add and update samples with CUDA 11.3 support

2026-10-23 21:28:17 +08:00 · 2021-04-16 11:54:26 +05:30
parent 067cb65523
commit 568b39bd5b
214 changed files with 6590 additions and 3856 deletions
--- a/Samples/memMapIPCDrv/Makefile
+++ b/Samples/memMapIPCDrv/Makefile
@@ -302,14 +302,10 @@ LIBRARIES :=

 ################################################################################

-FATBIN_FILE := memMapIpc_kernel${TARGET_SIZE}.fatbin
+PTX_FILE := memMapIpc_kernel${TARGET_SIZE}.ptx

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

 ifeq ($(GENCODE_FLAGS),)
 # Generate SASS code for each SM architecture listed in $(SMS)
@@ -395,7 +391,7 @@ endif
 # Target rules
 all: build

-build: memMapIPCDrv $(FATBIN_FILE)
+build: memMapIPCDrv $(PTX_FILE)

 check.deps:
 ifeq ($(SAMPLE_ENABLED),0)
@@ -404,8 +400,8 @@ else
 	@echo "Sample is ready - all dependencies have been met"
 endif

-$(FATBIN_FILE): memMapIpc_kernel.cu
-	$(EXEC) $(NVCC) $(INCLUDES) $(ALL_CCFLAGS) $(GENCODE_FLAGS) -o $@ -fatbin $<
+$(PTX_FILE): memMapIpc_kernel.cu
+	$(EXEC) $(NVCC) $(INCLUDES) $(ALL_CCFLAGS) $(GENCODE_FLAGS) -o $@ -ptx $<
 	$(EXEC) mkdir -p data
 	$(EXEC) cp -f $@ ./data
 	$(EXEC) mkdir -p ../../bin/$(TARGET_ARCH)/$(TARGET_OS)/$(BUILD_TYPE)
@@ -426,9 +422,8 @@ run: build
 	$(EXEC) ./memMapIPCDrv

 clean:
-	rm -f memMapIPCDrv helper_multiprocess.o memMapIpc.o  data/$(FATBIN_FILE) $(FATBIN_FILE)
+	rm -f memMapIPCDrv helper_multiprocess.o memMapIpc.o  data/$(PTX_FILE) $(PTX_FILE)
 	rm -rf ../../bin/$(TARGET_ARCH)/$(TARGET_OS)/$(BUILD_TYPE)/memMapIPCDrv
-
-	rm -rf ../../bin/$(TARGET_ARCH)/$(TARGET_OS)/$(BUILD_TYPE)/$(FATBIN_FILE)
+	rm -rf ../../bin/$(TARGET_ARCH)/$(TARGET_OS)/$(BUILD_TYPE)/$(PTX_FILE)

 clobber: clean
--- a/Samples/memMapIPCDrv/README.md
+++ b/Samples/memMapIPCDrv/README.md
@@ -30,7 +30,7 @@ cuModuleLoad, cuModuleLoadDataEx, cuModuleGetFunction, cuLaunchKernel, cuMemcpyD

 ## Prerequisites

-Download and install the [CUDA Toolkit 11.2](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
+Download and install the [CUDA Toolkit 11.3](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
 Make sure the dependencies mentioned in [Dependencies]() section above are installed.

 ## Build and Run
--- a/Samples/memMapIPCDrv/memMapIPCDrv_vs2017.vcxproj
+++ b/Samples/memMapIPCDrv/memMapIPCDrv_vs2017.vcxproj
@@ -38,7 +38,7 @@
  </PropertyGroup>
  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
  <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.2.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.3.props" />
  </ImportGroup>
  <ImportGroup Label="PropertySheets">
    <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -67,7 +67,7 @@
      <OutputFile>$(OutDir)/memMapIPCDrv.exe</OutputFile>
    </Link>
    <CudaCompile>
-      <CodeGeneration>compute_35,compute_35;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>
+      <CodeGeneration>compute_35,compute_35;</CodeGeneration>
      <AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
      <Include>./;../../Common</Include>
      <Defines>WIN32</Defines>
@@ -105,14 +105,14 @@
  <ItemGroup>
    <ClCompile Include="memMapIpc.cpp" />
    <CudaCompile Include="memMapIpc_kernel.cu">
-      <CompileOut Condition="'$(Platform)'=='x64'">data/%(Filename)64.fatbin</CompileOut>
-      <NvccCompilation>fatbin</NvccCompilation>
+      <CompileOut Condition="'$(Platform)'=='x64'">data/%(Filename)64.ptx</CompileOut>
+      <NvccCompilation>ptx</NvccCompilation>
    </CudaCompile>
    <ClCompile Include="../../Common/helper_multiprocess.cpp" />
    <ClInclude Include="../../Common/helper_multiprocess.h" />
  </ItemGroup>
  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
  <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.2.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.3.targets" />
  </ImportGroup>
 </Project>
--- a/Samples/memMapIPCDrv/memMapIPCDrv_vs2019.vcxproj
+++ b/Samples/memMapIPCDrv/memMapIPCDrv_vs2019.vcxproj
@@ -34,7 +34,7 @@
  </PropertyGroup>
  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
  <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.2.props" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.3.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>$(OutDir)/memMapIPCDrv.exe</OutputFile>
    </Link>
    <CudaCompile>
-      <CodeGeneration>compute_35,compute_35;compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
+      <CodeGeneration>compute_35,compute_35;</CodeGeneration>
      <AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
      <Include>./;../../Common</Include>
      <Defines>WIN32</Defines>
@@ -101,14 +101,14 @@
  <ItemGroup>
    <ClCompile Include="memMapIpc.cpp" />
    <CudaCompile Include="memMapIpc_kernel.cu">
-      <CompileOut Condition="'$(Platform)'=='x64'">data/%(Filename)64.fatbin</CompileOut>
-      <NvccCompilation>fatbin</NvccCompilation>
+      <CompileOut Condition="'$(Platform)'=='x64'">data/%(Filename)64.ptx</CompileOut>
+      <NvccCompilation>ptx</NvccCompilation>
    </CudaCompile>
    <ClCompile Include="../../Common/helper_multiprocess.cpp" />
    <ClInclude Include="../../Common/helper_multiprocess.h" />
  </ItemGroup>
  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
  <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(CUDAPropsPath)\CUDA 11.2.targets" />
+    <Import Project="$(CUDAPropsPath)\CUDA 11.3.targets" />
  </ImportGroup>
 </Project>
--- a/Samples/memMapIPCDrv/memMapIpc.cpp
+++ b/Samples/memMapIPCDrv/memMapIpc.cpp
@@ -64,9 +64,13 @@ typedef struct shmStruct_st {
  int sense;
 } shmStruct;

