NIAN1
New ContributorJoined 3 years ago
User Profile
New Contributor
User Widgets
Contributions
Re: Too many events in OpenCl host program on intel fpga
@BoonBengT_Altera Thank you for your reply， This is my code snippet: The OpenCl init and release function: bool init() { cl_int status; if(!setCwdToExeDir()) { return false; } // Get the OpenCL platform. platform = findPlatform("Intel(R) FPGA SDK for OpenCL(TM)"); if(platform == NULL) { printf("ERROR: Unable to find Intel(R) FPGA OpenCL platform.\n"); return false; } // User-visible output - Platform information { char char_buffer[STRING_BUFFER_LEN]; printf("Querying platform for info:\n"); printf("★★★★★★★★★★★★★★★★★★★★★★★\n"); clGetPlatformInfo(platform, CL_PLATFORM_NAME, STRING_BUFFER_LEN, char_buffer, NULL); printf("%-40s ★%s★\n", "CL_PLATFORM_NAME", char_buffer); clGetPlatformInfo(platform, CL_PLATFORM_VERSION, STRING_BUFFER_LEN, char_buffer, NULL); printf("%-40s ★%s★\n\n", "CL_PLATFORM_VERSION ", char_buffer); } // Query the available OpenCL devices. scoped_array<cl_device_id> devices; cl_uint num_devices; devices.reset(getDevices(platform, CL_DEVICE_TYPE_ALL, &num_devices)); // We'll just use the first device. device = devices[0]; // Create the context.&oclContextCallback context = clCreateContext(NULL, 1, &device, &oclContextCallback, NULL, &status); checkError(status, "Failed to create context"); // Create the command queue. queue = clCreateCommandQueue(context, device, CL_QUEUE_PROFILING_ENABLE, &status); checkError(status, "Failed to create command queue"); // Create the program. std::string binary_file = getBoardBinaryFile("No1k", device); printf("Using AOCX: %s\n", binary_file.c_str()); program = createProgramFromBinary(context, binary_file.c_str(), &device, 1); // Build the program that was just created. status = clBuildProgram(program, 0, NULL, "", NULL, NULL); checkError(status, "Failed to build program"); // Create the kernel - name passed in here must match kernel name in the // original CL file, that was compiled into an AOCX file using the AOC tool const char *kernel_kr = "kr"; // Kernel name, as defined in the CL file kr = clCreateKernel(program, kernel_kr, &status); checkError(status, "Failed to create kernel kr"); const char *kernel_kk = "kk"; // Kernel name, as defined in the CL file kk = clCreateKernel(program, kernel_kk, &status); checkError(status, "Failed to create kernel kk"); const char *kernel_name = "thirdKernel"; // Kernel name, as defined in the CL file kernel = clCreateKernel(program, kernel_name, &status); checkError(status, "Failed to create kernel"); printf("★ OpenCL init successfully!\n"); return true; } void cleanup() { if(kr) { clReleaseKernel(kr); } if(kk) { clReleaseKernel(kk); } if(kernel) { clReleaseKernel(kernel); } if(program) { clReleaseProgram(program); } if(queue) { clReleaseCommandQueue(queue); } if(context) { clReleaseContext(context); } printf("★ OpenCL clean successfully!\n"); } The main function: float *temp = (float *) malloc(sizeof(float) * dim * dim); for (unsigned int m = 0; m < dim; m++) { for (unsigned int n = 0; n < dim; n++) { temp[m * dim + n] = mat[m * dim + n]; if (m == n) { result[m * dim + n] = 1.0f; } else { result[m * dim + n] = 0.0f; } } } cl_int err = 0; cl_mem mem_temp = clCreateBuffer(context, CL_MEM_COPY_HOST_PTR | CL_MEM_READ_ONLY, sizeof(float) * dim *dim, temp, &err); checkError(err, "Failed to CreateBuffer mem_temp"); cl_mem mem_ratio = clCreateBuffer(context, CL_MEM_READ_ONLY, sizeof(float) * dim, NULL, &err); checkError(err, "Failed to CreateBuffer mem_ratio"); cl_mem mem_res = clCreateBuffer(context, CL_MEM_COPY_HOST_PTR | CL_MEM_READ_ONLY, sizeof(float) * dim *dim, result, &err); checkError(err, "Failed to CreateBuffer mem_res"); size_t work_item; size_t work_group; if (dim <= 300) { work_group = dim * dim; work_item = dim; } else { work_item = 300; work_group = dim * dim; } size_t global_work_size[] = {work_group}; size_t local_work_size[] = {work_item}; for (unsigned int i = 0; i < dim; i++) { err = clSetKernelArg(kr, 0, sizeof(cl_mem), &mem_temp); checkError(err, "Failed to SetKernelArg kr mem_temp"); err = clSetKernelArg(kr, 1, sizeof(cl_mem), &mem_ratio); checkError(err, "Failed to SetKernelArg kr mem_ratio"); err = clSetKernelArg(kr, 2, sizeof(cl_uint), (void *) &i); checkError(err, "Failed to SetKernelArg kr i"); err = clSetKernelArg(kr, 3, sizeof(cl_uint), (void *) &dim); checkError(err, "Failed