>From 210 cycles to 87 on penrynn.
Unrolling and not storing mask both save some cycles.
---
 libavcodec/x86/sbrdsp.asm    |   21 +++++++++++++++++++++
 libavcodec/x86/sbrdsp_init.c |    2 ++
 2 files changed, 23 insertions(+), 0 deletions(-)

diff --git a/libavcodec/x86/sbrdsp.asm b/libavcodec/x86/sbrdsp.asm
index aff6879..49dd78c 100644
--- a/libavcodec/x86/sbrdsp.asm
+++ b/libavcodec/x86/sbrdsp.asm
@@ -206,6 +206,26 @@ cglobal sbr_sum64x5, 1,2,4,z
   jne  .loop
   REP_RET
 
+cglobal sbr_neg_odd_64, 1,2,4,z
+  lea       r1q, [zq+256]
+.loop:
+  mova       m0, [zq+ 0]
+  mova       m1, [zq+16]
+  mova       m2, [zq+32]
+  mova       m3, [zq+48]
+  xorps      m0, [ps_mask2]
+  xorps      m1, [ps_mask2]
+  xorps      m2, [ps_mask2]
+  xorps      m3, [ps_mask2]
+  mova  [zq+ 0], m0
+  mova  [zq+16], m1
+  mova  [zq+32], m2
+  mova  [zq+48], m3
+  add        zq, 64
+  cmp        zq, r1q
+  jne     .loop
+  REP_RET
+
 cglobal sbr_qmf_post_shuffle, 2,3,3,W,z
   lea       r2q, [zq + (64-4)*4]
 .loop:
@@ -266,3 +286,4 @@ cglobal sbr_qmf_deint_neg, 2,3,4,v,src,vrev
   sub      srcq, 32
   cmp        vq, vrevq
   jl      .loop
+  REP_RET
diff --git a/libavcodec/x86/sbrdsp_init.c b/libavcodec/x86/sbrdsp_init.c
index e70b970..1ac64aa 100644
--- a/libavcodec/x86/sbrdsp_init.c
+++ b/libavcodec/x86/sbrdsp_init.c
@@ -31,6 +31,7 @@ void ff_sbr_hf_gen_sse(float (*X_high)[2], const float 
(*X_low)[2],
                        const float alpha0[2], const float alpha1[2],
                        float bw, int start, int end);
 void ff_sbr_sum64x5_sse(float *z);
+void ff_sbr_neg_odd_64_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_sbr_qmf_deint_neg_sse(float *v, const float *src);
@@ -44,6 +45,7 @@ void ff_sbrdsp_init_x86(SBRDSPContext *s)
         s->hf_g_filt  = ff_sbr_hf_g_filt_sse;
         s->hf_gen     = ff_sbr_hf_gen_sse;
         s->sum64x5    = ff_sbr_sum64x5_sse;
+        s->neg_odd_64 = ff_sbr_neg_odd_64_sse;
         s->qmf_post_shuffle = ff_sbr_qmf_post_shuffle_sse;
         s->qmf_pre_shuffle = ff_sbr_qmf_pre_shuffle_sse;
         s->qmf_deint_neg = ff_sbr_qmf_deint_neg_sse;
-- 
1.7.7.msysgit.0

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

Reply via email to