Tweak GEMM kernel (#38)

* add parameters

* tweak gemm

* tweak

* update conv

* update script

* adding bwd 1x1

* update script

* adding 1x1 bwd

* debugging bwd 1x1 failure

* update script

* update script

* test

* test v100

* clean up

[ROCm/composable_kernel commit: b3e8d57d51]

host/host_tensor/include/device.hpp

@@ -2,6 +2,8 @@
 #define DEVICE_HPP
 
 #include <memory>
+#include <thread>
+#include <chrono>
 #include "hip/hip_runtime.h"
 #include "hip/hip_fp16.h"
 
@@ -74,6 +76,8 @@ float launch_and_time_kernel(
 
     timer.End();
 
+    // std::this_thread::sleep_for (std::chrono::microseconds(10));
+
     return timer.GetElapsedTime() / nrepeat;
 }