Updating samples for CUDA 12.5

Author: rnertney

CHANGELOG.md

@@ -1,5 +1,7 @@
 ## Changelog
 
+### CUDA 12.5
+
 ### CUDA 12.4
 * Added graphConditionalNodes Sample
 

Common/helper_multiprocess.cpp

@@ -168,7 +168,7 @@ int waitProcess(Process *process) {
 #endif
 }
 
-#if defined(__linux__)
+#if defined(__linux__) || defined(__QNX__)
 int ipcCreateSocket(ipcHandle *&handle, const char *name,
                     const std::vector<Process> &processes) {
   int server_fd;
@@ -262,41 +262,48 @@ int ipcRecvShareableHandle(ipcHandle *handle, ShareableHandle *shHandle) {
   // Union to guarantee alignment requirements for control array
   union {
     struct cmsghdr cm;
-    char control[CMSG_SPACE(sizeof(int))];
+    // This will not work on QNX as QNX CMSG_SPACE calls __cmsg_alignbytes
+    // And __cmsg_alignbytes is a runtime function instead of compile-time macros
+    // char control[CMSG_SPACE(sizeof(int))]
+    char* control;
   } control_un;
 
+  size_t sizeof_control = CMSG_SPACE(sizeof(int)) * sizeof(char);
+  control_un.control = (char*) malloc(sizeof_control);
   struct cmsghdr *cmptr;
   ssize_t n;
   int receivedfd;
   char dummy_buffer[1];
   ssize_t sendResult;
-
   msg.msg_control = control_un.control;
-  msg.msg_controllen = sizeof(control_un.control);
+  msg.msg_controllen = sizeof_control;
 
   iov[0].iov_base = (void *)dummy_buffer;
   iov[0].iov_len = sizeof(dummy_buffer);
 
   msg.msg_iov = iov;
   msg.msg_iovlen = 1;
-
   if ((n = recvmsg(handle->socket, &msg, 0)) <= 0) {
     perror("IPC failure: Receiving data over socket failed");
+    free(control_un.control);
     return -1;
   }
 
   if (((cmptr = CMSG_FIRSTHDR(&msg)) != NULL) &&
       (cmptr->cmsg_len == CMSG_LEN(sizeof(int)))) {
     if ((cmptr->cmsg_level != SOL_SOCKET) || (cmptr->cmsg_type != SCM_RIGHTS)) {
+      free(control_un.control);
       return -1;
     }
 
     memmove(&receivedfd, CMSG_DATA(cmptr), sizeof(receivedfd));
     *(int *)shHandle = receivedfd;
   } else {
+    free(control_un.control);
     return -1;
   }
 
+  free(control_un.control);
   return 0;
 }
 
@@ -340,9 +347,12 @@ int ipcSendShareableHandle(ipcHandle *handle,
 
   union {
     struct cmsghdr cm;
-    char control[CMSG_SPACE(sizeof(int))];
+    char* control;
   } control_un;
 
+  size_t sizeof_control = CMSG_SPACE(sizeof(int)) * sizeof(char);
+  control_un.control = (char*) malloc(sizeof_control);
+
   struct cmsghdr *cmptr;
   ssize_t readResult;
   struct sockaddr_un cliaddr;
@@ -360,7 +370,7 @@ int ipcSendShareableHandle(ipcHandle *handle,
   int sendfd = (int)shareableHandles[data];
 
   msg.msg_control = control_un.control;
-  msg.msg_controllen = sizeof(control_un.control);
+  msg.msg_controllen = sizeof_control;
 
   cmptr = CMSG_FIRSTHDR(&msg);
   cmptr->cmsg_len = CMSG_LEN(sizeof(int));
@@ -380,9 +390,11 @@ int ipcSendShareableHandle(ipcHandle *handle,
   ssize_t sendResult = sendmsg(handle->socket, &msg, 0);
   if (sendResult <= 0) {
     perror("IPC failure: Sending data over socket failed");
+    free(control_un.control);
     return -1;
   }
 
+  free(control_un.control);
   return 0;
 }
 

Common/helper_multiprocess.h

@@ -84,7 +84,7 @@ int waitProcess(Process *process);
 #define checkIpcErrors(ipcFuncResult) \
     if (ipcFuncResult == -1) { fprintf(stderr, "Failure at %u %s\n", __LINE__, __FILE__); exit(EXIT_FAILURE); }
 
-#if defined(__linux__)
+#if defined(__linux__) || defined(__QNX__)
 struct ipcHandle_st {
     int socket;
     char *socketName;

README.md

@@ -1,35 +1,20 @@
 # CUDA Samples
 
-Samples for CUDA Developers which demonstrates features in CUDA Toolkit. This version supports [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads).
+Samples for CUDA Developers which demonstrates features in CUDA Toolkit. This version supports [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads).
 
