Take into account the cost of local intervals when selecting split candidate.

When selecting a split candidate for region splitting, the register allocator tries to predict which candidate will have the cheapest spill cost.
Global splitting may cause the creation of local intervals, and they might spill.

This patch makes RA take into account the spill cost of local split intervals in use blocks (we already take into account the spill cost in through blocks).
A flag ("-condsider-local-interval-cost") controls weather we do this advanced cost calculation (it's on by default for X86 target, off for the rest).

Differential Revision: https://reviews.llvm.org/D41585

Change-Id: Icccb8ad2dbf13124f5d97a18c67d95aa6be0d14d
llvm-svn: 323870

1 files changed, 16 insertions, 0 deletions

diff --git a/llvm/lib/CodeGen/LiveRegMatrix.cpp b/llvm/lib/CodeGen/LiveRegMatrix.cpp
index bd435968296..d8faf75466c 100644
--- a/llvm/lib/CodeGen/LiveRegMatrix.cpp
+++ b/llvm/lib/CodeGen/LiveRegMatrix.cpp
@@ -205,3 +205,19 @@ LiveRegMatrix::checkInterference(LiveInterval &VirtReg, unsigned PhysReg) {
 
   return IK_Free;
 }
+
+bool LiveRegMatrix::checkInterference(SlotIndex Start, SlotIndex End,
+                                      unsigned PhysReg) {
+  // Construct artificial live range containing only one segment [Start, End).
+  VNInfo valno(0, Start);
+  LiveRange::Segment Seg(Start, End, &valno);
+  LiveRange LR;
+  LR.addSegment(Seg);
+
+  // Check for interference with that segment
+  for (MCRegUnitIterator Units(PhysReg, TRI); Units.isValid(); ++Units) {
+    if (query(LR, *Units).checkInterference())
+      return true;
+  }
+  return false;
+}