[vectorizer] Add some flags which are useful for conducting experiments

with the unrolling behavior in the loop vectorizer. No functionality
changed at this point.

These are a bit hack-y, but talking with Hal, there doesn't seem to be
a cleaner way to easily experiment with different thresholds here and he
was also interested in them so I wanted to commit them. Suggestions for
improvement are very welcome here.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@200212 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Transforms/Vectorize/LoopVectorize.cpp b/lib/Transforms/Vectorize/LoopVectorize.cpp
index f904765f41e184d53af2bde8a3f369387591ac08..23dc8f39eea1f197586fd565e93dc6cdb86a58e8 100644 (file)
--- a/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -139,11 +139,30 @@ static const unsigned RuntimeMemoryCheckThreshold = 8;
 /// Maximum simd width.
 static const unsigned MaxVectorWidth = 64;
 
 /// Maximum simd width.
 static const unsigned MaxVectorWidth = 64;
 

+static cl::opt<unsigned> ForceTargetNumScalarRegs(
+    "force-target-num-scalar-regs", cl::init(0), cl::Hidden,
+    cl::desc("A flag that overrides the target's number of scalar registers."));
+
+static cl::opt<unsigned> ForceTargetNumVectorRegs(
+    "force-target-num-vector-regs", cl::init(0), cl::Hidden,
+    cl::desc("A flag that overrides the target's number of vector registers."));
+

 /// Maximum vectorization unroll count.
 static const unsigned MaxUnrollFactor = 16;
 
 /// Maximum vectorization unroll count.
 static const unsigned MaxUnrollFactor = 16;
 

-/// The cost of a loop that is considered 'small' by the unroller.
-static const unsigned SmallLoopCost = 20;
+static cl::opt<unsigned> ForceTargetMaxScalarUnrollFactor(
+    "force-target-max-scalar-unroll", cl::init(0), cl::Hidden,
+    cl::desc("A flag that overrides the target's max unroll factor for scalar "
+             "loops."));
+
+static cl::opt<unsigned> ForceTargetMaxVectorUnrollFactor(
+    "force-target-max-vector-unroll", cl::init(0), cl::Hidden,
+    cl::desc("A flag that overrides the target's max unroll factor for "
+             "vectorized loops."));
+
+static cl::opt<unsigned> SmallLoopCost(
+    "small-loop-cost", cl::init(20), cl::Hidden,
+    cl::desc("The cost of a loop that is considered 'small' by the unroller."));

 
 namespace {
 
 
 namespace {
 


@@ -4966,6 +4985,14 @@ LoopVectorizationCostModel::selectUnrollFactor(bool OptForSize,
   DEBUG(dbgs() << "LV: The target has " << TargetNumRegisters <<
         " registers\n");
 
   DEBUG(dbgs() << "LV: The target has " << TargetNumRegisters <<
         " registers\n");
 

+  if (VF == 1) {
+    if (ForceTargetNumScalarRegs.getNumOccurrences() > 0)
+      TargetNumRegisters = ForceTargetNumScalarRegs;
+  } else {
+    if (ForceTargetNumVectorRegs.getNumOccurrences() > 0)
+      TargetNumRegisters = ForceTargetNumVectorRegs;
+  }
+

   LoopVectorizationCostModel::RegisterUsage R = calculateRegisterUsage();
   // We divide by these constants so assume that we have at least one
   // instruction that uses at least one register.
   LoopVectorizationCostModel::RegisterUsage R = calculateRegisterUsage();
   // We divide by these constants so assume that we have at least one
   // instruction that uses at least one register.


@@ -4983,6 +5010,15 @@ LoopVectorizationCostModel::selectUnrollFactor(bool OptForSize,
   // Clamp the unroll factor ranges to reasonable factors.
   unsigned MaxUnrollSize = TTI.getMaximumUnrollFactor();
 
   // Clamp the unroll factor ranges to reasonable factors.
   unsigned MaxUnrollSize = TTI.getMaximumUnrollFactor();
 

+  // Check if the user has overridden the unroll max.
+  if (VF == 1) {
+    if (ForceTargetMaxScalarUnrollFactor.getNumOccurrences() > 0)
+      MaxUnrollSize = ForceTargetMaxScalarUnrollFactor;
+  } else {
+    if (ForceTargetMaxVectorUnrollFactor.getNumOccurrences() > 0)
+      MaxUnrollSize = ForceTargetMaxVectorUnrollFactor;
+  }
+

   // If we did not calculate the cost for VF (because the user selected the VF)
   // then we calculate the cost of VF here.
   if (LoopCost == 0)
   // If we did not calculate the cost for VF (because the user selected the VF)
   // then we calculate the cost of VF here.
   if (LoopCost == 0)