The amount of data generated, processed, and stored continues to grow rapidly. Humans, applications, algorithms, IoT devices, and more are leading constant innovation in storage technologies for consumer devices and IT data centers that power businesses across industries.
All that data comes with increasing costs. According to Gartner, worldwide IT spending totaled an estimated $5.26 trillion in 2024. Much of that recent spending is thanks to more organizations planning for and implementing GenAI applications.
“The compute power needs of GenAI are being felt across the data center, and spending in that segment reflects this ravenous demand,” said John-David Lovelock, Distinguished VP Analyst at Gartner.
Of course, data needs to live and operate somewhere. The value of storage systems is shifting from mere storage to active data processing for insights, driving the need for high-capacity, superfast, and reliable flash memory management.
Fortunately, advances in memory and storage technology have enabled data centers and cloud service providers to store and transfer massive volumes of data. Modernizing this part of a company’s IT infrastructure also brings value and benefits through new capabilities.
What is Flash Storage?
When it comes to cloud or cloud data center storage for everyday applications and data, most organizations have transitioned from hard disk drives (HDDs) to solid-state drives (SSDs). SSDs provide critical advantages in every aspect over HDDs:
Higher storage capacity per unit
Faster read, write, and erase times due to lower inherent latency and a software-defined management plane
Lower power consumption
Greater reliability, endurance, and longer life
Storage efficiencies that allow a competitive cost per bit compared with relatively slow hard disk drives
The building block of these SSDs is a semiconductor-based cell called flash. Flash memory today powers smartphones, laptops, servers, storage arrays, and storage chips in IoT and other devices.
“Disk drives used to be common in cost-sensitive consumer devices like PCs, DVRs, and even MP3 players. All consumer devices moved to flash as costs decreased because flash offers near-instant response times along with better power, cooling, and space characteristics,” said Lee Caswell, SVP of Product and Solutions Marketing at Nutanix.
In 2024, Nutanix contributed to the MLPerf Storage benchmarketing project and its Nutanix Unified Storage significantly outperformed other participating vendors.
“IT storage systems from the data center to the cloud are taking exactly the same path wherever processing speed and analytic insights are valued.”
3D NAND flash, a popular iteration of flash technology, involves silicon chips arranged in a planar matrix and on top of each other in multiple layers to make a 3D stack. The available storage per unit surface area is multiplied while the proximity between individual cells enables faster communication without adversely affecting performance or reliability. There’s also the expansion into NOR flash, particularly in the automotive industry, since cars can use NOR flash for rapid and reliable storage of software, firmware, mapping data, and other features of connected cars.
Contemporary SSDs use the Non-Volatile Memory Express (NVMe) interface to access the flash storage chip via a Peripheral Component Interconnect Express (PCIe) bus. NVMe allows for thousands of parallel requests over a single connection, significantly eliminating performance bottlenecks faced by the older SATA interface.
How Flash Storage Works for Cloud Computing and GenAI
Today’s enterprise data centers and cloud providers are jointly focused on serving up speed and availability for the most demanding applications. Data centers are now mirroring how the public cloud providers build scale - they rely on a scale-out design where all-flash enabled servers replace traditional storage arrays. These flash-enabled servers deliver high-performance block-based data storage along with compute so that customers can provide performance tuned to application needs.
While consumers mostly choose an SSD by capacity – think of your latest cell phone acquisition – cloud architects and product managers must carefully select each unit of storage hardware based on present and future application performance and capacity needs. The influx of GenAI tools and workflows simplifies the decision to use flash while complicating the calculus on future needs since Gen AI applications are changing so quickly.
“Flash SSDs are the de facto device in modern scale-out infrastructure, whether deployed on-premises, on the edge, or in the public cloud,” explained Caswell.
“AI workflows can require different storage repositories and protocols over the life of an AI. It’s a major benefit to consolidate disparate data lakes, ingest repositories, working data sets, and archive targets to a single, flash-based architecture. It’s now possible to get block, file, and object storage features, resiliency, and day 2 operations with a common operating model across teams.”
Flash-powered SSDs increasingly form the core of enterprise and hyperscale storage systems running on hybrid multicloud, high-performance computing (HPC), or hyperconverged infrastructure (HCI) architectures.
The ultimate test of any storage technology (hardware or software) lies in how it enables cloud applications—and, by extension, users—to access and process data. Flash has passed this test with flying colors by speeding up everything from productivity to telemetry apps, from LLM development to read/write-intensive scripts and databases.
In doing so, it has become the de facto standard for enterprise cloud architecture. Caswell expects that to continue as GenAI tools evolve.
“AI is an inherently hybrid workflow,” Caswell said. “LLMs are built in the public cloud, tuning can happen in a private data center, and inferencing is likely to happen close to where the data is created, namely at the distributed edge.”
