Add and update samples for cuda 11.1 support

Common/helper_cuda.h

@@ -664,6 +664,7 @@ inline int _ConvertSMVer2Cores(int major, int minor) {
       {0x72,  64},
       {0x75,  64},
       {0x80,  64},
+      {0x86, 128},
       {-1, -1}};
 
   int index = 0;
@@ -709,6 +710,7 @@ inline const char* _ConvertSMVer2ArchName(int major, int minor) {
       {0x72, "Xavier"},
       {0x75, "Turing"},
       {0x80, "Ampere"},
+      {0x86, "Ampere"},
       {-1, "Graphics Device"}};
 
   int index = 0;

Common/helper_cuda_drvapi.h

@@ -33,8 +33,10 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
+#include <iostream>
+#include <cstring>
+#include <sstream>
 
-#include <drvapi_error_string.h>
 #include <helper_string.h>
 
 #ifndef MAX
@@ -66,48 +68,22 @@ inline int ftoi(float value) {
 // These are the inline versions for all of the SDK helper functions
 inline void __checkCudaErrors(CUresult err, const char *file, const int line) {
   if (CUDA_SUCCESS != err) {
+    const char *errorStr = NULL;
+    cuGetErrorString(err, &errorStr);
     fprintf(stderr,
             "checkCudaErrors() Driver API error = %04d \"%s\" from file <%s>, "
             "line %i.\n",
-            err, getCudaDrvErrorString(err), file, line);
+            err, errorStr, file, line);
     exit(EXIT_FAILURE);
   }
 }
 #endif
 
-#ifdef getLastCudaDrvErrorMsg
-#undef getLastCudaDrvErrorMsg
-#endif
-
-#define getLastCudaDrvErrorMsg(msg) \
-  __getLastCudaDrvErrorMsg(msg, __FILE__, __LINE__)
-
-inline void __getLastCudaDrvErrorMsg(const char *msg, const char *file,
-                                     const int line) {
-  CUresult err = cuCtxSynchronize();
-
-  if (CUDA_SUCCESS != err) {
-    fprintf(stderr, "getLastCudaDrvErrorMsg -> %s", msg);
-    fprintf(stderr,
-            "getLastCudaDrvErrorMsg -> cuCtxSynchronize API error = %04d "
-            "\"%s\" in file <%s>, line %i.\n",
-            err, getCudaDrvErrorString(err), file, line);
-    exit(EXIT_FAILURE);
-  }
-}
-
 // This function wraps the CUDA Driver API into a template function
 template <class T>
 inline void getCudaAttribute(T *attribute, CUdevice_attribute device_attribute,
                              int device) {
-  CUresult error_result =
+  checkCudaErrors(cuDeviceGetAttribute(attribute, device_attribute, device));
-      cuDeviceGetAttribute(attribute, device_attribute, device);
-
-  if (error_result != CUDA_SUCCESS) {
-    printf("cuDeviceGetAttribute returned %d\n-> %s\n",
-           static_cast<int>(error_result), getCudaDrvErrorString(error_result));
-    exit(EXIT_SUCCESS);
-  }
 }
 #endif
 
@@ -135,6 +111,8 @@ inline int _ConvertSMVer2CoresDRV(int major, int minor) {
       {0x70,  64},
       {0x72,  64},
       {0x75,  64},
+      {0x80,  64},
+      {0x86, 128},
       {-1, -1}};
 
   int index = 0;
@@ -161,11 +139,9 @@ inline int _ConvertSMVer2CoresDRV(int major, int minor) {
 inline int gpuDeviceInitDRV(int ARGC, const char **ARGV) {
   int cuDevice = 0;
   int deviceCount = 0;
-  CUresult err = cuInit(0);
+  checkCudaErrors(cuInit(0));
 
-  if (CUDA_SUCCESS == err) {
   checkCudaErrors(cuDeviceGetCount(&deviceCount));
-  }
 
   if (deviceCount == 0) {
     fprintf(stderr, "cudaDeviceInit error: no devices supporting CUDA\n");
@@ -192,7 +168,7 @@ inline int gpuDeviceInitDRV(int ARGC, const char **ARGV) {
 
   checkCudaErrors(cuDeviceGet(&cuDevice, dev));
   char name[100];
-  cuDeviceGetName(name, 100, cuDevice);
+  checkCudaErrors(cuDeviceGetName(name, 100, cuDevice));
 
   int computeMode;
   getCudaAttribute<int>(&computeMode, CU_DEVICE_ATTRIBUTE_COMPUTE_MODE, dev);
@@ -218,7 +194,6 @@ inline int gpuGetMaxGflopsDeviceIdDRV() {
   int device_count = 0;
   int sm_per_multiproc = 0;
   unsigned long long max_compute_perf = 0;
-  int best_SM_arch = 0;
   int major = 0;
   int minor = 0;
   int multiProcessorCount;
@@ -234,19 +209,6 @@ inline int gpuGetMaxGflopsDeviceIdDRV() {
     exit(EXIT_FAILURE);
   }
 
-  // Find the best major SM Architecture GPU device
-  while (current_device < device_count) {
-    checkCudaErrors(cuDeviceGetAttribute(
-        &major, CU_DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR, current_device));
-    checkCudaErrors(cuDeviceGetAttribute(
-        &minor, CU_DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR, current_device));
-    if (major > 0 && major < 9999) {
-      best_SM_arch = MAX(best_SM_arch, major);
-    }
-
-    current_device++;
-  }
-
   // Find the best CUDA capable GPU device
   current_device = 0;
 
@@ -277,18 +239,9 @@ inline int gpuGetMaxGflopsDeviceIdDRV() {
                                clockRate);
 
       if (compute_perf > max_compute_perf) {
-        // If we find GPU with SM major > 2, search only these
-        if (best_SM_arch > 2) {
-          // If our device==dest_SM_arch, choose this, or else pass
-          if (major == best_SM_arch) {
           max_compute_perf = compute_perf;
           max_perf_device = current_device;
       }
-        } else {
-          max_compute_perf = compute_perf;
-          max_perf_device = current_device;
-        }
-      }
     } else {
       devices_prohibited++;
     }
@@ -414,7 +367,39 @@ inline bool checkCudaCapabilitiesDRV(int major_version, int minor_version,
   }
 }
 #endif
+bool inline findFatbinPath(const char *module_file, std::string &module_path, char **argv, std::ostringstream &ostrm)
+{
+    char *actual_path = sdkFindFilePath(module_file, argv[0]);
+
+    if (actual_path)
+    {
+        module_path = actual_path;
+    }
+    else
+    {
+        printf("> findModulePath file not found: <%s> \n", module_file);
+        return false;
+    }
+
+    if (module_path.empty())
+    {
+        printf("> findModulePath could not find file: <%s> \n", module_file);
+        return false;
+    }
+    else
+    {
+        printf("> findModulePath found file at <%s>\n", module_path.c_str());
+        if (module_path.rfind("fatbin") != std::string::npos)
+        {
+            std::ifstream fileIn(module_path.c_str(), std::ios::binary);
+            ostrm << fileIn.rdbuf();
+            fileIn.close();
+        }
+        return true;
+    }
+}
 
   // end of CUDA Helper Functions
 
 #endif  // COMMON_HELPER_CUDA_DRVAPI_H_
+

Common/helper_string.h

@@ -293,6 +293,9 @@ inline char *sdkFindFilePath(const char *filename,
       "../../../../Samples/<executable_name>/data/",  // up 4 in tree
       "../../../Samples/<executable_name>/data/",     // up 3 in tree
       "../../Samples/<executable_name>/data/",        // up 2 in tree
+      "../../../../Common/data/",                     // up 4 in tree
+      "../../../Common/data",                         // up 3 in tree
+      "../../Common/data/"                            // up 2 in tree
   };
 
   // Extract the executable name

Common/nvrtc_helper.h

@@ -47,8 +47,8 @@
     }                                                           \
   } while (0)
 
-void compileFileToPTX(char *filename, int argc, char **argv, char **ptxResult,
+void compileFileToCUBIN(char *filename, int argc, char **argv, char **cubinResult,
-                      size_t *ptxResultSize, int requiresCGheaders) {
+                      size_t *cubinResultSize, int requiresCGheaders) {
   std::ifstream inputFile(filename,
                           std::ios::in | std::ios::binary | std::ios::ate);
 
@@ -83,9 +83,9 @@ void compileFileToPTX(char *filename, int argc, char **argv, char **ptxResult,
       &minor, CU_DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR, cuDevice));
   
   {
-  // Compile for the GPU arch on which are going to run cuda kernel.
+  // Compile cubin for the GPU arch on which are going to run cuda kernel.
   std::string compileOptions;
-  compileOptions = "--gpu-architecture=compute_";
+  compileOptions = "--gpu-architecture=sm_";
 
   compileParams[numCompileOptions] = reinterpret_cast<char *>(
                   malloc(sizeof(char) * (compileOptions.length() + 10)));
@@ -158,21 +158,20 @@ void compileFileToPTX(char *filename, int argc, char **argv, char **ptxResult,
   free(log);
 
   NVRTC_SAFE_CALL("nvrtcCompileProgram", res);
-  // fetch PTX
+
-  size_t ptxSize;
+  size_t codeSize;
-  NVRTC_SAFE_CALL("nvrtcGetPTXSize", nvrtcGetPTXSize(prog, &ptxSize));
+  NVRTC_SAFE_CALL("nvrtcGetCUBINSize", nvrtcGetCUBINSize(prog, &codeSize));
-  char *ptx = reinterpret_cast<char *>(malloc(sizeof(char) * ptxSize));
+  char *code = new char[codeSize];
-  NVRTC_SAFE_CALL("nvrtcGetPTX", nvrtcGetPTX(prog, ptx));
+  NVRTC_SAFE_CALL("nvrtcGetCUBIN", nvrtcGetCUBIN(prog, code));
-  NVRTC_SAFE_CALL("nvrtcDestroyProgram", nvrtcDestroyProgram(&prog));
+  *cubinResult = code;
-  *ptxResult = ptx;
+  *cubinResultSize = codeSize;
-  *ptxResultSize = ptxSize;
 
   for (int i = 0; i < numCompileOptions; i++) {
     free(compileParams[i]);
   }
 }
 
-CUmodule loadPTX(char *ptx, int argc, char **argv) {
+CUmodule loadCUBIN(char *cubin, int argc, char **argv) {
   CUmodule module;
   CUcontext context;
   int major = 0, minor = 0;
@@ -190,11 +189,10 @@ CUmodule loadPTX(char *ptx, int argc, char **argv) {
   printf("> GPU Device has SM %d.%d compute capability\n", major, minor);
 
   checkCudaErrors(cuInit(0));
-  checkCudaErrors(cuDeviceGet(&cuDevice, 0));
   checkCudaErrors(cuCtxCreate(&context, 0, cuDevice));
 
-  checkCudaErrors(cuModuleLoadDataEx(&module, ptx, 0, 0, 0));
+  checkCudaErrors(cuModuleLoadData(&module, cubin));
-  free(ptx);
+  free(cubin);
 
   return module;
 }

README.md

@@ -1,11 +1,20 @@
 # CUDA Samples
 
-Samples for CUDA Developers which demonstrates features in CUDA Toolkit. This version supports [CUDA Toolkit 11.0](https://developer.nvidia.com/cuda-downloads).
+Samples for CUDA Developers which demonstrates features in CUDA Toolkit. This version supports [CUDA Toolkit 11.1](https://developer.nvidia.com/cuda-downloads).
 
 ## Release Notes
 
 This section describes the release notes for the CUDA Samples on GitHub only.
 
+### CUDA 11.1
+*  Added `watershedSegmentationNPP`. Demonstrates how to use the NPP watershed segmentation function.
+*  Added `batchedLabelMarkersAndLabelCompressionNPP`. Demonstrates how to use the NPP label markers generation and label compression functions based on a Union Find (UF) algorithm including both single image and batched image versions.
+*  Dropped Visual Studio 2012, 2013 support from all the windows supported samples.
+*  Added kernel performing warp aggregated atomic max in multi buckets using cg::labeled_partition & cg::reduce in `warpAggregatedAtomicsCG`.
+*  Added extended CG shuffle mechanics to `shfl_scan` sample.
+*  Added `cudaOpenMP`. Demonstrates how to use OpenMP API to write an application for multiple GPUs.
+*  Added `simpleZeroCopy`. Demonstrates how to use zero copy, kernels can read and write directly to pinned system memory.
+
 ### CUDA 11.0
 *  Added `dmmaTensorCoreGemm`. Demonstrates double precision GEMM computation using the Double precision Warp Matrix Multiply and Accumulate (WMMA) API introduced with CUDA 11 in Ampere chip family tensor cores.
 *  Added `bf16TensorCoreGemm`. Demonstrates __nv_bfloat16 (e8m7) GEMM computation using the __nv_bfloat16 WMMA API introduced with CUDA 11 in Ampere chip family tensor cores.
@@ -84,7 +93,7 @@ This is the first release of CUDA Samples on GitHub:
 
 ### Prerequisites
 
-Download and install the [CUDA Toolkit 11.0](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
+Download and install the [CUDA Toolkit 11.1](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
 For system requirements and installation instructions of cuda toolkit, please refer to the [Linux Installation Guide](http://docs.nvidia.com/cuda/cuda-installation-guide-linux/), and the [Windows Installation Guide](http://docs.nvidia.com/cuda/cuda-installation-guide-microsoft-windows/index.html).
 
 ### Getting the CUDA Samples
@@ -144,31 +153,33 @@ The samples makefiles can take advantage of certain options:
 **[warpAggregatedAtomicsCG](./Samples/warpAggregatedAtomicsCG)** | **[boxFilterNPP](./Samples/boxFilterNPP)** | **[binaryPartitionCG](./Samples/binaryPartitionCG)** | **[dmmaTensorCoreGemm](./Samples/dmmaTensorCoreGemm)** |
 ---|---|---|---|
 **[EGLStream_CUDA_Interop](./Samples/EGLStream_CUDA_Interop)** | **[conjugateGradientMultiBlockCG](./Samples/conjugateGradientMultiBlockCG)** | **[simpleIPC](./Samples/simpleIPC)** | **[memMapIPCDrv](./Samples/memMapIPCDrv)** |
-**[vectorAddMMAP](./Samples/vectorAddMMAP)** | **[shfl_scan](./Samples/shfl_scan)** | **[conjugateGradientCudaGraphs](./Samples/conjugateGradientCudaGraphs)** | **[globalToShmemAsyncCopy](./Samples/globalToShmemAsyncCopy)** |
+**[vectorAddMMAP](./Samples/vectorAddMMAP)** | **[shfl_scan](./Samples/shfl_scan)** | **[simpleZeroCopy](./Samples/simpleZeroCopy)** | **[conjugateGradientCudaGraphs](./Samples/conjugateGradientCudaGraphs)** |
-**[nvJPEG](./Samples/nvJPEG)** | **[simpleCudaGraphs](./Samples/simpleCudaGraphs)** | **[deviceQuery](./Samples/deviceQuery)** | **[simpleVoteIntrinsics](./Samples/simpleVoteIntrinsics)** |
+**[globalToShmemAsyncCopy](./Samples/globalToShmemAsyncCopy)** | **[nvJPEG](./Samples/nvJPEG)** | **[batchedLabelMarkersAndLabelCompressionNPP](./Samples/batchedLabelMarkersAndLabelCompressionNPP)** | **[watershedSegmentationNPP](./Samples/watershedSegmentationNPP)** |
-**[simpleCUBLASXT](./Samples/simpleCUBLASXT)** | **[simpleAttributes](./Samples/simpleAttributes)** | **[cudaNvSci](./Samples/cudaNvSci)** | **[tf32TensorCoreGemm](./Samples/tf32TensorCoreGemm)** |
+**[simpleCudaGraphs](./Samples/simpleCudaGraphs)** | **[deviceQuery](./Samples/deviceQuery)** | **[simpleVoteIntrinsics](./Samples/simpleVoteIntrinsics)** | **[simpleCUBLASXT](./Samples/simpleCUBLASXT)** |
-**[UnifiedMemoryPerf](./Samples/UnifiedMemoryPerf)** | **[cudaCompressibleMemory](./Samples/cudaCompressibleMemory)** | **[bf16TensorCoreGemm](./Samples/bf16TensorCoreGemm)** | **[cuSolverDn_LinearSolver](./Samples/cuSolverDn_LinearSolver)** |
+**[simpleAttributes](./Samples/simpleAttributes)** | **[cudaNvSci](./Samples/cudaNvSci)** | **[tf32TensorCoreGemm](./Samples/tf32TensorCoreGemm)** | **[UnifiedMemoryPerf](./Samples/UnifiedMemoryPerf)** |
-**[vulkanImageCUDA](./Samples/vulkanImageCUDA)** | **[conjugateGradientMultiDeviceCG](./Samples/conjugateGradientMultiDeviceCG)** | **[matrixMulDrv](./Samples/matrixMulDrv)** | **[cuSolverSp_LinearSolver](./Samples/cuSolverSp_LinearSolver)** |
+**[cudaCompressibleMemory](./Samples/cudaCompressibleMemory)** | **[bf16TensorCoreGemm](./Samples/bf16TensorCoreGemm)** | **[cuSolverDn_LinearSolver](./Samples/cuSolverDn_LinearSolver)** | **[vulkanImageCUDA](./Samples/vulkanImageCUDA)** |
-**[simpleCUFFT](./Samples/simpleCUFFT)** | **[reduction](./Samples/reduction)** | **[nvJPEG_encoder](./Samples/nvJPEG_encoder)** | **[simpleDrvRuntime](./Samples/simpleDrvRuntime)** |
+**[conjugateGradientMultiDeviceCG](./Samples/conjugateGradientMultiDeviceCG)** | **[matrixMulDrv](./Samples/matrixMulDrv)** | **[cuSolverSp_LinearSolver](./Samples/cuSolverSp_LinearSolver)** | **[simpleCUFFT](./Samples/simpleCUFFT)** |
-**[MersenneTwisterGP11213](./Samples/MersenneTwisterGP11213)** | **[simpleAWBarrier](./Samples/simpleAWBarrier)** | **[immaTensorCoreGemm](./Samples/immaTensorCoreGemm)** | **[bandwidthTest](./Samples/bandwidthTest)** |
+**[reduction](./Samples/reduction)** | **[nvJPEG_encoder](./Samples/nvJPEG_encoder)** | **[simpleDrvRuntime](./Samples/simpleDrvRuntime)** | **[MersenneTwisterGP11213](./Samples/MersenneTwisterGP11213)** |
-**[concurrentKernels](./Samples/concurrentKernels)** | **[simpleCUBLAS](./Samples/simpleCUBLAS)** | **[NV12toBGRandResize](./Samples/NV12toBGRandResize)** | **[cudaTensorCoreGemm](./Samples/cudaTensorCoreGemm)** |
+**[simpleAWBarrier](./Samples/simpleAWBarrier)** | **[immaTensorCoreGemm](./Samples/immaTensorCoreGemm)** | **[bandwidthTest](./Samples/bandwidthTest)** | **[concurrentKernels](./Samples/concurrentKernels)** |
-**[jacobiCudaGraphs](./Samples/jacobiCudaGraphs)** | **[simpleVulkan](./Samples/simpleVulkan)** | **[vectorAdd_nvrtc](./Samples/vectorAdd_nvrtc)** | **[cannyEdgeDetectorNPP](./Samples/cannyEdgeDetectorNPP)** |
+**[simpleCUBLAS](./Samples/simpleCUBLAS)** | **[NV12toBGRandResize](./Samples/NV12toBGRandResize)** | **[cudaTensorCoreGemm](./Samples/cudaTensorCoreGemm)** | **[jacobiCudaGraphs](./Samples/jacobiCudaGraphs)** |
-**[p2pBandwidthLatencyTest](./Samples/p2pBandwidthLatencyTest)** | **[simpleVulkanMMAP](./Samples/simpleVulkanMMAP)** | **[matrixMul](./Samples/matrixMul)** | **[systemWideAtomics](./Samples/systemWideAtomics)** |
+**[simpleVulkan](./Samples/simpleVulkan)** | **[vectorAdd_nvrtc](./Samples/vectorAdd_nvrtc)** | **[cannyEdgeDetectorNPP](./Samples/cannyEdgeDetectorNPP)** | **[p2pBandwidthLatencyTest](./Samples/p2pBandwidthLatencyTest)** |
+**[simpleVulkanMMAP](./Samples/simpleVulkanMMAP)** | **[cudaOpenMP](./Samples/cudaOpenMP)** | **[matrixMul](./Samples/matrixMul)** | **[systemWideAtomics](./Samples/systemWideAtomics)** |
 
