aboutsummaryrefslogtreecommitdiffstats
path: root/src/mesa/drivers/dri/i965/brw_fs_reg_allocate.cpp
diff options
context:
space:
mode:
authorEric Anholt <[email protected]>2013-11-06 17:38:23 -0800
committerEric Anholt <[email protected]>2013-11-12 15:06:28 -0800
commite9daead784921e453906853a4a78a2f3135af2e0 (patch)
tree889cfdb316b7d80ea88bd56a1cdc3b721c172d02 /src/mesa/drivers/dri/i965/brw_fs_reg_allocate.cpp
parentfbd8303a943d0d491b7c2415eb237a0731c7dec5 (diff)
i965/fs: Try a different pre-scheduling heuristic if the first spills.
Since LIFO fails on some shaders in one particular way, and non-LIFO systematically fails in another way on different kinds of shaders, try them both, and pick whichever one successfully register allocates first. Slightly prefer non-LIFO in case we produce extra dependencies in register allocation, since it should start out with fewer stalls than LIFO. This is madness, but I haven't come up with another way to get unigine tropics to not spill while keeping other programs from not spilling and retaining the non-unigine performance wins from texture-grf. total instructions in shared programs: 1626728 -> 1626288 (-0.03%) instructions in affected programs: 1015 -> 575 (-43.35%) GAINED: 50 LOST: 0 Improves Unigine Tropics performance by 14.5257% +/- 0.241838% (n=38) Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=70445 Cc: "10.0" <[email protected]> Reviewed-by: Matt Turner <[email protected]>
Diffstat (limited to 'src/mesa/drivers/dri/i965/brw_fs_reg_allocate.cpp')
-rw-r--r--src/mesa/drivers/dri/i965/brw_fs_reg_allocate.cpp10
1 files changed, 3 insertions, 7 deletions
diff --git a/src/mesa/drivers/dri/i965/brw_fs_reg_allocate.cpp b/src/mesa/drivers/dri/i965/brw_fs_reg_allocate.cpp
index d9e80d07f48..8567afd3c16 100644
--- a/src/mesa/drivers/dri/i965/brw_fs_reg_allocate.cpp
+++ b/src/mesa/drivers/dri/i965/brw_fs_reg_allocate.cpp
@@ -417,7 +417,7 @@ fs_visitor::setup_mrf_hack_interference(struct ra_graph *g, int first_mrf_node)
}
bool
-fs_visitor::assign_regs()
+fs_visitor::assign_regs(bool allow_spilling)
{
/* Most of this allocation was written for a reg_width of 1
* (dispatch_width == 8). In extending to 16-wide, the code was
@@ -496,14 +496,10 @@ fs_visitor::assign_regs()
if (reg == -1) {
fail("no register to spill:\n");
dump_instructions();
- } else if (dispatch_width == 16) {
- fail("Failure to register allocate. Reduce number of live scalar "
- "values to avoid this.");
- } else {
- spill_reg(reg);
+ } else if (allow_spilling) {
+ spill_reg(reg);
}
-
ralloc_free(g);
return false;