GEMM with Multiple Source, GEMM+Bias+Add+FastGeLU example and ckProfiler (#241)

* ad gelu and fast_gelu

* added GeLU and fast GeLU

* clean up

* add gemm+fastgelu example

* add gemm+gelu instances

* update profiler

* clean up

* clean up

* adding gemm+bias+activation

* clean

* adding bias

* clean

* adding gemm multiple d

* debugging

* add gemm bias add fastgelu

* rename, clean

* refactoring; add readme

* refactor

* refactor

* refactor

* refactor

* refactor

* refactor

* fix

* fix

* update example

* update example

* rename

* update example

* add ckProfiler

* clean

* clean

* clean

* clean

* add comment

* use type_convert

* clean

* clean element wise op

[ROCm/composable_kernel commit: 56adf7e9cc]

include/ck/tensor_description/tensor_adaptor.hpp

@@ -136,7 +136,11 @@ struct TensorAdaptor
     using ElementSize = remove_cv_t<decltype(InitializeElementSize(Transforms{}))>;
 
     public:
+#if 0 // workaround compiler complaint about constexpr
     __host__ __device__ constexpr TensorAdaptor() = default;
+#else
+    __host__ __device__ constexpr TensorAdaptor() : transforms_{}, element_size_{} {}
+#endif
 
     __host__ __device__ constexpr TensorAdaptor(const Transforms& transforms)
         : transforms_{transforms}, element_size_{InitializeElementSize(transforms)}

include/ck/tensor_description/tensor_descriptor.hpp

@@ -111,7 +111,14 @@ struct TensorDescriptor
     using ElementSize = remove_cv_t<decltype(InitializeElementSize(Transforms{}))>;
 
     public:
+#if 0 // workaround compiler complaint about constexpr
     __host__ __device__ constexpr TensorDescriptor() = default;
+#else
+    __host__ __device__ constexpr TensorDescriptor()
+        : transforms_{}, element_size_{}, element_space_size_{}
+    {
+    }
+#endif
 
     __host__ __device__ constexpr TensorDescriptor(const Transforms& transforms,
                                                    ElementSpaceSize element_space_size)