 #### Windows
 **[warpAggregatedAtomicsCG](./Samples/warpAggregatedAtomicsCG)** | **[boxFilterNPP](./Samples/boxFilterNPP)** | **[binaryPartitionCG](./Samples/binaryPartitionCG)** | **[dmmaTensorCoreGemm](./Samples/dmmaTensorCoreGemm)** |
 ---|---|---|---|
 **[conjugateGradientMultiBlockCG](./Samples/conjugateGradientMultiBlockCG)** | **[simpleIPC](./Samples/simpleIPC)** | **[memMapIPCDrv](./Samples/memMapIPCDrv)** | **[vectorAddMMAP](./Samples/vectorAddMMAP)** |
-**[shfl_scan](./Samples/shfl_scan)** | **[conjugateGradientCudaGraphs](./Samples/conjugateGradientCudaGraphs)** | **[globalToShmemAsyncCopy](./Samples/globalToShmemAsyncCopy)** | **[nvJPEG](./Samples/nvJPEG)** |
+**[shfl_scan](./Samples/shfl_scan)** | **[simpleZeroCopy](./Samples/simpleZeroCopy)** | **[conjugateGradientCudaGraphs](./Samples/conjugateGradientCudaGraphs)** | **[globalToShmemAsyncCopy](./Samples/globalToShmemAsyncCopy)** |
-**[simpleD3D12](./Samples/simpleD3D12)** | **[simpleCudaGraphs](./Samples/simpleCudaGraphs)** | **[deviceQuery](./Samples/deviceQuery)** | **[simpleVoteIntrinsics](./Samples/simpleVoteIntrinsics)** |
+**[nvJPEG](./Samples/nvJPEG)** | **[batchedLabelMarkersAndLabelCompressionNPP](./Samples/batchedLabelMarkersAndLabelCompressionNPP)** | **[simpleD3D12](./Samples/simpleD3D12)** | **[watershedSegmentationNPP](./Samples/watershedSegmentationNPP)** |
-**[simpleCUBLASXT](./Samples/simpleCUBLASXT)** | **[simpleAttributes](./Samples/simpleAttributes)** | **[tf32TensorCoreGemm](./Samples/tf32TensorCoreGemm)** | **[UnifiedMemoryPerf](./Samples/UnifiedMemoryPerf)** |
+**[simpleCudaGraphs](./Samples/simpleCudaGraphs)** | **[deviceQuery](./Samples/deviceQuery)** | **[simpleVoteIntrinsics](./Samples/simpleVoteIntrinsics)** | **[simpleCUBLASXT](./Samples/simpleCUBLASXT)** |
-**[cudaCompressibleMemory](./Samples/cudaCompressibleMemory)** | **[bf16TensorCoreGemm](./Samples/bf16TensorCoreGemm)** | **[cuSolverDn_LinearSolver](./Samples/cuSolverDn_LinearSolver)** | **[vulkanImageCUDA](./Samples/vulkanImageCUDA)** |
+**[simpleAttributes](./Samples/simpleAttributes)** | **[tf32TensorCoreGemm](./Samples/tf32TensorCoreGemm)** | **[UnifiedMemoryPerf](./Samples/UnifiedMemoryPerf)** | **[cudaCompressibleMemory](./Samples/cudaCompressibleMemory)** |
-**[conjugateGradientMultiDeviceCG](./Samples/conjugateGradientMultiDeviceCG)** | **[matrixMulDrv](./Samples/matrixMulDrv)** | **[cuSolverSp_LinearSolver](./Samples/cuSolverSp_LinearSolver)** | **[simpleCUFFT](./Samples/simpleCUFFT)** |
+**[bf16TensorCoreGemm](./Samples/bf16TensorCoreGemm)** | **[cuSolverDn_LinearSolver](./Samples/cuSolverDn_LinearSolver)** | **[vulkanImageCUDA](./Samples/vulkanImageCUDA)** | **[conjugateGradientMultiDeviceCG](./Samples/conjugateGradientMultiDeviceCG)** |
-**[reduction](./Samples/reduction)** | **[nvJPEG_encoder](./Samples/nvJPEG_encoder)** | **[simpleDrvRuntime](./Samples/simpleDrvRuntime)** | **[simpleD3D11](./Samples/simpleD3D11)** |
+**[matrixMulDrv](./Samples/matrixMulDrv)** | **[cuSolverSp_LinearSolver](./Samples/cuSolverSp_LinearSolver)** | **[simpleCUFFT](./Samples/simpleCUFFT)** | **[reduction](./Samples/reduction)** |
-**[MersenneTwisterGP11213](./Samples/MersenneTwisterGP11213)** | **[simpleAWBarrier](./Samples/simpleAWBarrier)** | **[immaTensorCoreGemm](./Samples/immaTensorCoreGemm)** | **[bandwidthTest](./Samples/bandwidthTest)** |
+**[nvJPEG_encoder](./Samples/nvJPEG_encoder)** | **[simpleDrvRuntime](./Samples/simpleDrvRuntime)** | **[simpleD3D11](./Samples/simpleD3D11)** | **[MersenneTwisterGP11213](./Samples/MersenneTwisterGP11213)** |
-**[concurrentKernels](./Samples/concurrentKernels)** | **[simpleCUBLAS](./Samples/simpleCUBLAS)** | **[NV12toBGRandResize](./Samples/NV12toBGRandResize)** | **[cudaTensorCoreGemm](./Samples/cudaTensorCoreGemm)** |
+**[simpleAWBarrier](./Samples/simpleAWBarrier)** | **[immaTensorCoreGemm](./Samples/immaTensorCoreGemm)** | **[bandwidthTest](./Samples/bandwidthTest)** | **[concurrentKernels](./Samples/concurrentKernels)** |
-**[jacobiCudaGraphs](./Samples/jacobiCudaGraphs)** | **[simpleVulkan](./Samples/simpleVulkan)** | **[vectorAdd_nvrtc](./Samples/vectorAdd_nvrtc)** | **[cannyEdgeDetectorNPP](./Samples/cannyEdgeDetectorNPP)** |
+**[simpleCUBLAS](./Samples/simpleCUBLAS)** | **[NV12toBGRandResize](./Samples/NV12toBGRandResize)** | **[cudaTensorCoreGemm](./Samples/cudaTensorCoreGemm)** | **[jacobiCudaGraphs](./Samples/jacobiCudaGraphs)** |
-**[p2pBandwidthLatencyTest](./Samples/p2pBandwidthLatencyTest)** | **[simpleVulkanMMAP](./Samples/simpleVulkanMMAP)** | **[matrixMul](./Samples/matrixMul)** |
+**[simpleVulkan](./Samples/simpleVulkan)** | **[vectorAdd_nvrtc](./Samples/vectorAdd_nvrtc)** | **[cannyEdgeDetectorNPP](./Samples/cannyEdgeDetectorNPP)** | **[p2pBandwidthLatencyTest](./Samples/p2pBandwidthLatencyTest)** |
+**[simpleVulkanMMAP](./Samples/simpleVulkanMMAP)** | **[cudaOpenMP](./Samples/cudaOpenMP)** | **[matrixMul](./Samples/matrixMul)** |
 
 ## Dependencies
 

Samples/EGLStream_CUDA_Interop/NsightEclipse.xml

@@ -59,6 +59,7 @@
   <sm-arch>sm72</sm-arch>
   <sm-arch>sm75</sm-arch>
   <sm-arch>sm80</sm-arch>
+  <sm-arch>sm86</sm-arch>
   <supported_envs>
     <env>
       <arch>x86_64</arch>

Samples/EGLStream_CUDA_Interop/README.md

@@ -10,7 +10,7 @@ EGLStreams Interop
 
 ## Supported SM Architectures
 
-[SM 3.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 3.7 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.1 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.0 ](https://developer.nvidia.com/cuda-gpus)
+[SM 3.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 3.7 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.1 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.6 ](https://developer.nvidia.com/cuda-gpus)
 
 ## Supported OSes
 
@@ -30,7 +30,7 @@ cuDeviceGet, cuDeviceGetAttribute, cuDeviceComputeCapability, cuDeviceGetCount,
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 11.0](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
+Download and install the [CUDA Toolkit 11.1](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/MersenneTwisterGP11213/MersenneTwisterGP11213_vs2015.vcxproj

@@ -33,7 +33,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -102,6 +102,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
   </ImportGroup>
 </Project>

Samples/MersenneTwisterGP11213/MersenneTwisterGP11213_vs2017.vcxproj

@@ -38,7 +38,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(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="$(CUDAPropsPath)\CUDA 11.0.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
   </ImportGroup>
 </Project>

Samples/MersenneTwisterGP11213/MersenneTwisterGP11213_vs2019.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(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="$(CUDAPropsPath)\CUDA 11.0.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
   </ImportGroup>
 </Project>

Samples/MersenneTwisterGP11213/NsightEclipse.xml

@@ -45,6 +45,7 @@
   <sm-arch>sm72</sm-arch>
   <sm-arch>sm75</sm-arch>
   <sm-arch>sm80</sm-arch>
+  <sm-arch>sm86</sm-arch>
   <supported_envs>
     <env>
       <arch>x86_64</arch>

Samples/MersenneTwisterGP11213/README.md

@@ -10,7 +10,7 @@ CURAND Library
 
 ## Supported SM Architectures
 
-[SM 3.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 3.7 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.1 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.0 ](https://developer.nvidia.com/cuda-gpus)
+[SM 3.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 3.7 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.1 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.6 ](https://developer.nvidia.com/cuda-gpus)
 
 ## Supported OSes
 
@@ -27,7 +27,7 @@ x86_64, ppc64le, armv7l
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 11.0](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
+Download and install the [CUDA Toolkit 11.1](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/NV12toBGRandResize/Makefile

@@ -274,9 +274,9 @@ LIBRARIES :=
 
 # Gencode arguments
 ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64))
-SMS ?= 35 37 50 52 60 61 70 72 75 80
+SMS ?= 35 37 50 52 60 61 70 72 75 80 86
 else
-SMS ?= 35 37 50 52 60 61 70 75 80
+SMS ?= 35 37 50 52 60 61 70 75 80 86
 endif
 
 ifeq ($(SMS),)

Samples/NV12toBGRandResize/NV12toBGRandResize_vs2013.sln

@@ -1,20 +0,0 @@
-
-Microsoft Visual Studio Solution File, Format Version 13.00
-# Visual Studio 2013
-Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "NV12toBGRandResize", "NV12toBGRandResize_vs2013.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}"
-EndProject
-Global
-	GlobalSection(SolutionConfigurationPlatforms) = preSolution
-		Debug|x64 = Debug|x64
-		Release|x64 = Release|x64
-	EndGlobalSection
-	GlobalSection(ProjectConfigurationPlatforms) = postSolution
-		{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.ActiveCfg = Debug|x64
-		{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.Build.0 = Debug|x64
-		{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.ActiveCfg = Release|x64
-		{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.Build.0 = Release|x64
-	EndGlobalSection
-	GlobalSection(SolutionProperties) = preSolution
-		HideSolutionNode = FALSE
-	EndGlobalSection
-EndGlobal

Samples/NV12toBGRandResize/NV12toBGRandResize_vs2013.vcxproj

@@ -1,112 +0,0 @@
-<?xml version="1.0" encoding="utf-8"?>
-<Project DefaultTargets="Build" ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
-  <PropertyGroup>
-    <CUDAPropsPath Condition="'$(CUDAPropsPath)'==''">$(VCTargetsPath)\BuildCustomizations</CUDAPropsPath>
-  </PropertyGroup>
-  <ItemGroup Label="ProjectConfigurations">
-    <ProjectConfiguration Include="Debug|x64">
-      <Configuration>Debug</Configuration>
-      <Platform>x64</Platform>
-    </ProjectConfiguration>
-    <ProjectConfiguration Include="Release|x64">
-      <Configuration>Release</Configuration>
-      <Platform>x64</Platform>
-    </ProjectConfiguration>
-  </ItemGroup>
-  <PropertyGroup Label="Globals">
-    <ProjectGuid>{997E0757-EA74-4A4E-A0FC-47D8C8831A15}</ProjectGuid>
-    <RootNamespace>NV12toBGRandResize_vs2013</RootNamespace>
-    <ProjectName>NV12toBGRandResize</ProjectName>
-    <CudaToolkitCustomDir />
-  </PropertyGroup>
-  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
-  <PropertyGroup>
-    <ConfigurationType>Application</ConfigurationType>
-    <CharacterSet>MultiByte</CharacterSet>
-    <PlatformToolset>v120</PlatformToolset>
-  </PropertyGroup>
-  <PropertyGroup Condition="'$(Configuration)'=='Debug'">
-    <UseDebugLibraries>true</UseDebugLibraries>
-  </PropertyGroup>
-  <PropertyGroup Condition="'$(Configuration)'=='Release'">
-    <WholeProgramOptimization>true</WholeProgramOptimization>
-  </PropertyGroup>
-  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
-  <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.props" />
-  </ImportGroup>
-  <ImportGroup Label="PropertySheets">
-    <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
-  </ImportGroup>
-  <PropertyGroup Label="UserMacros" />
-  <PropertyGroup>
-    <IntDir>$(Platform)/$(Configuration)/</IntDir>
-    <IncludePath>$(IncludePath)</IncludePath>
-    <CodeAnalysisRuleSet>AllRules.ruleset</CodeAnalysisRuleSet>
-    <CodeAnalysisRules />
-    <CodeAnalysisRuleAssemblies />
-  </PropertyGroup>
-  <PropertyGroup Condition="'$(Platform)'=='x64'">
-    <OutDir>../../bin/win64/$(Configuration)/</OutDir>
-  </PropertyGroup>
-  <ItemDefinitionGroup>
-    <ClCompile>
-      <WarningLevel>Level3</WarningLevel>
-      <PreprocessorDefinitions>WIN32;_MBCS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
-      <AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../Common;</AdditionalIncludeDirectories>
-    </ClCompile>
-    <Link>
-      <SubSystem>Console</SubSystem>
-      <AdditionalDependencies>cudart_static.lib;kernel32.lib;user32.lib;gdi32.lib;winspool.lib;comdlg32.lib;advapi32.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;odbc32.lib;odbccp32.lib;%(AdditionalDependencies)</AdditionalDependencies>
-      <AdditionalLibraryDirectories>$(CudaToolkitLibDir);</AdditionalLibraryDirectories>
-      <OutputFile>$(OutDir)/NV12toBGRandResize.exe</OutputFile>
-    </Link>
-    <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;</CodeGeneration>
-      <AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
-      <Include>./;../../Common</Include>
-      <Defines>WIN32</Defines>
-    </CudaCompile>
-  </ItemDefinitionGroup>
-  <ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
-    <ClCompile>
-      <Optimization>Disabled</Optimization>
-      <RuntimeLibrary>MultiThreadedDebug</RuntimeLibrary>
-    </ClCompile>
-    <Link>
-      <GenerateDebugInformation>true</GenerateDebugInformation>
-      <LinkTimeCodeGeneration>Default</LinkTimeCodeGeneration>
-    </Link>
-    <CudaCompile>
-      <Runtime>MTd</Runtime>
-      <TargetMachinePlatform>64</TargetMachinePlatform>
-    </CudaCompile>
-  </ItemDefinitionGroup>
-  <ItemDefinitionGroup Condition="'$(Configuration)'=='Release'">
-    <ClCompile>
-      <Optimization>MaxSpeed</Optimization>
-      <RuntimeLibrary>MultiThreaded</RuntimeLibrary>
-    </ClCompile>
-    <Link>
-      <GenerateDebugInformation>false</GenerateDebugInformation>
-      <LinkTimeCodeGeneration>UseLinkTimeCodeGeneration</LinkTimeCodeGeneration>
-    </Link>
-    <CudaCompile>
-      <Runtime>MT</Runtime>
-      <TargetMachinePlatform>64</TargetMachinePlatform>
-    </CudaCompile>
-  </ItemDefinitionGroup>
-  <ItemGroup>
-    <CudaCompile Include="bgr_resize.cu" />
-    <CudaCompile Include="nv12_resize.cu" />
-    <CudaCompile Include="nv12_to_bgr_planar.cu" />
-    <ClCompile Include="resize_convert_main.cpp" />
-    <CudaCompile Include="utils.cu" />
-    <ClInclude Include="resize_convert.h" />
-    <ClInclude Include="utils.h" />
-  </ItemGroup>
-  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
-  <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.targets" />
-  </ImportGroup>
-</Project>

Samples/NV12toBGRandResize/NV12toBGRandResize_vs2015.vcxproj

@@ -33,7 +33,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -62,7 +62,7 @@
       <OutputFile>$(OutDir)/NV12toBGRandResize.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;</CodeGeneration>
+      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
       <AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
       <Include>./;../../Common</Include>
       <Defines>WIN32</Defines>
@@ -107,6 +107,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
   </ImportGroup>
 </Project>

Samples/NV12toBGRandResize/NV12toBGRandResize_vs2017.vcxproj

@@ -38,7 +38,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -67,7 +67,7 @@
       <OutputFile>$(OutDir)/NV12toBGRandResize.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;</CodeGeneration>
+      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
       <AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
       <Include>./;../../Common</Include>
       <Defines>WIN32</Defines>
@@ -112,6 +112,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
   </ImportGroup>
 </Project>

Samples/NV12toBGRandResize/NV12toBGRandResize_vs2019.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -63,7 +63,7 @@
       <OutputFile>$(OutDir)/NV12toBGRandResize.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;</CodeGeneration>
+      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
       <AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
       <Include>./;../../Common</Include>
       <Defines>WIN32</Defines>
@@ -108,6 +108,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
   </ImportGroup>
 </Project>

Samples/NV12toBGRandResize/NsightEclipse.xml

@@ -42,6 +42,7 @@
   <sm-arch>sm72</sm-arch>
   <sm-arch>sm75</sm-arch>
   <sm-arch>sm80</sm-arch>
+  <sm-arch>sm86</sm-arch>
   <supported_envs>
     <env>
       <arch>x86_64</arch>

Samples/NV12toBGRandResize/README.md

@@ -10,7 +10,7 @@ Graphics Interop, Image Processing, Video Processing
 
 ## Supported SM Architectures
 
-[SM 3.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 3.7 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.1 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.0 ](https://developer.nvidia.com/cuda-gpus)
+[SM 3.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 3.7 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.1 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.6 ](https://developer.nvidia.com/cuda-gpus)
 
 ## Supported OSes
 
@@ -27,7 +27,7 @@ cudaMemcpy2D, cudaMallocManaged
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 11.0](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
+Download and install the [CUDA Toolkit 11.1](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
 
 ## Build and Run
 

Samples/UnifiedMemoryPerf/Makefile

@@ -274,9 +274,9 @@ LIBRARIES :=
 
 # Gencode arguments
 ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64))
-SMS ?= 35 37 50 52 60 61 70 72 75 80
+SMS ?= 35 37 50 52 60 61 70 72 75 80 86
 else
-SMS ?= 35 37 50 52 60 61 70 75 80
+SMS ?= 35 37 50 52 60 61 70 75 80 86
 endif
 
 ifeq ($(SMS),)

Samples/UnifiedMemoryPerf/README.md

@@ -28,7 +28,7 @@ cudaMallocManaged, cudaStreamAttachMemAsync, cudaMemcpyAsync, cudaMallocHost, cu
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 11.0](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
+Download and install the [CUDA Toolkit 11.1](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/UnifiedMemoryPerf/UnifiedMemoryPerf_vs2012.sln

@@ -1,20 +0,0 @@
-
-Microsoft Visual Studio Solution File, Format Version 12.00
-# Visual Studio 2012
-Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "UnifiedMemoryPerf", "UnifiedMemoryPerf_vs2012.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}"
-EndProject
-Global
-	GlobalSection(SolutionConfigurationPlatforms) = preSolution
-		Debug|x64 = Debug|x64
-		Release|x64 = Release|x64
-	EndGlobalSection
-	GlobalSection(ProjectConfigurationPlatforms) = postSolution
-		{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.ActiveCfg = Debug|x64
-		{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.Build.0 = Debug|x64
-		{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.ActiveCfg = Release|x64
-		{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.Build.0 = Release|x64
-	EndGlobalSection
-	GlobalSection(SolutionProperties) = preSolution
-		HideSolutionNode = FALSE
-	EndGlobalSection
-EndGlobal

Samples/UnifiedMemoryPerf/UnifiedMemoryPerf_vs2013.sln

@@ -1,20 +0,0 @@
-
-Microsoft Visual Studio Solution File, Format Version 13.00
-# Visual Studio 2013
-Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "UnifiedMemoryPerf", "UnifiedMemoryPerf_vs2013.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}"
-EndProject
-Global
-	GlobalSection(SolutionConfigurationPlatforms) = preSolution
-		Debug|x64 = Debug|x64
-		Release|x64 = Release|x64
-	EndGlobalSection
-	GlobalSection(ProjectConfigurationPlatforms) = postSolution
-		{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.ActiveCfg = Debug|x64
-		{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.Build.0 = Debug|x64
-		{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.ActiveCfg = Release|x64
-		{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.Build.0 = Release|x64
-	EndGlobalSection
-	GlobalSection(SolutionProperties) = preSolution
-		HideSolutionNode = FALSE
-	EndGlobalSection
-EndGlobal

