basic type mechanism working

1 files changed, 207 insertions, 4 deletions

diff --git a/ffmpeg/libavcodec/x86/sbrdsp.asm b/ffmpeg/libavcodec/x86/sbrdsp.asm
index 1b7f3a8..adc13c4 100644
--- a/ffmpeg/libavcodec/x86/sbrdsp.asm
+++ b/ffmpeg/libavcodec/x86/sbrdsp.asm
@@ -2,20 +2,20 @@
 ;* AAC Spectral Band Replication decoding functions
 ;* Copyright (C) 2012 Christophe Gisquet <christophe.gisquet@gmail.com>
 ;*
-;* This file is part of Libav.
+;* This file is part of FFmpeg.
 ;*
-;* Libav is free software; you can redistribute it and/or
+;* FFmpeg is free software; you can redistribute it and/or
 ;* modify it under the terms of the GNU Lesser General Public
 ;* License as published by the Free Software Foundation; either
 ;* version 2.1 of the License, or (at your option) any later version.
 ;*
-;* Libav is distributed in the hope that it will be useful,
+;* FFmpeg is distributed in the hope that it will be useful,
 ;* but WITHOUT ANY WARRANTY; without even the implied warranty of
 ;* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 ;* Lesser General Public License for more details.
 ;*
 ;* You should have received a copy of the GNU Lesser General Public
-;* License along with Libav; if not, write to the Free Software
+;* License along with FFmpeg; if not, write to the Free Software
 ;* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
 ;******************************************************************************
 
@@ -24,7 +24,14 @@
 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
+ps_noise0       times 2 dd  1.0,  0.0,
+ps_noise2       times 2 dd -1.0,  0.0
+ps_noise13      dd  0.0,  1.0, 0.0, -1.0
+                dd  0.0, -1.0, 0.0,  1.0
+                dd  0.0,  1.0, 0.0, -1.0
+cextern         sbr_noise_table
 
 SECTION_TEXT
 
@@ -220,3 +227,199 @@ 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
+
+; 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]
+.loop:
+    mova              m0, [src0q+cq]
+    mova              m1, [src1q]
+    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
+%else
+    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
+    mova  [vrevq+mmsize], m5
+    mova         [vq+cq], m0
+    mova  [vq+cq+mmsize], m4
+    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, 1,4,6,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
+
+%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
+
+%macro LOAD_NST  1
+%ifdef PIC
+    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
+%ifdef PIC
+    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