to SetKernelArg kr dim"); err = clEnqueueNDRangeKernel(queue, kr, 1, NULL, &global_work_size[0], &local_work_size[0], 0, NULL, NULL); checkError(err, "Failed to EnqueueNDRangeKernel kr"); err = clSetKernelArg(kk, 0, sizeof(cl_mem), &mem_res); checkError(err, "Failed to SetKernelArg kk mem_res"); err = clSetKernelArg(kk, 1, sizeof(cl_mem), &mem_temp); checkError(err, "Failed to SetKernelArg kk mem_temp"); err = clSetKernelArg(kk, 2, sizeof(cl_mem), &mem_ratio); checkError(err, "Failed to SetKernelArg kk mem_ratio"); err = clSetKernelArg(kk, 3, sizeof(cl_uint), (void *) &i); checkError(err, "Failed to SetKernelArg kk i"); err = clSetKernelArg(kk, 4, sizeof(cl_uint), (void *) &dim); checkError(err, "Failed to SetKernelArg kk dim"); err = clEnqueueNDRangeKernel(queue, kk, 1, NULL, &global_work_size[0], &local_work_size[0], 0, NULL, NULL); checkError(err, "Failed to EnqueueNDRangeKernel kk"); } err = clSetKernelArg(kernel, 0, sizeof(cl_mem), &mem_res); checkError(err, "Failed to SetKernelArg mem_res"); err = clSetKernelArg(kernel, 1, sizeof(cl_mem), &mem_temp); checkError(err, "Failed to SetKernelArg mem_temp"); err = clSetKernelArg(kernel, 2, sizeof(cl_uint), (void *) &dim); checkError(err, "Failed to SetKernelArg dim"); err = clEnqueueNDRangeKernel(queue, kernel, 1, NULL, &global_work_size[0], &local_work_size[0], 0, NULL, NULL); checkError(err, "Failed to EnqueueNDRangeKernel"); err = clFinish(queue); checkError(err, "Failed to Finish"); err = clEnqueueReadBuffer(queue, mem_res, CL_TRUE, 0, sizeof(float) * dim * dim, result, 0, NULL, NULL); checkError(err, "Failed to ReadBuffer mem_res"); free(temp); err = clReleaseMemObject(mem_res); checkError(err, "Failed to ReleaseMemObject mem_res"); err = clReleaseMemObject(mem_temp); checkError(err, "Failed to ReleaseMemObject mem_temp"); err = clReleaseMemObject(mem_ratio); checkError(err, "Failed to ReleaseMemObject mem_ratio"); As you can see, I didn't create any cl_event in the code, but in the callback function, it prompts too many events in the host. This is my compilation command that I used in Makefile: ifeq ($(VERBOSE),1) ECHO := else ECHO := @ endif # Where is the Intel(R) FPGA SDK for OpenCL(TM) software? ifeq ($(wildcard $(INTELFPGAOCLSDKROOT)),) $(error Set INTELFPGAOCLSDKROOT to the root directory of the Intel(R) FPGA SDK for OpenCL(TM) software installation) endif ifeq ($(wildcard $(INTELFPGAOCLSDKROOT)/host/include/CL/opencl.h),) $(error Set INTELFPGAOCLSDKROOT to the root directory of the Intel(R) FPGA SDK for OpenCL(TM) software installation.) endif # OpenCL compile and link flags. AOCL_COMPILE_CONFIG := $(shell aocl compile-config --arm) #AOCL_LINK_CONFIG := $(shell aocl link-config --arm) AOCL_LINK_CONFIG := $(wildcard $(INTELFPGAOCLSDKROOT)/host/arm32/lib/*.so) $(wildcard $(AOCL_BOARD_PACKAGE_ROOT)/arm32/lib/*.so) # Compilation flags ifeq ($(DEBUG),1) CXXFLAGS += -g else CXXFLAGS += -O3 endif # Compiler. ARM cross-compiler. CXX := arm-linux-gnueabihf-g++ # Target TARGET := host TARGET_DIR := bin TARGET_NAME := time_FPGA_trasform_and_kernel_exe # Directories INC_DIRS := ../common/inc LIB_DIRS := # Files INCS := $(wildcard ) SRCS := $(wildcard host/src/*.cpp ../common/src/AOCLUtils/*.cpp) LIBS := rt pthread # Make it all! all : $(TARGET_DIR)/$(TARGET) # Host executable target. $(TARGET_DIR)/$(TARGET) : Makefile $(SRCS) $(INCS) $(TARGET_DIR) $(CXX) $(CPPFLAGS) $(CXXFLAGS) -Wall -fPIC $(foreach D,$(INC_DIRS),-I$D) \ $(AOCL_COMPILE_CONFIG) $(SRCS) $(AOCL_LINK_CONFIG) \ $(foreach D,$(LIB_DIRS),-L$D) \ $(foreach L,$(LIBS),-l$L) \ -o $(TARGET_DIR)/$(TARGET_NAME) $(TARGET_DIR) : $(ECHO)mkdir $(TARGET_DIR) # Standard make targets clean : $(ECHO)rm -f $(TARGET_DIR)/$(TARGET_NAME) .PHONY : all clean Thanks for your help.1.4KViews0likes0CommentsToo many events in OpenCl host program on intel fpga
Hi, When I run my opencl program on x86,there was nothing happened.But when I run the same opencl code in intel FPGA host,the program will prompt me ([Runtime Warning]: Too many 'event' objects in the host. This causes deterioration in runtime performance.) I tried to find some answers on google,the intel manual said that I need to release the cl_event objects in my program,but in my opencl program, I did not create any cl_event object,so I could not use the clReleaseEvent()API to release any cl_event.What should I do? Thanks for your help.Solved1.5KViews0likes4Comments