Samples/UnifiedMemoryPerf/UnifiedMemoryPerf_vs2013.vcxproj

@@ -1,110 +0,0 @@
-<?xml version="1.0" encoding="utf-8"?>
-<Project DefaultTargets="Build" ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
-  <PropertyGroup>
-    <CUDAPropsPath Condition="'$(CUDAPropsPath)'==''">$(VCTargetsPath)\BuildCustomizations</CUDAPropsPath>
-  </PropertyGroup>
-  <ItemGroup Label="ProjectConfigurations">
-    <ProjectConfiguration Include="Debug|x64">
-      <Configuration>Debug</Configuration>
-      <Platform>x64</Platform>
-    </ProjectConfiguration>
-    <ProjectConfiguration Include="Release|x64">
-      <Configuration>Release</Configuration>
-      <Platform>x64</Platform>
-    </ProjectConfiguration>
-  </ItemGroup>
-  <PropertyGroup Label="Globals">
-    <ProjectGuid>{997E0757-EA74-4A4E-A0FC-47D8C8831A15}</ProjectGuid>
-    <RootNamespace>UnifiedMemoryPerf_vs2013</RootNamespace>
-    <ProjectName>UnifiedMemoryPerf</ProjectName>
-    <CudaToolkitCustomDir />
-  </PropertyGroup>
-  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
-  <PropertyGroup>
-    <ConfigurationType>Application</ConfigurationType>
-    <CharacterSet>MultiByte</CharacterSet>
-    <PlatformToolset>v120</PlatformToolset>
-  </PropertyGroup>
-  <PropertyGroup Condition="'$(Configuration)'=='Debug'">
-    <UseDebugLibraries>true</UseDebugLibraries>
-  </PropertyGroup>
-  <PropertyGroup Condition="'$(Configuration)'=='Release'">
-    <WholeProgramOptimization>true</WholeProgramOptimization>
-  </PropertyGroup>
-  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
-  <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.props" />
-  </ImportGroup>
-  <ImportGroup Label="PropertySheets">
-    <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
-  </ImportGroup>
-  <PropertyGroup Label="UserMacros" />
-  <PropertyGroup>
-    <IntDir>$(Platform)/$(Configuration)/</IntDir>
-    <IncludePath>$(IncludePath)</IncludePath>
-    <CodeAnalysisRuleSet>AllRules.ruleset</CodeAnalysisRuleSet>
-    <CodeAnalysisRules />
-    <CodeAnalysisRuleAssemblies />
-  </PropertyGroup>
-  <PropertyGroup Condition="'$(Platform)'=='x64'">
-    <OutDir>../../bin/win64/$(Configuration)/</OutDir>
-  </PropertyGroup>
-  <ItemDefinitionGroup>
-    <ClCompile>
-      <WarningLevel>Level3</WarningLevel>
-      <PreprocessorDefinitions>WIN32;_MBCS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
-      <AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../Common;</AdditionalIncludeDirectories>
-    </ClCompile>
-    <Link>
-      <SubSystem>Console</SubSystem>
-      <AdditionalDependencies>cudart_static.lib;kernel32.lib;user32.lib;gdi32.lib;winspool.lib;comdlg32.lib;advapi32.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;odbc32.lib;odbccp32.lib;%(AdditionalDependencies)</AdditionalDependencies>
-      <AdditionalLibraryDirectories>$(CudaToolkitLibDir);</AdditionalLibraryDirectories>
-      <OutputFile>$(OutDir)/UnifiedMemoryPerf.exe</OutputFile>
-    </Link>
-    <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;</CodeGeneration>
-      <AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
-      <Include>./;../../Common</Include>
-      <Defines>WIN32</Defines>
-    </CudaCompile>
-  </ItemDefinitionGroup>
-  <ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
-    <ClCompile>
-      <Optimization>Disabled</Optimization>
-      <RuntimeLibrary>MultiThreadedDebug</RuntimeLibrary>
-    </ClCompile>
-    <Link>
-      <GenerateDebugInformation>true</GenerateDebugInformation>
-      <LinkTimeCodeGeneration>Default</LinkTimeCodeGeneration>
-    </Link>
-    <CudaCompile>
-      <Runtime>MTd</Runtime>
-      <TargetMachinePlatform>64</TargetMachinePlatform>
-    </CudaCompile>
-  </ItemDefinitionGroup>
-  <ItemDefinitionGroup Condition="'$(Configuration)'=='Release'">
-    <ClCompile>
-      <Optimization>MaxSpeed</Optimization>
-      <RuntimeLibrary>MultiThreaded</RuntimeLibrary>
-    </ClCompile>
-    <Link>
-      <GenerateDebugInformation>false</GenerateDebugInformation>
-      <LinkTimeCodeGeneration>UseLinkTimeCodeGeneration</LinkTimeCodeGeneration>
-    </Link>
-    <CudaCompile>
-      <Runtime>MT</Runtime>
-      <TargetMachinePlatform>64</TargetMachinePlatform>
-    </CudaCompile>
-  </ItemDefinitionGroup>
-  <ItemGroup>
-    <CudaCompile Include="commonKernels.cu" />
-    <ClCompile Include="helperFunctions.cpp" />
-    <CudaCompile Include="matrixMultiplyPerf.cu" />
-    <ClInclude Include="commonDefs.hpp" />
-    <ClInclude Include="commonKernels.hpp" />
-  </ItemGroup>
-  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
-  <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.targets" />
-  </ImportGroup>
-</Project>

Samples/UnifiedMemoryPerf/UnifiedMemoryPerf_vs2015.vcxproj

@@ -33,7 +33,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -62,7 +62,7 @@
       <OutputFile>$(OutDir)/UnifiedMemoryPerf.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;</CodeGeneration>
+      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
       <AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
       <Include>./;../../Common</Include>
       <Defines>WIN32</Defines>
@@ -105,6 +105,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
   </ImportGroup>
 </Project>

Samples/UnifiedMemoryPerf/UnifiedMemoryPerf_vs2017.vcxproj

@@ -38,7 +38,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -67,7 +67,7 @@
       <OutputFile>$(OutDir)/UnifiedMemoryPerf.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;</CodeGeneration>
+      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
       <AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
       <Include>./;../../Common</Include>
       <Defines>WIN32</Defines>
@@ -110,6 +110,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
   </ImportGroup>
 </Project>

Samples/UnifiedMemoryPerf/UnifiedMemoryPerf_vs2019.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -63,7 +63,7 @@
       <OutputFile>$(OutDir)/UnifiedMemoryPerf.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;</CodeGeneration>
+      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
       <AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
       <Include>./;../../Common</Include>
       <Defines>WIN32</Defines>
@@ -106,6 +106,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
   </ImportGroup>
 </Project>

Samples/UnifiedMemoryPerf/matrixMultiplyPerf.cu

@@ -33,7 +33,7 @@
 #define VERIFY_GPU_CORRECTNESS 0
 
 size_t maxSampleSizeInMb = 64;
-int numKernelRuns = 100;
+int numKernelRuns = 20;
 int verboseResults = 0;
 
 const char *memAllocTypeStr[MEMALLOC_TYPE_COUNT] = {

Samples/bandwidthTest/Makefile

@@ -268,9 +268,9 @@ LIBRARIES :=
 
 # Gencode arguments
 ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64))
-SMS ?= 35 37 50 52 60 61 70 72 75 80
+SMS ?= 35 37 50 52 60 61 70 72 75 80 86
 else
-SMS ?= 35 37 50 52 60 61 70 75 80
+SMS ?= 35 37 50 52 60 61 70 75 80 86
 endif
 
 ifeq ($(SMS),)

Samples/bandwidthTest/NsightEclipse.xml

@@ -51,6 +51,7 @@
   <sm-arch>sm72</sm-arch>
   <sm-arch>sm75</sm-arch>
   <sm-arch>sm80</sm-arch>
+  <sm-arch>sm86</sm-arch>
   <supported_envs>
     <env>
       <arch>x86_64</arch>

Samples/bandwidthTest/README.md

@@ -10,7 +10,7 @@ CUDA Streams and Events, Performance Strategies
 
 ## Supported SM Architectures
 
-[SM 3.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 3.7 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.1 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.0 ](https://developer.nvidia.com/cuda-gpus)
+[SM 3.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 3.7 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.1 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.6 ](https://developer.nvidia.com/cuda-gpus)
 
 ## Supported OSes
 
@@ -27,7 +27,7 @@ cudaSetDevice, cudaHostAlloc, cudaFree, cudaMallocHost, cudaFreeHost, cudaMemcpy
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 11.0](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
+Download and install the [CUDA Toolkit 11.1](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
 
 ## Build and Run
 

Samples/bandwidthTest/bandwidthTest_vs2012.sln

@@ -1,20 +0,0 @@
-
-Microsoft Visual Studio Solution File, Format Version 12.00
-# Visual Studio 2012
-Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "bandwidthTest", "bandwidthTest_vs2012.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}"
-EndProject
-Global
-	GlobalSection(SolutionConfigurationPlatforms) = preSolution
-		Debug|x64 = Debug|x64
-		Release|x64 = Release|x64
-	EndGlobalSection
-	GlobalSection(ProjectConfigurationPlatforms) = postSolution
-		{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.ActiveCfg = Debug|x64
-		{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.Build.0 = Debug|x64
-		{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.ActiveCfg = Release|x64
-		{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.Build.0 = Release|x64
-	EndGlobalSection
-	GlobalSection(SolutionProperties) = preSolution
-		HideSolutionNode = FALSE
-	EndGlobalSection
-EndGlobal

Samples/bandwidthTest/bandwidthTest_vs2013.sln

@@ -1,20 +0,0 @@
-
-Microsoft Visual Studio Solution File, Format Version 13.00
-# Visual Studio 2013
-Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "bandwidthTest", "bandwidthTest_vs2013.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}"
-EndProject
-Global
-	GlobalSection(SolutionConfigurationPlatforms) = preSolution
-		Debug|x64 = Debug|x64
-		Release|x64 = Release|x64
-	EndGlobalSection
-	GlobalSection(ProjectConfigurationPlatforms) = postSolution
-		{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.ActiveCfg = Debug|x64
-		{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.Build.0 = Debug|x64
-		{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.ActiveCfg = Release|x64
-		{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.Build.0 = Release|x64
-	EndGlobalSection
-	GlobalSection(SolutionProperties) = preSolution
-		HideSolutionNode = FALSE
-	EndGlobalSection
-EndGlobal

Samples/bandwidthTest/bandwidthTest_vs2015.vcxproj

@@ -33,7 +33,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -62,7 +62,7 @@
       <OutputFile>$(OutDir)/bandwidthTest.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;</CodeGeneration>
+      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
       <AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
       <Include>./;../../Common</Include>
       <Defines>WIN32</Defines>
@@ -102,6 +102,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
   </ImportGroup>
 </Project>

Samples/bandwidthTest/bandwidthTest_vs2017.vcxproj

@@ -38,7 +38,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -67,7 +67,7 @@
       <OutputFile>$(OutDir)/bandwidthTest.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;</CodeGeneration>
+      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
       <AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
       <Include>./;../../Common</Include>
       <Defines>WIN32</Defines>
@@ -107,6 +107,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
   </ImportGroup>
 </Project>

Samples/bandwidthTest/bandwidthTest_vs2019.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -63,7 +63,7 @@
       <OutputFile>$(OutDir)/bandwidthTest.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;</CodeGeneration>
+      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
       <AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
       <Include>./;../../Common</Include>
       <Defines>WIN32</Defines>
@@ -103,6 +103,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
   </ImportGroup>
 </Project>

Samples/batchedLabelMarkersAndLabelCompressionNPP/Makefile

@@ -0,0 +1,329 @@
+################################################################################
+# Copyright (c) 2019, NVIDIA CORPORATION. All rights reserved.
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions
+# are met:
+#  * Redistributions of source code must retain the above copyright
+#    notice, this list of conditions and the following disclaimer.
+#  * Redistributions in binary form must reproduce the above copyright
+#    notice, this list of conditions and the following disclaimer in the
+#    documentation and/or other materials provided with the distribution.
+#  * Neither the name of NVIDIA CORPORATION nor the names of its
+#    contributors may be used to endorse or promote products derived
+#    from this software without specific prior written permission.
+#
+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS ``AS IS'' AND ANY
+# EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+# PURPOSE ARE DISCLAIMED.  IN NO EVENT SHALL THE COPYRIGHT OWNER OR
+# CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
+# EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
+# PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
+# PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
+# OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+#
+################################################################################
+#
+# Makefile project only supported on Mac OS X and Linux Platforms)
+#
+################################################################################
+
+# Location of the CUDA Toolkit
+CUDA_PATH ?= /usr/local/cuda
+
+##############################
+# start deprecated interface #
+##############################
+ifeq ($(x86_64),1)
+    $(info WARNING - x86_64 variable has been deprecated)
+    $(info WARNING - please use TARGET_ARCH=x86_64 instead)
+    TARGET_ARCH ?= x86_64
+endif
+ifeq ($(ARMv7),1)
+    $(info WARNING - ARMv7 variable has been deprecated)
+    $(info WARNING - please use TARGET_ARCH=armv7l instead)
+    TARGET_ARCH ?= armv7l
+endif
+ifeq ($(aarch64),1)
+    $(info WARNING - aarch64 variable has been deprecated)
+    $(info WARNING - please use TARGET_ARCH=aarch64 instead)
+    TARGET_ARCH ?= aarch64
+endif
+ifeq ($(ppc64le),1)
+    $(info WARNING - ppc64le variable has been deprecated)
+    $(info WARNING - please use TARGET_ARCH=ppc64le instead)
+    TARGET_ARCH ?= ppc64le
+endif
+ifneq ($(GCC),)
+    $(info WARNING - GCC variable has been deprecated)
+    $(info WARNING - please use HOST_COMPILER=$(GCC) instead)
+    HOST_COMPILER ?= $(GCC)
+endif
+ifneq ($(abi),)
+    $(error ERROR - abi variable has been removed)
+endif
+############################
+# end deprecated interface #
+############################
+
+# architecture
+HOST_ARCH   := $(shell uname -m)
+TARGET_ARCH ?= $(HOST_ARCH)
+ifneq (,$(filter $(TARGET_ARCH),x86_64 aarch64 sbsa ppc64le armv7l))
+    ifneq ($(TARGET_ARCH),$(HOST_ARCH))
+        ifneq (,$(filter $(TARGET_ARCH),x86_64 aarch64 sbsa ppc64le))
+            TARGET_SIZE := 64
+        else ifneq (,$(filter $(TARGET_ARCH),armv7l))
+            TARGET_SIZE := 32
+        endif
+    else
+        TARGET_SIZE := $(shell getconf LONG_BIT)
+    endif
+else
+    $(error ERROR - unsupported value $(TARGET_ARCH) for TARGET_ARCH!)
+endif
+
+# sbsa and aarch64 systems look similar. Need to differentiate them at host level for now.
+ifeq ($(HOST_ARCH),aarch64)
+    ifeq ($(CUDA_PATH)/targets/sbsa-linux,$(shell ls -1d $(CUDA_PATH)/targets/sbsa-linux))
+        HOST_ARCH := sbsa
+        TARGET_ARCH := sbsa
+    endif
+endif
+
+ifneq ($(TARGET_ARCH),$(HOST_ARCH))
+    ifeq (,$(filter $(HOST_ARCH)-$(TARGET_ARCH),aarch64-armv7l x86_64-armv7l x86_64-aarch64 x86_64-sbsa x86_64-ppc64le))
+        $(error ERROR - cross compiling from $(HOST_ARCH) to $(TARGET_ARCH) is not supported!)
+    endif
+endif
+
+# When on native aarch64 system with userspace of 32-bit, change TARGET_ARCH to armv7l
+ifeq ($(HOST_ARCH)-$(TARGET_ARCH)-$(TARGET_SIZE),aarch64-aarch64-32)
+    TARGET_ARCH = armv7l
+endif
+
+# operating system
+HOST_OS   := $(shell uname -s 2>/dev/null | tr "[:upper:]" "[:lower:]")
+TARGET_OS ?= $(HOST_OS)
+ifeq (,$(filter $(TARGET_OS),linux darwin qnx android))
+    $(error ERROR - unsupported value $(TARGET_OS) for TARGET_OS!)
+endif
+
+# host compiler
+ifeq ($(TARGET_OS),darwin)
+    ifeq ($(shell expr `xcodebuild -version | grep -i xcode | awk '{print $$2}' | cut -d'.' -f1` \>= 5),1)
+        HOST_COMPILER ?= clang++
+    endif
+else ifneq ($(TARGET_ARCH),$(HOST_ARCH))
+    ifeq ($(HOST_ARCH)-$(TARGET_ARCH),x86_64-armv7l)
+        ifeq ($(TARGET_OS),linux)
+            HOST_COMPILER ?= arm-linux-gnueabihf-g++
+        else ifeq ($(TARGET_OS),qnx)
+            ifeq ($(QNX_HOST),)
+                $(error ERROR - QNX_HOST must be passed to the QNX host toolchain)
+            endif
+            ifeq ($(QNX_TARGET),)
+                $(error ERROR - QNX_TARGET must be passed to the QNX target toolchain)
+            endif
+            export QNX_HOST
+            export QNX_TARGET
+            HOST_COMPILER ?= $(QNX_HOST)/usr/bin/arm-unknown-nto-qnx6.6.0eabi-g++
+        else ifeq ($(TARGET_OS),android)
+            HOST_COMPILER ?= arm-linux-androideabi-g++
+        endif
+    else ifeq ($(TARGET_ARCH),aarch64)
+        ifeq ($(TARGET_OS), linux)
+            HOST_COMPILER ?= aarch64-linux-gnu-g++
+        else ifeq ($(TARGET_OS),qnx)
+            ifeq ($(QNX_HOST),)
+                $(error ERROR - QNX_HOST must be passed to the QNX host toolchain)
+            endif
+            ifeq ($(QNX_TARGET),)
+                $(error ERROR - QNX_TARGET must be passed to the QNX target toolchain)
+            endif
+            export QNX_HOST
+            export QNX_TARGET
+            HOST_COMPILER ?= $(QNX_HOST)/usr/bin/aarch64-unknown-nto-qnx7.0.0-g++
+        else ifeq ($(TARGET_OS), android)
+            HOST_COMPILER ?= aarch64-linux-android-clang++
+        endif
+    else ifeq ($(TARGET_ARCH),sbsa)
+        HOST_COMPILER ?= aarch64-linux-gnu-g++
+    else ifeq ($(TARGET_ARCH),ppc64le)
+        HOST_COMPILER ?= powerpc64le-linux-gnu-g++
+    endif
+endif
+HOST_COMPILER ?= g++
+NVCC          := $(CUDA_PATH)/bin/nvcc -ccbin $(HOST_COMPILER)
+
+# internal flags
+NVCCFLAGS   := -m${TARGET_SIZE}
+CCFLAGS     :=
+LDFLAGS     :=
+
+# build flags
+ifeq ($(TARGET_OS),darwin)
+    LDFLAGS += -rpath $(CUDA_PATH)/lib
+    CCFLAGS += -arch $(HOST_ARCH)
+else ifeq ($(HOST_ARCH)-$(TARGET_ARCH)-$(TARGET_OS),x86_64-armv7l-linux)
+    LDFLAGS += --dynamic-linker=/lib/ld-linux-armhf.so.3
+    CCFLAGS += -mfloat-abi=hard
+else ifeq ($(TARGET_OS),android)
+    LDFLAGS += -pie
+    CCFLAGS += -fpie -fpic -fexceptions
+endif
+
+ifneq ($(TARGET_ARCH),$(HOST_ARCH))
+    ifeq ($(TARGET_ARCH)-$(TARGET_OS),armv7l-linux)
+        ifneq ($(TARGET_FS),)
+            GCCVERSIONLTEQ46 := $(shell expr `$(HOST_COMPILER) -dumpversion` \<= 4.6)
+            ifeq ($(GCCVERSIONLTEQ46),1)
+                CCFLAGS += --sysroot=$(TARGET_FS)
+            endif
+            LDFLAGS += --sysroot=$(TARGET_FS)
+            LDFLAGS += -rpath-link=$(TARGET_FS)/lib
+            LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib
+            LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib/arm-linux-gnueabihf
+        endif
+    endif
+    ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-linux)
+        ifneq ($(TARGET_FS),)
+            GCCVERSIONLTEQ46 := $(shell expr `$(HOST_COMPILER) -dumpversion` \<= 4.6)
+            ifeq ($(GCCVERSIONLTEQ46),1)
+                CCFLAGS += --sysroot=$(TARGET_FS)
+            endif
+            LDFLAGS += --sysroot=$(TARGET_FS)
+            LDFLAGS += -rpath-link=$(TARGET_FS)/lib -L$(TARGET_FS)/lib
+            LDFLAGS += -rpath-link=$(TARGET_FS)/lib/aarch64-linux-gnu -L$(TARGET_FS)/lib/aarch64-linux-gnu
+            LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib -L$(TARGET_FS)/usr/lib
+            LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib/aarch64-linux-gnu -L$(TARGET_FS)/usr/lib/aarch64-linux-gnu
+            LDFLAGS += --unresolved-symbols=ignore-in-shared-libs
+            CCFLAGS += -isystem=$(TARGET_FS)/usr/include  -I$(TARGET_FS)/usr/include
+            CCFLAGS += -isystem=$(TARGET_FS)/usr/include/aarch64-linux-gnu -I$(TARGET_FS)/usr/include/aarch64-linux-gnu
+        endif
+    endif
+    ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-qnx)
+        CCFLAGS += -DWIN_INTERFACE_CUSTOM -I/usr/include/aarch64-qnx-gnu
+        LDFLAGS += -lsocket
+        LDFLAGS += -rpath=/usr/lib/aarch64-qnx-gnu -L/usr/lib/aarch64-qnx-gnu
+        ifneq ($(TARGET_FS),)
+            LDFLAGS += -rpath=$(TARGET_FS)/usr/lib -L $(TARGET_FS)/usr/lib
+            LDFLAGS += -rpath=$(TARGET_FS)/usr/libnvidia -L $(TARGET_FS)/usr/libnvidia
+        endif
+        ifdef TARGET_OVERRIDE # cuda toolkit targets override
+            NVCCFLAGS += -target-dir $(TARGET_OVERRIDE)
+        endif
+    endif
+endif
+
+# Install directory of different arch
+CUDA_INSTALL_TARGET_DIR :=
+ifeq ($(TARGET_ARCH)-$(TARGET_OS),armv7l-linux)
+    CUDA_INSTALL_TARGET_DIR = targets/armv7-linux-gnueabihf/
+else ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-linux)
+    CUDA_INSTALL_TARGET_DIR = targets/aarch64-linux/
+else ifeq ($(TARGET_ARCH)-$(TARGET_OS),sbsa-linux)
+    CUDA_INSTALL_TARGET_DIR = targets/sbsa-linux/
+else ifeq ($(TARGET_ARCH)-$(TARGET_OS),armv7l-android)
+    CUDA_INSTALL_TARGET_DIR = targets/armv7-linux-androideabi/
+else ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-android)
+    CUDA_INSTALL_TARGET_DIR = targets/aarch64-linux-androideabi/
+else ifeq ($(TARGET_ARCH)-$(TARGET_OS),armv7l-qnx)
+    CUDA_INSTALL_TARGET_DIR = targets/ARMv7-linux-QNX/
+else ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-qnx)
+    CUDA_INSTALL_TARGET_DIR = targets/aarch64-qnx/
+else ifeq ($(TARGET_ARCH),ppc64le)
+    CUDA_INSTALL_TARGET_DIR = targets/ppc64le-linux/
+endif
+
+# Debug build flags
+ifeq ($(dbg),1)
+      NVCCFLAGS += -g -G
+      BUILD_TYPE := debug
+else
+      BUILD_TYPE := release
+endif
+
+ALL_CCFLAGS :=
+ALL_CCFLAGS += $(NVCCFLAGS)
+ALL_CCFLAGS += $(EXTRA_NVCCFLAGS)
+ALL_CCFLAGS += $(addprefix -Xcompiler ,$(CCFLAGS))
+ALL_CCFLAGS += $(addprefix -Xcompiler ,$(EXTRA_CCFLAGS))
+
+SAMPLE_ENABLED := 1
+
+# This sample is not supported on Mac OSX
+ifeq ($(TARGET_OS),darwin)
+  $(info >>> WARNING - batchedLabelMarkersAndLabelCompressionNPP is not supported on Mac OSX - waiving sample <<<)
+  SAMPLE_ENABLED := 0
+endif
+
+ALL_LDFLAGS :=
+ALL_LDFLAGS += $(ALL_CCFLAGS)
+ALL_LDFLAGS += $(addprefix -Xlinker ,$(LDFLAGS))
+ALL_LDFLAGS += $(addprefix -Xlinker ,$(EXTRA_LDFLAGS))
+
+# Common includes and paths for CUDA
+INCLUDES  := -I../../Common
+LIBRARIES :=
+
+################################################################################
+
+# Gencode arguments
+SMS ?=
+
+ifeq ($(GENCODE_FLAGS),)
+# Generate SASS code for each SM architecture listed in $(SMS)
+$(foreach sm,$(SMS),$(eval GENCODE_FLAGS += -gencode arch=compute_$(sm),code=sm_$(sm)))
+
+ifeq ($(SMS),)
+# Generate PTX code from SM 35
+GENCODE_FLAGS += -gencode arch=compute_35,code=compute_35
+endif
+
+# Generate PTX code from the highest SM architecture in $(SMS) to guarantee forward-compatibility
+HIGHEST_SM := $(lastword $(sort $(SMS)))
+ifneq ($(HIGHEST_SM),)
+GENCODE_FLAGS += -gencode arch=compute_$(HIGHEST_SM),code=compute_$(HIGHEST_SM)
+endif
+endif
+
+LIBRARIES += -lnppisu_static -lnppif_static -lnppc_static -lculibos
+
+ifeq ($(SAMPLE_ENABLED),0)
+EXEC ?= @echo "[@]"
+endif
+
+################################################################################
+
+# Target rules
+all: build
+
+build: batchedLabelMarkersAndLabelCompressionNPP
+
+check.deps:
+ifeq ($(SAMPLE_ENABLED),0)
+	@echo "Sample will be waived due to the above missing dependencies"
+else
+	@echo "Sample is ready - all dependencies have been met"
+endif
+
+batchedLabelMarkersAndLabelCompressionNPP.o:batchedLabelMarkersAndLabelCompressionNPP.cpp
+	$(EXEC) $(NVCC) $(INCLUDES) $(ALL_CCFLAGS) $(GENCODE_FLAGS) -o $@ -c $<
+
+batchedLabelMarkersAndLabelCompressionNPP: batchedLabelMarkersAndLabelCompressionNPP.o
+	$(EXEC) $(NVCC) $(ALL_LDFLAGS) $(GENCODE_FLAGS) -o $@ $+ $(LIBRARIES)
+	$(EXEC) mkdir -p ../../bin/$(TARGET_ARCH)/$(TARGET_OS)/$(BUILD_TYPE)
+	$(EXEC) cp $@ ../../bin/$(TARGET_ARCH)/$(TARGET_OS)/$(BUILD_TYPE)
+
+run: build
+	$(EXEC) ./batchedLabelMarkersAndLabelCompressionNPP
+
+clean:
+	rm -f batchedLabelMarkersAndLabelCompressionNPP batchedLabelMarkersAndLabelCompressionNPP.o
+	rm -rf ../../bin/$(TARGET_ARCH)/$(TARGET_OS)/$(BUILD_TYPE)/batchedLabelMarkersAndLabelCompressionNPP
+
+clobber: clean

