summaryrefslogtreecommitdiffstats
path: root/src/gallium
diff options
context:
space:
mode:
authorIlia Mirkin <[email protected]>2015-12-06 23:25:54 -0500
committerIlia Mirkin <[email protected]>2015-12-08 23:15:29 -0500
commit99581ca393037e10d17aab1f4c90ff2bdb1ec557 (patch)
tree6dfd71adaeb4ae8c5e9d24263213a54efb184a24 /src/gallium
parent0f647bd65bae16c7a2dc7a960c96593ad6ab729c (diff)
nv50/ir: only unspill once ahead of a group of instructions
We already semi-did this but the list of uses as unsorted, so it was unreliable. Sort the uses by bb and serial, and don't unspill for each instruction in a sequence. (And also don't unspill multiple times for a single instruction that uses the value in question multiple times.) This causes a minor reduction in generated instructions for shader-db (as few programs spill) but more importantly it brings determinism to each run's output. On SM10: total instructions in shared programs : 6387945 -> 6379359 (-0.13%) total gprs used in shared programs : 728544 -> 728544 (0.00%) total local used in shared programs : 9904 -> 9904 (0.00%) local gpr inst bytes helped 0 0 322 322 hurt 0 0 0 0 Signed-off-by: Ilia Mirkin <[email protected]>
Diffstat (limited to 'src/gallium')
-rw-r--r--src/gallium/drivers/nouveau/codegen/nv50_ir_ra.cpp25
1 files changed, 20 insertions, 5 deletions
diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_ra.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_ra.cpp
index 143fd5107f2..f5143bf3137 100644
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_ra.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_ra.cpp
@@ -23,6 +23,7 @@
#include "codegen/nv50_ir.h"
#include "codegen/nv50_ir_target.h"
+#include <algorithm>
#include <stack>
#include <limits>
#if __cplusplus >= 201103L
@@ -1649,6 +1650,13 @@ SpillCodeInserter::unspill(Instruction *usei, LValue *lval, Value *slot)
return lval;
}
+static bool
+value_cmp(ValueRef *a, ValueRef *b) {
+ Instruction *ai = a->getInsn(), *bi = b->getInsn();
+ if (ai->bb != bi->bb)
+ return ai->bb->getId() < bi->bb->getId();
+ return ai->serial < bi->serial;
+}
// For each value that is to be spilled, go through all its definitions.
// A value can have multiple definitions if it has been coalesced before.
@@ -1682,18 +1690,25 @@ SpillCodeInserter::run(const std::list<ValuePair>& lst)
LValue *dval = (*d)->get()->asLValue();
Instruction *defi = (*d)->getInsn();
+ // Sort all the uses by BB/instruction so that we don't unspill
+ // multiple times in a row, and also remove a source of
+ // non-determinism.
+ std::vector<ValueRef *> refs(dval->uses.begin(), dval->uses.end());
+ std::sort(refs.begin(), refs.end(), value_cmp);
+
// Unspill at each use *before* inserting spill instructions,
// we don't want to have the spill instructions in the use list here.
- while (!dval->uses.empty()) {
- ValueRef *u = *dval->uses.begin();
+ for (std::vector<ValueRef*>::const_iterator it = refs.begin();
+ it != refs.end(); ++it) {
+ ValueRef *u = *it;
Instruction *usei = u->getInsn();
assert(usei);
if (usei->isPseudo()) {
tmp = (slot->reg.file == FILE_MEMORY_LOCAL) ? NULL : slot;
last = NULL;
- } else
- if (!last || usei != last->next) { // TODO: sort uses
- tmp = unspill(usei, dval, slot);
+ } else {
+ if (!last || (usei != last->next && usei != last))
+ tmp = unspill(usei, dval, slot);
last = usei;
}
u->set(tmp);