What is persistent memory?

The main advantages of persistent memory include: 

• Provides access latencies less than those of flash SSDs.
• Increases throughput more than flash storage.
• Cheaper than DRAM. 
• PMEM is cacheable. This is a huge advantage over PCIe interconnect, which cannot be cached in the CPU.
• Real-time access to data; allows ultrafast access to large datasets. 
• Data persists in memory after power interruption, like flash.

Persistent memory can be used in a variety of ways to deliver lower latency for applications, such as: 

• Fraud detection. Persistent memory improves the speed at which financial institutions and insurance companies can perform data analytics on millions of records to detect fraudulent transactions, preventing financial loses and impact on brand name.
• Cyberthreat analysis. Persistent memory allows companies to move quickly to detect and defend against increasing cyberthreats. 
• Web-scale personalization. Persistent memory allows companies to tailor online experiences to the user by returning relevant content and advertisements to the user, resulting in higher user click-through and more e-commerce revenue opportunity.
• Financial trading. Financial trading applications can use persistent memory to rapidly process and execute financial transactions, allowing them to gain a competitive advantage and create higher revenue opportunity.
• Internet of Things (IoT). Faster processing of huge datasets in real time reduces time to value.

Nonvolatile random-access memory (NVRAM) is random-access memory that retains its information even if there is no power. If power is lost before the data is written to disk, you don’t lose the data because it can be recovered from NVRAM. 

NVRAM uses battery backup to keep data persistent. During this time it can flash the data out to a flash device that is attached directly. In most cases, NVRAM resides on the PCIe bus. 

PMEM or NVDIMM-N can also be backed up by battery. It resides only on the memory bus.