Hi,
2014-11-06 23:04 GMT+01:00 James Almer jamr...@gmail.com:
No, the function checks for alignment and jumps to a branch that uses movdqu
if needed.
ff_int32_to_float_a_avx also uses ymm regs and this same macro.
OK, so nothing new here, same 32-bytes alignment.
when mulps m0, m1, [mem]
On 07/11/14 6:05 AM, Christophe Gisquet wrote:
Hi,
2014-11-06 23:04 GMT+01:00 James Almer jamr...@gmail.com:
No, the function checks for alignment and jumps to a branch that uses movdqu
if needed.
ff_int32_to_float_a_avx also uses ymm regs and this same macro.
OK, so nothing new here,
13797 decicycles in ff_float_to_int32_a_sse2, 32768 runs, 0 skips
8603 decicycles in ff_float_to_int32_a_avx2, 32766 runs, 2 skips
Signed-off-by: James Almer jamr...@gmail.com
---
x86inc.asm doesn't seem to handle cmpps or its aliases properly when using avx.
libswresample/x86/audio_convert.asm
Hi,
2014-11-06 21:48 GMT+01:00 James Almer jamr...@gmail.com:
13797 decicycles in ff_float_to_int32_a_sse2, 32768 runs, 0 skips
8603 decicycles in ff_float_to_int32_a_avx2, 32766 runs, 2 skips
A couple of naïve questions (I haven't checked):
Does it increase the alignment requirement?
If yes,
On 06/11/14 6:35 PM, Christophe Gisquet wrote:
Hi,
2014-11-06 21:48 GMT+01:00 James Almer jamr...@gmail.com:
13797 decicycles in ff_float_to_int32_a_sse2, 32768 runs, 0 skips
8603 decicycles in ff_float_to_int32_a_avx2, 32766 runs, 2 skips
A couple of naïve questions (I haven't checked):