

Zero Code Change

The value of Bigstream is that it provides the communication and translation between Spark code and the computing environment.

While other acceleration approaches force you to alter your code or switch platforms entirely, with Bigstream your Spark code remains 100% unchanged.