As AI training models process trillions of data points, subtle differences between cloud storage options can significantly impact performance. The stability and speed of flash are some of the major draws for organizations, especially as GenAI applications require managing, storing, and processing staggering amounts of data.
Hybrid Cloud and HCI Environments Are Defaulting to Flash Storage
As more workloads move to the cloud and applications execute more data processing tasks, cloud data centers, HPC, and HCI environments must employ storage acceleration methods such as parallelization and shuffling. NVMe SSDs perfectly fit these intensive data processing needs.
The price of flash SSDs compared to HDDs used to be a concern. However, prices of NAND flash are nosediving. By 2026, SSDs are projected to be cheaper than HDDs on a cost-per-unit capacity ($/TB) basis. This trend is coupled with another interesting storage development.
“For the very first time, storage latencies are less than network latencies,” Caswell said. “And as capacity points exceed 30TiB, lower drive write per day specs are completely accepted.”
“That’s what allows us to build these scale-out systems based on high-volume server hardware. Servers offer the economics of seamless scaling, so you can add new nodes on the fly. The right software architecture is required, of course, and this is what allows us to support the highest performance block-based storage all the way to the highest capacity object-based storage with a single architecture.”
HCI and hybrid cloud environments need to process vast amounts of data every day, and the price-to-performance advantage of flash storage comes into play here. Due to their DRAM-level read/write speeds and bandwidth, flash SSDs deliver I/O performance several orders of magnitude better than HDDs. Legacy HDDs and tapes are not built to handle the I/O-intensive requirements of present-day cloud-native apps and databases.
Flash storage lowers the organization's cost-per-IOPS and makes it easier to move workloads between on-prem and cloud environments, more accurately predicting the impact of such shifts on operations.
If training a model is part of an organization’s plan, choosing the right environment for the process is essential. That means identifying infrastructure requirements and costs, determining time-to-business value, building a unified platform for training, deploying, and using a model for enterprise AI applications, and benchmarking storage performance.
“When an application is slow to respond, customers are quick to move on,” Caswell said.
“Flash is especially good for accelerating workloads like databases, data warehousing, data analytics, and virtual desktops. Flash acceleration makes it possible to run these applications on server-based scale-out infrastructure that can offer a consistent experience for applications running in the cloud or on-premises.”
Benefits of Flash Storage for the Cloud
Cloud flash storage is finding favor with applications in:
AI and ML, where large datasets need to be processed over extended periods of time.
Hi-res streaming media with high availability for uninterrupted access.
High-end gaming and AR/VR, which both mandate extremely high read speeds and very low latency.
High-performance computing (HPC), which needs isolated data processing, maximum capacity, and ultra-low latency.
It’s now possible to access the latest flash technology using common servers across the hybrid cloud. The local storage devices on these servers are aggregated, protected, and shared across virtual compute instances using software-defined virtualization technologies that create large-scale block, file, or object virtual storage arrays.
This gives organizations the freedom to prioritize performance, availability, or reliability according to the requirements of their workloads. Some of the primary benefits include:
Scalable I/O operations per second (IOPS)
A “try hard or fail fast” per I/O retry policy
Lower-tail latency
Granular access to disk analytics and telemetry on a per-block basis
Ability to prioritize requests by overriding the disk firmware schedule
Control over the timing of background tasks
Standardizing performance-intensive storage hardware leads to lower TCO, reduced data fragmentation, higher availability, and simple, no-lock-in memory management.
Modernizing IT infrastructure helps organizations realize these benefits and unlocks new opportunities that might not have previously been possible. As a result, more companies are adopting all-flash storage. During its 2025 second fiscal quarter, NetApp reported a 19 percent year-over-year increase in organizations going that route.
“Remember when you had a disk drive, and you could only use your laptop for a couple of hours, and you’d see the disc light sitting there and spinning?” Caswell said. “Today, your laptop can stay powered for an entire day of use. In fact, most people will never buy a disk drive again. There’s no capacity restraint. You can take it to more remote and rugged environments. It’s also better for your power footprint, with less dust buildup. The benefits just go on and on.”
This is an updated version of the article originally published on November 10, 2022.
Learn about modern storage fabric solutions and Nutanix Enterprise AI solutions.
Dipti Parmar is a marketing consultant and contributing writer to Nutanix. She’s a columnist for major tech and business publications such as IDG’s CIO.com, Adobe’s CMO.com, Entrepreneur Mag, and Inc. Follow Dipti on Twitter @dipTparmar or connect with her on LinkedIn for little specks of gold-dust-insights.
© 2025 Nutanix, Inc. All rights reserved. For additional information and important legal disclaimers, please go here.