Computational storage represents a paradigm shift in data storage, directly integrating computational capabilities within storage devices. CSDs have processors that can execute specific computational functions directly within the storage hardware.
Reduced Data Movement
Processing is done within the storage device, reducing the need to move large volumes of data.
Increased parallelism and decreased computational load on the CPU. This leads to faster processing and reduced latency.
This localized processing reduces the overall system power consumption, contributing to energy efficiency.
Applicability in enterprise environments
The innovative technology is especially relevant in industries like technology startups, where vast amounts of data must be processed efficiently. For example, computational storage SSD can significantly enhance the capabilities of enterprises by delivering real-time insights and accommodating ever-expanding datasets.
A closer look at the ScaleFlux approach
The CSD 3000 is a best-in-class enterprise NVMe SSD, delivering better performance, capacity utilization, and endurance than other ordinary drives.
Other vendors try to deliver computational storage technology using an FPGA, adding cost, power, and software requirements to servers. At ScaleFlux, we designed and built the SFX 3000, an SoC ASIC Computational Storage controller that delivers what the market wants – a high-performing, NVMe SSD at the right price. Our ASIC sits at the heart of our CSD 3000, a next-generation SSD, allowing us to transparently compress data directly on the drive, offloading the CPU to accelerate performance and add capacity.
What does this deliver?
Compressing data in hardware reduces write-amplification, and you have an increase in performance from an IOPS or bandwidth perspective from the host. You can also run the device to a far higher capacity utilization before you see any abnormal performance side effects.
Even with a modest amount of data compression, you get industry-leading performance in IOPS and bandwidth resulting in double or even triple the usable capacity and improving drive endurance, extending device life by 4x and more.
Guide 2023: What is Computational Storage?
And how to take advantage of it.