[Top][All Lists]
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [Freetype] LoadGlyph Time
From: |
James H. Cloos Jr. |
Subject: |
Re: [Freetype] LoadGlyph Time |
Date: |
01 May 2002 20:18:41 -0400 |
User-agent: |
Gnus/5.09 (Gnus v5.9.0) Emacs/21.1 |
>> Would cpu-specific optimizations using [SIMD] instructions help
>> speed things up?
David> This wouldn't add much I believe. Since it's not possible to
David> automatically parallelize TrueType bytecode.
>> How about a jit for the bytecodes?
David> You won't win much in terms of performance, and you're going to
David> explode the memory requirements of the engine (and the code's
David> complexity).
I didn't think there would be much of a gain, but dialog is always
better than thinking to oneself....
>> Or do patent issues start popping up with such optimiaztions?
>>
David> Nope, the patents protect the _result_ of computations, not the
David> way they're done. Otherwise, we would have side-stepped them
David> for long by now :-)
I should have said *more* patent issues; but it looks like they didn't
need to bother with anything beyond what they did go for.
-JimC