Samples/batchedLabelMarkersAndLabelCompressionNPP/NsightEclipse.xml

@@ -0,0 +1,76 @@
+<?xml version="1.0" encoding="UTF-8"?> 
+<!DOCTYPE entry SYSTEM "SamplesInfo.dtd">
+<entry>
+  <name>batchedLabelMarkersAndLabelCompressionNPP</name>
+  <description><![CDATA[An NPP CUDA Sample that demonstrates how to use the NPP label markers generation and label compression functions based on a Union Find (UF) algorithm including both
+single image and batched image versions.]]></description>
+  <devicecompilation>whole</devicecompilation>
+  <fallback_min_ptx>true</fallback_min_ptx>
+  <includepaths>
+    <path>./</path>
+    <path>../</path>
+    <path>../../common/inc</path>
+  </includepaths>
+  <keyconcepts>
+    <concept level="basic">Performance Strategies</concept>
+    <concept level="basic">Image Processing</concept>
+    <concept level="basic">NPP Library</concept>
+    <concept level="basic">Using NPP Batch Functions</concept>
+  </keyconcepts>
+  <keywords>
+    <keyword>CUDA</keyword>
+    <keyword>NPP</keyword>
+    <keyword>Image Processing</keyword>
+  </keywords>
+  <libraries>
+    <library>nppisu_static</library>
+    <library>nppif_static</library>
+    <library>nppc_static</library>
+    <library>culibos</library>
+  </libraries>
+  <librarypaths>
+  </librarypaths>
+  <nsight_eclipse>true</nsight_eclipse>
+  <primary_file>batchedLabelMarkersAndLabelCompressionNPP.cpp</primary_file>
+  <required_dependencies>
+    <dependency>NPP</dependency>
+  </required_dependencies>
+  <scopes>
+    <scope>1:CUDA Basic Topics</scope>
+    <scope>1:Performance Strategies</scope>
+    <scope>2:Image Processing</scope>
+    <scope>2:Computer Vision</scope>
+  </scopes>
+  <sm-arch>sm35</sm-arch>
+  <sm-arch>sm37</sm-arch>
+  <sm-arch>sm50</sm-arch>
+  <sm-arch>sm52</sm-arch>
+  <sm-arch>sm60</sm-arch>
+  <sm-arch>sm61</sm-arch>
+  <sm-arch>sm70</sm-arch>
+  <sm-arch>sm72</sm-arch>
+  <sm-arch>sm75</sm-arch>
+  <sm-arch>sm80</sm-arch>
+  <sm-arch>sm86</sm-arch>
+  <supported_envs>
+    <env>
+      <arch>x86_64</arch>
+      <platform>linux</platform>
+    </env>
+    <env>
+      <platform>windows7</platform>
+    </env>
+    <env>
+      <arch>arm</arch>
+    </env>
+    <env>
+      <arch>ppc64le</arch>
+      <platform>linux</platform>
+    </env>
+  </supported_envs>
+  <supported_sm_architectures>
+    <include>all</include>
+  </supported_sm_architectures>
+  <title>Batched Label Markers And Label Compression NPP</title>
+  <type>exe</type>
+</entry>

Samples/batchedLabelMarkersAndLabelCompressionNPP/README.md

@@ -0,0 +1,72 @@
+# batchedLabelMarkersAndLabelCompressionNPP - Batched Label Markers And Label Compression NPP
+
+## Description
+
+An NPP CUDA Sample that demonstrates how to use the NPP label markers generation and label compression functions based on a Union Find (UF) algorithm including both
+single image and batched image versions.
+
+## Key Concepts
+
+Performance Strategies, Image Processing, NPP Library, Using NPP Batch Functions
+
+## Supported SM Architectures
+
+[SM 3.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 3.7 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.1 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.6 ](https://developer.nvidia.com/cuda-gpus)
+
+## Supported OSes
+
+Linux, Windows
+
+## Supported CPU Architecture
+
+x86_64, ppc64le, armv7l
+
+## CUDA APIs involved
+
+## Dependencies needed to build/run
+[NPP](../../README.md#npp)
+
+## Prerequisites
+
+Download and install the [CUDA Toolkit 11.1](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
+Make sure the dependencies mentioned in [Dependencies]() section above are installed.
+
+## Build and Run
+
+### Windows
+The Windows samples are built using the Visual Studio IDE. Solution files (.sln) are provided for each supported version of Visual Studio, using the format:
+```
+*_vs<version>.sln - for Visual Studio <version>
+```
+Each individual sample has its own set of solution files in its directory:
+
+To build/examine all the samples at once, the complete solution files should be used. To build/examine a single sample, the individual sample solution files should be used.
+> **Note:** Some samples require that the Microsoft DirectX SDK (June 2010 or newer) be installed and that the VC++ directory paths are properly set up (**Tools > Options...**). Check DirectX Dependencies section for details."
+
+### Linux
+The Linux samples are built using makefiles. To use the makefiles, change the current directory to the sample directory you wish to build, and run make:
+```
+$ cd <sample_dir>
+$ make
+```
+The samples makefiles can take advantage of certain options:
+*  **TARGET_ARCH=<arch>** - cross-compile targeting a specific architecture. Allowed architectures are x86_64, ppc64le, armv7l.
+    By default, TARGET_ARCH is set to HOST_ARCH. On a x86_64 machine, not setting TARGET_ARCH is the equivalent of setting TARGET_ARCH=x86_64.<br/>
+`$ make TARGET_ARCH=x86_64` <br/> `$ make TARGET_ARCH=ppc64le` <br/> `$ make TARGET_ARCH=armv7l` <br/>
+    See [here](http://docs.nvidia.com/cuda/cuda-samples/index.html#cross-samples) for more details.
+*   **dbg=1** - build with debug symbols
+    ```
+    $ make dbg=1
+    ```
+*   **SMS="A B ..."** - override the SM architectures for which the sample will be built, where `"A B ..."` is a space-delimited list of SM architectures. For example, to generate SASS for SM 50 and SM 60, use `SMS="50 60"`.
+    ```
+    $ make SMS="50 60"
+    ```
+
+*  **HOST_COMPILER=<host_compiler>** - override the default g++ host compiler. See the [Linux Installation Guide](http://docs.nvidia.com/cuda/cuda-installation-guide-linux/index.html#system-requirements) for a list of supported host compilers.
+```
+    $ make HOST_COMPILER=g++
+```
+
+## References (for more details)
+

Samples/batchedLabelMarkersAndLabelCompressionNPP/batchedLabelMarkersAndLabelCompressionNPP.cpp

