[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [ft-devel] ttinterp.c optimization
From: |
Alexei Podtelezhnikov |
Subject: |
Re: [ft-devel] ttinterp.c optimization |
Date: |
Wed, 27 Aug 2014 07:38:53 -0400 |
On Wed, Aug 27, 2014 at 12:42 AM, Werner LEMBERG <address@hidden> wrote:
>
>> Furthermore, it turns out that MPS instruction is *very* *very*
>> common. Why do we call CURRENT_Ppem here? The comment suggest that
>> the decision was arbitrary and, perhaps, wasteful. I see a huge
>> number of trivial FT_MulFix's by 1.0 still.
>
> Measuring ppem and pt values are done along the projection vector, so
> they *must* be recomputed each time since this value can change any
> time. However, it certainly makes sense to catch factor `1.0'
> explicitly instead of performing a multiplication. So please
> optimize :-)
Never mind my MPS nonsense due to a gdb miss. It is MPPEM which is
called a lot. I wonder if it makes sense to cache the value and update
it only when it potentially changes by other instructions. What do you
think? What can change it?