Resolution of issue #153: Add compiler warning on comparing int and size_t (#212)

* Turning compare warnings on

* Cleaning part I

* Cleaning part II

* Explicit static_cast to ck::type_convert

* Resolving large tensor size issue.

* format

* revert change to tensor descriptor; promote lementSpaceSize to 64bit

* use integer value for GEMM test

* Review remarks

* Review remarks + issues with (un)signed arithmetic

* Format fix

* Format

* Clang-format.

* fix 2gb limit issue

Co-authored-by: Chao Liu <chao.liu2@amd.com>
Co-authored-by: Adam Osewski <aosewski@amd.com>

[ROCm/composable_kernel commit: f03a1738d9]

test/reduce/reduce_no_index.cpp

@@ -460,7 +460,7 @@ class SimpleAppArgs
 
     int processArgs(int argc, char* argv[])
     {
-        unsigned int ch;
+        int ch;
 
         while(1)
         {

test/reduce/reduce_util.hpp

@@ -9,7 +9,7 @@ namespace reduce_util {
 template <typename T>
 void to_f32_vector(const Tensor<T>& src, Tensor<float>& dst)
 {
-    for(int i = 0; i < src.mData.size(); ++i)
+    for(std::size_t i = 0; i < src.mData.size(); ++i)
         dst.mData[i] = type_convert<float>(src.mData[i]);
 }
 

test/reduce/reduce_with_index.cpp

@@ -463,7 +463,7 @@ class SimpleAppArgs
 
     int processArgs(int argc, char* argv[])
     {
-        unsigned int ch;
+        int ch;
 
         while(1)
         {