Prev: AMD X2 3800+ processor has bottleneck in integer multiplier ?
Next: How many branches in a loop can be predicted successfully ?
From: Eugene Miya on 6 May 2008 19:04
>> Actually, I think there's a lot of inherent parallelism in the
>> task TeX tries to achieve (typesetting).

In article <yf3ve1rupic.fsf(a)tree.gp.example.com>,
Peter Grandi <pg_nh(a)0710.exp.sabi.co.UK> wrote:
>And to merge Nick's (and mine) liking of Algol 68 and the topic
>of microparallelism, I will mention here a rather amazing paper
>by Banatre on compiling Algol 68 by starting a new thread for
>every syntactic construct. This was done more to avoid explicit

I thought A68 had fork-join syntax. You don't have to get into
microparallelism, because you have MIMD parallelism in the language to begin
with right? But I'm also not aware of any of the European vector
machines Cray or CDC/ETA (ha) taking the time to move the a68 compiler over
so no one ever explored vectorizing a68 (which merely would have ended
up looking like CFT or cft77 fortran) much less the ICL/AMT DAP, the
SUPRENUM, the LAU, the ...fill in your favorite research
machine/Manchester.... Much less APL or that ascii APL (what was it? J?).

>multiple passes in a language with perverse forward references:
....
>On a similar, but not parallel-programming note, there was the
>diabolical left-to-right and right-to-left parsing technique of
>Bohm from the MC, which could parse Algol 68 in two passes.

Ah the things done with memory was more expensive.

--
 | 
Pages: 1
Prev: AMD X2 3800+ processor has bottleneck in integer multiplier ?
Next: How many branches in a loop can be predicted successfully ?