>From 253 to 185c.
---
 libavcodec/x86/sbrdsp.asm    |   23 +++++++++++++++++++++++
 libavcodec/x86/sbrdsp_init.c |    2 ++
 2 files changed, 25 insertions(+), 0 deletions(-)

diff --git a/libavcodec/x86/sbrdsp.asm b/libavcodec/x86/sbrdsp.asm
index 2b90100..b9f0709 100644
--- a/libavcodec/x86/sbrdsp.asm
+++ b/libavcodec/x86/sbrdsp.asm
@@ -224,3 +224,26 @@ cglobal sbr_qmf_post_shuffle, 2,3,3,W,z
   cmp        zq, r2q
   jl      .loop
   REP_RET
+
+cglobal sbr_qmf_pre_shuffle, 1,4,4,z
+  movh       m3, [zq]
+  lea       r3q, [zq + 64*4]
+  lea       r2q, [zq + (64-3)*4]
+  add        zq, 4
+.loop:
+  movu       m0, [r2q]
+  movu       m1, [zq ]
+  xorps      m0, [ps_neg]
+  shufps     m0, m0, 0x1B
+  mova       m2, m0
+  unpcklps   m0, m1
+  unpckhps   m2, m1
+  mova  [r3q +  0], m0
+  mova  [r3q + 16], m2
+  add       r3q, 32
+  sub       r2q, 16
+  add        zq, 16
+  cmp        zq, r2q
+  jl      .loop
+  movh  [r3q-256], m3
+  REP_RET
diff --git a/libavcodec/x86/sbrdsp_init.c b/libavcodec/x86/sbrdsp_init.c
index 3f6dd97..5babe62 100644
--- a/libavcodec/x86/sbrdsp_init.c
+++ b/libavcodec/x86/sbrdsp_init.c
@@ -32,6 +32,7 @@ void ff_sbr_hf_gen_sse(float (*X_high)[2], const float 
(*X_low)[2],
                        float bw, int start, int end);
 void ff_sbr_sum64x5_sse(float *z);
 void ff_sbr_qmf_post_shuffle_sse(float W[32][2], const float *z);
+void ff_sbr_qmf_pre_shuffle_sse(float *z);
 
 void ff_sbrdsp_init_x86(SBRDSPContext *s)
 {
@@ -43,5 +44,6 @@ void ff_sbrdsp_init_x86(SBRDSPContext *s)
         s->hf_gen     = ff_sbr_hf_gen_sse;
         s->sum64x5    = ff_sbr_sum64x5_sse;
         s->qmf_post_shuffle = ff_sbr_qmf_post_shuffle_sse;
+        s->qmf_pre_shuffle = ff_sbr_qmf_pre_shuffle_sse;
     }
 }
-- 
1.7.7.msysgit.0

_______________________________________________
libav-devel mailing list
[email protected]
https://lists.libav.org/mailman/listinfo/libav-devel

Reply via email to