- Class-leading data center performance of up to 2.3x in real-world, mixed workload applications1
- 6x9s read latency leads the industry by as much as 3.2x2
- Capacities from 6.4TB up to a class-leading 30.72TB3
Note: All values provided are for reference only and are not warranted values. For warranty information, visit https://www.micron.com/support/sales-support/returns-and-warranties/enterprise-ssd-warranty or contact your Micron sales representative. Values represent the theoretical maximum endurance for the given transfer size and type. The endurance will vary by workload. Performance values measured at 25 watts.
- Comparisons are made based on other leading PCIe Gen4 Data Center U.2/U.3 NVMe SSDs based on data center market share as noted in the http://forward-insights.com/reportslist.html and available on the open market at the time of this document’s initial publication. 1GB = 1 billion bytes, formatted capacity is less.
- Performance measured using 7.68TB SSDs at queue depth (QD) = 256 with FIO (additional details on FIO are available here: https://fio.readthedocs.io/en/latest/).
- 3. 30.72TB capacity is the largest option. User capacity: 1GB = 1 billion bytes; formatted capacity is less.
- Warranty valid for 5 years from the original date of purchase or before writing the maximum total bytes written (TBW) as published in the product datasheet and as measured in the product’s SMART data, whichever comes first.
- 77% efficiency improvement is vs the Micron 9300 SSD. Efficiency is defined as performance per watt.
- Additional information available here: http://www.micron.com/176
- Performance measured under the following conditions: Steady-state as defined by SNIA Solid State Storage Performance Test Specification Enterprise v1.1; Drive write cache enabled; NVMe power state 0; Sequential workloads measured using FIO with a 128K IO size and a queue depth of 32; Random read workloads measured using FIO with a 4K IO size and queue depth of 256; Random write workloads measured using FIO with a 4K IO size and a queue depth of 128.
- Latency values measured with random workloads using FIO, 4KB transfers, queue depth = 1; Typical latency = median, 50th percentile