Displaying 3 results from an estimated 3 matches for "optimizing_assembly".
2014 Jan 14
1
PATCH for lpc_asm.nasm
...Two comments ";ASSERT(lp_quantization <= 31)" in the new functions ..._wide_asm_ia32()
-- just to mention this constraint.
(max. possible value of lp_quantization is 15, so it's not a problem)
2) "mov cl, ..." was replaced with "mov ecx, ..." (again Agner Fog, optimizing_assembly.pdf)
summary: write to a partial register may result in false dependencies
between instructions, so it is better to avoid it.
(also bitreader_asm.nasm and stream_encoder_asm.nasm both have "mov ecx, ..."
instructions, and no "mov cl, ...").
-------------- next part ------------...
2014 Jan 03
1
PATCH: match calls and returns
According to Agner Fog, "...you must make sure that all calls
are matched with returns. Never jump out of a subroutine without
a return and never use a return as an indirect jump."
(see paragraph 3.15 in microarchitecture.pdf and
examples 3.5a and 3.5b in optimizing_assembly.pdf)
Basically this patch replaces
call .get_eip0
.get_eip0:
pop eax
with
call .mov_eip_to_eax
.get_eip0:
and
.mov_eip_to_eax:
mov eax, [esp]
ret
-------------- next part --------------
A non-text attachment was scrubbed...
Name: get_eip.diff
Type: application/octet-stream
Size...
2016 Jan 19
1
Lets do a 1.3.2 release
Dave Yeo wrote:
>> I cannot find information what version of binutils supports AVX/AVX2/FMA
>> instructions, but IIRC OS/2 doesn't support AVX instructions anyway,
>> so it doesn't matter much.
>
> Surprisingly, I've yet to have a report of an AVX related crash or trap
> (used in FFmpeg and projects based on it, Mozilla, probably others).
> As I