Array
(
    [content] => 
    [params] => Array
        (
            [0] => /forum/threads/on-3dxpoint-and-crossbar-memory.6996/
        )

    [addOns] => Array
        (
            [DL6/MLTP] => 13
            [Hampel/TimeZoneDebug] => 1000070
            [SV/ChangePostDate] => 2010200
            [SemiWiki/Newsletter] => 1000010
            [SemiWiki/WPMenu] => 1000010
            [SemiWiki/XPressExtend] => 1000010
            [ThemeHouse/XLink] => 1000970
            [ThemeHouse/XPress] => 1010570
            [XF] => 2021770
            [XFI] => 1050270
        )

    [wordpress] => /var/www/html
)

? on 3DxPoint and CrossBar Memory

Arthur Hanson

Well-known member
It looks like Intel has plans for the data center market with 3DxPoint with not only the memory, but architecture and controllers. 3DxPoint looks like it could cause many changes in the memory market as it improves from one generation to the next. CrossBar which looks like TSM is developing for imbedded memory is more of a mystery as to where it's going and how it will evolve generation to generation. I have been told by an expert in the cell phone industry that phase change memories like this could change the whole ecosystem, which brings Apple into the equation. Could this be a future part of a vastly different ecosystem from the other smart phone makers? Does anyone have a clue on to how 3DxPoint will be marketed and by Micron and Intel and how conflicts might be handled? Any opinions, thoughts or ideas on this would be more than welcome. Also any thoughts on how these two technologies will evolve?
Thanks
 
The barriers to change the industry are high for any new technology and/or interface. The standard memory devices today benefit from massive economies of scale which give them a insurmountable cost and time to market advantage. Now that the 'memory' industry has really, really hit the wall the cost advantages are diminished and the introduction of new nodes takes longer, giving the opportunity for innovative memories and alternative architectures that can take advantage of them.

Your premise is spot-on and inevitable. It will take a long time. A good recent example is the conversion of image sensor technology from CCD to CMOS. The CMOS camp thought it would take a few years, but it's still not over yet:
CMOS Is Winning the Camera Sensor Battle, and Here's Why | TechHive
 
It looks like Intel has plans for the data center market with 3DxPoint with not only the memory, but architecture and controllers. 3DxPoint looks like it could cause many changes in the memory market as it improves from one generation to the next. CrossBar which looks like TSM is developing for imbedded memory is more of a mystery as to where it's going and how it will evolve generation to generation. I have been told by an expert in the cell phone industry that phase change memories like this could change the whole ecosystem, which brings Apple into the equation. Could this be a future part of a vastly different ecosystem from the other smart phone makers? Does anyone have a clue on to how 3DxPoint will be marketed and by Micron and Intel and how conflicts might be handled? Any opinions, thoughts or ideas on this would be more than welcome. Also any thoughts on how these two technologies will evolve?
Thanks

3D XPoint is being marketed for Storage Class Memory. 3D XPoint lacks the speed and endurance to replace DRAM in main memory and is more expensive than NAND. 3D NAND scales better for cost than 3D XPoint so 3D XPoint will likely stay more expensive than NAND. Both Micron and Intel have said 3D XPoint is targeted at storage class and the specs are perfect for that.
 
Back
Top