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

Popular posts from this blog

c++ - Difference between pre and post decrement in recursive function argument -

i have following sample code used pre-decrement void function(int c) { if(c == 0) { return; } else { cout << "dp" << c << endl; function(--c); cout << c << endl; return; } } this function give output input 4 : dp3 dp2 dp1 dp0 0 1 2 3 but when use post decrement void function(int c) { if(c == 0) { return; } else { cout << "dp" << c << endl; function(c--); cout << c << endl; return; } } output goes in infinite loop dp4 can explain me in detail why happens ? this happens because function(c--) called same value of c , when finishes c decremented. recursively called, hence called same value no chance of return , hit stack overflow error. assume this, int x = 1, y = 0; y = x++ result y == 1 , x == 2. if y = ++x , bot x , y 2.
Read more

php - Nothing but 'run(); ' when browsing to my local project, how do I fix this? -

i added new project. made mistake in projectname.conf file in sites-available apache2, led me reinstalling apache2. after reinstalling , re-enabling projects on every page of every project .. <body> run(); </body> .. i've run composer update, restarted service, restarted pc, checked config files, tried disabling new project. there nothing in error log, , access.log: 127.0.0.1 - - [15/may/2015:01:40:47 +0200] "get / http/1.1" 304 181 "-" "mozilla/5.0 (x11; ubuntu; linux x86_64; rv:38.0) gecko/20100101 firefox/38.0" maybe i'm forgetting apache2 reinstall? don't think did different last time installed it. looks haven't setup php correctly. take @ this great guide , maybe you're forgetting link php config apache2.
Read more

php - How can I echo out this array? -

i don't know how go grabbing data in variable , put foreach loop. class tree{ private $info = array( array('name'=>'jim','state'=>'nu','company'=>'nu','phone'=>array('cell'=>'5615111111','office'=>'5611111111'),'email'=>array('primary'=>'exs@example.com','ex@there.com')), array('name'=>'joe smith','city'=>'phoenix','phone'=>'4805551111','email'=>'jsmith@some_email.com'), array('name'=>'john doe','city'=>'chandler','company'=>'doe co.','email'=>array('jdoe@gmail.com','personal'=>'email@email.com'),'phone'=>'6025550002') ); } if you're inside of class, can access private variable using $this->variablename . example, i...
Read more