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

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

diff --git a/lib/CodeGen/RegAllocGreedy.cpp b/lib/CodeGen/RegAllocGreedy.cpp
index 19a9e3182e71269a9dbfd9d35910001922fd560d..6e6a594479e8b1e0812e944c030c3a8f0defbee1 100644 (file)
--- a/lib/CodeGen/RegAllocGreedy.cpp
+++ b/lib/CodeGen/RegAllocGreedy.cpp
@@ -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

diff --git a/test/CodeGen/X86/misched-matmul.ll b/test/CodeGen/X86/misched-matmul.ll
index 5454b7cf780a14193187915cfd22006cd60cc67a..3ea6512258d414db8bb9f25310e8ea7d6fd5be0f 100644 (file)
--- a/test/CodeGen/X86/misched-matmul.ll
+++ b/test/CodeGen/X86/misched-matmul.ll
@@ -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: