IBM has unveiled its latest storage innovation, the IBM Storage Scale System 6000. This cloud-scale global data platform is specifically tailored to address the demands of today’s data-intensive and AI workloads, making it a noteworthy addition to the IBM Storage for Data and AI portfolio.
IBM has unveiled its latest storage innovation, the IBM Storage Scale System 6000. This cloud-scale global data platform is specifically tailored to address the demands of today’s data-intensive and AI workloads, making it a noteworthy addition to the IBM Storage for Data and AI portfolio.
IBM has established itself as a leader in the sector. IBM has led the Gartner Magic Quadrant for Distributed File Systems and Object Storage for seven consecutive years. With the introduction of the IBM Storage Scale System 6000, the company aims to bolster its leadership standing even further. This state-of-the-art system boasts an impressive high-performance parallel file system specifically crafted for data-intensive scenarios. With capabilities such as delivering up to 7M IOPS and achieving up to 256GB/s throughput for read-only workloads in a compact 4U footprint, it’s clear that IBM is pushing boundaries.
Denis Kennelly, the general manager of IBM Storage, shared his insights on storage’s impact on AI, emphasizing the transformative potential of the current AI era. Kennelly believes that for this potential to be fully harnessed, organizations must adopt strategies allowing data unification from varied sources in near real-time. This should be achieved without the redundancy of creating multiple data copies or the constant iterations of data ingest. The IBM Storage Scale System 6000, he suggests, is the ideal solution, adeptly bringing together data from core, edge, and cloud onto a singular platform that’s fine-tuned for GPU workloads.
Redefining Efficiencies And Scalability
The Storage Scale System 6000 system from IBM is not just a storage solution; it is optimized for semi-structured and unstructured data types. This includes a vast array of content, from videos and images to text and instrumentation data, all generated daily. Consequently, organizations can vastly accelerate their digital presence across hybrid environments.
The IBM Storage Scale System is set to redefine data efficiencies and scalability with the forthcoming inclusion of IBM FlashCore Modules (FCM) in the first half of 2024. The new system will include a new maximum capacity NVMe FCM poised to redefine capacity efficiency, offering a 70 percent reduction in cost and consuming 53 percent less energy per terabyte when compared to IBM’s previous top-tier flash drives. Such advancements will enable clients to experience the peak performance of NVMe while also benefiting from the cost-efficiencies of Quad-level Cell (QLC).
Advanced in-line hardware-accelerated data compression and encryption capabilities ensure data security even in environments with multiple users and tenants. The upcoming Storage Scale System 6000, when integrated with FCM, will champion data storage, supporting 2.5x more data within the same floor space compared to its predecessor.
NVMeoF Turbo Tier
The IBM Storage Scale System is expected to accelerate the adoption and operationalization of AI workloads with IBM Watsonx. Innovative features like a novel NVMeoF turbo tier, parallel multi-tenant data isolation, and IBM’s patented computational storage drives all aim to boost performance, security, and efficiency for AI-centric tasks.
Powered by Storage Scale software, the Scale System 6000 connects data with an open ecosystem consisting of multi-vendor storage options that include AWS, Azure, IBM Cloud, and other public clouds, as well as IBM Storage Tape.
Customers gain faster access to data with over 2.5x the GB/s throughput and 2x IOPs performance of market-leading competitors. The high processing throughput and access speed with multiple concurrent AI and data-intensive workloads can run to meet a range of use cases.
Regarding performance metrics, IBM’s Storage Scale has already demonstrated its prowess. The University of Queensland, a premier research institution, has benefited significantly from the IBM Storage Scale global data platform. Through the deployment of the IBM Storage Scale System, the university has managed to achieve quicker data access, bolstering efficiency and expanding capabilities across various research domains.
IBM Storage Scale System and NVIDIA
The AI-driven future seems even brighter with the partnership between the IBM Storage Scale System and NVIDIA. IBM’s new system can establish a seamless information supply chain, extending from an NVIDIA AI solution to a myriad of other AI tasks, regardless of their location. With support for cutting-edge features like NVIDIA Magnum IOTM GPUDirect Storage (GDS) and capabilities like direct GPU memory and storage pathways, the IBM Storage Scale System 6000 is a testament to the future of AI and data storage.
Moreover, IBM’s new NVMeoF turbo tier has been engineered for small files like those collected from remote devices or to provide access to smaller transactions like data lake or lakehouse analytics so they can be integrated into an NVIDIA solution. By utilizing NVIDIA ConnectX-7 NICs, the Scale System 6000 supports up to 16 ports of 100Gb RDMA over Converged Ethernet (RoCE), 200Gb/s and/or 400Gb/s InfiniBand, or a combination of both to increase performance between nodes or directly to NVIDIA GPUs.
Engage with StorageReview
Newsletter | YouTube | Podcast iTunes/Spotify | Instagram | Twitter | TikTok | RSS Feed
