Updating samples for CUDA 12.4

Samples/3_CUDA_Features/README.md

@@ -74,3 +74,6 @@ A CUDA sample demonstrating tf32 (e8m10) GEMM computation using the Warp Matrix
 ### [warpAggregatedAtomicsCG](./warpAggregatedAtomicsCG)
 This sample demonstrates how using Cooperative Groups (CG) to perform warp aggregated atomics to single and multiple counters, a useful technique to improve performance when many threads atomically add to a single or multiple counters.
 
+### [graphConditionalNodes](./graphConditionalNodes)
+Demonstrate the use of CUDA Graph conditional nodes available starting in CUDA 12.4.
+

Samples/3_CUDA_Features/StreamPriorities/README.md

@@ -28,7 +28,7 @@ cudaMemcpy, cudaStreamCreateWithPriority, cudaDeviceGetStreamPriorityRange, cuda
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 12.3](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
+Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
 Make sure the dependencies mentioned in [Dependencies]() section above are installed.
 
 ## Build and Run

Samples/3_CUDA_Features/bf16TensorCoreGemm/README.md

@@ -30,7 +30,7 @@ cudaMemcpy, cudaFree, cudaGetErrorString, cudaGetLastError, cudaEventSynchronize
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 12.3](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
+Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
 Make sure the dependencies mentioned in [Dependencies]() section above are installed.
 
 ## Build and Run

Samples/3_CUDA_Features/bf16TensorCoreGemm/bf16TensorCoreGemm_vs2017.vcxproj

@@ -38,7 +38,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -107,6 +107,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/bf16TensorCoreGemm/bf16TensorCoreGemm_vs2019.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -103,6 +103,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/bf16TensorCoreGemm/bf16TensorCoreGemm_vs2022.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -103,6 +103,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/binaryPartitionCG/README.md

@@ -27,7 +27,7 @@ cudaStreamCreateWithFlags, cudaFree, cudaMallocHost, cudaFreeHost, cudaStreamSyn
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 12.3](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
+Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
 
 ## Build and Run
 

Samples/3_CUDA_Features/binaryPartitionCG/binaryPartitionCG_vs2017.vcxproj

@@ -38,7 +38,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -107,6 +107,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/binaryPartitionCG/binaryPartitionCG_vs2019.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -103,6 +103,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/binaryPartitionCG/binaryPartitionCG_vs2022.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -103,6 +103,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/bindlessTexture/README.md

@@ -28,7 +28,7 @@ cudaMemcpy, cudaGetMipmappedArrayLevel, cudaGraphicsMapResources, cudaDestroySur
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 12.3](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
+Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
 Make sure the dependencies mentioned in [Dependencies]() section above are installed.
 
 ## Build and Run

Samples/3_CUDA_Features/bindlessTexture/bindlessTexture_vs2017.vcxproj

@@ -38,7 +38,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -118,6 +118,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/bindlessTexture/bindlessTexture_vs2019.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -114,6 +114,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/bindlessTexture/bindlessTexture_vs2022.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -114,6 +114,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/cdpAdvancedQuicksort/README.md

@@ -28,7 +28,7 @@ cudaStreamCreateWithFlags, cudaMemcpy, cudaMemcpyAsync, cudaFree, cudaGetErrorSt
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 12.3](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
+Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
 Make sure the dependencies mentioned in [Dependencies]() section above are installed.
 
 ## Build and Run

Samples/3_CUDA_Features/cdpAdvancedQuicksort/cdpAdvancedQuicksort_vs2017.vcxproj

@@ -38,7 +38,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -72,6 +72,7 @@
       <Include>./;../../../Common</Include>
       <Defines>WIN32</Defines>
       <GenerateRelocatableDeviceCode>true</GenerateRelocatableDeviceCode>
+      <MaxRegCount>64</MaxRegCount>
     </CudaCompile>
   </ItemDefinitionGroup>
   <ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@@ -109,6 +110,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/cdpAdvancedQuicksort/cdpAdvancedQuicksort_vs2019.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -68,6 +68,7 @@
       <Include>./;../../../Common</Include>
       <Defines>WIN32</Defines>
       <GenerateRelocatableDeviceCode>true</GenerateRelocatableDeviceCode>
+      <MaxRegCount>64</MaxRegCount>
     </CudaCompile>
   </ItemDefinitionGroup>
   <ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@@ -105,6 +106,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/cdpAdvancedQuicksort/cdpAdvancedQuicksort_vs2022.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -68,6 +68,7 @@
       <Include>./;../../../Common</Include>
       <Defines>WIN32</Defines>
       <GenerateRelocatableDeviceCode>true</GenerateRelocatableDeviceCode>
+      <MaxRegCount>64</MaxRegCount>
     </CudaCompile>
   </ItemDefinitionGroup>
   <ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@@ -105,6 +106,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/cdpBezierTessellation/README.md

@@ -28,7 +28,7 @@ cudaMemcpy, cudaFree, cudaGetDeviceCount, cudaMalloc, cudaGetDeviceProperties
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 12.3](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
+Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
 Make sure the dependencies mentioned in [Dependencies]() section above are installed.
 
