fdo-mirrors/mesa
1
0
Fork 0
mirror of https://gitlab.freedesktop.org/mesa/mesa.git synced 2026-01-01 22:40:09 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions 4

i965/fs: Also do the gen4 SEND dependency workaround against other SENDs.

Browse source 
We were handling the the dependency workaround for the first written reg
of a send preceding the one we're fixing up, but didn't consider the other
regs.  Thus if you had two sampler calls that got allocated to the same
set of regs, one might, rarely, ovewrite the other.  This was occurring in
XBMC's GLSL shaders.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=44567
NOTE: This is a candidate for the stable branches.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
This commit is contained in:
Eric Anholt 2013-03-06 17:50:50 -08:00
parent 4c1fdae0a0
commit 4dc7e6dcbf
1 changed files with 15 additions and 9 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

24
src/mesa/drivers/dri/i965/brw_fs.cpp
View file

@ -2300,7 +2300,8 @@ clear_deps_for_inst_src(fs_inst *inst, int dispatch_width, bool *deps,
void
fs_visitor::insert_gen4_pre_send_dependency_workarounds(fs_inst *inst)
{
int write_len = inst->regs_written() * dispatch_width / 8;
int reg_size = dispatch_width / 8;
int write_len = inst->regs_written() * reg_size;
int first_write_grf = inst->dst.reg;
bool needs_dep[BRW_MAX_MRF];
assert(write_len < (int)sizeof(needs_dep) - 1);
@ -2339,14 +2340,19 @@ fs_visitor::insert_gen4_pre_send_dependency_workarounds(fs_inst *inst)
* instruction but a MOV that might have left us an outstanding
* dependency has more latency than a MOV.
*/
if (scan_inst->dst.file == GRF &&
scan_inst->dst.reg >= first_write_grf &&
scan_inst->dst.reg < first_write_grf + write_len &&
needs_dep[scan_inst->dst.reg - first_write_grf]) {
inst->insert_before(DEP_RESOLVE_MOV(scan_inst->dst.reg));
needs_dep[scan_inst->dst.reg - first_write_grf] = false;
if (scan_inst_16wide)
needs_dep[scan_inst->dst.reg - first_write_grf + 1] = false;
if (scan_inst->dst.file == GRF) {
for (int i = 0; i < scan_inst->regs_written(); i++) {
int reg = scan_inst->dst.reg + i * reg_size;
if (reg >= first_write_grf &&
reg < first_write_grf + write_len &&
needs_dep[reg - first_write_grf]) {
inst->insert_before(DEP_RESOLVE_MOV(reg));
needs_dep[reg - first_write_grf] = false;
if (scan_inst_16wide)
needs_dep[reg - first_write_grf + 1] = false;
}
}
}
/* Clear the flag for registers that actually got read (as expected). */