Re: [PATCH 0/7] MR724: vkd3d-shader/hlsl: Improve SM1 support for non-float operations, part 4.

[Giovanni Mascellani (＠giomasce)]

Giovanni Mascellani (@giomasce) commented about libs/vkd3d-shader/d3dbc.c:
>          }
>          break;
>
> -
>    case HLSL_OP2_LOGIC_AND:
> -
>        write_sm1_binary_op(ctx, buffer, D3DSIO_MUL, &instr->reg, &arg1->reg, &arg2->reg);

As far as I can see, native prefers to generate some kind on MIN. I suppose that a comparison should be faster to perform than a multiplication on the GPU.