 ## Build and Run

Samples/3_CUDA_Features/cdpBezierTessellation/cdpBezierTessellation_vs2017.vcxproj

@@ -38,7 +38,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -108,6 +108,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/cdpBezierTessellation/cdpBezierTessellation_vs2019.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -104,6 +104,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/cdpBezierTessellation/cdpBezierTessellation_vs2022.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -104,6 +104,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/cdpQuadtree/README.md

@@ -28,7 +28,7 @@ cudaMemcpy, cudaFree, cudaGetLastError, cudaDeviceSetLimit, cudaMalloc, cudaGetD
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 12.3](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
+Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
 Make sure the dependencies mentioned in [Dependencies]() section above are installed.
 
 ## Build and Run

Samples/3_CUDA_Features/cdpQuadtree/cdpQuadtree_vs2017.vcxproj

@@ -38,7 +38,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -108,6 +108,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/cdpQuadtree/cdpQuadtree_vs2019.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -104,6 +104,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/cdpQuadtree/cdpQuadtree_vs2022.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -104,6 +104,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/cdpSimplePrint/README.md

@@ -28,7 +28,7 @@ cudaDeviceSynchronize, cudaGetLastError, cudaGetDeviceProperties, cudaDeviceSetL
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 12.3](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
+Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
 Make sure the dependencies mentioned in [Dependencies]() section above are installed.
 
 ## Build and Run

Samples/3_CUDA_Features/cdpSimplePrint/cdpSimplePrint_vs2017.vcxproj

@@ -38,7 +38,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -108,6 +108,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/cdpSimplePrint/cdpSimplePrint_vs2019.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -104,6 +104,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/cdpSimplePrint/cdpSimplePrint_vs2022.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -104,6 +104,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/cdpSimpleQuicksort/README.md

@@ -28,7 +28,7 @@ cudaStreamCreateWithFlags, cudaMemcpy, cudaStreamDestroy, cudaFree, cudaDeviceSy
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 12.3](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
+Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
 Make sure the dependencies mentioned in [Dependencies]() section above are installed.
 
 ## Build and Run

Samples/3_CUDA_Features/cdpSimpleQuicksort/cdpSimpleQuicksort_vs2017.vcxproj

@@ -38,7 +38,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -108,6 +108,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/cdpSimpleQuicksort/cdpSimpleQuicksort_vs2019.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -104,6 +104,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/cdpSimpleQuicksort/cdpSimpleQuicksort_vs2022.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -104,6 +104,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/cudaCompressibleMemory/README.md

@@ -30,7 +30,7 @@ cudaMemcpy, cudaEventSynchronize, cudaEventRecord, cudaEventElapsedTime, cudaOcc
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 12.3](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
+Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
 
 ## Build and Run
 

Samples/3_CUDA_Features/cudaCompressibleMemory/cudaCompressibleMemory_vs2017.vcxproj

@@ -38,7 +38,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -108,6 +108,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/cudaCompressibleMemory/cudaCompressibleMemory_vs2019.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -104,6 +104,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/cudaCompressibleMemory/cudaCompressibleMemory_vs2022.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -104,6 +104,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/cudaTensorCoreGemm/README.md

@@ -31,7 +31,7 @@ cudaMemcpy, cudaFree, cudaGetErrorString, cudaGetLastError, cudaEventSynchronize
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 12.3](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
+Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
 
 ## Build and Run
 

Samples/3_CUDA_Features/cudaTensorCoreGemm/cudaTensorCoreGemm_vs2017.vcxproj

@@ -38,7 +38,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -71,6 +71,7 @@
       <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
       <Include>./;../../../Common</Include>
       <Defines>WIN32</Defines>
+      <MaxRegCount>255</MaxRegCount>
     </CudaCompile>
   </ItemDefinitionGroup>
   <ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@@ -107,6 +108,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/cudaTensorCoreGemm/cudaTensorCoreGemm_vs2019.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -67,6 +67,7 @@
       <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
       <Include>./;../../../Common</Include>
       <Defines>WIN32</Defines>
+      <MaxRegCount>255</MaxRegCount>
     </CudaCompile>
   </ItemDefinitionGroup>
   <ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@@ -103,6 +104,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/cudaTensorCoreGemm/cudaTensorCoreGemm_vs2022.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -67,6 +67,7 @@
       <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
       <Include>./;../../../Common</Include>
       <Defines>WIN32</Defines>
+      <MaxRegCount>255</MaxRegCount>
     </CudaCompile>
   </ItemDefinitionGroup>
   <ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@@ -103,6 +104,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/dmmaTensorCoreGemm/README.md

@@ -30,7 +30,7 @@ cudaMemcpy, cudaFree, cudaGetErrorString, cudaGetLastError, cudaEventSynchronize
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 12.3](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
+Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
 Make sure the dependencies mentioned in [Dependencies]() section above are installed.
 
