On 1/31/2016 6:18 PM, James Almer wrote: > On 1/31/2016 4:48 PM, Timothy Gu wrote: >> +; ff_vc1_inv_trans_?x?_dc_mmxext(uint8_t *dest, int linesize, int16_t >> *block) >> +INIT_MMX mmxext >> +cglobal vc1_inv_trans_4x4_dc, 3,4,0, dest, linesize, block >> + movsx r3d, WORD [blockq] > > Can this value be negative? Because you're using it as an argument > for lea using native size after movsx sign extended the value to 32 > bits, which means that on x86_64 the upper bits of the register will > be zeroed. > > If it can you'll have to use blockq/r3q everywhere, and if it can't > then use movzx and shr.
Or not... Seems to work as is and using movzx breaks it. > >> + mov blockd, r3d ; dc >> + shl blockd, 4 ; 16 * dc >> + lea blockd, [blockq+r3+4] ; 17 * dc + 4 >> + sar blockd, 3 ; >> 3 >> + mov r3d, blockd ; dc >> + shl blockd, 4 ; 16 * dc >> + lea blockd, [blockq+r3+64] ; 17 * dc + 64 >> + sar blockd, 7 ; >> 7 > _______________________________________________ ffmpeg-devel mailing list ffmpeg-devel@ffmpeg.org http://ffmpeg.org/mailman/listinfo/ffmpeg-devel
