Merge commit '4a7af92cc80ced8498626401ed21f25ffe6740c8'

* commit '4a7af92cc80ced8498626401ed21f25ffe6740c8':
  sbrdsp: Unroll and use integer operations
  sbrdsp: Unroll sbr_autocorrelate_c
  x86: sbrdsp: Implement SSE2 qmf_deint_bfly

Conflicts:
	libavcodec/sbrdsp.c
	libavcodec/x86/sbrdsp.asm
	libavcodec/x86/sbrdsp_init.c

Merged-by: Michael Niedermayer <michaelni@gmx.at>

diff --cc libavcodec/sbrdsp.c
index 7207f3bc542b574ef24d06d201d97b82f8f3bfc6,4d07af58f8554b0e8cfabd1518e0650bae2c040a..de961cf70ec94c510f013161fce7841b1e49cb6b
--- 1/libavcodec/sbrdsp.c
--- 2/libavcodec/sbrdsp.c
+++ b/libavcodec/sbrdsp.c
@@@ -67,14 -66,14 +66,15 @@@ static void sbr_qmf_pre_shuffle_c(floa
      int k;
      zi[64].i = zi[0].i;
      zi[65].i = zi[1].i;
-     for (k = 1; k < 31; k+=2) {
-         zi[64+2*k+0].i = zi[64 - k].i ^ (1U<<31);
-         zi[64+2*k+1].i = zi[ k + 1].i;
-         zi[64+2*k+2].i = zi[63 - k].i ^ (1U<<31);
-         zi[64+2*k+3].i = zi[ k + 2].i;
+     for (k = 1; k < 31; k += 2) {
+         zi[64 + 2 * k + 0].i = zi[64 - k].i ^ (1U << 31);
+         zi[64 + 2 * k + 1].i = zi[ k + 1].i;
+         zi[64 + 2 * k + 2].i = zi[63 - k].i ^ (1U << 31);
+         zi[64 + 2 * k + 3].i = zi[ k + 2].i;
      }
-     zi[64+2*31+0].i = zi[64 - 31].i ^ (1U<<31);
-     zi[64+2*31+1].i = zi[31 + 1].i;
++
+     zi[64 + 2 * 31 + 0].i = zi[64 - 31].i ^ (1U << 31);
+     zi[64 + 2 * 31 + 1].i = zi[31 +  1].i;
  }
  
  static void sbr_qmf_post_shuffle_c(float W[32][2], const float *z)

diff --cc libavcodec/x86/sbrdsp.asm
index 1ce57776021d83552271022ddd7efb51c3077e70,bfc37c2a1fd518c2c274d3b85d4dbf6f3dd218b0..c4c95780ee63784182c9307b05c8b22d68a65239
--- 1/libavcodec/x86/sbrdsp.asm
--- 2/libavcodec/x86/sbrdsp.asm
+++ b/libavcodec/x86/sbrdsp.asm
@@@ -249,186 -246,30 +249,186 @@@ cglobal sbr_neg_odd_64, 1,2,4,
      jne      .loop
      REP_RET
  
