As AI workloads continue to scale, the need for faster, more efficient storage and memory architectures is becoming increasingly important. To help address that demand, KIOXIA has announced the development of its new KIOXIA GP Series Super High IOPS SSDs, purpose-built for GPU-initiated, IOPS-intensive workloads.
Designed to support the NVIDIA Storage-Next™ initiative, the new SSDs allow GPUs to directly access high-speed flash memory as an extension of High Bandwidth Memory (HBM) and CPU memory. This approach is intended to improve GPU utilization and enable faster access to larger AI datasets.
The KIOXIA GP Series leverages KIOXIA XL-FLASH™ Storage Class Memory to deliver lower latency, higher IOPS, and reduced power consumption per IO compared with conventional TLC SSDs. Evaluation samples are expected to be available to select customers by late 2026.
To learn more about KIOXIA’s latest AI storage innovations, view our press release here.
Notes:
PCIe is a registered trademark of PCI-SIG.
Definition of SSD capacity: Kioxia Corporation defines a kilobyte (KB) as 1,000 bytes, a megabyte (MB) as 1,000,000 bytes, a gigabyte (GB) as 1,000,000,000 bytes, a terabyte (TB) as 1,000,000,000,000 bytes, and a kibibyte (KiB) is 1,024 bytes. A computer operating system, however, reports storage capacity using powers of 2 for the definition of 1GB = 2^30 bytes = 1,073,741,824 bytes and 1TB = 2^40 bytes = 1,099,511,627,776 bytes and therefore shows less storage capacity. Available storage capacity (including examples of various media files) will vary based on file size, formatting, settings, software and operating system, and/or pre-installed software applications, or media content. Actual formatted capacity may vary.
Company names, product names and service names may be trademarks of third-party companies.
Disclaimer
The views and opinions expressed in this blog are those of the author(s) and do not necessarily reflect those of KIOXIA America, Inc.