KonstantinSeurer
/
mesa
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

intel/fs: Emit MOV_DISPATCH_TO_FLAGS once for the centroid workaround 

There's no reason for us to emit it a pile of times and then have a
whole pass to clean it up.  Just emit it once like we really want.

Reviewed-by: Matt Turner <mattst88@gmail.com>
This commit is contained in:
Jason Ekstrand 2018-05-23 17:54:54 -07:00
parent 40fe108e2b
commit 5e3028d826
2 changed files with 16 additions and 50 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

39
src/intel/compiler/brw_fs.cpp
View File

@ -6211,44 +6211,6 @@ fs_visitor::calculate_register_pressure()
}
}
/**
* Look for repeated FS_OPCODE_MOV_DISPATCH_TO_FLAGS and drop the later ones.
*
* The needs_unlit_centroid_workaround ends up producing one of these per
* channel of centroid input, so it's good to clean them up.
*
* An assumption here is that nothing ever modifies the dispatched pixels
* value that FS_OPCODE_MOV_DISPATCH_TO_FLAGS reads from, but the hardware
* dictates that anyway.
*/
bool
fs_visitor::opt_drop_redundant_mov_to_flags()
{
bool flag_mov_found[4] = {false};
bool progress = false;
/* Instructions removed by this pass can only be added if this were true */
if (!devinfo->needs_unlit_centroid_workaround)
return false;
foreach_block_and_inst_safe(block, fs_inst, inst, cfg) {
if (inst->is_control_flow()) {
memset(flag_mov_found, 0, sizeof(flag_mov_found));
} else if (inst->opcode == FS_OPCODE_MOV_DISPATCH_TO_FLAGS) {
if (!flag_mov_found[inst->flag_subreg]) {
flag_mov_found[inst->flag_subreg] = true;
} else {
inst->remove(block);
progress = true;
}
} else if (inst->flags_written()) {
flag_mov_found[inst->flag_subreg] = false;
}
}
return progress;
}
void
fs_visitor::optimize()
{
@ -6306,7 +6268,6 @@ fs_visitor::optimize()
int iteration = 0;
int pass_num = 0;
OPT(opt_drop_redundant_mov_to_flags);
OPT(remove_extra_rounding_modes);
do {

27
src/intel/compiler/brw_fs_visitor.cpp
View File

@ -263,24 +263,29 @@ fs_visitor::emit_interpolation_setup_gen6()
abld.emit(SHADER_OPCODE_RCP, this->wpos_w, this->pixel_w);
struct brw_wm_prog_data *wm_prog_data = brw_wm_prog_data(prog_data);
uint32_t centroid_modes = wm_prog_data->barycentric_interp_modes &
(1 << BRW_BARYCENTRIC_PERSPECTIVE_CENTROID |
1 << BRW_BARYCENTRIC_NONPERSPECTIVE_CENTROID);
for (int i = 0; i < BRW_BARYCENTRIC_MODE_COUNT; ++i) {
this->delta_xy[i] = fetch_payload_reg(
bld, payload.barycentric_coord_reg[i], BRW_REGISTER_TYPE_F, 2);
}
uint32_t centroid_modes = wm_prog_data->barycentric_interp_modes &
(1 << BRW_BARYCENTRIC_PERSPECTIVE_CENTROID |
1 << BRW_BARYCENTRIC_NONPERSPECTIVE_CENTROID);
if (devinfo->needs_unlit_centroid_workaround && centroid_modes) {
/* Get the pixel/sample mask into f0 so that we know which
* pixels are lit. Then, for each channel that is unlit,
* replace the centroid data with non-centroid data.
*/
bld.emit(FS_OPCODE_MOV_DISPATCH_TO_FLAGS);
for (int i = 0; i < BRW_BARYCENTRIC_MODE_COUNT; ++i) {
if (!(centroid_modes & (1 << i)))
continue;
if (devinfo->needs_unlit_centroid_workaround &&
(centroid_modes & (1 << i))) {
const fs_reg &pixel_delta_xy = delta_xy[i - 1];
/* Get the pixel/sample mask into f0 so that we know which
* pixels are lit. Then, for each channel that is unlit,
* replace the centroid data with non-centroid data.
*/
bld.emit(FS_OPCODE_MOV_DISPATCH_TO_FLAGS);
for (unsigned q = 0; q < dispatch_width / 8; q++) {
for (unsigned c = 0; c < 2; c++) {
const unsigned idx = c + (q & 2) + (q & 1) * dispatch_width / 8;