gemm + layernorm (#261)

* Implement reduction meand and reduction square mean

* Refine file name

* Add reduce mean and square mean

* Fix parameter name

* Add normalize device op (not implement invoker::run())

* Remove epislon

* Refine deviceop

* Add 5ary elementwise for normalization

* Add layernorm example

* layerNorm verication

* Fix compiler error due to merge from develop

* Fix typo

* Fix compile error

* Refine naming

* [What] Suport non pointer for invoker and argument
[Why] Snyc coding style with gemm

* Refine folder name

* Refine class name

* Evaluate perf of the kernel

* Fix compile error

* [What] Refine perf evaluation in example of gemm + reduction
[Why] evaluation of gemm + reduction may cause verification fail. Because evaluation will not initial global memory

* clang-format

include/ck/tensor_operation/gpu/element/element_wise_operation.hpp

@@ -143,6 +143,24 @@ struct AddHardswishAdd
     }
 };
 
+struct Normalize
+{
+    Normalize(float epsilon = 1e-4) : epsilon_(epsilon) {}
+
+    __host__ __device__ constexpr void operator()(float& y,
+                                                  const float& x,
+                                                  const float& mean,
+                                                  const float& mean_square,
+                                                  const float& gamma,
+                                                  const float& beta) const
+    {
+        float variance = mean_square - (mean * mean);
+        y              = ((x - mean) / sqrtf(variance + epsilon_)) * gamma + beta;
+    }
+
+    float epsilon_;
+};
+
 // Unary operators are usually called element-wisely before/after the reduction is executed on the
 // elements. They are needed for easy implementation of reduction types of AVG, NRM1, NRM2