This is a guest post from Mike Montemorra, who is a technology guru with long and successful career in computer industry. Mike keeps an eye on the latest developments in computer and storage technology and publishes his observations weekly. Below is his brief summary of what was important in the past week.
What did we learn last week?
To add to my comments from last week, when we emerge from the current solid state memory glut next year, what will the storage landscape look like for client, cloud and enterprise? I suspect we will begin to see the emergence of memory-centric compute as 5G begins rollout. I’d love to hear your comments and thoughts!
Is HAMR really ready now for real-life workloads? Seagate and NetApp say yes. Results from this upcoming integration step will finally tell the tale of HAMR. If successful, look for lots of chest beating from STX… (link)
Tom Coughlin has assembled a pretty comprehensive review of the storage landscape in this series. I found it be be quite insightful. In part 1, he comments about solid state memory pricing and elaborates on how the industry will achieve this in part 2. Finally in part 3, he speculates on how all the data that is generated will be managed. It’s getting interesting out there, folks!
High speed AFA’s with huge capacities should proliferate in CY19, partly due to lower flash pricing. The cost vs performance tradeoff will suddenly appeal to more customers, spelling good times ahead for AFA makers as they continue to expand their market presence.
Here’s a good review of the big data landscape in CY18. A lot has happened this year… the data universe has dramatically expanded as have ways to deal with all this information. For example, AWS revenues are $27B and growing at a 46% CAGR! Others are growing even faster, but AWS illustrates what a monster cloud data management really is. It looks like CY19-CY20 will see some of the other companies noted in this article explode to the forefront as efficient solutions begin to appear.
An interesting annealing study on HAMR media. It looks like control of the multilayer interfaces is critical here. Not sure this is controllable in mass production however, but the paper highlights how critically important HAMR media interfaces are to good behavior. If they can get that anneal temp down to <200C, it might open the door to cheaper media substrates (like aluminum disks).
It looks like IBM wants to be a part of the 7nm SOC revolution. With this partnership with Samsung, they get a place at the table for their leading edge designs.
It looks like 1st generation 5G rollouts are underway by multiple carriers (here is AT&T’s announcement), but with only a few phones capable of using the technology, these rollouts are more about early bragging rights and less about performance.
Finally, besides the Rose Parade and champagne, here’s another thing to look forward to New Year’s Day. This space rock (Ultima Thule) should yield some interesting science and perhaps we will learn a little more about it’s strange luminescence properties. Stay tuned!