[FFmpeg-devel] [PATCH 1/9] SBR DSP x86: implement SSE qmf_pre_shuffle

[Christophe Gisquet]

>From 253 to 70c on Arrandale and Win64.
---
 libavcodec/x86/sbrdsp.asm    | 33 +++++++++++++++++++++++++++++++++
 libavcodec/x86/sbrdsp_init.c |  2 ++
 2 files changed, 35 insertions(+)

diff --git a/libavcodec/x86/sbrdsp.asm b/libavcodec/x86/sbrdsp.asm
index 1b7f3a8..2029b45 100644
--- a/libavcodec/x86/sbrdsp.asm
+++ b/libavcodec/x86/sbrdsp.asm
@@ -220,3 +220,36 @@ cglobal sbr_qmf_post_shuffle, 2,3,4,W,z
     cmp               zq, r2q
     jl             .loop
     REP_RET
+
+INIT_XMM sse
+cglobal sbr_qmf_pre_shuffle, 1,4,7,z
+%define OFFSET  (32*4-2*mmsize)
+    mov       r3q, OFFSET
+    lea       r1q, [zq + (32+1)*4]
+    lea       r2q, [zq + 64*4]
+    mova       m6, [ps_neg]
+.loop:
+    movu       m0, [r1q]
+    movu       m2, [r1q + mmsize]
+    movu       m1, [zq + r3q + 4 + mmsize]
+    movu       m3, [zq + r3q + 4]
+    xorps      m2, m6
+    xorps      m0, m6
+    shufps     m2, m2, q0123
+    shufps     m0, m0, q0123
+    mova       m5, m2
+    mova       m4, m0
+    unpcklps   m2, m3
+    unpckhps   m5, m3
+    unpcklps   m0, m1
+    unpckhps   m4, m1
+    mova  [r2q + 2*r3q + 0*mmsize], m2
+    mova  [r2q + 2*r3q + 1*mmsize], m5
+    mova  [r2q + 2*r3q + 2*mmsize], m0
+    mova  [r2q + 2*r3q + 3*mmsize], m4
+    add       r1q, 2*mmsize
+    sub       r3q, 2*mmsize
+    jge      .loop
+    mova       m2, [zq]
+    movlps  [r2q], m2
+    REP_RET
diff --git a/libavcodec/x86/sbrdsp_init.c b/libavcodec/x86/sbrdsp_init.c
index 27fade1..5f87cf4 100644
--- a/libavcodec/x86/sbrdsp_init.c
+++ b/libavcodec/x86/sbrdsp_init.c
@@ -33,6 +33,7 @@ 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_qmf_post_shuffle_sse(float W[32][2], const float *z);
+void ff_sbr_qmf_pre_shuffle_sse(float *z);
 
 av_cold void ff_sbrdsp_init_x86(SBRDSPContext *s)
 {
@@ -44,5 +45,6 @@ av_cold 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->qmf_post_shuffle = ff_sbr_qmf_post_shuffle_sse;
+        s->qmf_pre_shuffle  = ff_sbr_qmf_pre_shuffle_sse;
     }
 }
-- 
1.8.0.msysgit.0