[IPRA] Change algorithm for RegUsageInfoCollector.

The previous algorithm for RegUsageInfoCollector had pretty bad
performance on architectures with a lot of registers that alias
a lot one another, because we potentially iterate for every register
over all the aliasing registers. This costs even more if the function
is small and doesn't define a lot of registers.
This patch changes the algorithm to one that while iterating over
all the registers it will iterate over the aliasing registers only
if the register itself is defined.
This should be faster based on the assumption that only a subset
of the whole LLVM registers set is actually defined in the function.

Differential Revision: https://reviews.llvm.org/D30880

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@297673 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/CodeGen/RegUsageInfoCollector.cpp b/lib/CodeGen/RegUsageInfoCollector.cpp
index ece44c28e9ede2c4cdf35b3894bda5f8685818d4..855aa37ff3c36a4564052b0ef70a4afc59f5c22c 100644 (file)
--- a/lib/CodeGen/RegUsageInfoCollector.cpp
+++ b/lib/CodeGen/RegUsageInfoCollector.cpp
@@ -103,9 +103,27 @@ bool RegUsageInfoCollector::runOnMachineFunction(MachineFunction &MF) {
 
   DEBUG(dbgs() << "Clobbered Registers: ");
 
-  for (unsigned PReg = 1, PRegE = TRI->getNumRegs(); PReg < PRegE; ++PReg)
-    if (MRI->isPhysRegModified(PReg, true))
-      RegMask[PReg / 32] &= ~(1u << PReg % 32);
+  const BitVector &UsedPhysRegsMask = MRI->getUsedPhysRegsMask();
+  auto SetRegAsDefined = [&RegMask] (unsigned Reg) {
+    RegMask[Reg / 32] &= ~(1u << Reg % 32);
+  };
+  // Scan all the physical registers. When a register is defined in the current
+  // function set it and all the aliasing registers as defined in the regmask.
+  for (unsigned PReg = 1, PRegE = TRI->getNumRegs(); PReg < PRegE; ++PReg) {
+    // If a register is in the UsedPhysRegsMask set then mark it as defined.
+    // All it's aliases will also be in the set, so we can skip setting
+    // as defined all the aliases here.
+    if (UsedPhysRegsMask.test(PReg)) {
+      SetRegAsDefined(PReg);
+      continue;
+    }
+    // If a register is defined by an instruction mark it as defined together
+    // with all it's aliases.
+    if (!MRI->def_empty(PReg)) {
+      for (MCRegAliasIterator AI(PReg, TRI, true); AI.isValid(); ++AI)
+        SetRegAsDefined(*AI);
+    }
+  }
 
   if (!TargetFrameLowering::isSafeForNoCSROpt(F)) {
     const uint32_t *CallPreservedMask =