Until now, the evolution of SSDs has been based on improving storage capacity and access speed. However, in the years to come, thanks to the use of CXL technology in SSDswe will see how the latter will completely change the way applications and operating systems will use our computers.
One of the most interesting things seen at this year’s Hot Chips was the presentation of a Samsung NVMe type SSD with the capacities that we are going to comment on below. This unit is currently intended for servers or what are now called data centers. At the moment, the CXL or Compute Express Link is not implemented in any processor on the market, but its advantages are such that there is no doubt that its adoption will be massive in many systems in the future.
RAM and storage at the same level
The CXL protocol, Calculate express linkis basically a PCI Express 5.0 expander which has, among other things, the ability to all devices connected to this port are fully consistent in memory access. This means that any changes made to any part of the system’s global memory, DRAM, or local memory, such as graphics card VRAM, will be seen by all devices connected to that port.
The main advantage of this is the fact that no longer have to explicitly code copy processes from one device to another. Although at the level of the operation of the hardware, this will not change. Since we are talking about physically separate memories, so it will continue to operate as a non-unified memory architecture, but the big difference is to make it easier for application programmers and one of the components that will benefit the most from these changes for comes NVMe SSD storage, especially with the advent of PCIe Gen 5 compatible drives.
The Future of NVMe SSDs Lies in CXL
However, the CXL protocol in NVMe SSDs goes beyond that, as you can see in the graph above, and the access latency is much lower than a conventional disk. This will remind many of what Intel promised with Optane, but this time we are dealing with a non-proprietary standard that does not require the use of special flash memory chips, only an update to the PCIe interface of the ‘computer.
Now let’s review what M.2 type SSDs are, they usually have their corresponding flash memory chips where the data is stored, the flash controller which is nothing more than a ditto memory with increased capacities and finally one or two DRAM memory chips, which can be DDR or LPDDR. Also, thanks to the CXL, said memory would be part of the system RAM. In other words, The process of copying to system memory would not be necessary, and CPU and graphics card can directly accesswithout waiting for the data to be copied into their corresponding working memories.
The big downside
However, we cannot forget that accessing RAM memory through the PCI Express port, and even if we do it consistently, adds latency to the equation. That is, data and instructions that are executed from SSD memory will not be executed with the same ease. However, it should be clarified that the CPU will continue to access RAM through its conventional mechanism, precisely the CXL is not based on the CPU accessing while taking this path.
And, on the other hand, and finally, in the vast majority of cases, it’s much faster to directly access the SSD’s RAM than not having to go through the whole process of copying from memory to memory. other, as is currently the case.
