SYCL: Add fp16 type support to unary op kernels (#12788)

* SYCL: Add fp16 support to some elementwise OP kernels

* remove comment

ggml-ci

* Use static_cast directly

* remove not needed cast from tanh

* Use static cast and remove unneeded castings

* Adjust device_support_op for unary OPs

* Use cast_data and typed_data struct to deduplicate casting code

ggml/src/ggml-sycl/element_wise.hpp

@@ -2,6 +2,13 @@
 #define GGML_SYCL_ELEMENTWISE_HPP
 
 #include "common.hpp"
+#include "ggml.h"
+#include <limits.h>
+
+template <typename T>
+T neg_infinity() {
+    return -std::numeric_limits<T>::infinity();
+}
 
 static __dpct_inline__ float op_repeat(const float a, const float b) {
     return b;
@@ -24,6 +31,19 @@ static __dpct_inline__ float op_div(const float a, const float b) {
     return a / b;
 }
 
+template<typename T>
+struct typed_data {
+    const T * src;
+    T * dst;
+};
+
+template<typename T>
+typed_data<T> cast_data(ggml_tensor * dst) {
+    return {
+        /* .src = */ static_cast<const T *>(dst->src[0]->data),
+        /* .dst = */ static_cast<T *>(dst->data)
+    };
+}
 
 void ggml_sycl_sqrt(ggml_backend_sycl_context & ctx, ggml_tensor * dst);
 
@@ -65,6 +85,10 @@ void ggml_sycl_upscale(ggml_backend_sycl_context & ctx, ggml_tensor * dst);
 
 void ggml_sycl_pad(ggml_backend_sycl_context & ctx, ggml_tensor * dst);
 
+void ggml_sycl_clamp(ggml_backend_sycl_context & ctx, ggml_tensor * dst);
+
+// ---------
+
 void ggml_sycl_add(ggml_backend_sycl_context & ctx, ggml_tensor * dst);
 
 void ggml_sycl_sub(ggml_backend_sycl_context & ctx, ggml_tensor * dst);