X86: Promote i8 cmov when both operands are coming from truncates of the same width.

X86 doesn't have i8 cmovs so isel would emit a branch. Emitting branches at this
level is often not a good idea because it's too late for many optimizations to
kick in. This solution doesn't add any extensions (truncs are free) and tries
to avoid introducing partial register stalls by filtering direct copyfromregs.

I'm seeing a ~10% speedup on reading a random .png file with libpng15 via
graphicsmagick on x86_64/westmere, but YMMV depending on the microarchitecture.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@165868 91177308-0d34-0410-b5e6-96231b3b80d8

2 files changed, 28 insertions, 0 deletions

diff --git a/lib/Target/X86/X86ISelLowering.cpp b/lib/Target/X86/X86ISelLowering.cpp
index 1580935..b7a9f6f 100644
--- a/lib/Target/X86/X86ISelLowering.cpp
+++ b/lib/Target/X86/X86ISelLowering.cpp
@@ -9148,6 +9148,21 @@ SDValue X86TargetLowering::LowerSELECT(SDValue Op, SelectionDAG &DAG) const {
     }
   }
 
+  // X86 doesn't have an i8 cmov. If both operands are the result of a truncate
+  // widen the cmov and push the truncate through. This avoids introducing a new
+  // branch during isel and doesn't add any extensions.
+  if (Op.getValueType() == MVT::i8 &&
+      Op1.getOpcode() == ISD::TRUNCATE && Op2.getOpcode() == ISD::TRUNCATE) {
+    SDValue T1 = Op1.getOperand(0), T2 = Op2.getOperand(0);
+    if (T1.getValueType() == T2.getValueType() &&
+        // Blacklist CopyFromReg to avoid partial register stalls.
+        T1.getOpcode() != ISD::CopyFromReg && T2.getOpcode()!=ISD::CopyFromReg){
+      SDVTList VTs = DAG.getVTList(T1.getValueType(), MVT::Glue);
+      SDValue Cmov = DAG.getNode(X86ISD::CMOV, DL, VTs, T1, T2, CC, Cond);
+      return DAG.getNode(ISD::TRUNCATE, DL, Op.getValueType(), Cmov);
+    }
+  }
+
   // X86ISD::CMOV means set the result (which is operand 1) to the RHS if
   // condition is true.
   SDVTList VTs = DAG.getVTList(Op.getValueType(), MVT::Glue);
diff --git a/test/CodeGen/X86/select.ll b/test/CodeGen/X86/select.ll
index 2e39473..f4c8d9e 100644
--- a/test/CodeGen/X86/select.ll
+++ b/test/CodeGen/X86/select.ll
@@ -344,3 +344,16 @@ entry:
 ; ATOM: negw
 ; ATOM: sbbw
 }
+
+define i8 @test18(i32 %x, i8 zeroext %a, i8 zeroext %b) nounwind {
+  %cmp = icmp slt i32 %x, 15
+  %sel = select i1 %cmp, i8 %a, i8 %b
+  ret i8 %sel
+; CHECK: test18:
+; CHECK: cmpl $15
+; CHECK: cmovll
+
+; ATOM: test18:
+; ATOM: cmpl $15
+; ATOM: cmovll
+}