#78303 Add transformation ~v1 & v2 to VectorXxx.AndNot(v1, v2)

src/coreclr/jit/gentree.cpp

@@ -25468,6 +25468,54 @@ void GenTreeHWIntrinsic::Initialize(NamedIntrinsic intrinsicId)
         }
     }
 }
+
+//------------------------------------------------------------------------------
+// HWOperGet : Returns Oper based on the HWIntrinsicId
+//
+genTreeOps GenTreeHWIntrinsic::HWOperGet()
+{
+    switch (GetHWIntrinsicId())
+    {
+#if defined(TARGET_XARCH)
+        case NI_SSE_And:
+        case NI_SSE2_And:
+        case NI_AVX_And:
+        case NI_AVX2_And:
+#elif defined(TARGET_ARM64)
+        case NI_AdvSimd_And:
+#endif
+        {
+            return GT_AND;
+        }
+
+#if defined(TARGET_ARM64)
+        case NI_AdvSimd_Not:
+        {
+            return GT_NOT;
+        }
+#endif
+
+#if defined(TARGET_XARCH)
+        case NI_SSE_Xor:
+        case NI_SSE2_Xor:
+        case NI_AVX_Xor:
+        case NI_AVX2_Xor:
+#elif defined(TARGET_ARM64)
+        case NI_AdvSimd_Xor:
+#endif
+        {
+            return GT_XOR;
+        }
+
+        // TODO: Handle other cases
+
+        default:
+        {
+            return GT_NONE;
+        }
+    }
+}
+
 #endif // FEATURE_HW_INTRINSICS
 
 //---------------------------------------------------------------------------------------

src/coreclr/jit/gentree.h

@@ -6343,6 +6343,8 @@ struct GenTreeHWIntrinsic : public GenTreeJitIntrinsic
 
     static bool Equals(GenTreeHWIntrinsic* op1, GenTreeHWIntrinsic* op2);
 
+    genTreeOps HWOperGet();
+
 private:
     void SetHWIntrinsicId(NamedIntrinsic intrinsicId);
 

src/coreclr/jit/morph.cpp

@@ -10787,7 +10787,6 @@ GenTree* Compiler::fgOptimizeHWIntrinsic(GenTreeHWIntrinsic* node)
             INDEBUG(node->gtDebugFlags |= GTF_DEBUG_NODE_MORPHED);
             return node;
         }
-
 #if defined(TARGET_XARCH)
         case NI_AVX512F_Add:
         case NI_AVX512BW_Add:
@@ -10951,6 +10950,98 @@ GenTree* Compiler::fgOptimizeHWIntrinsic(GenTreeHWIntrinsic* node)
         }
     }
 
+    // Transforms:
+    // 1.(~v1 & v2) to VectorXxx.AndNot(v1, v2)
+    // 2.(v1 & (~v2)) to VectorXxx.AndNot(v2, v1)
+    switch (node->HWOperGet())
+    {
+        case GT_AND:
+        {
+            GenTree* op1 = node->Op(1);
+            GenTree* op2 = node->Op(2);
+            GenTree* lhs = nullptr;
+            GenTree* rhs = nullptr;
+
+            if (op1->OperIsHWIntrinsic())
+            {
+                // Try handle: ~op1 & op2
+                GenTreeHWIntrinsic* hw     = op1->AsHWIntrinsic();
+                genTreeOps          hwOper = hw->HWOperGet();
+
+                if (hwOper == GT_NOT)
+                {
+                    lhs = op2;
+                    rhs = hw->Op(1);
+                }
+                else if (hwOper == GT_XOR)
+                {
+                    GenTree* hwOp1 = hw->Op(1);
+                    GenTree* hwOp2 = hw->Op(2);
+
+                    if (hwOp1->IsVectorAllBitsSet())
+                    {
+                        lhs = op2;
+                        rhs = hwOp2;
+                    }
+                    else if (hwOp2->IsVectorAllBitsSet())
+                    {
+                        lhs = op2;
+                        rhs = hwOp1;
+                    }
+                }
+            }
+
+            if ((lhs == nullptr) && op2->OperIsHWIntrinsic())
+            {
+                // Try handle: op1 & ~op2
+                GenTreeHWIntrinsic* hw     = op2->AsHWIntrinsic();
+                genTreeOps          hwOper = hw->HWOperGet();
+
+                if (hwOper == GT_NOT)
+                {
+                    lhs = op1;
+                    rhs = hw->Op(1);
+                }
+                else if (hwOper == GT_XOR)
+                {
+                    GenTree* hwOp1 = hw->Op(1);
+                    GenTree* hwOp2 = hw->Op(2);
+
+                    if (hwOp1->IsVectorAllBitsSet())
+                    {
+                        lhs = op1;
+                        rhs = hwOp2;
+                    }
+                    else if (hwOp2->IsVectorAllBitsSet())
+                    {
+                        lhs = op1;
+                        rhs = hwOp1;
+                    }
+                }
+            }
+
+            if (lhs == nullptr || rhs == nullptr)
+            {
+                break;
+            }
+
+            var_types    simdType        = node->TypeGet();
+            CorInfoType  simdBaseJitType = node->GetSimdBaseJitType();
+            unsigned int simdSize        = node->GetSimdSize();
+
+            GenTree* andnNode = gtNewSimdBinOpNode(GT_AND_NOT, simdType, lhs, rhs, simdBaseJitType, simdSize);
+
+            DEBUG_DESTROY_NODE(node);
+            INDEBUG(andnNode->gtDebugFlags |= GTF_DEBUG_NODE_MORPHED);
+
+            return andnNode;
+        }
+        default:
+        {
+            break;
+        }
+    }
+
     return node;
 }