Remove redundant <fstream> includes (#563)

* Remove redundant <fstream> includes

* Fix fstream in examples/

* Fix <fstream> in test/

* Use consistent order for <fstream> (always after <iostream>)

* Remove an unneeded include in a file where std::ofstream usage is commented out

Co-authored-by: Ivan Komarov <dfyz@yandex-team.ru>

test/unit/gemm/threadblock/mma_multistage_testbed_slicedk.h

@@ -35,6 +35,8 @@
 
 #pragma once
 
+#include <fstream>
+
 #include "../../common/cutlass_unit_test.h"
 
 #include "cutlass/aligned_buffer.h"

test/unit/gemm/threadblock/mma_pipelined_testbed.h

@@ -34,6 +34,8 @@
 
 #pragma once
 
+#include <fstream>
+
 #include "../../common/cutlass_unit_test.h"
 
 #include "cutlass/aligned_buffer.h"

test/unit/gemm/threadblock/mma_pipelined_testbed_slicedk.h

@@ -35,6 +35,8 @@
 
 #pragma once
 
+#include <fstream>
+
 #include "../../common/cutlass_unit_test.h"
 
 #include "cutlass/aligned_buffer.h"

test/unit/gemm/threadblock/mma_planar_complex_testbed.h

@@ -34,6 +34,8 @@
 
 #pragma once
 
+#include <fstream>
+
 #include "../../common/cutlass_unit_test.h"
 
 #include "cutlass/cutlass.h"