 ## Release Notes
 
 This section describes the release notes for the CUDA Samples on GitHub only.
 
-### CUDA 12.4
-
-- Hopper Confidential Computing Modes do not support Video samples, nor do they support host-pinned memory due to the restrictions created by CPU IOMMUs. The following Samples are affected:
-  - convolutionTexture
-  - cudaNvSci
-  - dct8x8
-  - lineOfSight
-  - simpleCubemapTexture
-  - simpleIPC
-  - simpleLayeredTexture
-  - simplePitchLinearTexture
-  - simpleStream
-  - simpleTexture
-  - simpleTextureDrv
-  - watershedSegmentationNPP
-
+### CUDA 12.5
 
 ### [older versions...](./CHANGELOG.md)
 
 ## Getting Started
 
 ### Prerequisites
 
-Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
+Download and install the [CUDA Toolkit 12.5](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

Samples/0_Introduction/UnifiedMemoryStreams/Makefile

@@ -169,6 +169,19 @@ CCFLAGS     :=
 LDFLAGS     :=
 
 # build flags
+
+# Link flag for customized HOST_COMPILER with gcc realpath
+GCC_PATH := $(shell which gcc)
+ifeq ($(CUSTOM_HOST_COMPILER),1)
+    ifneq ($(filter /%,$(HOST_COMPILER)),)
+        ifneq ($(findstring gcc,$(HOST_COMPILER)),)
+            ifneq ($(GCC_PATH),$(HOST_COMPILER))
+                LDFLAGS += -lstdc++
+            endif
+        endif
+    endif
+endif
+
 ifeq ($(TARGET_OS),darwin)
     LDFLAGS += -rpath $(CUDA_PATH)/lib
     CCFLAGS += -arch $(HOST_ARCH)

Samples/0_Introduction/UnifiedMemoryStreams/README.md

@@ -28,7 +28,7 @@ cudaStreamDestroy, cudaFree, cudaMallocManaged, cudaStreamAttachMemAsync, cudaSe
 
 ## Prerequisites
 
-Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
+Download and install the [CUDA Toolkit 12.5](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/0_Introduction/UnifiedMemoryStreams/UnifiedMemoryStreams_vs2017.vcxproj

@@ -38,7 +38,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -108,6 +108,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.targets" />
   </ImportGroup>
 </Project>

Samples/0_Introduction/UnifiedMemoryStreams/UnifiedMemoryStreams_vs2019.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -104,6 +104,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.targets" />
   </ImportGroup>
 </Project>

Samples/0_Introduction/UnifiedMemoryStreams/UnifiedMemoryStreams_vs2022.vcxproj

@@ -34,7 +34,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.4.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets">
     <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -104,6 +104,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 12.5.targets" />
   </ImportGroup>
 </Project>

Samples/0_Introduction/asyncAPI/Makefile

@@ -169,6 +169,19 @@ CCFLAGS     :=
 LDFLAGS     :=
 
 # build flags
+
+# Link flag for customized HOST_COMPILER with gcc realpath
+GCC_PATH := $(shell which gcc)
+ifeq ($(CUSTOM_HOST_COMPILER),1)
+    ifneq ($(filter /%,$(HOST_COMPILER)),)
+        ifneq ($(findstring gcc,$(HOST_COMPILER)),)
+            ifneq ($(GCC_PATH),$(HOST_COMPILER))
+                LDFLAGS += -lstdc++
+            endif
+        endif
+    endif
+endif
+
 ifeq ($(TARGET_OS),darwin)
     LDFLAGS += -rpath $(CUDA_PATH)/lib
     CCFLAGS += -arch $(HOST_ARCH)