commit 34974ed50349d6ab40e921475b50147718dc2d79
author Hal Finkel <hfinkel@anl.gov> Sat Apr 12 21:52:38 2014 +0000
committer Hal Finkel <hfinkel@anl.gov> Sat Apr 12 21:52:38 2014 +0000
tree e46f201b74d90184a5902a4b7b5a05779e5a9351
parent c1e13e2fe5971edeac6196e5d2163fadcc2dd5ef

[PowerPC] Implement some additional TLI callbacks

Add implementations of:
  bool isLegalICmpImmediate(int64_t Imm) const
  bool isLegalAddImmediate(int64_t Imm) const
  bool isTruncateFree(Type *Ty1, Type *Ty2) const
  bool isTruncateFree(EVT VT1, EVT VT2) const
  bool shouldConvertConstantLoadToIntImm(const APInt &Imm, Type *Ty) const

Unfortunately, this regresses counter-register-based loop formation because
some of the loops now end up in forms were SE cannot compute loop counts.
However, nevertheless, the test-suite results favor committing:

SingleSource/Benchmarks/BenchmarkGame/puzzle: 26% speedup
MultiSource/Benchmarks/FreeBench/analyzer/analyzer: 21% speedup
MultiSource/Benchmarks/MiBench/automotive-susan/automotive-susan: 20% speedup
SingleSource/Benchmarks/Polybench/linear-algebra/kernels/trisolv/trisolv: 19% speedup
SingleSource/Benchmarks/Polybench/linear-algebra/kernels/gesummv/gesummv: 15% speedup
MultiSource/Benchmarks/FreeBench/pcompress2/pcompress2: 2% speedup

MultiSource/Benchmarks/VersaBench/bmm/bmm: 26% slowdown

llvm-svn: 206120

llvm/lib/Target/PowerPC/PPCISelLowering.cpp

diff --git a/llvm/lib/Target/PowerPC/PPCISelLowering.cpp b/llvm/lib/Target/PowerPC/PPCISelLowering.cpp
index d1c0756..3be0f92 100644
--- a/llvm/lib/Target/PowerPC/PPCISelLowering.cpp
+++ b/llvm/lib/Target/PowerPC/PPCISelLowering.cpp
@@ -8795,6 +8795,42 @@
   }
 }
 
+/// \brief Returns true if it is beneficial to convert a load of a constant
+/// to just the constant itself.
+bool PPCTargetLowering::shouldConvertConstantLoadToIntImm(const APInt &Imm,
+                                                          Type *Ty) const {
+  assert(Ty->isIntegerTy());
+
+  unsigned BitSize = Ty->getPrimitiveSizeInBits();
+  if (BitSize == 0 || BitSize > 64)
+    return false;
+  return true;
+}
+
+bool PPCTargetLowering::isTruncateFree(Type *Ty1, Type *Ty2) const {
+  if (!Ty1->isIntegerTy() || !Ty2->isIntegerTy())
+    return false;
+  unsigned NumBits1 = Ty1->getPrimitiveSizeInBits();
+  unsigned NumBits2 = Ty2->getPrimitiveSizeInBits();
+  return NumBits1 == 64 && NumBits2 == 32;
+}
+
+bool PPCTargetLowering::isTruncateFree(EVT VT1, EVT VT2) const {
+  if (!VT1.isInteger() || !VT2.isInteger())
+    return false;
+  unsigned NumBits1 = VT1.getSizeInBits();
+  unsigned NumBits2 = VT2.getSizeInBits();
+  return NumBits1 == 64 && NumBits2 == 32;
+}
+
+bool PPCTargetLowering::isLegalICmpImmediate(int64_t Imm) const {
+  return isInt<16>(Imm) || isUInt<16>(Imm);
+}
+
+bool PPCTargetLowering::isLegalAddImmediate(int64_t Imm) const {
+  return isInt<16>(Imm) || isUInt<16>(Imm);
+}
+
 bool PPCTargetLowering::allowsUnalignedMemoryAccesses(EVT VT,
                                                       unsigned,
                                                       bool *Fast) const {