News for hackers. Stuff that matters.

A comment on AMD Ryzen 9 3950X Review. Parent comment

Re:AMD Ryzen 9 3950X Review by mjevans on Thursday November 14, 2019 @04:15PM (#21539506)
It would be interesting if we moved back to the final layer of cache being off-core, likely within the IO die or attached as additional chips within the package. That should decrease the core size, improve yields, and allow for differentiation in L3 size as well.
[ Parent | on HN ]
Re:AMD Ryzen 9 3950X Review by gameswithgo on Thursday November 14, 2019 @04:41PM (#21539758)
but it would add latency :( but maybe an L4 cache, off core, as additional chips!
[ Parent | on HN ]
Re:AMD Ryzen 9 3950X Review by wahern on Thursday November 14, 2019 @08:04PM (#21541329)
At some point both higher latencies and deeper cache hierarchies seem inevitable: http://www.ilikebigbits.com/2014_04_21_myth_of_ram_1.html

Though, perhaps 3D integration can stave that off for many more generations.

[ Parent | on HN ]
Re:AMD Ryzen 9 3950X Review by paulmd on Thursday November 14, 2019 @04:57PM (#21539908)
Interestingly, Broadwell-S and Broadwell-R did this using the "Crystal Well" L4 cache.

However, DDR4 memory now provides more bandwidth than the L4 could (although probably at a higher latency).

[ Parent | on HN ]