nvprof

Notable details Large datasets (10 million x 5), (200 x 10 million x 5) Numpy mostly Takes longer after every run Using Spyder3 Windows 10 First thing is attempting to use guvectorize with the following function. I am passing in a bunch of numpy arrays and attempting to use them to multiply across two of the arrays. This works if run with a target other than cuda. However, when switched to cuda it results in an unknown error being: File "C:\ProgramData\Anaconda3\lib\site-packages\numba\cuda\decorators.py", >line 82, in jitwrapper debug=debug) TypeError: init () got an unexpected keyword

I'm trying to profile OpenCL application, a.out , in a system with NVIDIA TITAN X and CUDA 8.0. If it was CUDA application, nvprof ./a.out would be enough. But I found this does not work with OpenCL application, with a message "No kernels were profiled." Until CUDA 7.5, I successfully used COMPUTE_PROFILE=1 following this . Unfortunately, the documentation says "The support for command-line profiler using the environment variable COMPUTE_PROFILE has been dropped in the CUDA 8.0 release." The question is, is there any way other than downgrading CUDA to profile OpenCL application with nvprof? To

I'm familiar with using nvprof to access the events and metrics of a benchmark, e.g., nvprof --system-profiling on --print-gpu-trace -o (file name) --events inst_issued1 ./benchmarkname The system-profiling on --print-gpu-trace -o (filename) command gives timestamps for start time, kernel end times, power, temp and saves the info an nvvp files so we can view it in the visual profiler. This allows us to see what's happening in any section of a code, in particular when a specific kernel is running. My question is this-- Is there a way to isolate the events counted for only a section of the

What is the correct option for measuring bandwidth using nvprof --metrics from the command line? I am using flop_dp_efficiency to get the percentage of peak FLOPS, but there seems to be many options for bandwidth measurement in the manual that I don't really understand what I am measuring. e.g. dram_read, dram_write, gld_read, gld_write all look the same to me. Also, should I report bandwdith as a sum of read+write throughput by assuming both happen simultaneously ? Edit: Based on the excellent answer with the diagram, what would be the bandwidth going from the device memory to the kernel ? I