diff options
| author | Eric Anholt <[email protected]> | 2013-03-06 17:50:50 -0800 |
|---|---|---|
| committer | Eric Anholt <[email protected]> | 2013-03-11 12:11:53 -0700 |
| commit | 4dc7e6dcbf0d9c360e257c704774c9b083511b47 (patch) | |
| tree | 9b1542fe6d69e350f53e58550c59c4c10d488d7b /src | |
| parent | 4c1fdae0a01b3f92ec03b61aac1d3df500d51fc6 (diff) | |
i965/fs: Also do the gen4 SEND dependency workaround against other SENDs.
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 <[email protected]>
Diffstat (limited to 'src')
| -rw-r--r-- | src/mesa/drivers/dri/i965/brw_fs.cpp | 24 |
1 files changed, 15 insertions, 9 deletions
diff --git a/src/mesa/drivers/dri/i965/brw_fs.cpp b/src/mesa/drivers/dri/i965/brw_fs.cpp index 5380abfe2f4..8ce39543002 100644 --- a/src/mesa/drivers/dri/i965/brw_fs.cpp +++ b/src/mesa/drivers/dri/i965/brw_fs.cpp @@ -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). */ |