yading@10: ;******************************************************************************
yading@10: ;* V210 SIMD unpack
yading@10: ;* Copyright (c) 2011 Loren Merritt <lorenm@u.washington.edu>
yading@10: ;* Copyright (c) 2011 Kieran Kunhya <kieran@kunhya.com>
yading@10: ;*
yading@10: ;* This file is part of Libav.
yading@10: ;*
yading@10: ;* Libav is free software; you can redistribute it and/or
yading@10: ;* modify it under the terms of the GNU Lesser General Public
yading@10: ;* License as published by the Free Software Foundation; either
yading@10: ;* version 2.1 of the License, or (at your option) any later version.
yading@10: ;*
yading@10: ;* Libav is distributed in the hope that it will be useful,
yading@10: ;* but WITHOUT ANY WARRANTY; without even the implied warranty of
yading@10: ;* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
yading@10: ;* Lesser General Public License for more details.
yading@10: ;*
yading@10: ;* You should have received a copy of the GNU Lesser General Public
yading@10: ;* License along with Libav; if not, write to the Free Software
yading@10: ;* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
yading@10: ;******************************************************************************
yading@10: 
yading@10: %include "libavutil/x86/x86util.asm"
yading@10: 
yading@10: SECTION_RODATA
yading@10: 
yading@10: v210_mask: times 4 dd 0x3ff
yading@10: v210_mult: dw 64,4,64,4,64,4,64,4
yading@10: v210_luma_shuf: db 8,9,0,1,2,3,12,13,4,5,6,7,-1,-1,-1,-1
yading@10: v210_chroma_shuf: db 0,1,8,9,6,7,-1,-1,2,3,4,5,12,13,-1,-1
yading@10: 
yading@10: SECTION .text
yading@10: 
yading@10: %macro v210_planar_unpack 2
yading@10: 
yading@10: ; v210_planar_unpack(const uint32_t *src, uint16_t *y, uint16_t *u, uint16_t *v, int width)
yading@10: cglobal v210_planar_unpack_%1_%2, 5, 5, 7
yading@10:     movsxdifnidn r4, r4d
yading@10:     lea    r1, [r1+2*r4]
yading@10:     add    r2, r4
yading@10:     add    r3, r4
yading@10:     neg    r4
yading@10: 
yading@10:     mova   m3, [v210_mult]
yading@10:     mova   m4, [v210_mask]
yading@10:     mova   m5, [v210_luma_shuf]
yading@10:     mova   m6, [v210_chroma_shuf]
yading@10: .loop
yading@10: %ifidn %1, unaligned
yading@10:     movu   m0, [r0]
yading@10: %else
yading@10:     mova   m0, [r0]
yading@10: %endif
yading@10: 
yading@10:     pmullw m1, m0, m3
yading@10:     psrld  m0, 10
yading@10:     psrlw  m1, 6  ; u0 v0 y1 y2 v1 u2 y4 y5
yading@10:     pand   m0, m4 ; y0 __ u1 __ y3 __ v2 __
yading@10: 
yading@10:     shufps m2, m1, m0, 0x8d ; y1 y2 y4 y5 y0 __ y3 __
yading@10:     pshufb m2, m5 ; y0 y1 y2 y3 y4 y5 __ __
yading@10:     movu   [r1+2*r4], m2
yading@10: 
yading@10:     shufps m1, m0, 0xd8 ; u0 v0 v1 u2 u1 __ v2 __
yading@10:     pshufb m1, m6 ; u0 u1 u2 __ v0 v1 v2 __
yading@10:     movq   [r2+r4], m1
yading@10:     movhps [r3+r4], m1
yading@10: 
yading@10:     add r0, mmsize
yading@10:     add r4, 6
yading@10:     jl  .loop
yading@10: 
yading@10:     REP_RET
yading@10: %endmacro
yading@10: 
yading@10: INIT_XMM
yading@10: v210_planar_unpack unaligned, ssse3
yading@10: %if HAVE_AVX_EXTERNAL
yading@10: INIT_AVX
yading@10: v210_planar_unpack unaligned, avx
yading@10: %endif
yading@10: 
yading@10: INIT_XMM
yading@10: v210_planar_unpack aligned, ssse3
yading@10: %if HAVE_AVX_EXTERNAL
yading@10: INIT_AVX
yading@10: v210_planar_unpack aligned, avx
yading@10: %endif