fdo-mirrors/mesa
1
0
Fork 0
mirror of https://gitlab.freedesktop.org/mesa/mesa.git synced 2026-05-08 15:38:09 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

i965/fs: Do CSE on gen7's varying-index pull constant loads.

Browse source 
This is our first CSE on a regs_written() > 1 instruction, so it takes a
bit of extra fixup.  Reduces the number of loads on kwin's Lanczos shader
from 12 to 2.

v2: Fix compiler warning (false positive on possibly-uninitialized variable)

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=61554
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org> (v1)
NOTE: This is a candidate for the 9.1 branch.
(cherry picked from commit 9f43b84928)
This commit is contained in:
Eric Anholt 2013-03-15 14:43:28 -07:00 • committed by Ian Romanick
parent f523c0fb21
commit 724269bb32
1 changed files with 32 additions and 9 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

41
src/mesa/drivers/dri/i965/brw_fs_cse.cpp
View file

@ -66,6 +66,7 @@ is_expression(const fs_inst *const inst)
case BRW_OPCODE_LINE:
case BRW_OPCODE_PLN:
case BRW_OPCODE_MAD:
case FS_OPCODE_VARYING_PULL_CONSTANT_LOAD_GEN7:
case FS_OPCODE_CINTERP:
case FS_OPCODE_LINTERP:
return true;
@ -126,19 +127,41 @@ fs_visitor::opt_cse_local(bblock_t *block, exec_list *aeb)
*/
bool no_existing_temp = entry->tmp.file == BAD_FILE;
if (no_existing_temp) {
entry->tmp = fs_reg(this, glsl_type::float_type);
entry->tmp.type = inst->dst.type;
int written = entry->generator->regs_written();
fs_inst *copy = new(ralloc_parent(inst))
fs_inst(BRW_OPCODE_MOV, entry->generator->dst, entry->tmp);
entry->generator->insert_after(copy);
entry->generator->dst = entry->tmp;
fs_reg orig_dst = entry->generator->dst;
fs_reg tmp = fs_reg(GRF, virtual_grf_alloc(written),
orig_dst.type);
entry->tmp = tmp;
entry->generator->dst = tmp;
for (int i = 0; i < written; i++) {
fs_inst *copy = MOV(orig_dst, tmp);
copy->force_writemask_all =
entry->generator->force_writemask_all;
entry->generator->insert_after(copy);
orig_dst.reg_offset++;
tmp.reg_offset++;
}
}
/* dest <- temp */
fs_inst *copy = new(ralloc_parent(inst))
fs_inst(BRW_OPCODE_MOV, inst->dst, entry->tmp);
inst->replace_with(copy);
int written = inst->regs_written();
assert(written == entry->generator->regs_written());
assert(inst->dst.type == entry->tmp.type);
fs_reg dst = inst->dst;
fs_reg tmp = entry->tmp;
fs_inst *copy = NULL;
for (int i = 0; i < written; i++) {
copy = MOV(dst, tmp);
copy->force_writemask_all = inst->force_writemask_all;
inst->insert_before(copy);
dst.reg_offset++;
tmp.reg_offset++;
}
inst->remove();
/* Appending an instruction may have changed our bblock end. */
if (inst == block->end) {