Fun fact, the Mill's proposed method for hiding that latency, "deferred loads" h... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		deepnotderp on July 19, 2017 \| parent \| context \| favorite \| on: The Mill CPU Architecture: Switches [video] Fun fact, the Mill's proposed method for hiding that latency, "deferred loads" has already been done by Duke's Architecture Group: http://people.duke.edu/~bcl15/documents/huang2016-nisc.pdf (warning PDF link). The big gain? A measly ~8%.

cwzwarich on July 19, 2017 [–]

This doesn't decouple across function calls like the Mill claims to, right? Although doing that optimization on existing C/C++ programs will be difficult.

deepnotderp on July 19, 2017 | [–]

I don't think that's enough of a difference, YMMV, but nothing indicates that it should.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact