6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2025-02-08 21:32:39 +00:00
Code Issues Projects Releases Wiki Activity

Add a limit to the heuristic that register allocates instructions in local order.

Browse Source 
This handles pathological cases in which we see 2x increase in spill
code for large blocks (~50k instructions). I don't have a unit test
for this behavior.

Fixes rdar://16072279.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@202304 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Andrew Trick 2014-02-26 22:07:26 +00:00
parent 692c94c1c9
commit eaf8a32859
2 changed files with 9 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
lib/CodeGen/RegAllocGreedy.cpp
View File

@ -454,12 +454,18 @@ void RAGreedy::enqueue(PQueue &CurQueue, LiveInterval *LI) {
// everything else has been allocated.
Prio = Size;
} else {
if (ExtraRegInfo[Reg].Stage == RS_Assign && !LI->empty() &&
// Giant live ranges fall back to the global assignment heuristic, which
// prevents excessive spilling in pathological cases.
bool ReverseLocal = TRI->reverseLocalAssignment();
bool ForceGlobal = !ReverseLocal &&
(Size / SlotIndex::InstrDist) > (2 * MRI->getRegClass(Reg)->getNumRegs());
if (ExtraRegInfo[Reg].Stage == RS_Assign && !ForceGlobal && !LI->empty() &&
LIS->intervalIsInOneMBB(*LI)) {
// Allocate original local ranges in linear instruction order. Since they
// are singly defined, this produces optimal coloring in the absence of
// global interference and other constraints.
if (!TRI->reverseLocalAssignment())
if (!ReverseLocal)
Prio = LI->beginIndex().getInstrDistance(Indexes->getLastIndex());
else {
// Allocating bottom up may allow many short LRGs to be assigned first

2
test/CodeGen/X86/misched-matmul.ll
View File

@ -10,7 +10,7 @@
; more complex cases.
;
; CHECK: @wrap_mul4
; CHECK: 23 regalloc - Number of spills inserted
; CHECK: 22 regalloc - Number of spills inserted
define void @wrap_mul4(double* nocapture %Out, [4 x double]* nocapture %A, [4 x double]* nocapture %B) #0 {
entry: