enhance 64bit builds performance

x11 perf is now close to x86 binary, but its not the case on all algos.

Add also a build.cmd script to remember how to build on windows cmdline

build.cmd

@@ -0,0 +1,4 @@
+REM COMMAND LINE MS BUILD
+REM Note: /m:2 = 2 threads, but for host code only...
+
+msbuild ccminer.vcxproj /m /p:Configuration=Release

ccminer.vcxproj

@@ -90,6 +90,7 @@
       <PreprocessorDefinitions>WIN32;_DEBUG;_CONSOLE;_CRT_SECURE_NO_WARNINGS;CURL_STATICLIB;USE_WRAPNVML;SCRYPT_KECCAK512;SCRYPT_CHACHA;SCRYPT_CHOOSE_COMPILETIME;%(PreprocessorDefinitions)</PreprocessorDefinitions>
       <AdditionalIncludeDirectories>.;compat;compat\curl-for-windows\curl\include;compat\jansson;compat\getopt;compat\pthreads;compat\curl-for-windows\openssl\openssl\include;compat\curl-for-windows\zlib;%(AdditionalIncludeDirectories);$(CudaToolkitIncludeDir)</AdditionalIncludeDirectories>
       <EnableParallelCodeGeneration>true</EnableParallelCodeGeneration>
+      <MultiProcessorCompilation>true</MultiProcessorCompilation>
     </ClCompile>
     <Link>
       <GenerateDebugInformation>true</GenerateDebugInformation>
@@ -118,6 +119,7 @@
       <AdditionalIncludeDirectories>.;compat;compat\curl-for-windows\curl\include;compat\jansson;compat\getopt;compat\pthreads;compat\curl-for-windows\openssl\openssl\include;compat\curl-for-windows\zlib;%(AdditionalIncludeDirectories);$(CudaToolkitIncludeDir)</AdditionalIncludeDirectories>
       <StructMemberAlignment>8Bytes</StructMemberAlignment>
       <EnableParallelCodeGeneration>true</EnableParallelCodeGeneration>
+      <MultiProcessorCompilation>true</MultiProcessorCompilation>
     </ClCompile>
     <Link>
       <GenerateDebugInformation>true</GenerateDebugInformation>
@@ -135,6 +137,7 @@
       <Keep>true</Keep>
       <CodeGeneration>compute_50,sm_50</CodeGeneration>
       <Include>$(NVTOOLSEXT_PATH)\include;..\..\..\Common\C99</Include>
+      <TargetMachinePlatform>64</TargetMachinePlatform>
     </CudaCompile>
     <CudaLink>
       <PerformDeviceLink>false</PerformDeviceLink>
@@ -153,6 +156,7 @@
       <PreprocessorDefinitions>WIN32;NDEBUG;_CONSOLE;_CRT_SECURE_NO_WARNINGS;CURL_STATICLIB;USE_WRAPNVML;SCRYPT_KECCAK512;SCRYPT_CHACHA;SCRYPT_CHOOSE_COMPILETIME;%(PreprocessorDefinitions)</PreprocessorDefinitions>
       <AdditionalIncludeDirectories>.;compat;compat\curl-for-windows\curl\include;compat\jansson;compat\getopt;compat\pthreads;compat\curl-for-windows\openssl\openssl\include;compat\curl-for-windows\zlib;%(AdditionalIncludeDirectories);$(CudaToolkitIncludeDir)</AdditionalIncludeDirectories>
       <EnableParallelCodeGeneration>true</EnableParallelCodeGeneration>
+      <MultiProcessorCompilation>true</MultiProcessorCompilation>
       <ExceptionHandling>SyncCThrow</ExceptionHandling>
     </ClCompile>
     <Link>
@@ -198,6 +202,7 @@
       <IntrinsicFunctions>true</IntrinsicFunctions>
       <PreprocessorDefinitions>WIN32;NDEBUG;_CONSOLE;_CRT_SECURE_NO_WARNINGS;CURL_STATICLIB;USE_WRAPNVML;SCRYPT_KECCAK512;SCRYPT_CHACHA;SCRYPT_CHOOSE_COMPILETIME;%(PreprocessorDefinitions)</PreprocessorDefinitions>
       <AdditionalIncludeDirectories>.;compat;compat\curl-for-windows\curl\include;compat\jansson;compat\getopt;compat\pthreads;compat\curl-for-windows\openssl\openssl\include;compat\curl-for-windows\zlib;%(AdditionalIncludeDirectories);$(CudaToolkitIncludeDir)</AdditionalIncludeDirectories>
+      <MultiProcessorCompilation>true</MultiProcessorCompilation>
     </ClCompile>
     <Link>
       <GenerateDebugInformation>false</GenerateDebugInformation>
@@ -219,6 +224,7 @@
       <CodeGeneration>compute_50,sm_50</CodeGeneration>
       <Include>
       </Include>
+      <TargetMachinePlatform>64</TargetMachinePlatform>
     </CudaCompile>
     <CudaLink>
       <PerformDeviceLink>false</PerformDeviceLink>
@@ -495,4 +501,4 @@
   <Target Name="AfterClean">
     <Delete Files="@(FilesToCopy->'$(OutDir)%(Filename)%(Extension)')" TreatErrorsAsWarnings="true" />
   </Target>
-</Project>
+</Project>