int glsl_version;
bool native_integers;
bool have_sqrt;
+ bool have_fma;
variable_storage *find_variable_storage(ir_variable *var);
case3fid(ADD, UADD, DADD);
case3fid(MUL, UMUL, DMUL);
case3fid(MAD, UMAD, DMAD);
+ case3fid(FMA, UMAD, DFMA);
case3(DIV, IDIV, UDIV);
case4d(MAX, IMAX, UMAX, DMAX);
case4d(MIN, IMIN, UMIN, DMIN);
emit(ir, TGSI_OPCODE_IMUL_HI, result_dst, op[0], op[1]);
break;
case ir_triop_fma:
- /* NOTE: Perhaps there should be a special opcode that enforces fused
- * mul-add. Just use MAD for now.
- */
- emit(ir, TGSI_OPCODE_MAD, result_dst, op[0], op[1], op[2]);
+ /* In theory, MAD is incorrect here. */
+ if (have_fma)
+ emit(ir, TGSI_OPCODE_FMA, result_dst, op[0], op[1], op[2]);
+ else
+ emit(ir, TGSI_OPCODE_MAD, result_dst, op[0], op[1], op[2]);
break;
case ir_unop_interpolate_at_centroid:
emit(ir, TGSI_OPCODE_INTERP_CENTROID, result_dst, op[0]);
v->have_sqrt = pscreen->get_shader_param(pscreen, ptarget,
PIPE_SHADER_CAP_TGSI_SQRT_SUPPORTED);
+ v->have_fma = pscreen->get_shader_param(pscreen, ptarget,
+ PIPE_SHADER_CAP_TGSI_FMA_SUPPORTED);
_mesa_copy_linked_program_data(shader->Stage, shader_program, prog);
_mesa_generate_parameters_list_for_uniforms(shader_program, shader,