[FFmpeg-cvslog] x86/opusdsp: replace loads with shuffles

[Lynne]

ffmpeg | branch: master | Lynne <dev at lynne.ee> | Wed Apr 24 12:19:48 2019 +0100| [4b7166c9d57d3cc7ece02171338a27e129b12250] | committer: James Almer

x86/opusdsp: replace loads with shuffles

Has a slight speedup.
Can't be carried over to aarch64, since it has no shufps-like instruction.

Reviewed-by: Paul B Mahol <onemda at gmail.com>
Signed-off-by: James Almer <jamrial at gmail.com>

> http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=4b7166c9d57d3cc7ece02171338a27e129b12250
---

 libavcodec/x86/opusdsp.asm | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/libavcodec/x86/opusdsp.asm b/libavcodec/x86/opusdsp.asm
index 6c99821b89..f5d206a8b1 100644
--- a/libavcodec/x86/opusdsp.asm
+++ b/libavcodec/x86/opusdsp.asm
@@ -24,9 +24,6 @@ SECTION_RODATA
 
          ; 0.85..^1    0.85..^2    0.85..^3    0.85..^4
 tab_st: dd 0x3f599a00, 0x3f38f671, 0x3f1d382a, 0x3f05a32f
-tab_x0: dd 0x0,        0x3f599a00, 0x3f599a00, 0x3f599a00
-tab_x1: dd 0x0,        0x0,        0x3f38f671, 0x3f38f671
-tab_x2: dd 0x0,        0x0,        0x0,        0x3f1d382a
 
 SECTION .text
 
@@ -45,9 +42,9 @@ cglobal opus_deemphasis, 4, 4, 8, out, in, coeff, len
 %endif
 
     movaps m4, [tab_st]
-    movaps m5, [tab_x0]
-    movaps m6, [tab_x1]
-    movaps m7, [tab_x2]
+    VBROADCASTSS m5, m4
+    shufps m6, m4, m4, q1111
+    shufps m7, m4, m4, q2222
 
 .loop:
     movaps  m1, [inq]                ; x0, x1, x2, x3