Jump to content

Talk:Explicit data graph execution

Page contents not supported in other languages.
From Wikipedia, the free encyclopedia
This is an old revision of this page, as edited by Musaran (talk | contribs) at 16:44, 21 November 2023 (Registers & ALUs details please: new section). The present address (URL) is a permanent link to this revision, which may differ significantly from the current revision.
WikiProject iconComputing Start‑class
WikiProject iconThis article is within the scope of WikiProject Computing, a collaborative effort to improve the coverage of computers, computing, and information technology on Wikipedia. If you would like to participate, please visit the project page, where you can join the discussion and see a list of open tasks.
StartThis article has been rated as Start-class on Wikipedia's content assessment scale.
???This article has not yet received a rating on the project's importance scale.
Taskforce icon
This article is supported by Computer hardware task force.

Marketing-ish

Current version [1] sounds a bit too much marketing: enthusiastic, all positive, too abstract, long lead-in. Musaran (talk) 16:16, 21 November 2023 (UTC)[reply]

Registers & ALUs details please

These look dubious and/or requires more explanation:

each basic block is given its own local registers

This is bound to make them either too scarce or wasteful, a know problem of independent unit design.
And does not address how data is passed between blocks/engines.

an EDGE CPU would normally consist of a single type of ALU-like unit.

Floating-point or division are known to be complex and have a big footprint, while a lot of code does not use them. One would expect hyperblocks dispatched to specialized engines ; or identical engines to dispatch operations to shared parallel execution units ; or maybe a slow but highly parallel microcode implementation. Musaran (talk) 16:44, 21 November 2023 (UTC)[reply]