CUTLASS 2.1 (#83)

CUTLASS 2.1 contributes:
- BLAS-style host-side API added to CUTLASS Library
- Planar Complex GEMM kernels targeting Volta and Turing Tensor Cores
- Minor enhancements and bug fixes

test/unit/gemm/device/testbed_splitk.h

@@ -26,6 +26,8 @@
     \brief Tests for device-wide GEMM interface
 */
 
+#pragma once
+
 #include <iostream>
 #include <fstream>
 #include <sstream>