diff options
author | Marek Olšák <[email protected]> | 2015-02-28 00:26:31 +0100 |
---|---|---|
committer | Marek Olšák <[email protected]> | 2015-03-16 12:54:18 +0100 |
commit | 216543ea547dd0572d9f2f0364f7a239a5aeafe1 (patch) | |
tree | a7d6fb2160c1c736e0dcfb2d24790d6cb2ce315d /src/mesa/state_tracker | |
parent | e92bc6b38e90339a394e95a562bcce35c3ee9696 (diff) |
gallium: add FMA and DFMA opcodes (v3)
Needed by ARB_gpu_shader5.
v2: select DMAD for FMA with double precision
v3: add and select DFMA
Reviewed-by: Ilia Mirkin <[email protected]>
Diffstat (limited to 'src/mesa/state_tracker')
-rw-r--r-- | src/mesa/state_tracker/st_glsl_to_tgsi.cpp | 13 |
1 files changed, 9 insertions, 4 deletions
diff --git a/src/mesa/state_tracker/st_glsl_to_tgsi.cpp b/src/mesa/state_tracker/st_glsl_to_tgsi.cpp index bd191d864fe..efee4b258e5 100644 --- a/src/mesa/state_tracker/st_glsl_to_tgsi.cpp +++ b/src/mesa/state_tracker/st_glsl_to_tgsi.cpp @@ -332,6 +332,7 @@ public: int glsl_version; bool native_integers; bool have_sqrt; + bool have_fma; variable_storage *find_variable_storage(ir_variable *var); @@ -836,6 +837,7 @@ glsl_to_tgsi_visitor::get_opcode(ir_instruction *ir, unsigned op, 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); @@ -2222,10 +2224,11 @@ glsl_to_tgsi_visitor::visit(ir_expression *ir) 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]); @@ -5564,6 +5567,8 @@ get_mesa_program(struct gl_context *ctx, 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, |