tiffdec: remove an unneeded variable

[ffmpeg] / libavcodec / x86 / sbrdsp.asm

diff --git a/libavcodec/x86/sbrdsp.asm b/libavcodec/x86/sbrdsp.asm
index bfc37c2a1fd518c2c274d3b85d4dbf6f3dd218b0..d7164b6496189fac99cc31775aecac6c0e17ba9a 100644 (file)
--- a/libavcodec/x86/sbrdsp.asm
+++ b/libavcodec/x86/sbrdsp.asm
@@ -118,9 +118,9 @@ cglobal sbr_hf_g_filt, 5, 6, 5
 .end:
     RET
 
-; static void sbr_hf_gen_c(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_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)
 ;
 cglobal sbr_hf_gen, 4,4,8, X_high, X_low, alpha0, alpha1, BW, S, E
     ; load alpha factors
@@ -247,7 +247,7 @@ cglobal sbr_neg_odd_64, 1,2,4,z
     REP_RET
 
 INIT_XMM sse2
-; sbr_qmf_deint_bfly(float *v, const float *src0, const float *src1)
+; void ff_sbr_qmf_deint_bfly_sse2(float *v, const float *src0, const float *src1)
 cglobal sbr_qmf_deint_bfly, 3,5,8, v,src0,src1,vrev,c
     mov               cq, 64*4-2*mmsize
     lea            vrevq, [vq + 64*4]
@@ -273,3 +273,33 @@ cglobal sbr_qmf_deint_bfly, 3,5,8, v,src0,src1,vrev,c
     sub               cq, 2*mmsize
     jge            .loop
     REP_RET
+
+INIT_XMM sse2
+cglobal sbr_qmf_pre_shuffle, 1,4,6,z
+%define OFFSET  (32*4-2*mmsize)
+    mov       r3q, OFFSET
+    lea       r1q, [zq + (32+1)*4]
+    lea       r2q, [zq + 64*4]
+    mova       m5, [ps_neg]
+.loop:
+    movu       m0, [r1q]
+    movu       m2, [r1q + mmsize]
+    movu       m1, [zq + r3q + 4 + mmsize]
+    movu       m3, [zq + r3q + 4]
+
+    pxor       m2, m5
+    pxor       m0, m5
+    pshufd     m2, m2, q0123
+    pshufd     m0, m0, q0123
+    SBUTTERFLY dq, 2, 3, 4
+    SBUTTERFLY dq, 0, 1, 4
+    mova  [r2q + 2*r3q + 0*mmsize], m2
+    mova  [r2q + 2*r3q + 1*mmsize], m3
+    mova  [r2q + 2*r3q + 2*mmsize], m0
+    mova  [r2q + 2*r3q + 3*mmsize], m1
+    add       r1q, 2*mmsize
+    sub       r3q, 2*mmsize
+    jge      .loop
+    movq       m2, [zq]
+    movq    [r2q], m2
+    REP_RET