5989add4ab
lavu/x86/lls: add fma3 optimizations for update_lls
...
This improves accuracy (very slightly) and speed for processors having
fma3.
Sample benchmark (fate flac-16-lpc-cholesky, Haswell):
old:
5993610 decicycles in ff_lpc_calc_coefs, 64 runs, 0 skips
5951528 decicycles in ff_lpc_calc_coefs, 128 runs, 0 skips
new:
5252410 decicycles in ff_lpc_calc_coefs, 64 runs, 0 skips
5232869 decicycles in ff_lpc_calc_coefs, 128 runs, 0 skips
Tested with FATE and --disable-fma3, also examined contents of
lavu/lls-test.
Reviewed-by: James Almer <jamrial@gmail.com>
Reviewed-by: Henrik Gramner <henrik@gramner.com>
Signed-off-by: Ganesh Ajjanagadde <gajjanagadde@gmail.com>
2016-01-15 16:46:13 -05:00
70b8668fb5
drop LLS1, rename LLS2 to LLS
...
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-08-09 23:20:31 +02:00
c3814ab654
rename new lls code to lls2 to avoid conflict with the old which has a different ABI
...
also remove failed attempt at a compatibility layer, the code simply cannot work
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2013-11-17 16:41:08 +01:00
a478e99a60
avutil/x86: reenable ff_update_lls_avx()
...
The bug has been fixed in c8b920a9b7
2013-07-02 12:02:08 +02:00
d1fa671895
Merge commit 'c8b920a9b7fa534a6141695ace4e8c2dfcd56cee'
...
* commit 'c8b920a9b7fa534a6141695ace4e8c2dfcd56cee':
lls/x86: use 3-operator vaddpd in ADDPD_MEM
Merged-by: Michael Niedermayer <michaelni@gmx.at>
2013-07-02 11:40:44 +02:00
c8b920a9b7
lls/x86: use 3-operator vaddpd in ADDPD_MEM
...
Fixes build with yasm-1.1
Signed-off-by: Anton Khirnov <anton@khirnov.net>
2013-07-02 10:15:09 +02:00
4e488ac5f5
Merge remote-tracking branch 'qatar/master'
...
* qatar/master:
x86: lpc: fix a segfault in av_evaluate_lls_sse2()
Merged-by: Michael Niedermayer <michaelni@gmx.at>
2013-07-01 02:26:22 +02:00
1221bb6239
x86: lpc: fix a segfault in av_evaluate_lls_sse2()
2013-06-30 23:11:19 +00:00
6e76e6a05a
Merge commit 'b545179fdff1ccfbbb9d422e4e9720cb6c6d9191'
...
* commit 'b545179fdff1ccfbbb9d422e4e9720cb6c6d9191':
x86: lpc: simd av_evaluate_lls
Conflicts:
libavutil/x86/lls.asm
Merged-by: Michael Niedermayer <michaelni@gmx.at>
2013-06-30 12:15:12 +02:00
a285079bc7
lls.asm: disable ff_update_lls_avx
...
The code doesnt build with yasm from ubuntu 12.04
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2013-06-30 12:12:11 +02:00
0b40c50508
lls.asm: put avx code under if HAVE_AVX_EXTERNAL
...
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2013-06-30 12:12:01 +02:00
78b5479633
Merge commit '502ab21af0ca68f76d6112722c46d2f35c004053'
...
* commit '502ab21af0ca68f76d6112722c46d2f35c004053':
x86: lpc: simd av_update_lls
The versions are bumped due to changes in lls.h which is used across
libraries affecting intra library ABI
(This version bump also covers changes to lls.h in the immedeatly previous
commits)
Merged-by: Michael Niedermayer <michaelni@gmx.at>
2013-06-30 11:35:52 +02:00
b545179fdf
x86: lpc: simd av_evaluate_lls
...
1.5x-1.8x faster on sandybridge
Signed-off-by: Luca Barbato <lu_zero@gentoo.org>
2013-06-29 13:23:57 +02:00
502ab21af0
x86: lpc: simd av_update_lls
...
4x-6x faster on sandybridge
Signed-off-by: Luca Barbato <lu_zero@gentoo.org>
2013-06-29 13:23:57 +02:00
Ganesh Ajjanagadde
Michael Niedermayer
Loren Merritt
Loren Merritt