-// define input fatbin file
-#ifndef FATBIN_FILE
-#define FATBIN_FILE "memMapIpc_kernel64.fatbin"
+bool findModulePath(const char *, string &, char **, string &);
+
+// define input ptx file for different platforms
+#if defined(_WIN64) || defined(__LP64__)
+#define PTX_FILE "memMapIpc_kernel64.ptx"
+#else
+#define PTX_FILE "memMapIpc_kernel32.ptx"
 #endif

 // `ipcHandleTypeFlag` specifies the platform specific handle type this sample
@@ -255,23 +259,44 @@ static void memMapUnmapAndFreeMemory(CUdeviceptr dptr, size_t size) {

 static void memMapGetDeviceFunction(char **argv) {
  // first search for the module path before we load the results
-  string module_path;
-  std::ostringstream fatbin;
-
-  if (!findFatbinPath(FATBIN_FILE, module_path, argv, fatbin)) {
-    exit(EXIT_FAILURE);
+  string module_path, ptx_source;
+  if (!findModulePath(PTX_FILE, module_path, argv, ptx_source)) {
+    if (!findModulePath("memMapIpc_kernel.cubin", module_path, argv,
+                        ptx_source)) {
+      printf(
+          "> findModulePath could not find <simpleMemMapIpc> ptx or cubin\n");
+      exit(EXIT_FAILURE);
+    }
  } else {
    printf("> initCUDA loading module: <%s>\n", module_path.c_str());
  }

-  if (!fatbin.str().size()) {
-    printf("fatbin file empty. exiting..\n");
-    exit(EXIT_FAILURE);
+  // Create module from binary file (PTX or CUBIN)
+  if (module_path.rfind("ptx") != string::npos) {
+    // in this branch we use compilation with parameters
+    const unsigned int jitNumOptions = 3;
+    CUjit_option *jitOptions = new CUjit_option[jitNumOptions];
+    void **jitOptVals = new void *[jitNumOptions];
+    // set up size of compilation log buffer
+    jitOptions[0] = CU_JIT_INFO_LOG_BUFFER_SIZE_BYTES;
+    int jitLogBufferSize = 1024;
+    jitOptVals[0] = (void *)(size_t)jitLogBufferSize;
+    // set up pointer to the compilation log buffer
+    jitOptions[1] = CU_JIT_INFO_LOG_BUFFER;
+    char *jitLogBuffer = new char[jitLogBufferSize];
+    jitOptVals[1] = jitLogBuffer;
+    // set up pointer to set the Maximum # of registers for a particular kernel
+    jitOptions[2] = CU_JIT_MAX_REGISTERS;
+    int jitRegCount = 32;
+    jitOptVals[2] = (void *)(size_t)jitRegCount;
+    checkCudaErrors(cuModuleLoadDataEx(&cuModule, ptx_source.c_str(),
+                                       jitNumOptions, jitOptions,
+                                       (void **)jitOptVals));
+    printf("> PTX JIT log:\n%s\n", jitLogBuffer);
+  } else {
+    checkCudaErrors(cuModuleLoad(&cuModule, module_path.c_str()));
  }

-  // Create module from binary file (FATBIN)
-  checkCudaErrors(cuModuleLoadData(&cuModule, fatbin.str().c_str()));
-
  // Get function handle from module
  checkCudaErrors(
      cuModuleGetFunction(&_memMapIpc_kernel, cuModule, "memMapIpc_kernel"));
@@ -585,3 +610,37 @@ int main(int argc, char **argv) {
  return EXIT_SUCCESS;
 #endif
 }
+
+bool inline findModulePath(const char *module_file, string &module_path,
+                           char **argv, string &ptx_source) {
+  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(".ptx") != string::npos) {
+      FILE *fp = fopen(module_path.c_str(), "rb");
+      fseek(fp, 0, SEEK_END);
+      int file_size = ftell(fp);
+      char *buf = new char[file_size + 1];
+      fseek(fp, 0, SEEK_SET);
+      fread(buf, sizeof(char), file_size, fp);
+      fclose(fp);
+      buf[file_size] = '\0';
+      ptx_source = buf;
+      delete[] buf;
+    }
+
+    return true;
+  }
+}