x86: sbrdsp: Implement SSE neg_odd_64

Timing on Arrandale:
        C   SSE
Win32:  57   44
Win64:  47   38
Unrolling and not storing mask both save some cycles.

Signed-off-by: Diego Biurrun <diego@biurrun.de>

libavcodec/x86/sbrdsp.asm

@@ -24,6 +24,7 @@
 SECTION_RODATA
 ; mask equivalent for multiply by -1.0 1.0
 ps_mask         times 2 dd 1<<31, 0
+ps_mask2        times 2 dd 0, 1<<31
 ps_neg          times 4 dd 1<<31
 
 SECTION_TEXT
@@ -223,3 +224,24 @@ cglobal sbr_qmf_post_shuffle, 2,3,4,W,z
     cmp               zq, r2q
     jl             .loop
     REP_RET
+
+INIT_XMM sse
+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

libavcodec/x86/sbrdsp_init.c

@@ -32,6 +32,7 @@ void ff_sbr_hf_g_filt_sse(float (*Y)[2], const float (*X_high)[40][2],
 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_neg_odd_64_sse(float *z);
 void ff_sbr_qmf_post_shuffle_sse(float W[32][2], const float *z);
 
 av_cold void ff_sbrdsp_init_x86(SBRDSPContext *s)
@@ -39,6 +40,7 @@ av_cold void ff_sbrdsp_init_x86(SBRDSPContext *s)
     int mm_flags = av_get_cpu_flags();
 
     if (EXTERNAL_SSE(mm_flags)) {
+        s->neg_odd_64 = ff_sbr_neg_odd_64_sse;
         s->sum_square = ff_sbr_sum_square_sse;
         s->sum64x5    = ff_sbr_sum64x5_sse;
         s->hf_g_filt  = ff_sbr_hf_g_filt_sse;