@@ -0,0 +1,798 @@
+/* Copyright (c) 2020, NVIDIA CORPORATION. All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *  * Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ *  * Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ *  * Neither the name of NVIDIA CORPORATION nor the names of its
+ *    contributors may be used to endorse or promote products derived
+ *    from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+ * PURPOSE ARE DISCLAIMED.  IN NO EVENT SHALL THE COPYRIGHT OWNER OR
+ * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
+ * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
+ * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
+ * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
+ * OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#if defined(WIN32) || defined(_WIN32) || defined(WIN64) || defined(_WIN64)
+#define WINDOWS_LEAN_AND_MEAN
+#define NOMINMAX
+#include <windows.h>
+#pragma warning(disable : 4819)
+#endif
+
+#include <stdio.h>
+#include <string.h>
+#include <fstream>
+
+#include <helper_cuda.h>
+#include <npp.h>
+
+// Note:  If you want to view these images we HIGHLY recommend using imagej
+// which is free on the internet and works on most platforms
+//        because it is one of the few image viewing apps that can display 32
+//        bit integer image data.  While it normalizes the data to floating
+//        point values for viewing it still provides a good representation of
+//        the relative brightness of each label value. Note that label
+//        compression output results in smaller differences between label values
+//        making it visually more difficult to detect differences in labeled
+//        regions.  If you have an editor that can display hex values you can
+//        see what the exact values of each label is, every 4 bytes represents 1
+//        32 bit integer label value.
+//
+//        The files read and written by this sample app use RAW image format,
+//        that is, only the image data itself exists in the files with no image
+//        format information.   When viewing RAW files with imagej just enter
+//        the image size and bit depth values that are part of the file name
+//        when requested by imagej.
+//
+//        This sample app works in 2 stages, first it processes all of the
+//        images individually then it processes them all again in 1 batch using
+//        the Batch_Advanced versions of the NPP batch functions which allow
+//        each image to have it's own ROI.  The 2 stages are completely
+//        separable but in this sample the second stage takes advantage of some
+//        of the data that has already been initialized.
+//
+//        Note that there is a small amount of variability in the number of
+//        unique label markers generated from one run to the next by the UF
+//        algorithm.
+//
+//        Performance of ALL NPP image batch functions is limited by the maximum
+//        ROI height in the list of images.
+
+// Batched label compression support is only available on NPP versions > 11.0,
+// comment out if using NPP 11.0
+#define USE_BATCHED_LABEL_COMPRESSION 1
+
+#define NUMBER_OF_IMAGES 5
+
+Npp8u *pInputImageDev[NUMBER_OF_IMAGES];
+Npp8u *pInputImageHost[NUMBER_OF_IMAGES];
+Npp8u *pUFGenerateLabelsScratchBufferDev[NUMBER_OF_IMAGES];
+Npp8u *pUFCompressedLabelsScratchBufferDev[NUMBER_OF_IMAGES];
+Npp32u *pUFLabelDev[NUMBER_OF_IMAGES];
+Npp32u *pUFLabelHost[NUMBER_OF_IMAGES];
+NppiImageDescriptor *pUFBatchSrcImageListDev = 0;
+NppiImageDescriptor *pUFBatchSrcDstImageListDev = 0;
+NppiImageDescriptor *pUFBatchSrcImageListHost = 0;
+NppiImageDescriptor *pUFBatchSrcDstImageListHost = 0;
+NppiBufferDescriptor *pUFBatchSrcDstScratchBufferListDev =
+    0;  // from nppi_filtering_functions.h
+NppiBufferDescriptor *pUFBatchSrcDstScratchBufferListHost = 0;
+Npp32u *pUFBatchPerImageCompressedCountListDev = 0;
+Npp32u *pUFBatchPerImageCompressedCountListHost = 0;
+
+void tearDown()  // Clean up and tear down
+{
+  if (pUFBatchPerImageCompressedCountListDev != 0)
+    cudaFree(pUFBatchPerImageCompressedCountListDev);
+  if (pUFBatchSrcDstScratchBufferListDev != 0)
+    cudaFree(pUFBatchSrcDstScratchBufferListDev);
+  if (pUFBatchSrcDstImageListDev != 0) cudaFree(pUFBatchSrcDstImageListDev);
+  if (pUFBatchSrcImageListDev != 0) cudaFree(pUFBatchSrcImageListDev);
+  if (pUFBatchPerImageCompressedCountListHost != 0)
+    free(pUFBatchPerImageCompressedCountListHost);
+  if (pUFBatchSrcDstScratchBufferListHost != 0)
+    free(pUFBatchSrcDstScratchBufferListHost);
+  if (pUFBatchSrcDstImageListHost != 0) free(pUFBatchSrcDstImageListHost);
+  if (pUFBatchSrcImageListHost != 0) free(pUFBatchSrcImageListHost);
+
+  for (int j = 0; j < NUMBER_OF_IMAGES; j++) {
+    if (pUFCompressedLabelsScratchBufferDev[j] != 0)
+      cudaFree(pUFCompressedLabelsScratchBufferDev[j]);
+    if (pUFGenerateLabelsScratchBufferDev[j] != 0)
+      cudaFree(pUFGenerateLabelsScratchBufferDev[j]);
+    if (pUFLabelDev[j] != 0) cudaFree(pUFLabelDev[j]);
+    if (pInputImageDev[j] != 0) cudaFree(pInputImageDev[j]);
+    if (pUFLabelHost[j] != 0) free(pUFLabelHost[j]);
+    if (pInputImageHost[j] != 0) free(pInputImageHost[j]);
+  }
+}
+
+const std::string &LabelMarkersOutputFile0 =
+    "Lena_LabelMarkersUF_8Way_512x512_32u.raw";
+const std::string &LabelMarkersOutputFile1 =
+    "CT_skull_LabelMarkersUF_8Way_512x512_32u.raw";
+const std::string &LabelMarkersOutputFile2 =
+    "PCB_METAL_LabelMarkersUF_8Way_509x335_32u.raw";
+const std::string &LabelMarkersOutputFile3 =
+    "PCB2_LabelMarkersUF_8Way_1024x683_32u.raw";
+const std::string &LabelMarkersOutputFile4 =
+    "PCB_LabelMarkersUF_8Way_1280x720_32u.raw";
+
+const std::string &CompressedMarkerLabelsOutputFile0 =
+    "Lena_CompressedMarkerLabelsUF_8Way_512x512_32u.raw";
+const std::string &CompressedMarkerLabelsOutputFile1 =
+    "CT_skull_CompressedMarkerLabelsUF_8Way_512x512_32u.raw";
+const std::string &CompressedMarkerLabelsOutputFile2 =
+    "PCB_METAL_CompressedMarkerLabelsUF_8Way_509x335_32u.raw";
+const std::string &CompressedMarkerLabelsOutputFile3 =
+    "PCB2_CompressedMarkerLabelsUF_8Way_1024x683_32u.raw";
+const std::string &CompressedMarkerLabelsOutputFile4 =
+    "PCB_CompressedMarkerLabelsUF_8Way_1280x720_32u.raw";
+
+const std::string &LabelMarkersBatchOutputFile0 =
+    "Lena_LabelMarkersUFBatch_8Way_512x512_32u.raw";
+const std::string &LabelMarkersBatchOutputFile1 =
+    "CT_skull_LabelMarkersUFBatch_8Way_512x512_32u.raw";
+const std::string &LabelMarkersBatchOutputFile2 =
+    "PCB_METAL_LabelMarkersUFBatch_8Way_509x335_32u.raw";
+const std::string &LabelMarkersBatchOutputFile3 =
+    "PCB2_LabelMarkersUFBatch_8Way_1024x683_32u.raw";
+const std::string &LabelMarkersBatchOutputFile4 =
+    "PCB_LabelMarkersUFBatch_8Way_1280x720_32u.raw";
+
+const std::string &CompressedMarkerLabelsBatchOutputFile0 =
+    "Lena_CompressedMarkerLabelsUFBatch_8Way_512x512_32u.raw";
+const std::string &CompressedMarkerLabelsBatchOutputFile1 =
+    "CT_skull_CompressedMarkerLabelsUFBatch_8Way_512x512_32u.raw";
+const std::string &CompressedMarkerLabelsBatchOutputFile2 =
+    "PCB_METAL_CompressedMarkerLabelsUFBatch_8Way_509x335_32u.raw";
+const std::string &CompressedMarkerLabelsBatchOutputFile3 =
+    "PCB2_CompressedMarkerLabelsUFBatch_8Way_1024x683_32u.raw";
+const std::string &CompressedMarkerLabelsBatchOutputFile4 =
+    "PCB_CompressedMarkerLabelsUFBatch_8Way_1280x720_32u.raw";
+
+int loadRaw8BitImage(Npp8u *pImage, int nWidth, int nHeight, int nImage) {
+  FILE *bmpFile;
+  size_t nSize;
+
+  if (nImage == 0) {
+    if (nWidth != 512 || nHeight != 512) return -1;
+    const char *fileName = "lena_512x512_8u.raw";
+    const char *InputFile = sdkFindFilePath(fileName, ".");
+    if (InputFile == NULL) {
+      printf("%s file not found.. exiting\n", fileName);
+      exit(EXIT_WAIVED);
+    }
+
+    bmpFile = fopen(InputFile, "rb");
+  } else if (nImage == 1) {
+    if (nWidth != 512 || nHeight != 512) return -1;
+    const char *fileName = "CT_skull_512x512_8u.raw";
+    const char *InputFile = sdkFindFilePath(fileName, ".");
+    if (InputFile == NULL) {
+      printf("%s file not found.. exiting\n", fileName);
+      exit(EXIT_WAIVED);
+    }
+
+    bmpFile = fopen(InputFile, "rb");
+  } else if (nImage == 2) {
+    if (nWidth != 509 || nHeight != 335) return -1;
+    const char *fileName = "PCB_METAL_509x335_8u.raw";
+    const char *InputFile = sdkFindFilePath(fileName, ".");
+    if (InputFile == NULL) {
+      printf("%s file not found.. exiting\n", fileName);
+      exit(EXIT_WAIVED);
+    }
+
+    bmpFile = fopen(InputFile, "rb");
+  } else if (nImage == 3) {
+    if (nWidth != 1024 || nHeight != 683) return -1;
+    const char *fileName = "PCB2_1024x683_8u.raw";
+    const char *InputFile = sdkFindFilePath(fileName, ".");
+    if (InputFile == NULL) {
+      printf("%s file not found.. exiting\n", fileName);
+      exit(EXIT_WAIVED);
+    }
+
+    bmpFile = fopen(InputFile, "rb");
+  } else if (nImage == 4) {
+    if (nWidth != 1280 || nHeight != 720) return -1;
+    const char *fileName = "PCB_1280x720_8u.raw";
+    const char *InputFile = sdkFindFilePath(fileName, ".");
+    if (InputFile == NULL) {
+      printf("%s file not found.. exiting\n", fileName);
+      exit(EXIT_WAIVED);
+    }
+
+    bmpFile = fopen(InputFile, "rb");
+  } else {
+    printf("Input file load failed.\n");
+    return -1;
+  }
+
+  if (bmpFile == NULL) return -1;
+  nSize = fread(pImage, 1, nWidth * nHeight, bmpFile);
+  if (nSize < nWidth * nHeight) {
+    fclose(bmpFile);
+    return -1;
+  }
+  fclose(bmpFile);
+
+  printf("Input file load succeeded.\n");
+
+  return 0;
+}
+
+int main(int argc, char **argv) {
+  int aGenerateLabelsScratchBufferSize[NUMBER_OF_IMAGES];
+  int aCompressLabelsScratchBufferSize[NUMBER_OF_IMAGES];
+
+  int nCompressedLabelCount = 0;
+  cudaError_t cudaError;
+  NppStatus nppStatus;
+  NppStreamContext nppStreamCtx;
+  FILE *bmpFile;
+
+  for (int j = 0; j < NUMBER_OF_IMAGES; j++) {
+    pInputImageDev[j] = 0;
+    pInputImageHost[j] = 0;
+    pUFGenerateLabelsScratchBufferDev[j] = 0;
+    pUFCompressedLabelsScratchBufferDev[j] = 0;
+    pUFLabelDev[j] = 0;
+    pUFLabelHost[j] = 0;
+  }
+
+  nppStreamCtx.hStream = 0;  // The NULL stream by default, set this to whatever
+                             // your stream ID is if not the NULL stream.
+
+  cudaError = cudaGetDevice(&nppStreamCtx.nCudaDeviceId);
+  if (cudaError != cudaSuccess) {
+    printf("CUDA error: no devices supporting CUDA.\n");
+    return NPP_NOT_SUFFICIENT_COMPUTE_CAPABILITY;
+  }
+
+  const NppLibraryVersion *libVer = nppGetLibVersion();
+
+  printf("NPP Library Version %d.%d.%d\n", libVer->major, libVer->minor,
+         libVer->build);
+
+  int driverVersion, runtimeVersion;
+  cudaDriverGetVersion(&driverVersion);
+  cudaRuntimeGetVersion(&runtimeVersion);
+
+  printf("CUDA Driver  Version: %d.%d\n", driverVersion / 1000,
+         (driverVersion % 100) / 10);
+  printf("CUDA Runtime Version: %d.%d\n\n", runtimeVersion / 1000,
+         (runtimeVersion % 100) / 10);
+
+  cudaError = cudaDeviceGetAttribute(
+      &nppStreamCtx.nCudaDevAttrComputeCapabilityMajor,
+      cudaDevAttrComputeCapabilityMajor, nppStreamCtx.nCudaDeviceId);
+  if (cudaError != cudaSuccess) return NPP_NOT_SUFFICIENT_COMPUTE_CAPABILITY;
+
+  cudaError = cudaDeviceGetAttribute(
+      &nppStreamCtx.nCudaDevAttrComputeCapabilityMinor,
+      cudaDevAttrComputeCapabilityMinor, nppStreamCtx.nCudaDeviceId);
+  if (cudaError != cudaSuccess) return NPP_NOT_SUFFICIENT_COMPUTE_CAPABILITY;
+
+  cudaError =
+      cudaStreamGetFlags(nppStreamCtx.hStream, &nppStreamCtx.nStreamFlags);
+
+  cudaDeviceProp oDeviceProperties;
+
+  cudaError =
+      cudaGetDeviceProperties(&oDeviceProperties, nppStreamCtx.nCudaDeviceId);
+
+  nppStreamCtx.nMultiProcessorCount = oDeviceProperties.multiProcessorCount;
+  nppStreamCtx.nMaxThreadsPerMultiProcessor =
+      oDeviceProperties.maxThreadsPerMultiProcessor;
+  nppStreamCtx.nMaxThreadsPerBlock = oDeviceProperties.maxThreadsPerBlock;
+  nppStreamCtx.nSharedMemPerBlock = oDeviceProperties.sharedMemPerBlock;
+
+  NppiSize oSizeROI[NUMBER_OF_IMAGES];
+
+  for (int nImage = 0; nImage < NUMBER_OF_IMAGES; nImage++) {
+    if (nImage == 0) {
+      oSizeROI[nImage].width = 512;
+      oSizeROI[nImage].height = 512;
+    } else if (nImage == 1) {
+      oSizeROI[nImage].width = 512;
+      oSizeROI[nImage].height = 512;
+    } else if (nImage == 2) {
+      oSizeROI[nImage].width = 509;
+      oSizeROI[nImage].height = 335;
+    } else if (nImage == 3) {
+      oSizeROI[nImage].width = 1024;
+      oSizeROI[nImage].height = 683;
+    } else if (nImage == 4) {
+      oSizeROI[nImage].width = 1280;
+      oSizeROI[nImage].height = 720;
+    }
+
+    // NOTE: While using cudaMallocPitch() to allocate device memory for NPP can
+    // significantly improve the performance of many NPP functions, for UF
+    // function label markers generation or compression DO NOT USE
+    // cudaMallocPitch().  Doing so could result in incorrect output.
+
+    cudaError = cudaMalloc(
+        (void **)&pInputImageDev[nImage],
+        oSizeROI[nImage].width * sizeof(Npp8u) * oSizeROI[nImage].height);
+    if (cudaError != cudaSuccess) return NPP_MEMORY_ALLOCATION_ERR;
+
+    // For images processed with UF label markers functions ROI width and height
+    // for label markers generation output AND marker compression functions MUST
+    // be the same AND line pitch MUST be equal to ROI.width * sizeof(Npp32u).
+    // Also the image pointer used for label markers generation output must
+    // start at the same position in the image as it does in the marker
+    // compression function.  Also note that actual input image size and ROI do
+    // not necessarily need to be related other than ROI being less than or
+    // equal to image size and image starting position does not necessarily have
+    // to be at pixel 0 in the input image.
+
+    cudaError = cudaMalloc(
+        (void **)&pUFLabelDev[nImage],
+        oSizeROI[nImage].width * sizeof(Npp32u) * oSizeROI[nImage].height);
+    if (cudaError != cudaSuccess) return NPP_MEMORY_ALLOCATION_ERR;
+
+    pInputImageHost[nImage] = reinterpret_cast<Npp8u *>(malloc(
+        oSizeROI[nImage].width * sizeof(Npp8u) * oSizeROI[nImage].height));
+    pUFLabelHost[nImage] = reinterpret_cast<Npp32u *>(malloc(
+        oSizeROI[nImage].width * sizeof(Npp32u) * oSizeROI[nImage].height));
+
+    // Use UF functions throughout this sample.
+
+    nppStatus = nppiLabelMarkersUFGetBufferSize_32u_C1R(
+        oSizeROI[nImage], &aGenerateLabelsScratchBufferSize[nImage]);
+
+    // One at a time image processing
+
+    cudaError = cudaMalloc((void **)&pUFGenerateLabelsScratchBufferDev[nImage],
+                           aGenerateLabelsScratchBufferSize[nImage]);
+    if (cudaError != cudaSuccess) return NPP_MEMORY_ALLOCATION_ERR;
+
+    if (loadRaw8BitImage(pInputImageHost[nImage],
+                         oSizeROI[nImage].width * sizeof(Npp8u),
+                         oSizeROI[nImage].height, nImage) == 0) {
+      cudaError = cudaMemcpy2DAsync(
+          pInputImageDev[nImage], oSizeROI[nImage].width * sizeof(Npp8u),
+          pInputImageHost[nImage], oSizeROI[nImage].width * sizeof(Npp8u),
+          oSizeROI[nImage].width * sizeof(Npp8u), oSizeROI[nImage].height,
+          cudaMemcpyHostToDevice, nppStreamCtx.hStream);
+
+      nppStatus = nppiLabelMarkersUF_8u32u_C1R_Ctx(
+          pInputImageDev[nImage], oSizeROI[nImage].width * sizeof(Npp8u),
+          pUFLabelDev[nImage], oSizeROI[nImage].width * sizeof(Npp32u),
+          oSizeROI[nImage], nppiNormInf,
+          pUFGenerateLabelsScratchBufferDev[nImage], nppStreamCtx);
+
+      if (nppStatus != NPP_SUCCESS) {
+        if (nImage == 0)
+          printf("Lena_LabelMarkersUF_8Way_512x512_32u failed.\n");
+        else if (nImage == 1)
+          printf("CT_skull_LabelMarkersUF_8Way_512x512_32u failed.\n");
+        else if (nImage == 2)
+          printf("PCB_METAL_LabelMarkersUF_8Way_509x335_32u failed.\n");
+        else if (nImage == 3)
+          printf("PCB2_LabelMarkersUF_8Way_1024x683_32u failed.\n");
+        else if (nImage == 4)
+          printf("PCB_LabelMarkersUF_8Way_1280x720_32u failed.\n");
+        tearDown();
+        return -1;
+      }
+
+      cudaError = cudaMemcpy2DAsync(
+          pUFLabelHost[nImage], oSizeROI[nImage].width * sizeof(Npp32u),
+          pUFLabelDev[nImage], oSizeROI[nImage].width * sizeof(Npp32u),
+          oSizeROI[nImage].width * sizeof(Npp32u), oSizeROI[nImage].height,
+          cudaMemcpyDeviceToHost, nppStreamCtx.hStream);
+
+      // Wait host image read backs to complete, not necessary if no need to
+      // synchronize
+      if ((cudaError = cudaStreamSynchronize(nppStreamCtx.hStream)) !=
+          cudaSuccess) {
+        printf("Post label generation cudaStreamSynchronize failed\n");
+        tearDown();
+        return -1;
+      }
+
+      if (nImage == 0)
+        bmpFile = fopen(LabelMarkersOutputFile0.c_str(), "wb");
+      else if (nImage == 1)
+        bmpFile = fopen(LabelMarkersOutputFile1.c_str(), "wb");
+      else if (nImage == 2)
+        bmpFile = fopen(LabelMarkersOutputFile2.c_str(), "wb");
+      else if (nImage == 3)
+        bmpFile = fopen(LabelMarkersOutputFile3.c_str(), "wb");
+      else if (nImage == 4)
+        bmpFile = fopen(LabelMarkersOutputFile4.c_str(), "wb");
+
+      if (bmpFile == NULL) return -1;
+      size_t nSize = 0;
+      for (int j = 0; j < oSizeROI[nImage].height; j++) {
+        nSize += fwrite(&pUFLabelHost[nImage][j * oSizeROI[nImage].width],
+                        sizeof(Npp32u), oSizeROI[nImage].width, bmpFile);
+      }
+      fclose(bmpFile);
+
+      nppStatus = nppiCompressMarkerLabelsGetBufferSize_32u_C1R(
+          oSizeROI[nImage].width * oSizeROI[nImage].height,
+          &aCompressLabelsScratchBufferSize[nImage]);
+      if (nppStatus != NPP_NO_ERROR) return nppStatus;
+
+      cudaError =
+          cudaMalloc((void **)&pUFCompressedLabelsScratchBufferDev[nImage],
+                     aCompressLabelsScratchBufferSize[nImage]);
+      if (cudaError != cudaSuccess) return NPP_MEMORY_ALLOCATION_ERR;
+
+      nCompressedLabelCount = 0;
+
+      nppStatus = nppiCompressMarkerLabelsUF_32u_C1IR(
+          pUFLabelDev[nImage], oSizeROI[nImage].width * sizeof(Npp32u),
+          oSizeROI[nImage], oSizeROI[nImage].width * oSizeROI[nImage].height,
+          &nCompressedLabelCount, pUFCompressedLabelsScratchBufferDev[nImage]);
+
+      if (nppStatus != NPP_SUCCESS) {
+        if (nImage == 0)
+          printf("Lena_CompressedLabelMarkersUF_8Way_512x512_32u failed.\n");
+        else if (nImage == 1)
+          printf(
+              "CT_Skull_CompressedLabelMarkersUF_8Way_512x512_32u failed.\n");
+        else if (nImage == 2)
+          printf(
+              "PCB_METAL_CompressedLabelMarkersUF_8Way_509x335_32u failed.\n");
+        else if (nImage == 3)
+          printf("PCB2_CompressedLabelMarkersUF_8Way_1024x683_32u failed.\n");
+        else if (nImage == 4)
+          printf("PCB_CompressedLabelMarkersUF_8Way_1280x720_32u failed.\n");
+        tearDown();
+        return -1;
+      }
+
+      cudaError = cudaMemcpy2DAsync(
+          pUFLabelHost[nImage], oSizeROI[nImage].width * sizeof(Npp32u),
+          pUFLabelDev[nImage], oSizeROI[nImage].width * sizeof(Npp32u),
+          oSizeROI[nImage].width * sizeof(Npp32u), oSizeROI[nImage].height,
+          cudaMemcpyDeviceToHost, nppStreamCtx.hStream);
+
+      // Wait for host image read backs to finish, not necessary if no need to
+      // synchronize
+      if ((cudaError = cudaStreamSynchronize(nppStreamCtx.hStream)) !=
+              cudaSuccess ||
+          nCompressedLabelCount == 0) {
+        printf("Post label compression cudaStreamSynchronize failed\n");
+        tearDown();
+        return -1;
+      }
+
+      if (nImage == 0)
+        bmpFile = fopen(CompressedMarkerLabelsOutputFile0.c_str(), "wb");
+      else if (nImage == 1)
+        bmpFile = fopen(CompressedMarkerLabelsOutputFile1.c_str(), "wb");
+      else if (nImage == 2)
+        bmpFile = fopen(CompressedMarkerLabelsOutputFile2.c_str(), "wb");
+      else if (nImage == 3)
+        bmpFile = fopen(CompressedMarkerLabelsOutputFile3.c_str(), "wb");
+      else if (nImage == 4)
+        bmpFile = fopen(CompressedMarkerLabelsOutputFile4.c_str(), "wb");
+
+      if (bmpFile == NULL) return -1;
+      nSize = 0;
+      for (int j = 0; j < oSizeROI[nImage].height; j++) {
+        nSize += fwrite(&pUFLabelHost[nImage][j * oSizeROI[nImage].width],
+                        sizeof(Npp32u), oSizeROI[nImage].width, bmpFile);
+      }
+      fclose(bmpFile);
+
+      if (nImage == 0)
+        printf(
+            "Lena_CompressedMarkerLabelsUF_8Way_512x512_32u succeeded, "
+            "compressed label count is %d.\n",
+            nCompressedLabelCount);
+      else if (nImage == 1)
+        printf(
+            "CT_Skull_CompressedMarkerLabelsUF_8Way_512x512_32u succeeded, "
+            "compressed label count is %d.\n",
+            nCompressedLabelCount);
+      else if (nImage == 2)
+        printf(
+            "PCB_METAL_CompressedMarkerLabelsUF_8Way_509x335_32u succeeded, "
+            "compressed label count is %d.\n",
+            nCompressedLabelCount);
+      else if (nImage == 3)
+        printf(
+            "PCB2_CompressedMarkerLabelsUF_8Way_1024x683_32u succeeded, "
+            "compressed label count is %d.\n",
+            nCompressedLabelCount);
+      else if (nImage == 4)
+        printf(
+            "PCB_CompressedMarkerLabelsUF_8Way_1280x720_32u succeeded, "
+            "compressed label count is %d.\n",
+            nCompressedLabelCount);
+    }
+  }
+
+  // Batch image processing
+
+  // We want to allocate scratch buffers more efficiently for batch processing
+  // so first we free up the scratch buffers for image 0 and reallocate them.
+  // This is not required but helps cudaMalloc to work more efficiently.
+
+  cudaFree(pUFCompressedLabelsScratchBufferDev[0]);
+
+  int nTotalBatchedUFCompressLabelsScratchBufferDevSize = 0;
+
+  for (int k = 0; k < NUMBER_OF_IMAGES; k++)
+    nTotalBatchedUFCompressLabelsScratchBufferDevSize +=
+        aCompressLabelsScratchBufferSize[k];
+
+  cudaError = cudaMalloc((void **)&pUFCompressedLabelsScratchBufferDev[0],
+                         nTotalBatchedUFCompressLabelsScratchBufferDevSize);
+  if (cudaError != cudaSuccess) return NPP_MEMORY_ALLOCATION_ERR;
+
+  // Now allocate batch lists
+
+  int nBatchImageListBytes = NUMBER_OF_IMAGES * sizeof(NppiImageDescriptor);
+
+  cudaError =
+      cudaMalloc((void **)&pUFBatchSrcImageListDev, nBatchImageListBytes);
+  if (cudaError != cudaSuccess) return NPP_MEMORY_ALLOCATION_ERR;
+
+  cudaError =
+      cudaMalloc((void **)&pUFBatchSrcDstImageListDev, nBatchImageListBytes);
+  if (cudaError != cudaSuccess) return NPP_MEMORY_ALLOCATION_ERR;
+
+  pUFBatchSrcImageListHost =
+      reinterpret_cast<NppiImageDescriptor *>(malloc(nBatchImageListBytes));
+  pUFBatchSrcDstImageListHost =
+      reinterpret_cast<NppiImageDescriptor *>(malloc(nBatchImageListBytes));
+
+  NppiSize oMaxROISize = {0, 0};
+
+  for (int nImage = 0; nImage < NUMBER_OF_IMAGES; nImage++) {
+    pUFBatchSrcImageListHost[nImage].pData = pInputImageDev[nImage];
+    pUFBatchSrcImageListHost[nImage].nStep =
+        oSizeROI[nImage].width * sizeof(Npp8u);
+    // src image oSize parameter is ignored in these NPP functions
+    pUFBatchSrcDstImageListHost[nImage].pData = pUFLabelDev[nImage];
+    pUFBatchSrcDstImageListHost[nImage].nStep =
+        oSizeROI[nImage].width * sizeof(Npp32u);
+    pUFBatchSrcDstImageListHost[nImage].oSize = oSizeROI[nImage];
+    if (oSizeROI[nImage].width > oMaxROISize.width)
+      oMaxROISize.width = oSizeROI[nImage].width;
+    if (oSizeROI[nImage].height > oMaxROISize.height)
+      oMaxROISize.height = oSizeROI[nImage].height;
+  }
+
+  // Copy label generation batch lists from CPU to GPU
+  cudaError = cudaMemcpyAsync(pUFBatchSrcImageListDev, pUFBatchSrcImageListHost,
+                              nBatchImageListBytes, cudaMemcpyHostToDevice,
+                              nppStreamCtx.hStream);
+  if (cudaError != cudaSuccess) return NPP_MEMCPY_ERROR;
+
+  cudaError = cudaMemcpyAsync(pUFBatchSrcDstImageListDev,
+                              pUFBatchSrcDstImageListHost, nBatchImageListBytes,
+                              cudaMemcpyHostToDevice, nppStreamCtx.hStream);
+  if (cudaError != cudaSuccess) return NPP_MEMCPY_ERROR;
+
+  // We use 8-way neighbor search throughout this example
+  nppStatus = nppiLabelMarkersUFBatch_8u32u_C1R_Advanced_Ctx(
+      pUFBatchSrcImageListDev, pUFBatchSrcDstImageListDev, NUMBER_OF_IMAGES,
+      oMaxROISize, nppiNormInf, nppStreamCtx);
+
+  if (nppStatus != NPP_SUCCESS) {
+    printf("LabelMarkersUFBatch_8Way_8u32u failed.\n");
+    tearDown();
+    return -1;
+  }
+
+  // Now read back generated device images to the host
+
+  for (int nImage = 0; nImage < NUMBER_OF_IMAGES; nImage++) {
+    cudaError = cudaMemcpy2DAsync(
+        pUFLabelHost[nImage], oSizeROI[nImage].width * sizeof(Npp32u),
+        pUFLabelDev[nImage], oSizeROI[nImage].width * sizeof(Npp32u),
+        oSizeROI[nImage].width * sizeof(Npp32u), oSizeROI[nImage].height,
+        cudaMemcpyDeviceToHost, nppStreamCtx.hStream);
+  }
+
+  // Wait for host image read backs to complete, not necessary if no need to
+  // synchronize
+  if ((cudaError = cudaStreamSynchronize(nppStreamCtx.hStream)) !=
+      cudaSuccess) {
+    printf("Post label generation cudaStreamSynchronize failed\n");
+    tearDown();
+    return -1;
+  }
+
+  // Save output to files
+  for (int nImage = 0; nImage < NUMBER_OF_IMAGES; nImage++) {
+    if (nImage == 0)
+      bmpFile = fopen(LabelMarkersBatchOutputFile0.c_str(), "wb");
+    else if (nImage == 1)
+      bmpFile = fopen(LabelMarkersBatchOutputFile1.c_str(), "wb");
+    else if (nImage == 2)
+      bmpFile = fopen(LabelMarkersBatchOutputFile2.c_str(), "wb");
+    else if (nImage == 3)
+      bmpFile = fopen(LabelMarkersBatchOutputFile3.c_str(), "wb");
+    else if (nImage == 4)
+      bmpFile = fopen(LabelMarkersBatchOutputFile4.c_str(), "wb");
+
+    if (bmpFile == NULL) return -1;
+    size_t nSize = 0;
+    for (int j = 0; j < oSizeROI[nImage].height; j++) {
+      nSize += fwrite(&pUFLabelHost[nImage][j * oSizeROI[nImage].width],
+                      sizeof(Npp32u), oSizeROI[nImage].width, bmpFile);
+    }
+    fclose(bmpFile);
+  }
+
+#ifdef USE_BATCHED_LABEL_COMPRESSION
+
+  // Now allocate scratch buffer memory for batched label compression
+  cudaError = cudaMalloc((void **)&pUFBatchSrcDstScratchBufferListDev,
+                         NUMBER_OF_IMAGES * sizeof(NppiBufferDescriptor));
+  if (cudaError != cudaSuccess) return NPP_MEMORY_ALLOCATION_ERR;
+
+  cudaError = cudaMalloc((void **)&pUFBatchPerImageCompressedCountListDev,
+                         NUMBER_OF_IMAGES * sizeof(Npp32u));
+  if (cudaError != cudaSuccess) return NPP_MEMORY_ALLOCATION_ERR;
+
+  // Allocate host side scratch buffer point and size list and initialize with
+  // device scratch buffer pointers
+  pUFBatchSrcDstScratchBufferListHost =
+      reinterpret_cast<NppiBufferDescriptor *>(
+          malloc(NUMBER_OF_IMAGES * sizeof(NppiBufferDescriptor)));
+
+  pUFBatchPerImageCompressedCountListHost =
+      reinterpret_cast<Npp32u *>(malloc(NUMBER_OF_IMAGES * sizeof(Npp32u)));
+
+  // Start buffer pointer at beginning of full per image buffer list sized
+  // pUFCompressedLabelsScratchBufferDev[0]
+  Npp32u *pCurUFCompressedLabelsScratchBufferDev =
+      reinterpret_cast<Npp32u *>(pUFCompressedLabelsScratchBufferDev[0]);
+
+  int nMaxUFCompressedLabelsScratchBufferSize = 0;
+
+  for (int nImage = 0; nImage < NUMBER_OF_IMAGES; nImage++) {
+    // This particular function works on in-place data and SrcDst image batch
+    // list has already been initialized in batched label generation function
+    // setup
+
+    //  Initialize each per image buffer descriptor
+    pUFBatchSrcDstScratchBufferListHost[nImage].pData =
+        reinterpret_cast<void *>(pCurUFCompressedLabelsScratchBufferDev);
+    pUFBatchSrcDstScratchBufferListHost[nImage].nBufferSize =
+        aCompressLabelsScratchBufferSize[nImage];
+
+    if (aCompressLabelsScratchBufferSize[nImage] >
+        nMaxUFCompressedLabelsScratchBufferSize)
+      nMaxUFCompressedLabelsScratchBufferSize =
+          aCompressLabelsScratchBufferSize[nImage];
+
+    // Offset buffer pointer to next per image buffer
+    Npp8u *pTempBuffer =
+        reinterpret_cast<Npp8u *>(pCurUFCompressedLabelsScratchBufferDev);
+    pTempBuffer += aCompressLabelsScratchBufferSize[nImage];
+    pCurUFCompressedLabelsScratchBufferDev =
+        reinterpret_cast<Npp32u *>((void *)(pTempBuffer));
+  }
+
+  // Copy compression batch scratch buffer list from CPU to GPU
+  cudaError = cudaMemcpyAsync(pUFBatchSrcDstScratchBufferListDev,
+                              pUFBatchSrcDstScratchBufferListHost,
+                              NUMBER_OF_IMAGES * sizeof(NppiBufferDescriptor),
+                              cudaMemcpyHostToDevice, nppStreamCtx.hStream);
+  if (cudaError != cudaSuccess) return NPP_MEMCPY_ERROR;
+
+  nppStatus = nppiCompressMarkerLabelsUFBatch_32u_C1IR_Advanced_Ctx(
+      pUFBatchSrcDstImageListDev, pUFBatchSrcDstScratchBufferListDev,
+      pUFBatchPerImageCompressedCountListDev, NUMBER_OF_IMAGES, oMaxROISize,
+      nMaxUFCompressedLabelsScratchBufferSize, nppStreamCtx);
+  if (nppStatus != NPP_SUCCESS) {
+    printf("BatchCompressedLabelMarkersUF_8Way_32u failed.\n");
+    tearDown();
+    return -1;
+  }
+
+  // Copy output compressed label images back to host
+  for (int nImage = 0; nImage < NUMBER_OF_IMAGES; nImage++) {
+    cudaError = cudaMemcpy2DAsync(
+        pUFLabelHost[nImage], oSizeROI[nImage].width * sizeof(Npp32u),
+        pUFLabelDev[nImage], oSizeROI[nImage].width * sizeof(Npp32u),
+        oSizeROI[nImage].width * sizeof(Npp32u), oSizeROI[nImage].height,
+        cudaMemcpyDeviceToHost, nppStreamCtx.hStream);
+  }
+
+  // Wait for host image read backs to complete, not necessary if no need to
+  // synchronize
+  if ((cudaError = cudaStreamSynchronize(nppStreamCtx.hStream)) !=
+      cudaSuccess) {
+    printf("Post label compression cudaStreamSynchronize failed\n");
+    tearDown();
+    return -1;
+  }
+
+  // Save compressed label images into files
+  for (int nImage = 0; nImage < NUMBER_OF_IMAGES; nImage++) {
+    if (nImage == 0)
+      bmpFile = fopen(CompressedMarkerLabelsBatchOutputFile0.c_str(), "wb");
+    else if (nImage == 1)
+      bmpFile = fopen(CompressedMarkerLabelsBatchOutputFile1.c_str(), "wb");
+    else if (nImage == 2)
+      bmpFile = fopen(CompressedMarkerLabelsBatchOutputFile2.c_str(), "wb");
+    else if (nImage == 3)
+      bmpFile = fopen(CompressedMarkerLabelsBatchOutputFile3.c_str(), "wb");
+    else if (nImage == 4)
+      bmpFile = fopen(CompressedMarkerLabelsBatchOutputFile4.c_str(), "wb");
+
+    if (bmpFile == NULL) return -1;
+    size_t nSize = 0;
+    for (int j = 0; j < oSizeROI[nImage].height; j++) {
+      nSize += fwrite(&pUFLabelHost[nImage][j * oSizeROI[nImage].width],
+                      sizeof(Npp32u), oSizeROI[nImage].width, bmpFile);
+    }
+    fclose(bmpFile);
+  }
+
+  // Read back per image compressed label count.
+  cudaError = cudaMemcpyAsync(pUFBatchPerImageCompressedCountListHost,
+                              pUFBatchPerImageCompressedCountListDev,
+                              NUMBER_OF_IMAGES * sizeof(Npp32u),
+                              cudaMemcpyDeviceToHost, nppStreamCtx.hStream);
+  if (cudaError != cudaSuccess) {
+    tearDown();
+    return NPP_MEMCPY_ERROR;
+  }
+
+  // Wait for host read back to complete
+  cudaError = cudaStreamSynchronize(nppStreamCtx.hStream);
+
+  printf("\n\n");
+
+  for (int nImage = 0; nImage < NUMBER_OF_IMAGES; nImage++) {
+    if (nImage == 0)
+      printf(
+          "Lena_CompressedMarkerLabelsUFBatch_8Way_512x512_32u succeeded, "
+          "compressed label count is %d.\n",
+          pUFBatchPerImageCompressedCountListHost[nImage]);
+    else if (nImage == 1)
+      printf(
+          "CT_Skull_CompressedMarkerLabelsUFBatch_8Way_512x512_32u succeeded, "
+          "compressed label count is %d.\n",
+          pUFBatchPerImageCompressedCountListHost[nImage]);
+    else if (nImage == 2)
+      printf(
+          "PCB_METAL_CompressedMarkerLabelsUFBatch_8Way_509x335_32u succeeded, "
+          "compressed label count is %d.\n",
+          pUFBatchPerImageCompressedCountListHost[nImage]);
+    else if (nImage == 3)
+      printf(
+          "PCB2_CompressedMarkerLabelsUFBatch_8Way_1024x683_32u succeeded, "
+          "compressed label count is %d.\n",
+          pUFBatchPerImageCompressedCountListHost[nImage]);
+    else if (nImage == 4)
+      printf(
+          "PCB_CompressedMarkerLabelsUFBatch_8Way_1280x720_32u succeeded, "
+          "compressed label count is %d.\n",
+          pUFBatchPerImageCompressedCountListHost[nImage]);
+  }
+
+#endif  // USE_BATCHED_LABEL_COMPRESSION
+
+  tearDown();
+
+  return 0;
+}