 ## Build and Run

Samples/3_CUDA_Features/dmmaTensorCoreGemm/dmmaTensorCoreGemm_vs2017.vcxproj

@@ -38,7 +38,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -107,6 +107,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/dmmaTensorCoreGemm/dmmaTensorCoreGemm_vs2019.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -103,6 +103,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/dmmaTensorCoreGemm/dmmaTensorCoreGemm_vs2022.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -103,6 +103,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/globalToShmemAsyncCopy/README.md

@@ -30,7 +30,7 @@ cudaStreamCreateWithFlags, cudaMalloc, cudaDeviceGetAttribute, cudaFree, cudaMal
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 12.3](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
+Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
 Make sure the dependencies mentioned in [Dependencies]() section above are installed.
 
 ## Build and Run

Samples/3_CUDA_Features/globalToShmemAsyncCopy/globalToShmemAsyncCopy_vs2017.vcxproj

@@ -38,7 +38,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -107,6 +107,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/globalToShmemAsyncCopy/globalToShmemAsyncCopy_vs2019.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -103,6 +103,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/globalToShmemAsyncCopy/globalToShmemAsyncCopy_vs2022.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -103,6 +103,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/graphMemoryFootprint/README.md

@@ -27,7 +27,7 @@ cudaGraphAddMemAllocNode, cudaStreamCreateWithFlags, cudaGraphInstantiate, cudaS
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 12.3](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
+Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
 
 ## Build and Run
 

Samples/3_CUDA_Features/graphMemoryFootprint/graphMemoryFootprint_vs2017.vcxproj

@@ -38,7 +38,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -107,6 +107,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/graphMemoryFootprint/graphMemoryFootprint_vs2019.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -103,6 +103,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/graphMemoryFootprint/graphMemoryFootprint_vs2022.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -103,6 +103,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/graphMemoryNodes/README.md

@@ -27,7 +27,7 @@ cudaMemcpy, cudaDeviceGetAttribute, cudaDriverGetVersion, cudaGraphLaunch, cudaE
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 12.3](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
+Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
 
 ## Build and Run
 

Samples/3_CUDA_Features/graphMemoryNodes/graphMemoryNodes_vs2017.vcxproj

@@ -38,7 +38,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -107,6 +107,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/graphMemoryNodes/graphMemoryNodes_vs2019.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -103,6 +103,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/graphMemoryNodes/graphMemoryNodes_vs2022.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -103,6 +103,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/immaTensorCoreGemm/README.md

@@ -27,7 +27,7 @@ cudaMemcpy, cudaFree, cudaGetErrorString, cudaGetLastError, cudaEventSynchronize
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 12.3](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
+Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
 
 ## Build and Run
 

Samples/3_CUDA_Features/immaTensorCoreGemm/immaTensorCoreGemm_vs2017.vcxproj

@@ -38,7 +38,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -71,6 +71,7 @@
       <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
       <Include>./;../../../Common</Include>
       <Defines>WIN32</Defines>
+      <MaxRegCount>255</MaxRegCount>
     </CudaCompile>
   </ItemDefinitionGroup>
   <ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@@ -107,6 +108,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/immaTensorCoreGemm/immaTensorCoreGemm_vs2019.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -67,6 +67,7 @@
       <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
       <Include>./;../../../Common</Include>
       <Defines>WIN32</Defines>
+      <MaxRegCount>255</MaxRegCount>
     </CudaCompile>
   </ItemDefinitionGroup>
   <ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@@ -103,6 +104,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/immaTensorCoreGemm/immaTensorCoreGemm_vs2022.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -67,6 +67,7 @@
       <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
       <Include>./;../../../Common</Include>
       <Defines>WIN32</Defines>
+      <MaxRegCount>255</MaxRegCount>
     </CudaCompile>
   </ItemDefinitionGroup>
   <ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@@ -103,6 +104,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/jacobiCudaGraphs/README.md

@@ -25,7 +25,7 @@ cudaExtent, cudaGraphLaunch, cudaGraphAddMemcpyNode, cudaMallocHost, cudaPitched
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 12.3](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
+Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
 
 ## Build and Run
 

Samples/3_CUDA_Features/jacobiCudaGraphs/jacobiCudaGraphs_vs2017.vcxproj

@@ -38,7 +38,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -108,6 +108,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/jacobiCudaGraphs/jacobiCudaGraphs_vs2019.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -104,6 +104,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/jacobiCudaGraphs/jacobiCudaGraphs_vs2022.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -104,6 +104,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/memMapIPCDrv/README.md

@@ -30,7 +30,7 @@ cuDeviceCanAccessPeer, cuMemImportFromShareableHandle, cuModuleLoadDataEx, cuMod
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 12.3](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
+Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
 Make sure the dependencies mentioned in [Dependencies]() section above are installed.
 
