[CPU][ARM64] Add JIT emitter for Eltwise LogicalXor operation (#26846)

### Details:
- Added a jit_logical_xor_emitter derived class in
aarch64/jit_eltwise_emitters
- Created entry Algorithm::EltwiseLogicalXor in the
get_supported_precisions in nodes/kernels/aarch64
- Add the EltwiseLogicalXor entry in the aarch64 executors supported
algorithms

### Tickets:
 - #24108

Signed-off-by: Nashez Zubair <nashezzubair@gmail.com>

Author: nashez

src/plugins/intel_cpu/src/emitters/plugin/aarch64/jit_eltwise_emitters.cpp

@@ -1198,6 +1198,58 @@ std::set<std::vector<element::Type>> jit_logical_not_emitter::get_supported_prec
     return {{element::f32}};
 }
 
+/// LOGICAL_XOR ///
+jit_logical_xor_emitter::jit_logical_xor_emitter(dnnl::impl::cpu::aarch64::jit_generator* host,
+                                                 dnnl::impl::cpu::aarch64::cpu_isa_t host_isa,
+                                                 const std::shared_ptr<ov::Node>& node)
+        : jit_emitter(host, host_isa, node, get_arithmetic_binary_exec_precision(node)) {
+    prepare_table();
+}
+
+jit_logical_xor_emitter::jit_logical_xor_emitter(dnnl::impl::cpu::aarch64::jit_generator* host,
+                                                 dnnl::impl::cpu::aarch64::cpu_isa_t host_isa,
+                                                 const ov::element::Type exec_prc)
+    : jit_emitter(host, host_isa, exec_prc) {
+    prepare_table();
+}
+
+size_t jit_logical_xor_emitter::get_inputs_count() const { return 2; }
+
+size_t jit_logical_xor_emitter::get_aux_vecs_count() const { return 1; }
+
+size_t jit_logical_xor_emitter::get_aux_gprs_count() const { return 1; }
+
+void jit_logical_xor_emitter::emit_impl(const std::vector<size_t> &in_vec_idxs, const std::vector<size_t> &out_vec_idxs) const {
+    if (host_isa_ == dnnl::impl::cpu::aarch64::asimd) {
+        emit_isa<dnnl::impl::cpu::aarch64::asimd>(in_vec_idxs, out_vec_idxs);
+    } else {
+        OV_CPU_JIT_EMITTER_THROW("Can't create jit eltwise kernel");
+    }
+}
+
+template <dnnl::impl::cpu::aarch64::cpu_isa_t isa>
+void jit_logical_xor_emitter::emit_isa(const std::vector<size_t> &in_vec_idxs, const std::vector<size_t> &out_vec_idxs) const {
+    OV_CPU_JIT_EMITTER_ASSERT(exec_prc_ == ov::element::f32, "unsupported precision: " + exec_prc_.to_string());
+
+    using TReg = typename dnnl::impl::cpu::aarch64::cpu_isa_traits<isa>::TReg;
+    const TReg src1 = TReg(in_vec_idxs[0]);
+    const TReg src2 = TReg(in_vec_idxs[1]);
+    const TReg dst = TReg(out_vec_idxs[0]);
+    const TReg aux = TReg(aux_vec_idxs[0]);
+
+    h->eor(dst.b16, src1.b16, src2.b16);
+    h->ld1r(aux.s, table_val2("one"));
+    h->and_(dst.b16, dst.b16, aux.b16);
+}
+
+void jit_logical_xor_emitter::register_table_entries() {
+    push_arg_entry_of("one", 0x3f800000, true);
+}
+
+std::set<std::vector<element::Type>> jit_logical_xor_emitter::get_supported_precisions(const std::shared_ptr<ov::Node>& node) {
+    return {{element::f32, element::f32}};
+}
+
 /// MAX ///
 jit_maximum_emitter::jit_maximum_emitter(dnnl::impl::cpu::aarch64::jit_generator* host,
                                          dnnl::impl::cpu::aarch64::cpu_isa_t host_isa,

src/plugins/intel_cpu/src/emitters/plugin/aarch64/jit_eltwise_emitters.hpp

@@ -549,6 +549,34 @@ class jit_logical_not_emitter : public jit_emitter {
     void register_table_entries() override;
 };
 
