- Longsys WM8500 offers lossless in-memory compression up to 2:1
- The 5nm chip currently supports up to 128TB in single drive capacity compared to conventional consumer SSDs which cap at 8TB.
- This is made possible by using the DRAM-less SPU as an active player in the storage stack, leveraging both its high-level cache (HLC) and intelligent storage agent (iSA) to deliver an industry-leading compression ratio.
Longsys, the world’s second-largest independent memory company and the force behind one of the best-known consumer brands in the West, Lexar, as well as one of the largest B2B storage players, FORESEE, may have a solution to the rising costs of SSDs and DRAM: a chip that compresses data on the fly extraordinarily well.
It has created a 5nm chip that handles on-the-fly compression for large SSDs, allowing them to essentially double their capacity beyond the capacity of a single 128GB drive it currently supports.
While this isn’t as close to what hardware-based data compression on tape drives looks like (with ratios as high as 2.5:1), it’s still an impressive feat for an industry reeling from the rising costs of NAND flash, even as many data centers continue to use hard drives to keep costs down.
How does the Longsys WM8500 essentially double storage?
The Longsys WM8500 is what the storage giant calls an SPU, or Storage Processing Unit, built on a 5nm process and fundamentally different from technologies like Samsung’s SmartSSD.
Unlike Samsung’s approach, which leverages a general-purpose FPGA or ARM-based CPU inside the SSD to handle computational tasks on the drive, the SPU is an ASIC (application-specific integrated circuit) designed for a specific purpose: compression and storage management.
The 5nm chip also offers a cost advantage that most high-end consumer and enterprise-grade controllers don’t have, aside from its compression capabilities: It’s a completely DRAM-less design that allows it to command a lower price, even as Longsys’ claim to offer “virtually” double the storage to its AI consumers comes true.
It should be noted that the 2:1 figure is an “up” ratio, and while it might be easier for one ASIC to compress data and context windows for certain AI models, others might make it considerably more difficult, especially if obfuscation or encryption is at play.
However, in an ideal scenario, the WM8500 SPU, along with its high-level cache (HLC) implementation and its intelligent storage agent (iSA), together form what the manufacturer calls a “closed-loop software-hardware collaborative technology system” that focuses on AI customers.
HLC cache delivers a 40% reduction in DRAM requirements, making it a cost-effective alternative to HDD storage, even as competitors prepare to launch 256TB enterprise SSDs later this year. AI data centers continue to demand large amounts of storage and memory to meet their growing needs.
Follow TechRadar on Google News and add us as a preferred source to receive news, reviews and opinions from our experts in your feeds.
