summaryrefslogtreecommitdiffstats
path: root/llvm/lib/Target
diff options
context:
space:
mode:
authorClement Courbet <courbet@google.com>2017-04-21 09:20:55 +0000
committerClement Courbet <courbet@google.com>2017-04-21 09:20:55 +0000
commitd5f6182bec48b40198742cb814816a396f8b831c (patch)
tree21c5349397d89efe5add82252836476345ade3c6 /llvm/lib/Target
parent203fc17797e2c56cd6715536bb6347864196a855 (diff)
downloadbcm5719-llvm-d5f6182bec48b40198742cb814816a396f8b831c.tar.gz
bcm5719-llvm-d5f6182bec48b40198742cb814816a396f8b831c.zip
use repmovsb when optimizing forminsize
llvm-svn: 300960
Diffstat (limited to 'llvm/lib/Target')
-rw-r--r--llvm/lib/Target/X86/X86SelectionDAGInfo.cpp39
1 files changed, 31 insertions, 8 deletions
diff --git a/llvm/lib/Target/X86/X86SelectionDAGInfo.cpp b/llvm/lib/Target/X86/X86SelectionDAGInfo.cpp
index f09040bfe88..1a72a0ba3a6 100644
--- a/llvm/lib/Target/X86/X86SelectionDAGInfo.cpp
+++ b/llvm/lib/Target/X86/X86SelectionDAGInfo.cpp
@@ -181,6 +181,24 @@ SDValue X86SelectionDAGInfo::EmitTargetCodeForMemset(
return Chain;
}
+namespace {
+
+// Represents a cover of a buffer of SizeVal bytes with blocks of size
+// AVT, as well as how many bytes remain (BytesLeft is always smaller than
+// the block size).
+struct RepMovsRepeats {
+ RepMovsRepeats(const uint64_t SizeVal, const MVT& AVT) {
+ const unsigned UBytes = AVT.getSizeInBits() / 8;
+ Count = SizeVal / UBytes;
+ BytesLeft = SizeVal % UBytes;
+ }
+
+ unsigned Count;
+ unsigned BytesLeft;
+};
+
+} // namespace
+
SDValue X86SelectionDAGInfo::EmitTargetCodeForMemcpy(
SelectionDAG &DAG, const SDLoc &dl, SDValue Chain, SDValue Dst, SDValue Src,
SDValue Size, unsigned Align, bool isVolatile, bool AlwaysInline,
@@ -231,14 +249,18 @@ SDValue X86SelectionDAGInfo::EmitTargetCodeForMemcpy(
// QWORD aligned
AVT = Subtarget.is64Bit() ? MVT::i64 : MVT::i32;
- unsigned UBytes = AVT.getSizeInBits() / 8;
- unsigned CountVal = SizeVal / UBytes;
- SDValue Count = DAG.getIntPtrConstant(CountVal, dl);
- unsigned BytesLeft = SizeVal % UBytes;
+ RepMovsRepeats Repeats(SizeVal, AVT);
+ if (Repeats.BytesLeft > 0 &&
+ DAG.getMachineFunction().getFunction()->optForMinSize()) {
+ // When agressively optimizing for size, avoid generating the code to handle
+ // BytesLeft.
+ AVT = MVT::i8;
+ Repeats = RepMovsRepeats(SizeVal, AVT);
+ }
SDValue InFlag;
Chain = DAG.getCopyToReg(Chain, dl, Subtarget.is64Bit() ? X86::RCX : X86::ECX,
- Count, InFlag);
+ DAG.getIntPtrConstant(Repeats.Count, dl), InFlag);
InFlag = Chain.getValue(1);
Chain = DAG.getCopyToReg(Chain, dl, Subtarget.is64Bit() ? X86::RDI : X86::EDI,
Dst, InFlag);
@@ -253,9 +275,9 @@ SDValue X86SelectionDAGInfo::EmitTargetCodeForMemcpy(
SmallVector<SDValue, 4> Results;
Results.push_back(RepMovs);
- if (BytesLeft) {
+ if (Repeats.BytesLeft) {
// Handle the last 1 - 7 bytes.
- unsigned Offset = SizeVal - BytesLeft;
+ unsigned Offset = SizeVal - Repeats.BytesLeft;
EVT DstVT = Dst.getValueType();
EVT SrcVT = Src.getValueType();
EVT SizeVT = Size.getValueType();
@@ -266,7 +288,8 @@ SDValue X86SelectionDAGInfo::EmitTargetCodeForMemcpy(
DAG.getNode(ISD::ADD, dl, SrcVT, Src,
DAG.getConstant(Offset, dl,
SrcVT)),
- DAG.getConstant(BytesLeft, dl, SizeVT),
+ DAG.getConstant(Repeats.BytesLeft, dl,
+ SizeVT),
Align, isVolatile, AlwaysInline, false,
DstPtrInfo.getWithOffset(Offset),
SrcPtrInfo.getWithOffset(Offset)));
OpenPOWER on IntegriCloud