+class jit_logical_xor_emitter : public jit_emitter {
+public:
+    jit_logical_xor_emitter(dnnl::impl::cpu::aarch64::jit_generator *host,
+                            dnnl::impl::cpu::aarch64::cpu_isa_t host_isa,
+                            const ov::element::Type exec_prc = ov::element::f32);
+
+    jit_logical_xor_emitter(dnnl::impl::cpu::aarch64::jit_generator *host,
+                            dnnl::impl::cpu::aarch64::cpu_isa_t host_isa,
+                            const std::shared_ptr<ov::Node>& n);
+
+    size_t get_inputs_count() const override;
+
+    size_t get_aux_vecs_count() const override;
+
+    size_t get_aux_gprs_count() const override;
+
+    static std::set<std::vector<element::Type>> get_supported_precisions(
+            const std::shared_ptr<ov::Node>& node = nullptr);
+
+private:
+    void emit_impl(const std::vector<size_t> &in_vec_idxs, const std::vector<size_t> &out_vec_idxs) const override;
+
+    template <dnnl::impl::cpu::aarch64::cpu_isa_t isa>
+    void emit_isa(const std::vector<size_t> &in_vec_idxs, const std::vector<size_t> &out_vec_idxs) const;
+
+    void register_table_entries() override;
+};
+
 class jit_mod_emitter : public jit_emitter {
 public:
     jit_mod_emitter(dnnl::impl::cpu::aarch64::jit_generator *host,

src/plugins/intel_cpu/src/nodes/executors/aarch64/jit_eltwise.cpp

@@ -35,6 +35,7 @@ bool JitEltwiseExecutor::isSupported(
                                      Algorithm::EltwiseIsNaN,
                                      Algorithm::EltwiseLessEqual,
                                      Algorithm::EltwiseLogicalNot,
+                                     Algorithm::EltwiseLogicalXor,
                                      Algorithm::EltwiseMaximum,
                                      Algorithm::EltwiseMinimum,
                                      Algorithm::EltwiseMish,

src/plugins/intel_cpu/src/nodes/kernels/aarch64/jit_uni_eltwise_generic.cpp

@@ -653,6 +653,7 @@ std::shared_ptr<jit_emitter> jit_uni_eltwise_generic<isa>::create_eltwise_emitte
     OV_CASE(Algorithm::EltwiseIsInf, ov::intel_cpu::aarch64::jit_is_inf_emitter),
     OV_CASE(Algorithm::EltwiseLessEqual, ov::intel_cpu::aarch64::jit_less_equal_emitter),
     OV_CASE(Algorithm::EltwiseLogicalNot, ov::intel_cpu::aarch64::jit_logical_not_emitter),
+    OV_CASE(Algorithm::EltwiseLogicalXor, ov::intel_cpu::aarch64::jit_logical_xor_emitter),
     OV_CASE(Algorithm::EltwiseIsNaN, ov::intel_cpu::aarch64::jit_is_nan_emitter),
     OV_CASE(Algorithm::EltwiseMaximum, ov::intel_cpu::aarch64::jit_maximum_emitter),
     OV_CASE(Algorithm::EltwiseMinimum, ov::intel_cpu::aarch64::jit_minimum_emitter),
@@ -833,6 +834,7 @@ std::set<std::vector<element::Type>> eltwise_precision_helper::get_supported_pre
         OV_CASE(Algorithm::EltwiseIsNaN, jit_is_nan_emitter),
         OV_CASE(Algorithm::EltwiseLessEqual, jit_less_equal_emitter),
         OV_CASE(Algorithm::EltwiseLogicalNot, jit_logical_not_emitter),
+        OV_CASE(Algorithm::EltwiseLogicalXor, jit_logical_xor_emitter),
         OV_CASE(Algorithm::EltwiseMaximum, jit_maximum_emitter),
         OV_CASE(Algorithm::EltwiseMinimum, jit_minimum_emitter),
         OV_CASE(Algorithm::EltwiseMish, jit_mish_emitter),