- Kioxia details her plans for a new SSD for the workloads of the AI reaching 10 million IOPS
- IOPS measures at what speed a storage device can manage small random requests
- New Drive uses XL-Flash, a type of SLC NAND and a new internal controller
Kioxia has unveiled plans for a new SSD which, according to him, could reach an impressive 10 million PI, a level of performance targeting the requests for the AI systems focused on.
The SSD will use XL-Flash, a type of cell nand at a level (SLC), combined with a new internal controller.
A spokesperson for Koxia said Techpowerup“We take our XL-Flash ultra-fast memory chips, which use cells at a level, and associating them with a completely new controller … We target more than 10 million iops, and we plan to have ready samples in the second half of 2026.”
Difference between IOPS and GBPS
IOPS, or input / output operations per second, measures the speed with which a storage device can manage small random requests, particularly important in AI and server applications where quick access to small files is essential.
This is different from GBPS, which refers to the actual data transfer speed and is used to measure how fast files can be read or written.
A reader with high GBPs can excel in video editing or major file transfers, but for automatic learning tasks where thousands of small data packets are read or written constantly, high IOPS are greater.
Kioxia’s approach in new generation storage includes not only unique projects, but a wider effort to respond to various use cases. Its CM9 series, which now sampled to customers, focuses on speed and reliability to match the high -end GPUs used in AI, while the LC9 series offers massive capabilities of 122 TB for large databases.
Behind these products is the 8th generation bics flash, which introduces CBA Tech to increase performance and efficiency.
Kioxia also prepares future generations of flash memory using two methods. The first will add more layers of capacity, while the second mixes new CMOS conceptions with older cellular structures to control investment costs.