Samples/batchedLabelMarkersAndLabelCompressionNPP/batchedLabelMarkersAndLabelCompressionNPP_vs2015.sln

@@ -1,7 +1,7 @@
 
-Microsoft Visual Studio Solution File, Format Version 13.00
+Microsoft Visual Studio Solution File, Format Version 14.00
-# Visual Studio 2013
+# Visual Studio 2015
-Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "matrixMul", "matrixMul_vs2013.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}"
+Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "batchedLabelMarkersAndLabelCompressionNPP", "batchedLabelMarkersAndLabelCompressionNPP_vs2015.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}"
 EndProject
 Global
 	GlobalSection(SolutionConfigurationPlatforms) = preSolution

Samples/batchedLabelMarkersAndLabelCompressionNPP/batchedLabelMarkersAndLabelCompressionNPP_vs2015.vcxproj

@@ -15,15 +15,15 @@
   </ItemGroup>
   <PropertyGroup Label="Globals">
     <ProjectGuid>{997E0757-EA74-4A4E-A0FC-47D8C8831A15}</ProjectGuid>
-    <RootNamespace>MersenneTwisterGP11213_vs2012</RootNamespace>
+    <RootNamespace>batchedLabelMarkersAndLabelCompressionNPP_vs2015</RootNamespace>
-    <ProjectName>MersenneTwisterGP11213</ProjectName>
+    <ProjectName>batchedLabelMarkersAndLabelCompressionNPP</ProjectName>
     <CudaToolkitCustomDir />
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
   <PropertyGroup>
     <ConfigurationType>Application</ConfigurationType>
     <CharacterSet>MultiByte</CharacterSet>
-    <PlatformToolset>v110</PlatformToolset>
+    <PlatformToolset>v140</PlatformToolset>
   </PropertyGroup>
   <PropertyGroup Condition="'$(Configuration)'=='Debug'">
     <UseDebugLibraries>true</UseDebugLibraries>
@@ -33,7 +33,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -57,9 +57,9 @@
     </ClCompile>
     <Link>
       <SubSystem>Console</SubSystem>
-      <AdditionalDependencies>curand.lib;cudart_static.lib;kernel32.lib;user32.lib;gdi32.lib;winspool.lib;comdlg32.lib;advapi32.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;odbc32.lib;odbccp32.lib;%(AdditionalDependencies)</AdditionalDependencies>
+      <AdditionalDependencies>nppisu.lib;nppif.lib;nppc.lib;cudart_static.lib;kernel32.lib;user32.lib;gdi32.lib;winspool.lib;comdlg32.lib;advapi32.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;odbc32.lib;odbccp32.lib;%(AdditionalDependencies)</AdditionalDependencies>
       <AdditionalLibraryDirectories>$(CudaToolkitLibDir);</AdditionalLibraryDirectories>
-      <OutputFile>$(OutDir)/MersenneTwisterGP11213.exe</OutputFile>
+      <OutputFile>$(OutDir)/batchedLabelMarkersAndLabelCompressionNPP.exe</OutputFile>
     </Link>
     <CudaCompile>
       <CodeGeneration>compute_35,compute_35;</CodeGeneration>
@@ -97,11 +97,11 @@
     </CudaCompile>
   </ItemDefinitionGroup>
   <ItemGroup>
-    <ClCompile Include="MersenneTwister.cpp" />
+    <ClCompile Include="batchedLabelMarkersAndLabelCompressionNPP.cpp" />
 
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
   </ImportGroup>
 </Project>

Samples/batchedLabelMarkersAndLabelCompressionNPP/batchedLabelMarkersAndLabelCompressionNPP_vs2017.sln

@@ -1,7 +1,7 @@
 
 Microsoft Visual Studio Solution File, Format Version 12.00
-# Visual Studio 2012
+# Visual Studio 2017
-Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "matrixMul", "matrixMul_vs2012.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}"
+Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "batchedLabelMarkersAndLabelCompressionNPP", "batchedLabelMarkersAndLabelCompressionNPP_vs2017.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}"
 EndProject
 Global
 	GlobalSection(SolutionConfigurationPlatforms) = preSolution

Samples/batchedLabelMarkersAndLabelCompressionNPP/batchedLabelMarkersAndLabelCompressionNPP_vs2017.vcxproj

@@ -15,15 +15,20 @@
   </ItemGroup>
   <PropertyGroup Label="Globals">
     <ProjectGuid>{997E0757-EA74-4A4E-A0FC-47D8C8831A15}</ProjectGuid>
-    <RootNamespace>cannyEdgeDetectorNPP_vs2012</RootNamespace>
+    <RootNamespace>batchedLabelMarkersAndLabelCompressionNPP_vs2017</RootNamespace>
-    <ProjectName>cannyEdgeDetectorNPP</ProjectName>
+    <ProjectName>batchedLabelMarkersAndLabelCompressionNPP</ProjectName>
     <CudaToolkitCustomDir />
   </PropertyGroup>
+  <PropertyGroup Condition="'$(WindowsTargetPlatformVersion)'==''">
+    <LatestTargetPlatformVersion>$([Microsoft.Build.Utilities.ToolLocationHelper]::GetLatestSDKTargetPlatformVersion('Windows', '10.0'))</LatestTargetPlatformVersion>
+    <WindowsTargetPlatformVersion Condition="'$(WindowsTargetPlatformVersion)' == ''">$(LatestTargetPlatformVersion)</WindowsTargetPlatformVersion>
+    <TargetPlatformVersion>$(WindowsTargetPlatformVersion)</TargetPlatformVersion>
+  </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
   <PropertyGroup>
     <ConfigurationType>Application</ConfigurationType>
     <CharacterSet>MultiByte</CharacterSet>
-    <PlatformToolset>v110</PlatformToolset>
+    <PlatformToolset>v141</PlatformToolset>
   </PropertyGroup>
   <PropertyGroup Condition="'$(Configuration)'=='Debug'">
     <UseDebugLibraries>true</UseDebugLibraries>
@@ -33,7 +38,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -53,13 +58,13 @@
     <ClCompile>
       <WarningLevel>Level3</WarningLevel>
       <PreprocessorDefinitions>WIN32;_MBCS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
-      <AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../Common;$(CudaToolkitIncludeDir);../../Common/UtilNPP;../../Common/FreeImage/include;</AdditionalIncludeDirectories>
+      <AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../Common;$(CudaToolkitIncludeDir);</AdditionalIncludeDirectories>
     </ClCompile>
     <Link>
       <SubSystem>Console</SubSystem>
       <AdditionalDependencies>nppisu.lib;nppif.lib;nppc.lib;cudart_static.lib;kernel32.lib;user32.lib;gdi32.lib;winspool.lib;comdlg32.lib;advapi32.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;odbc32.lib;odbccp32.lib;%(AdditionalDependencies)</AdditionalDependencies>
-      <AdditionalLibraryDirectories>$(CudaToolkitLibDir);../../Common/FreeImage/lib/x64;../../Common/FreeImage/lib/$(TARGET_OS);../../Common/FreeImage/lib/$(TARGET_OS)/$(TARGET_ARCH);</AdditionalLibraryDirectories>
+      <AdditionalLibraryDirectories>$(CudaToolkitLibDir);</AdditionalLibraryDirectories>
-      <OutputFile>$(OutDir)/cannyEdgeDetectorNPP.exe</OutputFile>
+      <OutputFile>$(OutDir)/batchedLabelMarkersAndLabelCompressionNPP.exe</OutputFile>
     </Link>
     <CudaCompile>
       <CodeGeneration>compute_35,compute_35;</CodeGeneration>
@@ -96,22 +101,12 @@
       <TargetMachinePlatform>64</TargetMachinePlatform>
     </CudaCompile>
   </ItemDefinitionGroup>
-  <ItemDefinitionGroup Condition="'$(Platform)'=='Win32'">
-    <Link>
-      
-    </Link>
-  </ItemDefinitionGroup>
-  <ItemDefinitionGroup Condition="'$(Platform)'=='x64'">
-    <Link>
-      <AdditionalDependencies>freeimage.lib;%(AdditionalDependencies)</AdditionalDependencies>
-    </Link>
-  </ItemDefinitionGroup>
   <ItemGroup>
-    <ClCompile Include="cannyEdgeDetectorNPP.cpp" />
+    <ClCompile Include="batchedLabelMarkersAndLabelCompressionNPP.cpp" />
 
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
   </ImportGroup>
 </Project>

Samples/batchedLabelMarkersAndLabelCompressionNPP/batchedLabelMarkersAndLabelCompressionNPP_vs2019.sln

@@ -1,7 +1,7 @@
 
 Microsoft Visual Studio Solution File, Format Version 12.00
-# Visual Studio 2012
+# Visual Studio 2019
-Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "reduction", "reduction_vs2012.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}"
+Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "batchedLabelMarkersAndLabelCompressionNPP", "batchedLabelMarkersAndLabelCompressionNPP_vs2019.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}"
 EndProject
 Global
 	GlobalSection(SolutionConfigurationPlatforms) = preSolution

Samples/batchedLabelMarkersAndLabelCompressionNPP/batchedLabelMarkersAndLabelCompressionNPP_vs2019.vcxproj

@@ -15,15 +15,16 @@
   </ItemGroup>
   <PropertyGroup Label="Globals">
     <ProjectGuid>{997E0757-EA74-4A4E-A0FC-47D8C8831A15}</ProjectGuid>
-    <RootNamespace>MersenneTwisterGP11213_vs2013</RootNamespace>
+    <RootNamespace>batchedLabelMarkersAndLabelCompressionNPP_vs2019</RootNamespace>
-    <ProjectName>MersenneTwisterGP11213</ProjectName>
+    <ProjectName>batchedLabelMarkersAndLabelCompressionNPP</ProjectName>
     <CudaToolkitCustomDir />
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
   <PropertyGroup>
     <ConfigurationType>Application</ConfigurationType>
     <CharacterSet>MultiByte</CharacterSet>
-    <PlatformToolset>v120</PlatformToolset>
+    <PlatformToolset>v142</PlatformToolset>
+    <WindowsTargetPlatformVersion>10.0</WindowsTargetPlatformVersion>
   </PropertyGroup>
   <PropertyGroup Condition="'$(Configuration)'=='Debug'">
     <UseDebugLibraries>true</UseDebugLibraries>
@@ -33,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -57,9 +58,9 @@
     </ClCompile>
     <Link>
       <SubSystem>Console</SubSystem>
-      <AdditionalDependencies>curand.lib;cudart_static.lib;kernel32.lib;user32.lib;gdi32.lib;winspool.lib;comdlg32.lib;advapi32.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;odbc32.lib;odbccp32.lib;%(AdditionalDependencies)</AdditionalDependencies>
+      <AdditionalDependencies>nppisu.lib;nppif.lib;nppc.lib;cudart_static.lib;kernel32.lib;user32.lib;gdi32.lib;winspool.lib;comdlg32.lib;advapi32.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;odbc32.lib;odbccp32.lib;%(AdditionalDependencies)</AdditionalDependencies>
       <AdditionalLibraryDirectories>$(CudaToolkitLibDir);</AdditionalLibraryDirectories>
-      <OutputFile>$(OutDir)/MersenneTwisterGP11213.exe</OutputFile>
+      <OutputFile>$(OutDir)/batchedLabelMarkersAndLabelCompressionNPP.exe</OutputFile>
     </Link>
     <CudaCompile>
       <CodeGeneration>compute_35,compute_35;</CodeGeneration>
@@ -97,11 +98,11 @@
     </CudaCompile>
   </ItemDefinitionGroup>
   <ItemGroup>
-    <ClCompile Include="MersenneTwister.cpp" />
+    <ClCompile Include="batchedLabelMarkersAndLabelCompressionNPP.cpp" />
 
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
   </ImportGroup>
 </Project>

Samples/bf16TensorCoreGemm/Makefile

@@ -306,7 +306,7 @@ ifeq ($(TARGET_OS),linux)
 endif
 
 # Gencode arguments
-SMS ?= 80
+SMS ?= 80 86
 
 ifeq ($(SMS),)
 $(info >>> WARNING - no SM architectures have been specified - waiving sample <<<)

Samples/bf16TensorCoreGemm/NsightEclipse.xml

@@ -43,6 +43,7 @@
     <scope>1:CUDA Basic Topics</scope>
   </scopes>
   <sm-arch>sm80</sm-arch>
+  <sm-arch>sm86</sm-arch>
   <supported_envs>
     <env>
       <arch>x86_64</arch>

