Some enhancements for memcpy / memset inline expansion.

1. Teach it to use overlapping unaligned load / store to copy / set the trailing
   bytes. e.g. On 86, use two pairs of movups / movaps for 17 - 31 byte copies.
2. Use f64 for memcpy / memset on targets where i64 is not legal but f64 is. e.g.
   x86 and ARM.
3. When memcpy from a constant string, do *not* replace the load with a constant
   if it's not possible to materialize an integer immediate with a single
   instruction (required a new target hook: TLI.isIntImmLegal()).
4. Use unaligned load / stores more aggressively if target hooks indicates they
   are "fast".
5. Update ARM target hooks to use unaligned load / stores. e.g. vld1.8 / vst1.8.
   Also increase the threshold to something reasonable (8 for memset, 4 pairs
   for memcpy).

This significantly improves Dhrystone, up to 50% on ARM iOS devices.

rdar://12760078


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@169791 91177308-0d34-0410-b5e6-96231b3b80d8

1 files changed, 4 insertions, 1 deletions

diff --git a/lib/Target/Mips/MipsISelLowering.cpp b/lib/Target/Mips/MipsISelLowering.cpp
index 703f8cec22..619ae077b3 100644
--- a/lib/Target/Mips/MipsISelLowering.cpp
+++ b/lib/Target/Mips/MipsISelLowering.cpp
@@ -457,7 +457,8 @@ MipsTargetLowering(MipsTargetMachine &TM)
   maxStoresPerMemcpy = 16;
 }
 
-bool MipsTargetLowering::allowsUnalignedMemoryAccesses(EVT VT) const {
+bool
+MipsTargetLowering::allowsUnalignedMemoryAccesses(EVT VT, bool *Fast) const {
   MVT::SimpleValueType SVT = VT.getSimpleVT().SimpleTy;
 
   if (Subtarget->inMips16Mode())
@@ -466,6 +467,8 @@ bool MipsTargetLowering::allowsUnalignedMemoryAccesses(EVT VT) const {
   switch (SVT) {
   case MVT::i64:
   case MVT::i32:
+    if (Fast)
+      *Fast = true;
     return true;
   default:
     return false;