[ARM] Add NEON support for ISD::ABDS/ABDU nodes.

As noted on llvm#94466, NEON has ABDS/ABDU instructions but only handles them via intrinsics, plus some VABDL custom patterns. Fixes llvm#94466
RKSimon · Jun 7, 2024 · 6b4fa32 · 6b4fa32
1 parent ac40463
commit 6b4fa32
Show file tree

Hide file tree

Showing 3 changed files with 87 additions and 154 deletions.
diff --git a/llvm/lib/Target/ARM/ARMISelLowering.cpp b/llvm/lib/Target/ARM/ARMISelLowering.cpp
@@ -205,9 +205,9 @@ void ARMTargetLowering::addTypeForNEON(MVT VT, MVT PromotedLdStVT) {
   setOperationAction(ISD::SDIVREM, VT, Expand);
   setOperationAction(ISD::UDIVREM, VT, Expand);
 
-  if (!VT.isFloatingPoint() &&
-      VT != MVT::v2i64 && VT != MVT::v1i64)
-    for (auto Opcode : {ISD::ABS, ISD::SMIN, ISD::SMAX, ISD::UMIN, ISD::UMAX})
+  if (!VT.isFloatingPoint() && VT != MVT::v2i64 && VT != MVT::v1i64)
+    for (auto Opcode : {ISD::ABS, ISD::ABDS, ISD::ABDU, ISD::SMIN, ISD::SMAX,
+                        ISD::UMIN, ISD::UMAX})
       setOperationAction(Opcode, VT, Legal);
   if (!VT.isFloatingPoint())
     for (auto Opcode : {ISD::SADDSAT, ISD::UADDSAT, ISD::SSUBSAT, ISD::USUBSAT})
@@ -4174,7 +4174,15 @@ ARMTargetLowering::LowerINTRINSIC_WO_CHAIN(SDValue Op, SelectionDAG &DAG,
   }
   case Intrinsic::arm_neon_vabs:
     return DAG.getNode(ISD::ABS, SDLoc(Op), Op.getValueType(),
-                        Op.getOperand(1));
+                       Op.getOperand(1));
+  case Intrinsic::arm_neon_vabds:
+    if (Op.getValueType().isInteger())
+      return DAG.getNode(ISD::ABDS, SDLoc(Op), Op.getValueType(),
+                         Op.getOperand(1), Op.getOperand(2));
+    return SDValue();
+  case Intrinsic::arm_neon_vabdu:
+    return DAG.getNode(ISD::ABDU, SDLoc(Op), Op.getValueType(),
+                       Op.getOperand(1), Op.getOperand(2));
   case Intrinsic::arm_neon_vmulls:
   case Intrinsic::arm_neon_vmullu: {
     unsigned NewOpc = (IntNo == Intrinsic::arm_neon_vmulls)

diff --git a/llvm/lib/Target/ARM/ARMInstrNEON.td b/llvm/lib/Target/ARM/ARMInstrNEON.td
@@ -5640,10 +5640,10 @@ def  VBITq    : N3VX<1, 0, 0b10, 0b0001, 1, 1,
 //   VABD     : Vector Absolute Difference
 defm VABDs    : N3VInt_QHS<0, 0, 0b0111, 0, N3RegFrm,
                            IIC_VSUBi4D, IIC_VSUBi4D, IIC_VSUBi4Q, IIC_VSUBi4Q,
-                           "vabd", "s", int_arm_neon_vabds, 1>;
+                           "vabd", "s", abds, 1>;
 defm VABDu    : N3VInt_QHS<1, 0, 0b0111, 0, N3RegFrm,
                            IIC_VSUBi4D, IIC_VSUBi4D, IIC_VSUBi4Q, IIC_VSUBi4Q,
-                           "vabd", "u", int_arm_neon_vabdu, 1>;
+                           "vabd", "u", abdu, 1>;
 def  VABDfd   : N3VDInt<1, 0, 0b10, 0b1101, 0, N3RegFrm, IIC_VBIND,
                         "vabd", "f32", v2f32, v2f32, int_arm_neon_vabds, 1>;
 def  VABDfq   : N3VQInt<1, 0, 0b10, 0b1101, 0, N3RegFrm, IIC_VBINQ,
@@ -5657,20 +5657,22 @@ def  VABDhq   : N3VQInt<1, 0, 0b11, 0b1101, 0, N3RegFrm, IIC_VBINQ,
 
 //   VABDL    : Vector Absolute Difference Long (Q = | D - D |)
 defm VABDLs   : N3VLIntExt_QHS<0,1,0b0111,0, IIC_VSUBi4Q,
-                               "vabdl", "s", int_arm_neon_vabds, zext, 1>;
+                               "vabdl", "s", abds, zext, 1>;
 defm VABDLu   : N3VLIntExt_QHS<1,1,0b0111,0, IIC_VSUBi4Q,
-                               "vabdl", "u", int_arm_neon_vabdu, zext, 1>;
+                               "vabdl", "u", abdu, zext, 1>;
 
 let Predicates = [HasNEON] in {
-def : Pat<(v8i16 (abs (sub (zext (v8i8 DPR:$opA)), (zext (v8i8 DPR:$opB))))),
+def : Pat<(v8i16 (zext (abdu (v8i8 DPR:$opA), (v8i8 DPR:$opB)))),
           (VABDLuv8i16 DPR:$opA, DPR:$opB)>;
-def : Pat<(v4i32 (abs (sub (zext (v4i16 DPR:$opA)), (zext (v4i16 DPR:$opB))))),
+def : Pat<(v4i32 (zext (abdu (v4i16 DPR:$opA), (v4i16 DPR:$opB)))),
           (VABDLuv4i32 DPR:$opA, DPR:$opB)>;
+def : Pat<(v2i64 (zext (abdu (v2i32 DPR:$opA), (v2i32 DPR:$opB)))),
+          (VABDLuv2i64 DPR:$opA, DPR:$opB)>;
 }
 
 // ISD::ABS is not legal for v2i64, so VABDL needs to be matched from the
 // shift/xor pattern for ABS.
-
+// TODO: Remove me.
 def abd_shr :
     PatFrag<(ops node:$in1, node:$in2, node:$shift),
             (ARMvshrsImm (sub (zext node:$in1),
@@ -5686,15 +5688,15 @@ def : Pat<(xor (v2i64 (abd_shr (v2i32 DPR:$opA), (v2i32 DPR:$opB), 63)),
 
 //   VABA     : Vector Absolute Difference and Accumulate
 defm VABAs    : N3VIntOp_QHS<0,0,0b0111,1, IIC_VABAD, IIC_VABAQ,
-                             "vaba", "s", int_arm_neon_vabds, add>;
+                             "vaba", "s", abds, add>;
 defm VABAu    : N3VIntOp_QHS<1,0,0b0111,1, IIC_VABAD, IIC_VABAQ,
-                             "vaba", "u", int_arm_neon_vabdu, add>;
+                             "vaba", "u", abdu, add>;
 
 //   VABAL    : Vector Absolute Difference and Accumulate Long (Q += | D - D |)
 defm VABALs   : N3VLIntExtOp_QHS<0,1,0b0101,0, IIC_VABAD,
-                                 "vabal", "s", int_arm_neon_vabds, zext, add>;
+                                 "vabal", "s", abds, zext, add>;
 defm VABALu   : N3VLIntExtOp_QHS<1,1,0b0101,0, IIC_VABAD,
-                                 "vabal", "u", int_arm_neon_vabdu, zext, add>;
+                                 "vabal", "u", abdu, zext, add>;
 
 // Vector Maximum and Minimum.