Samples/bf16TensorCoreGemm/README.md

@@ -10,7 +10,7 @@ Matrix Multiply, WMMA, Tensor Cores
 
 ## Supported SM Architectures
 
-[SM 8.0 ](https://developer.nvidia.com/cuda-gpus)
+[SM 8.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.6 ](https://developer.nvidia.com/cuda-gpus)
 
 ## Supported OSes
 
@@ -27,7 +27,7 @@ cudaMallocManaged, cudaDeviceSynchronize, cudaFuncSetAttribute, cudaEventCreate,
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 11.0](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
+Download and install the [CUDA Toolkit 11.1](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
 
 ## Build and Run
 

Samples/bf16TensorCoreGemm/bf16TensorCoreGemm_vs2015.vcxproj

@@ -33,7 +33,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -62,7 +62,7 @@
       <OutputFile>$(OutDir)/bf16TensorCoreGemm.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <CodeGeneration>compute_80,sm_80;</CodeGeneration>
+      <CodeGeneration>compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
       <AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
       <Include>./;../../Common</Include>
       <Defines>WIN32</Defines>
@@ -102,6 +102,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
   </ImportGroup>
 </Project>

Samples/bf16TensorCoreGemm/bf16TensorCoreGemm_vs2017.vcxproj

@@ -38,7 +38,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -67,7 +67,7 @@
       <OutputFile>$(OutDir)/bf16TensorCoreGemm.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <CodeGeneration>compute_80,sm_80;</CodeGeneration>
+      <CodeGeneration>compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
       <AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
       <Include>./;../../Common</Include>
       <Defines>WIN32</Defines>
@@ -107,6 +107,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
   </ImportGroup>
 </Project>

Samples/bf16TensorCoreGemm/bf16TensorCoreGemm_vs2019.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -63,7 +63,7 @@
       <OutputFile>$(OutDir)/bf16TensorCoreGemm.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <CodeGeneration>compute_80,sm_80;</CodeGeneration>
+      <CodeGeneration>compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
       <AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
       <Include>./;../../Common</Include>
       <Defines>WIN32</Defines>
@@ -103,6 +103,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
   </ImportGroup>
 </Project>

Samples/binaryPartitionCG/Makefile

@@ -301,9 +301,9 @@ endif
 
 # Gencode arguments
 ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64))
-SMS ?= 35 37 50 52 60 61 70 72 75 80
+SMS ?= 35 37 50 52 60 61 70 72 75 80 86
 else
-SMS ?= 35 37 50 52 60 61 70 75 80
+SMS ?= 35 37 50 52 60 61 70 75 80 86
 endif
 
 ifeq ($(SMS),)

Samples/binaryPartitionCG/NsightEclipse.xml

@@ -40,6 +40,7 @@
   <sm-arch>sm72</sm-arch>
   <sm-arch>sm75</sm-arch>
   <sm-arch>sm80</sm-arch>
+  <sm-arch>sm86</sm-arch>
   <supported_envs>
     <env>
       <arch>x86_64</arch>

Samples/binaryPartitionCG/README.md

@@ -10,7 +10,7 @@ Cooperative Groups
 
 ## Supported SM Architectures
 
-[SM 3.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 3.7 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.1 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.0 ](https://developer.nvidia.com/cuda-gpus)
+[SM 3.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 3.7 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.1 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.6 ](https://developer.nvidia.com/cuda-gpus)
 
 ## Supported OSes
 
@@ -24,7 +24,7 @@ x86_64, ppc64le, armv7l
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 11.0](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
+Download and install the [CUDA Toolkit 11.1](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
 
 ## Build and Run
 

Samples/binaryPartitionCG/binaryPartitionCG_vs2015.vcxproj

@@ -33,7 +33,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -62,7 +62,7 @@
       <OutputFile>$(OutDir)/binaryPartitionCG.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;</CodeGeneration>
+      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
       <AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
       <Include>./;../../Common</Include>
       <Defines>WIN32</Defines>
@@ -102,6 +102,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
   </ImportGroup>
 </Project>

Samples/binaryPartitionCG/binaryPartitionCG_vs2017.vcxproj

@@ -38,7 +38,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -67,7 +67,7 @@
       <OutputFile>$(OutDir)/binaryPartitionCG.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;</CodeGeneration>
+      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
       <AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
       <Include>./;../../Common</Include>
       <Defines>WIN32</Defines>
@@ -107,6 +107,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
   </ImportGroup>
 </Project>

Samples/binaryPartitionCG/binaryPartitionCG_vs2019.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -63,7 +63,7 @@
       <OutputFile>$(OutDir)/binaryPartitionCG.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;</CodeGeneration>
+      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
       <AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
       <Include>./;../../Common</Include>
       <Defines>WIN32</Defines>
@@ -103,6 +103,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
   </ImportGroup>
 </Project>

Samples/boxFilterNPP/NsightEclipse.xml

@@ -59,6 +59,7 @@
   <sm-arch>sm72</sm-arch>
   <sm-arch>sm75</sm-arch>
   <sm-arch>sm80</sm-arch>
+  <sm-arch>sm86</sm-arch>
   <supported_envs>
     <env>
       <arch>x86_64</arch>

Samples/boxFilterNPP/README.md

@@ -10,7 +10,7 @@ Performance Strategies, Image Processing, NPP Library
 
 ## Supported SM Architectures
 
-[SM 3.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 3.7 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.1 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.0 ](https://developer.nvidia.com/cuda-gpus)
+[SM 3.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 3.7 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.1 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.6 ](https://developer.nvidia.com/cuda-gpus)
 
 ## Supported OSes
 
@@ -27,7 +27,7 @@ x86_64, ppc64le, armv7l
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 11.0](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
+Download and install the [CUDA Toolkit 11.1](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/boxFilterNPP/boxFilterNPP_vs2012.sln

@@ -1,20 +0,0 @@
-
-Microsoft Visual Studio Solution File, Format Version 12.00
-# Visual Studio 2012
-Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "boxFilterNPP", "boxFilterNPP_vs2012.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}"
-EndProject
-Global
-	GlobalSection(SolutionConfigurationPlatforms) = preSolution
-		Debug|x64 = Debug|x64
-		Release|x64 = Release|x64
-	EndGlobalSection
-	GlobalSection(ProjectConfigurationPlatforms) = postSolution
-		{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.ActiveCfg = Debug|x64
-		{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.Build.0 = Debug|x64
-		{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.ActiveCfg = Release|x64
-		{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.Build.0 = Release|x64
-	EndGlobalSection
-	GlobalSection(SolutionProperties) = preSolution
-		HideSolutionNode = FALSE
-	EndGlobalSection
-EndGlobal

Samples/boxFilterNPP/boxFilterNPP_vs2013.sln

@@ -1,20 +0,0 @@
-
-Microsoft Visual Studio Solution File, Format Version 13.00
-# Visual Studio 2013
-Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "boxFilterNPP", "boxFilterNPP_vs2013.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}"
-EndProject
-Global
-	GlobalSection(SolutionConfigurationPlatforms) = preSolution
-		Debug|x64 = Debug|x64
-		Release|x64 = Release|x64
-	EndGlobalSection
-	GlobalSection(ProjectConfigurationPlatforms) = postSolution
-		{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.ActiveCfg = Debug|x64
-		{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.Build.0 = Debug|x64
-		{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.ActiveCfg = Release|x64
-		{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.Build.0 = Release|x64
-	EndGlobalSection
-	GlobalSection(SolutionProperties) = preSolution
-		HideSolutionNode = FALSE
-	EndGlobalSection
-EndGlobal

Samples/boxFilterNPP/boxFilterNPP_vs2013.vcxproj

@@ -1,117 +0,0 @@
-<?xml version="1.0" encoding="utf-8"?>
-<Project DefaultTargets="Build" ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
-  <PropertyGroup>
-    <CUDAPropsPath Condition="'$(CUDAPropsPath)'==''">$(VCTargetsPath)\BuildCustomizations</CUDAPropsPath>
-  </PropertyGroup>
-  <ItemGroup Label="ProjectConfigurations">
-    <ProjectConfiguration Include="Debug|x64">
-      <Configuration>Debug</Configuration>
-      <Platform>x64</Platform>
-    </ProjectConfiguration>
-    <ProjectConfiguration Include="Release|x64">
-      <Configuration>Release</Configuration>
-      <Platform>x64</Platform>
-    </ProjectConfiguration>
-  </ItemGroup>
-  <PropertyGroup Label="Globals">
-    <ProjectGuid>{997E0757-EA74-4A4E-A0FC-47D8C8831A15}</ProjectGuid>
-    <RootNamespace>boxFilterNPP_vs2013</RootNamespace>
-    <ProjectName>boxFilterNPP</ProjectName>
-    <CudaToolkitCustomDir />
-  </PropertyGroup>
-  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
-  <PropertyGroup>
-    <ConfigurationType>Application</ConfigurationType>
-    <CharacterSet>MultiByte</CharacterSet>
-    <PlatformToolset>v120</PlatformToolset>
-  </PropertyGroup>
-  <PropertyGroup Condition="'$(Configuration)'=='Debug'">
-    <UseDebugLibraries>true</UseDebugLibraries>
-  </PropertyGroup>
-  <PropertyGroup Condition="'$(Configuration)'=='Release'">
-    <WholeProgramOptimization>true</WholeProgramOptimization>
-  </PropertyGroup>
-  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
-  <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.props" />
-  </ImportGroup>
-  <ImportGroup Label="PropertySheets">
-    <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
-  </ImportGroup>
-  <PropertyGroup Label="UserMacros" />
-  <PropertyGroup>
-    <IntDir>$(Platform)/$(Configuration)/</IntDir>
-    <IncludePath>$(IncludePath)</IncludePath>
-    <CodeAnalysisRuleSet>AllRules.ruleset</CodeAnalysisRuleSet>
-    <CodeAnalysisRules />
-    <CodeAnalysisRuleAssemblies />
-  </PropertyGroup>
-  <PropertyGroup Condition="'$(Platform)'=='x64'">
-    <OutDir>../../bin/win64/$(Configuration)/</OutDir>
-  </PropertyGroup>
-  <ItemDefinitionGroup>
-    <ClCompile>
-      <WarningLevel>Level3</WarningLevel>
-      <PreprocessorDefinitions>WIN32;_MBCS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
-      <AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../Common;$(CudaToolkitIncludeDir);../../Common/UtilNPP;../../Common/FreeImage/include;</AdditionalIncludeDirectories>
-    </ClCompile>
-    <Link>
-      <SubSystem>Console</SubSystem>
-      <AdditionalDependencies>nppisu.lib;nppif.lib;nppc.lib;cudart_static.lib;kernel32.lib;user32.lib;gdi32.lib;winspool.lib;comdlg32.lib;advapi32.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;odbc32.lib;odbccp32.lib;%(AdditionalDependencies)</AdditionalDependencies>
-      <AdditionalLibraryDirectories>$(CudaToolkitLibDir);../../Common/FreeImage/lib/x64;../../Common/FreeImage/lib/$(TARGET_OS);../../Common/FreeImage/lib/$(TARGET_OS)/$(TARGET_ARCH);</AdditionalLibraryDirectories>
-      <OutputFile>$(OutDir)/boxFilterNPP.exe</OutputFile>
-    </Link>
-    <CudaCompile>
-      <CodeGeneration>compute_35,compute_35;</CodeGeneration>
-      <AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
-      <Include>./;../../Common</Include>
-      <Defines>WIN32</Defines>
-    </CudaCompile>
-  </ItemDefinitionGroup>
-  <ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
-    <ClCompile>
-      <Optimization>Disabled</Optimization>
-      <RuntimeLibrary>MultiThreadedDebug</RuntimeLibrary>
-    </ClCompile>
-    <Link>
-      <GenerateDebugInformation>true</GenerateDebugInformation>
-      <LinkTimeCodeGeneration>Default</LinkTimeCodeGeneration>
-    </Link>
-    <CudaCompile>
-      <Runtime>MTd</Runtime>
-      <TargetMachinePlatform>64</TargetMachinePlatform>
-    </CudaCompile>
-  </ItemDefinitionGroup>
-  <ItemDefinitionGroup Condition="'$(Configuration)'=='Release'">
-    <ClCompile>
-      <Optimization>MaxSpeed</Optimization>
-      <RuntimeLibrary>MultiThreaded</RuntimeLibrary>
-    </ClCompile>
-    <Link>
-      <GenerateDebugInformation>false</GenerateDebugInformation>
-      <LinkTimeCodeGeneration>UseLinkTimeCodeGeneration</LinkTimeCodeGeneration>
-    </Link>
-    <CudaCompile>
-      <Runtime>MT</Runtime>
-      <TargetMachinePlatform>64</TargetMachinePlatform>
-    </CudaCompile>
-  </ItemDefinitionGroup>
-  <ItemDefinitionGroup Condition="'$(Platform)'=='Win32'">
-    <Link>
-      
-    </Link>
-  </ItemDefinitionGroup>
-  <ItemDefinitionGroup Condition="'$(Platform)'=='x64'">
-    <Link>
-      <AdditionalDependencies>freeimage.lib;%(AdditionalDependencies)</AdditionalDependencies>
-    </Link>
-  </ItemDefinitionGroup>
-  <ItemGroup>
-    <ClCompile Include="boxFilterNPP.cpp" />
-
-  </ItemGroup>
-  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
-  <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.targets" />
-  </ImportGroup>
-</Project>

Samples/boxFilterNPP/boxFilterNPP_vs2015.vcxproj

@@ -33,7 +33,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(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="$(CUDAPropsPath)\CUDA 11.0.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
   </ImportGroup>
 </Project>

Samples/boxFilterNPP/boxFilterNPP_vs2017.vcxproj

@@ -38,7 +38,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -117,6 +117,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
   </ImportGroup>
 </Project>

Samples/boxFilterNPP/boxFilterNPP_vs2019.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -113,6 +113,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
   </ImportGroup>
 </Project>

Samples/cannyEdgeDetectorNPP/NsightEclipse.xml

@@ -55,6 +55,7 @@
   <sm-arch>sm72</sm-arch>
   <sm-arch>sm75</sm-arch>
   <sm-arch>sm80</sm-arch>
+  <sm-arch>sm86</sm-arch>
   <supported_envs>
     <env>
       <arch>x86_64</arch>

Samples/cannyEdgeDetectorNPP/README.md

@@ -10,7 +10,7 @@ Performance Strategies, Image Processing, NPP Library
 
 ## Supported SM Architectures
 
-[SM 3.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 3.7 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.1 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.0 ](https://developer.nvidia.com/cuda-gpus)
+[SM 3.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 3.7 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.1 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.6 ](https://developer.nvidia.com/cuda-gpus)
 
 ## Supported OSes
 
@@ -27,7 +27,7 @@ x86_64, ppc64le, armv7l
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 11.0](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
+Download and install the [CUDA Toolkit 11.1](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/cannyEdgeDetectorNPP/cannyEdgeDetectorNPP_vs2012.sln

@@ -1,20 +0,0 @@
-
-Microsoft Visual Studio Solution File, Format Version 12.00
-# Visual Studio 2012
-Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "cannyEdgeDetectorNPP", "cannyEdgeDetectorNPP_vs2012.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}"
-EndProject
-Global
-	GlobalSection(SolutionConfigurationPlatforms) = preSolution
-		Debug|x64 = Debug|x64
-		Release|x64 = Release|x64
-	EndGlobalSection
-	GlobalSection(ProjectConfigurationPlatforms) = postSolution
-		{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.ActiveCfg = Debug|x64
-		{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.Build.0 = Debug|x64
-		{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.ActiveCfg = Release|x64
-		{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.Build.0 = Release|x64
-	EndGlobalSection
-	GlobalSection(SolutionProperties) = preSolution
-		HideSolutionNode = FALSE
-	EndGlobalSection
-EndGlobal

Samples/cannyEdgeDetectorNPP/cannyEdgeDetectorNPP_vs2013.sln

@@ -1,20 +0,0 @@
-
-Microsoft Visual Studio Solution File, Format Version 13.00
-# Visual Studio 2013
-Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "cannyEdgeDetectorNPP", "cannyEdgeDetectorNPP_vs2013.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}"
-EndProject
-Global
-	GlobalSection(SolutionConfigurationPlatforms) = preSolution
-		Debug|x64 = Debug|x64
-		Release|x64 = Release|x64
-	EndGlobalSection
-	GlobalSection(ProjectConfigurationPlatforms) = postSolution
-		{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.ActiveCfg = Debug|x64
-		{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.Build.0 = Debug|x64
-		{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.ActiveCfg = Release|x64
-		{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.Build.0 = Release|x64
-	EndGlobalSection
-	GlobalSection(SolutionProperties) = preSolution
-		HideSolutionNode = FALSE
-	EndGlobalSection
-EndGlobal

Samples/cannyEdgeDetectorNPP/cannyEdgeDetectorNPP_vs2013.vcxproj

@@ -1,117 +0,0 @@
-<?xml version="1.0" encoding="utf-8"?>
-<Project DefaultTargets="Build" ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
-  <PropertyGroup>
-    <CUDAPropsPath Condition="'$(CUDAPropsPath)'==''">$(VCTargetsPath)\BuildCustomizations</CUDAPropsPath>
-  </PropertyGroup>
-  <ItemGroup Label="ProjectConfigurations">
-    <ProjectConfiguration Include="Debug|x64">
-      <Configuration>Debug</Configuration>
-      <Platform>x64</Platform>
-    </ProjectConfiguration>
-    <ProjectConfiguration Include="Release|x64">
-      <Configuration>Release</Configuration>
-      <Platform>x64</Platform>
-    </ProjectConfiguration>
-  </ItemGroup>
-  <PropertyGroup Label="Globals">
-    <ProjectGuid>{997E0757-EA74-4A4E-A0FC-47D8C8831A15}</ProjectGuid>
-    <RootNamespace>cannyEdgeDetectorNPP_vs2013</RootNamespace>
-    <ProjectName>cannyEdgeDetectorNPP</ProjectName>
-    <CudaToolkitCustomDir />
-  </PropertyGroup>
-  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
-  <PropertyGroup>
-    <ConfigurationType>Application</ConfigurationType>
-    <CharacterSet>MultiByte</CharacterSet>
-    <PlatformToolset>v120</PlatformToolset>
-  </PropertyGroup>
-  <PropertyGroup Condition="'$(Configuration)'=='Debug'">
-    <UseDebugLibraries>true</UseDebugLibraries>
-  </PropertyGroup>
-  <PropertyGroup Condition="'$(Configuration)'=='Release'">
-    <WholeProgramOptimization>true</WholeProgramOptimization>
-  </PropertyGroup>
-  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
-  <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.props" />
-  </ImportGroup>
-  <ImportGroup Label="PropertySheets">
-    <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
-  </ImportGroup>
-  <PropertyGroup Label="UserMacros" />
-  <PropertyGroup>
-    <IntDir>$(Platform)/$(Configuration)/</IntDir>
-    <IncludePath>$(IncludePath)</IncludePath>
-    <CodeAnalysisRuleSet>AllRules.ruleset</CodeAnalysisRuleSet>
-    <CodeAnalysisRules />
-    <CodeAnalysisRuleAssemblies />
-  </PropertyGroup>
-  <PropertyGroup Condition="'$(Platform)'=='x64'">
-    <OutDir>../../bin/win64/$(Configuration)/</OutDir>
-  </PropertyGroup>
-  <ItemDefinitionGroup>
-    <ClCompile>
-      <WarningLevel>Level3</WarningLevel>
-      <PreprocessorDefinitions>WIN32;_MBCS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
-      <AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../Common;$(CudaToolkitIncludeDir);../../Common/UtilNPP;../../Common/FreeImage/include;</AdditionalIncludeDirectories>
-    </ClCompile>
-    <Link>
-      <SubSystem>Console</SubSystem>
-      <AdditionalDependencies>nppisu.lib;nppif.lib;nppc.lib;cudart_static.lib;kernel32.lib;user32.lib;gdi32.lib;winspool.lib;comdlg32.lib;advapi32.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;odbc32.lib;odbccp32.lib;%(AdditionalDependencies)</AdditionalDependencies>
-      <AdditionalLibraryDirectories>$(CudaToolkitLibDir);../../Common/FreeImage/lib/x64;../../Common/FreeImage/lib/$(TARGET_OS);../../Common/FreeImage/lib/$(TARGET_OS)/$(TARGET_ARCH);</AdditionalLibraryDirectories>
-      <OutputFile>$(OutDir)/cannyEdgeDetectorNPP.exe</OutputFile>
-    </Link>
-    <CudaCompile>
-      <CodeGeneration>compute_35,compute_35;</CodeGeneration>
-      <AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
-      <Include>./;../../Common</Include>
-      <Defines>WIN32</Defines>
-    </CudaCompile>
-  </ItemDefinitionGroup>
-  <ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
-    <ClCompile>
-      <Optimization>Disabled</Optimization>
-      <RuntimeLibrary>MultiThreadedDebug</RuntimeLibrary>
-    </ClCompile>
-    <Link>
-      <GenerateDebugInformation>true</GenerateDebugInformation>
-      <LinkTimeCodeGeneration>Default</LinkTimeCodeGeneration>
-    </Link>
-    <CudaCompile>
-      <Runtime>MTd</Runtime>
-      <TargetMachinePlatform>64</TargetMachinePlatform>
-    </CudaCompile>
-  </ItemDefinitionGroup>
-  <ItemDefinitionGroup Condition="'$(Configuration)'=='Release'">
-    <ClCompile>
-      <Optimization>MaxSpeed</Optimization>
-      <RuntimeLibrary>MultiThreaded</RuntimeLibrary>
-    </ClCompile>
-    <Link>
-      <GenerateDebugInformation>false</GenerateDebugInformation>
-      <LinkTimeCodeGeneration>UseLinkTimeCodeGeneration</LinkTimeCodeGeneration>
-    </Link>
-    <CudaCompile>
-      <Runtime>MT</Runtime>
-      <TargetMachinePlatform>64</TargetMachinePlatform>
-    </CudaCompile>
-  </ItemDefinitionGroup>
-  <ItemDefinitionGroup Condition="'$(Platform)'=='Win32'">
-    <Link>
-      
-    </Link>
-  </ItemDefinitionGroup>
-  <ItemDefinitionGroup Condition="'$(Platform)'=='x64'">
-    <Link>
-      <AdditionalDependencies>freeimage.lib;%(AdditionalDependencies)</AdditionalDependencies>
-    </Link>
-  </ItemDefinitionGroup>
-  <ItemGroup>
-    <ClCompile Include="cannyEdgeDetectorNPP.cpp" />
-
-  </ItemGroup>
-  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
-  <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.targets" />
-  </ImportGroup>
-</Project>

