Losing Unified Memory support in CUDA 7.0 under Windows 10 -
recently updated cuda 6.0 cuda 7.0, , cuda programs unified memory allocation stopped working (other programs without unified memory still work, , cuda 7.0 template in visual studio 2013 still works). following what canonical way check errors using cuda runtime api?, found out cudamallocmanaged()
returns “operation not supported” error. behavior started happening since update.
my graphics card geforce gtx 780m compute capability 3.0. programs compiled visual studio 2013 targeting 64-bit platform, arch/code pair being compute_30,sm_30
. using windows 10 pro insider preview evaluation copy build 10074. geforce driver version 349.90.
the cuda 7.0 unifiedmemorystreams sample outputs:
gpu device 0: "geforce gtx 780m" compute capability 3.0 unified memory not supported on device
the cuda 7.0 devicequery sample outputs:
cuda device query (runtime api) version (cudart static linking) detected 1 cuda capable device(s) device 0: "geforce gtx 780m" cuda driver version / runtime version 7.0 / 7.0 cuda capability major/minor version number: 3.0 total amount of global memory: 4096 mbytes (4294967296 bytes) ( 8) multiprocessors, (192) cuda cores/mp: 1536 cuda cores gpu max clock rate: 797 mhz (0.80 ghz) memory clock rate: 2500 mhz memory bus width: 256-bit l2 cache size: 524288 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: 65536 warp size: 32 maximum number of threads per multiprocessor: 2048 maximum number of threads per block: 1024 max dimension size of thread block (x,y,z): (1024, 1024, 64) max dimension size of grid size (x,y,z): (2147483647, 65535, 65535) maximum memory pitch: 2147483647 bytes texture alignment: 512 bytes concurrent copy , kernel execution: yes 1 copy engine(s) run time limit on kernels: no integrated gpu sharing host memory: no support host page-locked memory mapping: yes alignment requirement surfaces: yes device has ecc support: disabled cuda device driver mode (tcc or wddm): wddm (windows display driver model) device supports unified addressing (uva): yes device pci domain id / bus id / location id: 0 / 1 / 0 compute mode: < default (multiple host threads can use ::cudasetdevice() device simultaneously) > devicequery, cuda driver = cudart, cuda driver version = 7.0, cuda runtime version = 7.0, numdevs = 1, device0 = geforce gtx 780m result = pass
here's minimum sample outputs "operation not supported":
#include "cuda_runtime.h" #include "device_launch_parameters.h" #include <stdio.h> #define gpuerrchk(ans) { gpuassert((ans), __file__, __line__); } inline void gpuassert(cudaerror_t code, char *file, int line, bool abort = true) { if (code != cudasuccess) { fprintf(stderr, "gpuassert: %s %s %d\n", cudageterrorstring(code), file, line); if (abort) exit(code); } } int main() { int n = 2048; int *a; gpuerrchk(cudamallocmanaged(&a, n * sizeof(int))); a[0] = 0; cudafree(a); cudadevicereset(); }
update:
i have downgraded windows 10 windows 8.1 other factors unchanged, , cudamallocmanaged()
works flawlessly (unifiedmemorystreams outputs):
gpu device 0: "geforce gtx 780m" compute capability 3.0 executing tasks on host / device task [0], thread [0] executing on device (512) task [1], thread [0] executing on device (207) ... task [38], thread [0] executing on device (417) task [39], thread [0] executing on device (563) done!
tested on geforce driver version both 347.62 , 350.12. yeah, hold off on windows upgrade if develop cuda 7.0...
windows 10 not supported platform cuda @ time. switch a supported platform, , unified memory operations should begin working again.
Comments
Post a Comment