Hi, I was trying to see the CUDA architecture on the Jetson Nano by running the deviceQuery function that came with CUDA 10.0, and found some weird results for the memory clock rate:
/usr/local/cuda/samples/1_Utilities/deviceQuery</b></font>$ ./deviceQuery ./deviceQuery Starting... CUDA Device Query (Runtime API) version (CUDART static linking) Detected 1 CUDA Capable device(s) Device 0: "NVIDIA Tegra X1" CUDA Driver Version / Runtime Version 10.0 / 10.0 CUDA Capability Major/Minor version number: 5.3 Total amount of global memory: 3965 MBytes (4157145088 bytes) ( 1) Multiprocessors, (128) CUDA Cores/MP: 128 CUDA Cores GPU Max Clock rate: 922 MHz (0.92 GHz) Memory Clock rate: 13 Mhz Memory Bus Width: 64-bit L2 Cache Size: 262144 bytes Maximum Texture Dimension Size (x,y,z) 1D=(65536), 2D=(65536, 65536), 3D=(4096, 4096, 4096) Maximum Layered 1D Texture Size, (num) layers 1D=(16384), 2048 layers Maximum Layered 2D Texture Size, (num) layers 2D=(16384, 16384), 2048 layers Total amount of constant memory: 65536 bytes Total amount of shared memory per block: 49152 bytes Total number of registers available per block: 32768 Warp size: 32 Maximum number of threads per multiprocessor: 2048 Maximum number of threads per block: 1024 Max dimension size of a thread block (x,y,z): (1024, 1024, 64) Max dimension size of a grid size (x,y,z): (2147483647, 65535, 65535) Maximum memory pitch: 2147483647 bytes Texture alignment: 512 bytes Concurrent copy and kernel execution: Yes with 1 copy engine(s) Run time limit on kernels: Yes Integrated GPU sharing Host Memory: Yes Support host page-locked memory mapping: Yes Alignment requirement for Surfaces: Yes Device has ECC support: Disabled Device supports Unified Addressing (UVA): Yes Device supports Compute Preemption: No Supports Cooperative Kernel Launch: No Supports MultiDevice Co-op Kernel Launch: No Device PCI Domain ID / Bus ID / location ID: 0 / 0 / 0 Compute Mode: < Default (multiple host threads can use ::cudaSetDevice() with device simultaneously) > deviceQuery, CUDA Driver = CUDART, CUDA Driver Version = 10.0, CUDA Runtime Version = 10.0, NumDevs = 1 Result = PASS
The LPDDR4 memory is not actually clocked at 13 Mhz, is it? That seems to be two orders of magnitude lower than the expected frequency of around 1600 Mhz. Is this having the issue as Jetson TX2, mentioned here: https://devtalk.nvidia.com/default/topic/1024058/jetson-tx2/cuda-devicequery-and-bandwidth-test-on-tx2-are-weird-/? If this is actually correct, I would be surprised if the GPU and CPU are not starved of data under any appreciable workload.