 ## Build and Run

Samples/3_CUDA_Features/memMapIPCDrv/memMapIPCDrv_vs2017.vcxproj

@@ -38,7 +38,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -112,6 +112,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/memMapIPCDrv/memMapIPCDrv_vs2019.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -108,6 +108,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/memMapIPCDrv/memMapIPCDrv_vs2022.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -108,6 +108,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/newdelete/README.md

@@ -27,7 +27,7 @@ cudaMemcpy, cudaFree, cudaDeviceSynchronize, cudaDeviceSetLimit, cudaMalloc
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 12.3](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
+Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
 
 ## Build and Run
 

Samples/3_CUDA_Features/newdelete/newdelete_vs2017.vcxproj

@@ -38,7 +38,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -107,6 +107,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/newdelete/newdelete_vs2019.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -103,6 +103,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/newdelete/newdelete_vs2022.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -103,6 +103,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/ptxjit/README.md

@@ -30,7 +30,7 @@ cudaMalloc, cudaDriverGetVersion, cudaMemcpy, cudaFree
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 12.3](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
+Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
 
 ## Build and Run
 

Samples/3_CUDA_Features/ptxjit/ptxjit_vs2017.vcxproj

@@ -38,7 +38,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -111,6 +111,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/ptxjit/ptxjit_vs2019.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -107,6 +107,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/ptxjit/ptxjit_vs2022.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -107,6 +107,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/simpleCudaGraphs/README.md

@@ -25,7 +25,7 @@ cudaGraphClone, cudaExtent, cudaGraphLaunch, cudaStreamCreate, cudaLaunchHostFun
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 12.3](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
+Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
 
 ## Build and Run
 

Samples/3_CUDA_Features/simpleCudaGraphs/simpleCudaGraphs_vs2017.vcxproj

@@ -38,7 +38,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -107,6 +107,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/simpleCudaGraphs/simpleCudaGraphs_vs2019.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -103,6 +103,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/simpleCudaGraphs/simpleCudaGraphs_vs2022.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -103,6 +103,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/tf32TensorCoreGemm/README.md

@@ -30,7 +30,7 @@ cudaMemcpy, cudaFree, cudaGetErrorString, cudaGetLastError, cudaEventSynchronize
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 12.3](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
+Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
 Make sure the dependencies mentioned in [Dependencies]() section above are installed.
 
 ## Build and Run

Samples/3_CUDA_Features/tf32TensorCoreGemm/tf32TensorCoreGemm_vs2017.vcxproj

@@ -38,7 +38,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -71,6 +71,7 @@
       <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
       <Include>./;../../../Common</Include>
       <Defines>WIN32</Defines>
+      <MaxRegCount>128</MaxRegCount>
     </CudaCompile>
   </ItemDefinitionGroup>
   <ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@@ -107,6 +108,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/tf32TensorCoreGemm/tf32TensorCoreGemm_vs2019.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -67,6 +67,7 @@
       <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
       <Include>./;../../../Common</Include>
       <Defines>WIN32</Defines>
+      <MaxRegCount>128</MaxRegCount>
     </CudaCompile>
   </ItemDefinitionGroup>
   <ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@@ -103,6 +104,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/tf32TensorCoreGemm/tf32TensorCoreGemm_vs2022.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -67,6 +67,7 @@
       <AdditionalOptions>-Xcompiler "/wd 4819"  --threads 0 </AdditionalOptions>
       <Include>./;../../../Common</Include>
       <Defines>WIN32</Defines>
+      <MaxRegCount>128</MaxRegCount>
     </CudaCompile>
   </ItemDefinitionGroup>
   <ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@@ -103,6 +104,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/warpAggregatedAtomicsCG/README.md

@@ -25,7 +25,7 @@ cudaMemcpy, cudaFree, cudaDeviceGetAttribute, cudaMemset, cudaMalloc
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 12.3](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
+Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
 
 ## Build and Run
 

Samples/3_CUDA_Features/warpAggregatedAtomicsCG/warpAggregatedAtomicsCG_vs2017.vcxproj

@@ -38,7 +38,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -107,6 +107,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/warpAggregatedAtomicsCG/warpAggregatedAtomicsCG_vs2019.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -103,6 +103,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>

Samples/3_CUDA_Features/warpAggregatedAtomicsCG/warpAggregatedAtomicsCG_vs2022.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -103,6 +103,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.3.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
   </ImportGroup>
 </Project>