Stories
Slash Boxes
Comments

SoylentNews is people

posted by martyb on Tuesday May 30 2017, @02:35PM   Printer-friendly
from the moah-fasteh dept.

Recently, Intel was rumored to be releasing 10 and 12 core "Core i9" CPUs to compete with AMD's 10-16 core "Threadripper" CPUs. Now, Intel has confirmed these as well as 14, 16, and 18 core Skylake-X CPUs. Every CPU with 6 or more cores appears to support quad-channel DDR4:

Intel CoreCores/ThreadsPrice$/core
i9-7980XE18/36$1,999$111
i9-7960X16/32$1,699$106
i9-7940X14/28$1,399$100
i9-7920X12/24$1,199$100
i9-7900X10/20$999$100
i7-7820X8/16$599$75
i7-7800X6/12$389$65
i7-7740X4/8$339$85
i7-7640X4/4$242$61 (less threads)

Last year at Computex, the flagship Broadwell-E enthusiast chip was launched: the 10-core i7-6950X at $1,723. Today at Computex, the 10-core i9-7900X costs $999, and the 16-core i9-7960X costs $1,699. Clearly, AMD's Ryzen CPUs have forced Intel to become competitive.

Although the pricing of AMD's 10-16 core Threadripper CPUs is not known yet, the 8-core Ryzen R7 launched at $500 (available now for about $460). The Intel i7-7820X has 8 cores for $599, and will likely have better single-threaded performance than the AMD equivalent. So while Intel's CPUs are still more expensive than AMD's, they may have similar price/performance.

For what it's worth, Intel also announced quad-core Kaby Lake-X processors.

Welcome to the post-quad-core era. Will you be getting any of these chips?


Original Submission

 
This discussion has been archived. No new comments can be posted.
Display Options Threshold/Breakthrough Mark All as Read Mark All as Unread
The Fine Print: The following comments are owned by whoever posted them. We are not responsible for them in any way.
  • (Score: 2) by fyngyrz on Tuesday May 30 2017, @08:52PM

    by fyngyrz (6567) on Tuesday May 30 2017, @08:52PM (#517879) Journal

    Honestly, there's not much point [...] or you have some really special applications.

    I have (and write) exactly those applications. Software defined radio; intensive realtime image processing. The former runs very nicely with many, many threads doing completely different things, none of which except the main thread are loaded heavily (and that only because OS graphics support tends to have to be done from the main loop, which I really wish they (everyone) would get past); the latter goes faster the more slices you can chop an image into right up until you run out of memory bandwidth vs. internal instruction cycle time where the bus is available to other cores. Cache is basically useless here because it's never, ever large enough. And you can tune how far to slice things up based on dynamic testing of the machine you're running on. More than I need means I can get the right amount that I need. And my current 12/24 isn't more than I need.

    So... if Apple comes with a dual-CPU i9-7980XE, so providing 36 cores and 72 threads, in a Mac Pro that actually has significant memory expandability, slots for multiple graphics cards, and proper connectivity, I will on that like white on rice. They just might do that, too. That's just a 2013 Mac Pro with new CPUs and a bigger memory bus. And they've admitted the trash can isn't working out.

    If they don't, still, I'm sure someone will, and I'll attempt to Hackintosh my way along. If that can't be done, then I may abandon OSX/MacOS altogether for an OS that can give me what I want. My code's in c, and the important stuff isn't tied to any OS. And I use POSIX threading, so that's generally agnostic enough.

    Starting Score:    1  point
    Karma-Bonus Modifier   +1  

    Total Score:   2