comparison h264.c @ 4040:9eaea06c5ba6 libavcodec

optimize sign decoding code in decode_residual() x86 is 4% faster on P3 C sign stuff + x86 code for everything else is also faster then before (sorry forgot to test pure C) ... and if i replace the second occurance of the sign decoding in decode_residual by the asm too then everything gets slower iam starting to think that it might be best to write the whole function in asm, playing this avoid random deoptimizations game with gcc is not fun at all

4039:866a83726985

        uint8_t *ctx = (abslevelgt1 != 0 ? 0 : FFMIN( 4, abslevel1 )) + abs_level_m1_ctx_base;
        int j= scantable[index[i]];

        if( get_cabac( CC, ctx ) == 0 ) {
            if( !qmul ) {
                if( get_cabac_bypass( CC ) ) block[j] = -1;
                else                                block[j] =  1;
            }else{
                if( get_cabac_bypass( CC ) ) block[j] = (-qmul[j] + 32) >> 6;
                else                                block[j] = ( qmul[j] + 32) >> 6;
            }

            abslevel1++;
        } else {
            int coeff_abs = 2;

4040:9eaea06c5ba6

        uint8_t *ctx = (abslevelgt1 != 0 ? 0 : FFMIN( 4, abslevel1 )) + abs_level_m1_ctx_base;
        int j= scantable[index[i]];

        if( get_cabac( CC, ctx ) == 0 ) {
            if( !qmul ) {
                block[j] = get_cabac_bypass_sign( CC, -1);
            }else{
                block[j] = (get_cabac_bypass_sign( CC, -qmul[j]) + 32) >> 6;;
            }

            abslevel1++;
        } else {
            int coeff_abs = 2;