Benchmarks: Code Revision - Revise CMake files for microbenchmarks. (#196)

**Description**
1. Do `enable_language(CUDA)` before using `CMAKE_CUDA_COMPILER_VERSION`
2. use `cmake --install` to install target which will call `cmake -P cmake_install.cmake` instead of `make Makefile` to avoid issue `make: *** No rule to make target 'install'.  Stop.`

superbench/benchmarks/build.sh

@@ -3,6 +3,7 @@
 # Copyright (c) Microsoft Corporation - All rights reserved
 # Licensed under the MIT License
 
+set -e
 
 SB_MICRO_PATH="${SB_MICRO_PATH:-/usr/local}"
 
@@ -12,6 +13,7 @@ for dir in micro_benchmarks/*/ ; do
         BUILD_ROOT=$dir/build
         mkdir -p $BUILD_ROOT
         cmake -DCMAKE_INSTALL_PREFIX=$SB_MICRO_PATH -DCMAKE_BUILD_TYPE=Release -S $SOURCE_DIR -B $BUILD_ROOT
-        cmake --build $BUILD_ROOT --target install
+        cmake --build $BUILD_ROOT
+        cmake --install $BUILD_ROOT
     fi
 done

superbench/benchmarks/micro_benchmarks/cublas_function/CMakeLists.txt

@@ -4,9 +4,9 @@
 cmake_minimum_required(VERSION 3.18)
 project(cublas_benchmark LANGUAGES CXX)
 
-include(../cuda_common.cmake)
 find_package(CUDAToolkit QUIET)
 if(CUDAToolkit_FOUND)
+  include(../cuda_common.cmake)
   set(SRC "cublas_helper.cpp" CACHE STRING "source file")
   set(TARGET_NAME "cublas_function" CACHE STRING "target name")
 

superbench/benchmarks/micro_benchmarks/cuda_common.cmake

@@ -6,6 +6,8 @@ if(NOT DEFINED CMAKE_CUDA_STANDARD)
     set(CMAKE_CUDA_STANDARD_REQUIRED ON)
 endif()
 
+enable_language(CUDA)
+
 if(NOT DEFINED NVCC_ARCHS_SUPPORTED)
     # Reference: https://github.com/NVIDIA/cutlass/blob/0e137486498a52954eff239d874ee27ab23358e7/CMakeLists.txt#L89
     set(NVCC_ARCHS_SUPPORTED "")

superbench/benchmarks/micro_benchmarks/cudnn_function/CMakeLists.txt

@@ -4,9 +4,9 @@
 cmake_minimum_required(VERSION 3.18)
 project(cudnn_benchmark LANGUAGES CXX)
 
-include(../cuda_common.cmake)
 find_package(CUDAToolkit QUIET)
 if(CUDAToolkit_FOUND)
+  include(../cuda_common.cmake)
   set(SRC "cudnn_helper.cpp" CACHE STRING "source file")
   set(TARGET_NAME "cudnn_function" CACHE STRING "target name")
 

superbench/benchmarks/micro_benchmarks/gpu_sm_copy_performance/CMakeLists.txt

@@ -5,22 +5,21 @@ cmake_minimum_required(VERSION 3.18)
 
 project(gpu_sm_copy LANGUAGES CXX)
 
-include(../cuda_common.cmake)
 find_package(CUDAToolkit QUIET)
-include(../rocm_common.cmake)
-find_package(HIP QUIET)
 
 # Cuda environment
 if(CUDAToolkit_FOUND)
     message(STATUS "Found CUDA: " ${CUDAToolkit_VERSION})
-    enable_language(CUDA)
 
+    include(../cuda_common.cmake)
     add_executable(gpu_sm_copy gpu_sm_copy.cu)
     set_property(TARGET gpu_sm_copy PROPERTY CUDA_ARCHITECTURES ${NVCC_ARCHS_SUPPORTED})
     install(TARGETS gpu_sm_copy RUNTIME DESTINATION bin)
-
-# ROCm environment
-elseif(HIP_FOUND)
+else()
+    # ROCm environment
+    include(../rocm_common.cmake)
+    find_package(HIP QUIET)
+    if(HIP_FOUND)
         message(STATUS "Found ROCm: " ${HIP_VERSION})
 
         # Convert cuda code to hip code inplace
@@ -33,8 +32,7 @@ elseif(HIP_FOUND)
         hip_add_executable(gpu_sm_copy gpu_sm_copy.cu)
         # Install tergets
         install(TARGETS gpu_sm_copy RUNTIME DESTINATION bin)
-
-else()
+    else()
         message(FATAL_ERROR "No CUDA or ROCm environment found.")
+    endif()
 endif()
-

superbench/benchmarks/micro_benchmarks/kernel_launch_overhead/CMakeLists.txt

@@ -5,22 +5,21 @@ cmake_minimum_required(VERSION 3.18)
 
 project(kernel_launch_overhead LANGUAGES CXX)
 
-include(../cuda_common.cmake)
 find_package(CUDAToolkit QUIET)
-include(../rocm_common.cmake)
-find_package(HIP QUIET)
 
 # Cuda environment
 if(CUDAToolkit_FOUND)
     message(STATUS "Found CUDA: " ${CUDAToolkit_VERSION})
-    enable_language(CUDA)
 
+    include(../cuda_common.cmake)
     add_executable(kernel_launch_overhead kernel_launch.cu)
     set_property(TARGET kernel_launch_overhead PROPERTY CUDA_ARCHITECTURES ${NVCC_ARCHS_SUPPORTED})
     install(TARGETS kernel_launch_overhead RUNTIME DESTINATION bin)
-
-# ROCm environment
-elseif(HIP_FOUND)
+else()
+    # ROCm environment
+    include(../rocm_common.cmake)
+    find_package(HIP QUIET)
+    if(HIP_FOUND)
         message(STATUS "Found HIP: " ${HIP_VERSION})
 
         # Convert cuda code to hip code inplace
@@ -33,8 +32,7 @@ elseif(HIP_FOUND)
         hip_add_executable(kernel_launch_overhead kernel_launch.cu)
         # Install tergets
         install(TARGETS kernel_launch_overhead RUNTIME DESTINATION bin)
-
-else()
+    else()
         message(FATAL_ERROR "No CUDA or ROCm environment found.")
+    endif()
 endif()
-