Samples/cannyEdgeDetectorNPP/cannyEdgeDetectorNPP_vs2015.vcxproj

@@ -33,7 +33,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(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="$(CUDAPropsPath)\CUDA 11.0.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
   </ImportGroup>
 </Project>

Samples/cannyEdgeDetectorNPP/cannyEdgeDetectorNPP_vs2017.vcxproj

@@ -38,7 +38,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -117,6 +117,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
   </ImportGroup>
 </Project>

Samples/cannyEdgeDetectorNPP/cannyEdgeDetectorNPP_vs2019.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -113,6 +113,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
   </ImportGroup>
 </Project>

Samples/concurrentKernels/Makefile

@@ -268,9 +268,9 @@ LIBRARIES :=
 
 # Gencode arguments
 ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64))
-SMS ?= 35 37 50 52 60 61 70 72 75 80
+SMS ?= 35 37 50 52 60 61 70 72 75 80 86
 else
-SMS ?= 35 37 50 52 60 61 70 75 80
+SMS ?= 35 37 50 52 60 61 70 75 80 86
 endif
 
 ifeq ($(SMS),)

Samples/concurrentKernels/NsightEclipse.xml

@@ -36,6 +36,7 @@
   <sm-arch>sm72</sm-arch>
   <sm-arch>sm75</sm-arch>
   <sm-arch>sm80</sm-arch>
+  <sm-arch>sm86</sm-arch>
   <supported_envs>
     <env>
       <arch>x86_64</arch>

Samples/concurrentKernels/README.md

@@ -10,7 +10,7 @@ Performance Strategies
 
 ## Supported SM Architectures
 
-[SM 3.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 3.7 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.1 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.0 ](https://developer.nvidia.com/cuda-gpus)
+[SM 3.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 3.7 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.1 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.6 ](https://developer.nvidia.com/cuda-gpus)
 
 ## Supported OSes
 
@@ -24,7 +24,7 @@ x86_64, ppc64le, armv7l
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 11.0](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
+Download and install the [CUDA Toolkit 11.1](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
 
 ## Build and Run
 

Samples/concurrentKernels/concurrentKernels.cu

@@ -163,7 +163,7 @@ int main(int argc, char **argv) {
 #if defined(__arm__) || defined(__aarch64__)
   // the kernel takes more time than the channel reset time on arm archs, so to
   // prevent hangs reduce time_clocks.
-  clock_t time_clocks = (clock_t)(kernel_time * (deviceProp.clockRate / 1000));
+  clock_t time_clocks = (clock_t)(kernel_time * (deviceProp.clockRate / 100));
 #else
   clock_t time_clocks = (clock_t)(kernel_time * deviceProp.clockRate);
 #endif

Samples/concurrentKernels/concurrentKernels_vs2012.sln

@@ -1,20 +0,0 @@
-
-Microsoft Visual Studio Solution File, Format Version 12.00
-# Visual Studio 2012
-Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "concurrentKernels", "concurrentKernels_vs2012.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}"
-EndProject
-Global
-	GlobalSection(SolutionConfigurationPlatforms) = preSolution
-		Debug|x64 = Debug|x64
-		Release|x64 = Release|x64
-	EndGlobalSection
-	GlobalSection(ProjectConfigurationPlatforms) = postSolution
-		{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.ActiveCfg = Debug|x64
-		{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.Build.0 = Debug|x64
-		{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.ActiveCfg = Release|x64
-		{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.Build.0 = Release|x64
-	EndGlobalSection
-	GlobalSection(SolutionProperties) = preSolution
-		HideSolutionNode = FALSE
-	EndGlobalSection
-EndGlobal

Samples/concurrentKernels/concurrentKernels_vs2013.sln

@@ -1,20 +0,0 @@
-
-Microsoft Visual Studio Solution File, Format Version 13.00
-# Visual Studio 2013
-Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "concurrentKernels", "concurrentKernels_vs2013.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}"
-EndProject
-Global
-	GlobalSection(SolutionConfigurationPlatforms) = preSolution
-		Debug|x64 = Debug|x64
-		Release|x64 = Release|x64
-	EndGlobalSection
-	GlobalSection(ProjectConfigurationPlatforms) = postSolution
-		{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.ActiveCfg = Debug|x64
-		{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.Build.0 = Debug|x64
-		{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.ActiveCfg = Release|x64
-		{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.Build.0 = Release|x64
-	EndGlobalSection
-	GlobalSection(SolutionProperties) = preSolution
-		HideSolutionNode = FALSE
-	EndGlobalSection
-EndGlobal

Samples/concurrentKernels/concurrentKernels_vs2015.vcxproj

@@ -33,7 +33,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -62,7 +62,7 @@
       <OutputFile>$(OutDir)/concurrentKernels.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;</CodeGeneration>
+      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
       <AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
       <Include>./;../../Common</Include>
       <Defines>WIN32</Defines>
@@ -102,6 +102,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
   </ImportGroup>
 </Project>

Samples/concurrentKernels/concurrentKernels_vs2017.vcxproj

@@ -38,7 +38,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -67,7 +67,7 @@
       <OutputFile>$(OutDir)/concurrentKernels.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;</CodeGeneration>
+      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
       <AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
       <Include>./;../../Common</Include>
       <Defines>WIN32</Defines>
@@ -107,6 +107,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
   </ImportGroup>
 </Project>

Samples/concurrentKernels/concurrentKernels_vs2019.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -63,7 +63,7 @@
       <OutputFile>$(OutDir)/concurrentKernels.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;</CodeGeneration>
+      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
       <AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
       <Include>./;../../Common</Include>
       <Defines>WIN32</Defines>
@@ -103,6 +103,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
   </ImportGroup>
 </Project>

Samples/conjugateGradientCudaGraphs/Makefile

@@ -268,9 +268,9 @@ LIBRARIES :=
 
 # Gencode arguments
 ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64))
-SMS ?= 35 37 50 52 60 61 70 72 75 80
+SMS ?= 35 37 50 52 60 61 70 72 75 80 86
 else
-SMS ?= 35 37 50 52 60 61 70 75 80
+SMS ?= 35 37 50 52 60 61 70 75 80 86
 endif
 
 ifeq ($(SMS),)

Samples/conjugateGradientCudaGraphs/NsightEclipse.xml

@@ -58,6 +58,7 @@
   <sm-arch>sm72</sm-arch>
   <sm-arch>sm75</sm-arch>
   <sm-arch>sm80</sm-arch>
+  <sm-arch>sm86</sm-arch>
   <supported_envs>
     <env>
       <arch>x86_64</arch>

Samples/conjugateGradientCudaGraphs/README.md

@@ -10,7 +10,7 @@ Linear Algebra, CUBLAS Library, CUSPARSE Library
 
 ## Supported SM Architectures
 
-[SM 3.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 3.7 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.1 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.0 ](https://developer.nvidia.com/cuda-gpus)
+[SM 3.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 3.7 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 5.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 6.1 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.2 ](https://developer.nvidia.com/cuda-gpus)  [SM 7.5 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.0 ](https://developer.nvidia.com/cuda-gpus)  [SM 8.6 ](https://developer.nvidia.com/cuda-gpus)
 
 ## Supported OSes
 
@@ -30,7 +30,7 @@ cudaStreamBeginCapture, cudaStreamEndCapture, cudaGraphCreate, cudaGraphLaunch,
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 11.0](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
+Download and install the [CUDA Toolkit 11.1](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/conjugateGradientCudaGraphs/conjugateGradientCudaGraphs_vs2012.sln

@@ -1,20 +0,0 @@
-
-Microsoft Visual Studio Solution File, Format Version 12.00
-# Visual Studio 2012
-Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "conjugateGradientCudaGraphs", "conjugateGradientCudaGraphs_vs2012.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}"
-EndProject
-Global
-	GlobalSection(SolutionConfigurationPlatforms) = preSolution
-		Debug|x64 = Debug|x64
-		Release|x64 = Release|x64
-	EndGlobalSection
-	GlobalSection(ProjectConfigurationPlatforms) = postSolution
-		{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.ActiveCfg = Debug|x64
-		{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.Build.0 = Debug|x64
-		{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.ActiveCfg = Release|x64
-		{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.Build.0 = Release|x64
-	EndGlobalSection
-	GlobalSection(SolutionProperties) = preSolution
-		HideSolutionNode = FALSE
-	EndGlobalSection
-EndGlobal

Samples/conjugateGradientCudaGraphs/conjugateGradientCudaGraphs_vs2012.vcxproj

@@ -1,107 +0,0 @@
-<?xml version="1.0" encoding="utf-8"?>
-<Project DefaultTargets="Build" ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
-  <PropertyGroup>
-    <CUDAPropsPath Condition="'$(CUDAPropsPath)'==''">$(VCTargetsPath)\BuildCustomizations</CUDAPropsPath>
-  </PropertyGroup>
-  <ItemGroup Label="ProjectConfigurations">
-    <ProjectConfiguration Include="Debug|x64">
-      <Configuration>Debug</Configuration>
-      <Platform>x64</Platform>
-    </ProjectConfiguration>
-    <ProjectConfiguration Include="Release|x64">
-      <Configuration>Release</Configuration>
-      <Platform>x64</Platform>
-    </ProjectConfiguration>
-  </ItemGroup>
-  <PropertyGroup Label="Globals">
-    <ProjectGuid>{997E0757-EA74-4A4E-A0FC-47D8C8831A15}</ProjectGuid>
-    <RootNamespace>conjugateGradientCudaGraphs_vs2012</RootNamespace>
-    <ProjectName>conjugateGradientCudaGraphs</ProjectName>
-    <CudaToolkitCustomDir />
-  </PropertyGroup>
-  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
-  <PropertyGroup>
-    <ConfigurationType>Application</ConfigurationType>
-    <CharacterSet>MultiByte</CharacterSet>
-    <PlatformToolset>v110</PlatformToolset>
-  </PropertyGroup>
-  <PropertyGroup Condition="'$(Configuration)'=='Debug'">
-    <UseDebugLibraries>true</UseDebugLibraries>
-  </PropertyGroup>
-  <PropertyGroup Condition="'$(Configuration)'=='Release'">
-    <WholeProgramOptimization>true</WholeProgramOptimization>
-  </PropertyGroup>
-  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
-  <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.props" />
-  </ImportGroup>
-  <ImportGroup Label="PropertySheets">
-    <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
-  </ImportGroup>
-  <PropertyGroup Label="UserMacros" />
-  <PropertyGroup>
-    <IntDir>$(Platform)/$(Configuration)/</IntDir>
-    <IncludePath>$(IncludePath)</IncludePath>
-    <CodeAnalysisRuleSet>AllRules.ruleset</CodeAnalysisRuleSet>
-    <CodeAnalysisRules />
-    <CodeAnalysisRuleAssemblies />
-  </PropertyGroup>
-  <PropertyGroup Condition="'$(Platform)'=='x64'">
-    <OutDir>../../bin/win64/$(Configuration)/</OutDir>
-  </PropertyGroup>
-  <ItemDefinitionGroup>
-    <ClCompile>
-      <WarningLevel>Level3</WarningLevel>
-      <PreprocessorDefinitions>WIN32;_MBCS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
-      <AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../Common;$(CudaToolkitIncludeDir);</AdditionalIncludeDirectories>
-    </ClCompile>
-    <Link>
-      <SubSystem>Console</SubSystem>
-      <AdditionalDependencies>cublas.lib;cusparse.lib;cudart_static.lib;kernel32.lib;user32.lib;gdi32.lib;winspool.lib;comdlg32.lib;advapi32.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;odbc32.lib;odbccp32.lib;%(AdditionalDependencies)</AdditionalDependencies>
-      <AdditionalLibraryDirectories>$(CudaToolkitLibDir);</AdditionalLibraryDirectories>
-      <OutputFile>$(OutDir)/conjugateGradientCudaGraphs.exe</OutputFile>
-    </Link>
-    <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;</CodeGeneration>
-      <AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
-      <Include>./;../../Common</Include>
-      <Defines>WIN32</Defines>
-    </CudaCompile>
-  </ItemDefinitionGroup>
-  <ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
-    <ClCompile>
-      <Optimization>Disabled</Optimization>
-      <RuntimeLibrary>MultiThreadedDebug</RuntimeLibrary>
-    </ClCompile>
-    <Link>
-      <GenerateDebugInformation>true</GenerateDebugInformation>
-      <LinkTimeCodeGeneration>Default</LinkTimeCodeGeneration>
-    </Link>
-    <CudaCompile>
-      <Runtime>MTd</Runtime>
-      <TargetMachinePlatform>64</TargetMachinePlatform>
-    </CudaCompile>
-  </ItemDefinitionGroup>
-  <ItemDefinitionGroup Condition="'$(Configuration)'=='Release'">
-    <ClCompile>
-      <Optimization>MaxSpeed</Optimization>
-      <RuntimeLibrary>MultiThreaded</RuntimeLibrary>
-    </ClCompile>
-    <Link>
-      <GenerateDebugInformation>false</GenerateDebugInformation>
-      <LinkTimeCodeGeneration>UseLinkTimeCodeGeneration</LinkTimeCodeGeneration>
-    </Link>
-    <CudaCompile>
-      <Runtime>MT</Runtime>
-      <TargetMachinePlatform>64</TargetMachinePlatform>
-    </CudaCompile>
-  </ItemDefinitionGroup>
-  <ItemGroup>
-    <CudaCompile Include="conjugateGradientCudaGraphs.cu" />
-
-  </ItemGroup>
-  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
-  <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.targets" />
-  </ImportGroup>
-</Project>

Samples/conjugateGradientCudaGraphs/conjugateGradientCudaGraphs_vs2013.sln

@@ -1,20 +0,0 @@
-
-Microsoft Visual Studio Solution File, Format Version 13.00
-# Visual Studio 2013
-Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "conjugateGradientCudaGraphs", "conjugateGradientCudaGraphs_vs2013.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}"
-EndProject
-Global
-	GlobalSection(SolutionConfigurationPlatforms) = preSolution
-		Debug|x64 = Debug|x64
-		Release|x64 = Release|x64
-	EndGlobalSection
-	GlobalSection(ProjectConfigurationPlatforms) = postSolution
-		{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.ActiveCfg = Debug|x64
-		{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.Build.0 = Debug|x64
-		{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.ActiveCfg = Release|x64
-		{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.Build.0 = Release|x64
-	EndGlobalSection
-	GlobalSection(SolutionProperties) = preSolution
-		HideSolutionNode = FALSE
-	EndGlobalSection
-EndGlobal

Samples/conjugateGradientCudaGraphs/conjugateGradientCudaGraphs_vs2013.vcxproj

@@ -1,107 +0,0 @@
-<?xml version="1.0" encoding="utf-8"?>
-<Project DefaultTargets="Build" ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
-  <PropertyGroup>
-    <CUDAPropsPath Condition="'$(CUDAPropsPath)'==''">$(VCTargetsPath)\BuildCustomizations</CUDAPropsPath>
-  </PropertyGroup>
-  <ItemGroup Label="ProjectConfigurations">
-    <ProjectConfiguration Include="Debug|x64">
-      <Configuration>Debug</Configuration>
-      <Platform>x64</Platform>
-    </ProjectConfiguration>
-    <ProjectConfiguration Include="Release|x64">
-      <Configuration>Release</Configuration>
-      <Platform>x64</Platform>
-    </ProjectConfiguration>
-  </ItemGroup>
-  <PropertyGroup Label="Globals">
-    <ProjectGuid>{997E0757-EA74-4A4E-A0FC-47D8C8831A15}</ProjectGuid>
-    <RootNamespace>conjugateGradientCudaGraphs_vs2013</RootNamespace>
-    <ProjectName>conjugateGradientCudaGraphs</ProjectName>
-    <CudaToolkitCustomDir />
-  </PropertyGroup>
-  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
-  <PropertyGroup>
-    <ConfigurationType>Application</ConfigurationType>
-    <CharacterSet>MultiByte</CharacterSet>
-    <PlatformToolset>v120</PlatformToolset>
-  </PropertyGroup>
-  <PropertyGroup Condition="'$(Configuration)'=='Debug'">
-    <UseDebugLibraries>true</UseDebugLibraries>
-  </PropertyGroup>
-  <PropertyGroup Condition="'$(Configuration)'=='Release'">
-    <WholeProgramOptimization>true</WholeProgramOptimization>
-  </PropertyGroup>
-  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
-  <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.props" />
-  </ImportGroup>
-  <ImportGroup Label="PropertySheets">
-    <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
-  </ImportGroup>
-  <PropertyGroup Label="UserMacros" />
-  <PropertyGroup>
-    <IntDir>$(Platform)/$(Configuration)/</IntDir>
-    <IncludePath>$(IncludePath)</IncludePath>
-    <CodeAnalysisRuleSet>AllRules.ruleset</CodeAnalysisRuleSet>
-    <CodeAnalysisRules />
-    <CodeAnalysisRuleAssemblies />
-  </PropertyGroup>
-  <PropertyGroup Condition="'$(Platform)'=='x64'">
-    <OutDir>../../bin/win64/$(Configuration)/</OutDir>
-  </PropertyGroup>
-  <ItemDefinitionGroup>
-    <ClCompile>
-      <WarningLevel>Level3</WarningLevel>
-      <PreprocessorDefinitions>WIN32;_MBCS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
-      <AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../Common;$(CudaToolkitIncludeDir);</AdditionalIncludeDirectories>
-    </ClCompile>
-    <Link>
-      <SubSystem>Console</SubSystem>
-      <AdditionalDependencies>cublas.lib;cusparse.lib;cudart_static.lib;kernel32.lib;user32.lib;gdi32.lib;winspool.lib;comdlg32.lib;advapi32.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;odbc32.lib;odbccp32.lib;%(AdditionalDependencies)</AdditionalDependencies>
-      <AdditionalLibraryDirectories>$(CudaToolkitLibDir);</AdditionalLibraryDirectories>
-      <OutputFile>$(OutDir)/conjugateGradientCudaGraphs.exe</OutputFile>
-    </Link>
-    <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;</CodeGeneration>
-      <AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
-      <Include>./;../../Common</Include>
-      <Defines>WIN32</Defines>
-    </CudaCompile>
-  </ItemDefinitionGroup>
-  <ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
-    <ClCompile>
-      <Optimization>Disabled</Optimization>
-      <RuntimeLibrary>MultiThreadedDebug</RuntimeLibrary>
-    </ClCompile>
-    <Link>
-      <GenerateDebugInformation>true</GenerateDebugInformation>
-      <LinkTimeCodeGeneration>Default</LinkTimeCodeGeneration>
-    </Link>
-    <CudaCompile>
-      <Runtime>MTd</Runtime>
-      <TargetMachinePlatform>64</TargetMachinePlatform>
-    </CudaCompile>
-  </ItemDefinitionGroup>
-  <ItemDefinitionGroup Condition="'$(Configuration)'=='Release'">
-    <ClCompile>
-      <Optimization>MaxSpeed</Optimization>
-      <RuntimeLibrary>MultiThreaded</RuntimeLibrary>
-    </ClCompile>
-    <Link>
-      <GenerateDebugInformation>false</GenerateDebugInformation>
-      <LinkTimeCodeGeneration>UseLinkTimeCodeGeneration</LinkTimeCodeGeneration>
-    </Link>
-    <CudaCompile>
-      <Runtime>MT</Runtime>
-      <TargetMachinePlatform>64</TargetMachinePlatform>
-    </CudaCompile>
-  </ItemDefinitionGroup>
-  <ItemGroup>
-    <CudaCompile Include="conjugateGradientCudaGraphs.cu" />
-
-  </ItemGroup>
-  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
-  <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.targets" />
-  </ImportGroup>
-</Project>

Samples/conjugateGradientCudaGraphs/conjugateGradientCudaGraphs_vs2015.vcxproj

@@ -33,7 +33,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -62,7 +62,7 @@
       <OutputFile>$(OutDir)/conjugateGradientCudaGraphs.exe</OutputFile>
     </Link>
     <CudaCompile>
-      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;</CodeGeneration>
+      <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
       <AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
       <Include>./;../../Common</Include>
       <Defines>WIN32</Defines>
@@ -102,6 +102,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.0.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.1.targets" />
   </ImportGroup>
 </Project>