[AArch64][GlobalISel] Added shadd intrinsic support

GlobalISel now selects shadd intrinsic, without falling back to SDAG.
Note that GlobalISel-generated code involving shadd seems to be inefficent when compared to SDAG.

Author: JoshdRod

llvm/lib/Target/AArch64/AArch64InstrGISel.td

@@ -251,6 +251,12 @@ def G_URHADD : AArch64GenericInstruction {
   let hasSideEffects = 0;
 }
 
+def G_SHADD : AArch64GenericInstruction {
+  let OutOperandList = (outs type0:$dst);
+  let InOperandList = (ins type0:$src1, type1:$src2);
+  let hasSideEffects = 0;
+}
+
 // Generic instruction for the BSP pseudo. It is expanded into BSP, which
 // expands into BSL/BIT/BIF after register allocation.
 def G_BSP : AArch64GenericInstruction {
@@ -300,6 +306,7 @@ def : GINodeEquiv<G_USDOT, AArch64usdot>;
 
 def : GINodeEquiv<G_UHADD, avgflooru>;
 def : GINodeEquiv<G_URHADD, avgceilu>;
+def : GINodeEquiv<G_SHADD, avgfloors>;
 
 def : GINodeEquiv<G_EXTRACT_VECTOR_ELT, vector_extract>;
 

llvm/lib/Target/AArch64/GISel/AArch64LegalizerInfo.cpp

@@ -1829,6 +1829,8 @@ bool AArch64LegalizerInfo::legalizeIntrinsic(LegalizerHelper &Helper,
     return LowerBinOp(AArch64::G_UHADD);
   case Intrinsic::aarch64_neon_urhadd:
     return LowerBinOp(AArch64::G_URHADD);
+  case Intrinsic::aarch64_neon_shadd:
+    return LowerBinOp(AArch64::G_SHADD);
   case Intrinsic::aarch64_neon_abs: {
     // Lower the intrinsic to G_ABS.
     MIB.buildInstr(TargetOpcode::G_ABS, {MI.getOperand(0)}, {MI.getOperand(2)});

llvm/test/CodeGen/AArch64/freeze.ll

@@ -3,7 +3,6 @@
 ; RUN: llc -mtriple=aarch64-unknown-linux-gnu -global-isel -global-isel-abort=2 2>&1 < %s | FileCheck %s --check-prefixes=CHECK,CHECK-GI
 
 ; CHECK-GI:       warning: Instruction selection used fallback path for freeze_v2i8
-; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for freeze_shadd
 ; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for freeze_srhadd
 
 %struct.T = type { i32, i32 }
@@ -485,12 +484,21 @@ define <8 x i16> @freeze_urhadd(<8 x i16> %a0, <8 x i16> %a1) {
 }
 
 define <8 x i16> @freeze_shadd(<8 x i8> %a0, <8 x i16> %a1) {
-; CHECK-LABEL: freeze_shadd:
-; CHECK:       // %bb.0:
-; CHECK-NEXT:    sshll v0.8h, v0.8b, #0
-; CHECK-NEXT:    sshr v1.8h, v1.8h, #8
-; CHECK-NEXT:    shadd v0.8h, v0.8h, v1.8h
-; CHECK-NEXT:    ret
+; CHECK-SD-LABEL: freeze_shadd:
+; CHECK-SD:       // %bb.0:
+; CHECK-SD-NEXT:    sshll v0.8h, v0.8b, #0
+; CHECK-SD-NEXT:    sshr v1.8h, v1.8h, #8
+; CHECK-SD-NEXT:    shadd v0.8h, v0.8h, v1.8h
+; CHECK-SD-NEXT:    ret
+;
+; CHECK-GI-LABEL: freeze_shadd:
+; CHECK-GI:       // %bb.0:
+; CHECK-GI-NEXT:    sshll v0.8h, v0.8b, #0
+; CHECK-GI-NEXT:    sshr v1.8h, v1.8h, #8
+; CHECK-GI-NEXT:    shadd v0.8h, v0.8h, v1.8h
+; CHECK-GI-NEXT:    shl v0.8h, v0.8h, #8
+; CHECK-GI-NEXT:    sshr v0.8h, v0.8h, #8
+; CHECK-GI-NEXT:    ret
   %x0 = sext <8 x i8> %a0 to <8 x i16>
   %x1 = ashr <8 x i16> %a1, splat (i16 8)
   %avg = call <8 x i16> @llvm.aarch64.neon.shadd.v8i16(<8 x i16> %x0, <8 x i16> %x1)