 -INIT_XMM sse2
  ; sbr_qmf_deint_bfly(float *v, const float *src0, const float *src1)
 +%macro SBR_QMF_DEINT_BFLY  0
  cglobal sbr_qmf_deint_bfly, 3,5,8, v,src0,src1,vrev,c
-     mov        cq, 64*4-2*mmsize
-     lea     vrevq, [vq + 64*4]
+     mov               cq, 64*4-2*mmsize
+     lea            vrevq, [vq + 64*4]
  .loop:
-     mova       m0, [src0q+cq]
-     mova       m1, [src1q]
-     mova       m4, [src0q+cq+mmsize]
-     mova       m5, [src1q+mmsize]
+     mova              m0, [src0q+cq]
+     mova              m1, [src1q]
 -    mova              m2, [src0q+cq+mmsize]
 -    mova              m3, [src1q+mmsize]
 -    pshufd            m4, m0, q0123
 -    pshufd            m5, m1, q0123
 -    pshufd            m6, m2, q0123
 -    pshufd            m7, m3, q0123
 -    addps             m3, m4
++    mova              m4, [src0q+cq+mmsize]
++    mova              m5, [src1q+mmsize]
 +%if cpuflag(sse2)
-     pshufd     m2, m0, q0123
-     pshufd     m3, m1, q0123
-     pshufd     m6, m4, q0123
-     pshufd     m7, m5, q0123
++    pshufd            m2, m0, q0123
++    pshufd            m3, m1, q0123
++    pshufd            m6, m4, q0123
++    pshufd            m7, m5, q0123
 +%else
-     shufps     m2, m0, m0, q0123
-     shufps     m3, m1, m1, q0123
-     shufps     m6, m4, m4, q0123
-     shufps     m7, m5, m5, q0123
++    shufps            m2, m0, m0, q0123
++    shufps            m3, m1, m1, q0123
++    shufps            m6, m4, m4, q0123
++    shufps            m7, m5, m5, q0123
 +%endif
-     addps      m5, m2
-     subps      m0, m7
-     addps      m1, m6
-     subps      m4, m3
-     mova  [vrevq], m1
++    addps             m5, m2
+     subps             m0, m7
+     addps             m1, m6
 -    subps             m2, m5
++    subps             m4, m3
+     mova         [vrevq], m1
 -    mova  [vrevq+mmsize], m3
 +    mova  [vrevq+mmsize], m5
-     mova  [vq+cq], m0
+     mova         [vq+cq], m0
 -    mova  [vq+cq+mmsize], m2
 +    mova  [vq+cq+mmsize], m4
-     add     src1q, 2*mmsize
-     add     vrevq, 2*mmsize
-     sub        cq, 2*mmsize
-     jge     .loop
+     add            src1q, 2*mmsize
+     add            vrevq, 2*mmsize
+     sub               cq, 2*mmsize
+     jge            .loop
      REP_RET
 +%endmacro
 +
 +INIT_XMM sse
 +SBR_QMF_DEINT_BFLY
 +
 +INIT_XMM sse2
 +SBR_QMF_DEINT_BFLY
 +
 +INIT_XMM sse2
 +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]
 +
 +    pxor       m2, m6
 +    pxor       m0, m6
 +    pshufd     m2, m2, q0123
 +    pshufd     m0, m0, q0123
 +    SBUTTERFLY dq, 2, 3, 5
 +    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
 +    mova       m2, [zq]
 +    movq    [r2q], m2
 +    REP_RET
 +
 +%if WIN64 == 0
 +
 +%if WIN64
 +%define NREGS 0
 +%define NOISE_TABLE sbr_noise_table
 +%else
 +%ifdef PIC
 +%define NREGS 1
 +%if UNIX64
 +%define NOISE_TABLE r6q ; r5q is m_max
 +%else
 +%define NOISE_TABLE r5q
 +%endif
 +%else
 +%define NREGS 0
 +%define NOISE_TABLE sbr_noise_table
 +%endif
 +%endif
 +
 +%macro LOAD_NST  1
 +%if NREGS
 +    lea  NOISE_TABLE, [%1]
 +    mova          m0, [kxq + NOISE_TABLE]
 +%else
 +    mova          m0, [kxq + %1]
 +%endif
 +%endmacro
 +
 +INIT_XMM sse2
 +; sbr_hf_apply_noise_0(float (*Y)[2], const float *s_m,
 +;                      const float *q_filt, int noise,
 +;                      int kx, int m_max)
 +cglobal sbr_hf_apply_noise_0, 5,5+NREGS+UNIX64,8, Y,s_m,q_filt,noise,kx,m_max
 +    mova       m0, [ps_noise0]
 +    jmp apply_noise_main
 +
 +; sbr_hf_apply_noise_1(float (*Y)[2], const float *s_m,
 +;                      const float *q_filt, int noise,
 +;                      int kx, int m_max)
 +cglobal sbr_hf_apply_noise_1, 5,5+NREGS+UNIX64,8, Y,s_m,q_filt,noise,kx,m_max
 +    and       kxq, 1
 +    shl       kxq, 4
 +    LOAD_NST  ps_noise13
 +    jmp apply_noise_main
 +
 +; sbr_hf_apply_noise_2(float (*Y)[2], const float *s_m,
 +;                      const float *q_filt, int noise,
 +;                      int kx, int m_max)
 +cglobal sbr_hf_apply_noise_2, 5,5+NREGS+UNIX64,8, Y,s_m,q_filt,noise,kx,m_max
 +    mova       m0, [ps_noise2]
 +    jmp apply_noise_main
 +
 +; sbr_hf_apply_noise_3(float (*Y)[2], const float *s_m,
 +;                      const float *q_filt, int noise,
 +;                      int kx, int m_max)
 +cglobal sbr_hf_apply_noise_3, 5,5+NREGS+UNIX64,8, Y,s_m,q_filt,noise,kx,m_max
 +    and       kxq, 1
 +    shl       kxq, 4
 +    LOAD_NST  ps_noise13+16
 +
 +apply_noise_main:
 +%if ARCH_X86_64 == 0 || WIN64
 +    mov       kxd, m_maxm
 +%define count kxq
 +%else
 +%define count m_maxq
 +%endif
 +    dec    noiseq
 +    shl    count, 2
 +%if NREGS
 +    lea NOISE_TABLE, [sbr_noise_table]
 +%endif
 +    lea        Yq, [Yq + 2*count]
 +    add      s_mq, count
 +    add   q_filtq, count
 +    shl    noiseq, 3
 +    pxor       m5, m5
 +    neg    count
 +.loop:
 +    mova       m1, [q_filtq + count]
 +    movu       m3, [noiseq + NOISE_TABLE + 1*mmsize]
 +    movu       m4, [noiseq + NOISE_TABLE + 2*mmsize]
 +    add    noiseq, 2*mmsize
 +    and    noiseq, 0x1ff<<3
 +    punpckhdq  m2, m1, m1
 +    punpckldq  m1, m1
 +    mulps      m1, m3 ; m2 = q_filt[m] * ff_sbr_noise_table[noise]
 +    mulps      m2, m4 ; m2 = q_filt[m] * ff_sbr_noise_table[noise]
 +    mova       m3, [s_mq + count]
 +    ; TODO: replace by a vpermd in AVX2
 +    punpckhdq  m4, m3, m3
 +    punpckldq  m3, m3
 +    pcmpeqd    m6, m3, m5 ; m6 == 0
 +    pcmpeqd    m7, m4, m5 ; m7 == 0
 +    mulps      m3, m0 ; s_m[m] * phi_sign
 +    mulps      m4, m0 ; s_m[m] * phi_sign
 +    pand       m1, m6
 +    pand       m2, m7
 +    movu       m6, [Yq + 2*count]
 +    movu       m7, [Yq + 2*count + mmsize]
 +    addps      m3, m1
 +    addps      m4, m2
 +    addps      m6, m3
 +    addps      m7, m4
 +    movu    [Yq + 2*count], m6
 +    movu    [Yq + 2*count + mmsize], m7
 +    add    count, mmsize
 +    jl      .loop
 +    RET
 +
 +%endif ; WIN64 == 0