Why in-memory?

Summary of a blog post by Amit Patel, IBM Program Director Data Warehouse Solutions Marketing, 

Memory is the new disk. Disk is the new tape. And all of this opens fascinating new possibilities.   

The chain is only as strong as its weakest link. For system performance, the weak link is disk storage. While there have been tremendous improvements in microprocessors, system design, and software, disk storage remains the bottleneck.  Disks need to spin and physics only allows them to spin so fast. For analytic systems, this means that complex queries running against large data sets on disk can take too long to complete. Businesses cannot get the answers they need at a moment’s notice.

This is where in-memory computing—which relies on main memory for data storage—comes in. Main memory is much faster than disk storage.  Memory is now the new disk, and disk is the new tape. This means that in-memory computing opens up fascinating new possibilities for analytics where answers can be delivered near instantaneously. Hours and days become minutes and seconds in getting results.

Three key shifts allow in-memory computing to make business sense: processing capabilities have improved, DRAM prices have fallen, and software for in-memory computing is now available in a fast easy-to-use format.  All of this opens up entirely new possibilities for businesses to gain a competitive edge with their data. Businesses that don’t take advantage of it risk falling behind their competition.

Read Amit Patel’s full post.


Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s