-problems with lightdm log in ( login loop )
-problems with driver istall ( "Driver Installation failed: it appears, that a X server is running..." )
To successfully install a NVidia CUDA Toolkit on Ubuntu 16.04 64bit I've just had to do:
- make a liveImage of Ubuntu on pendrive ( 8GB pen is enough ) -
such a try will save a ton of nerves, before unsuccessful
install on your host Linux system!!!
- login on live session on pendrive ( "Try Ubuntu, before install"
)
add sudo user at live session:
sudo adduser admin ( #pass: admin1 )
sudo usermod -aG sudo admin
logout from live session, log in as #admin
- download CUDA Toolkit from NVidia official site ( ~1.5GB )
change privileges for downloaded installer file ( DO NOT INSTALL
AT THIS STEP! ):
sudo chmod +x cuda_X.X.run
switch to console view:
Ctr+Alt+F1 ( to switch on terminal view )
Ctr+Alt+F7 ( to switch from terminal view to graphical server )
at console view ( Ctr+Alt+F1 ) log in:
login: admin
pass: admin1
stop graphical running service:
sudo service lightdm stop
check if graphical server is off - after switching Ctr+Alt+F7
the monitor should be blank black, switch back on console view
Ctr+Alt+F1
install CUDA Toolkit, with such configuration:
sudo ./cuda_X.X.run
( press 'q' for license read skip )
do not install OpenGL library
do not update system X configuration
other options make yes and paths as default
turn on graphical server:
sudo service lightdm start
log in as user ( if you automatically log in as #ubuntu at live
session log out ):
login: admin
pass: admin1
check whatever nvcc compiler works with provided simple
parallel vector sum at GPU Blocks:
save vecSum.cu and book.h at new files, compile and run at terminal:
/usr/local/cuda-8.0/bin/nvcc vecSum.cu && clear && ./a.out
check console printout - it should be similar to:
0.000000 + 0.000000 = 0.000000
-1.100000 + 0.630000 = -0.000000
-2.200000 + 2.520000 = 0.319985
-3.300000 + 5.670000 = 2.119756
-4.400000 + 10.080000 = 5.679756
-5.500000 + 15.750000 = 10.250000
-6.600000 + 22.680000 = 16.017500
-7.700000 + 30.870001 = 23.170002
-8.800000 + 40.320000 = 31.519997
-9.900000 + 51.029999 = 41.129967
if everything went well on pendrive live session, do the same
on your host linux system
P.S. Please note that it is not ideal tutorial, but works fine for me!
======= vecSum.cu =====
#include "book.h"
#define N 50000
///usr/local/cuda-8.0/bin/nvcc vecSum.cu && clear && ./a.out
//"HOST" = CPU
//"Device" = GPU
__global__ void add( float *a, float *b, float *c )
{
int tid = blockIdx.x;
if ( tid < N )
c[ tid ] = a[ tid ] + b[ tid ];
}
int main ( void )
{
float a[ N ], b[ N ], c[ N ];
float *dev_a, *dev_b, *dev_c;
//GPU memory allocation
HANDLE_ERROR( cudaMalloc( ( void** )&dev_a, N * sizeof( float ) ) );
HANDLE_ERROR( cudaMalloc( ( void** )&dev_b, N * sizeof( float ) ) );
HANDLE_ERROR( cudaMalloc( ( void** )&dev_c, N * sizeof( float ) ) );
//sample input vectors CPU generation
for ( int i = 0; i < N; i++ )
{
a[ i ] = -i * 1.1;
b[ i ] = i * i * 0.63;
}
//copy/load from CPU to GPU data vectors a[], b[] HostToDevice
HANDLE_ERROR( cudaMemcpy( dev_a, a, N * sizeof( float ), cudaMemcpyHostToDevice ) );
HANDLE_ERROR( cudaMemcpy( dev_b, b, N * sizeof( float ), cudaMemcpyHostToDevice ) );
//calculate sum of vectors on GPU
add<<<N,1>>> ( dev_a, dev_b, dev_c );
//copy/load result vector from GPU to CPU c[] DeviceToHost
HANDLE_ERROR( cudaMemcpy( c, dev_c, N * sizeof( float ), cudaMemcpyDeviceToHost ) );
//printout results
for ( int i = 0; i < 10; i++ ) printf( "%f + %f = %f\n", a[ i ], b[ i ], c[ i ] );
//free memory and constructed objects on GPU
cudaFree( dev_a );
cudaFree( dev_b );
cudaFree( dev_c );
return 0;
}
========= book.h ======
/*
* Copyright 1993-2010 NVIDIA Corporation. All rights reserved.
*
* NVIDIA Corporation and its licensors retain all intellectual property and
* proprietary rights in and to this software and related documentation.
* Any use, reproduction, disclosure, or distribution of this software
* and related documentation without an express license agreement from
* NVIDIA Corporation is strictly prohibited.
*
* Please refer to the applicable NVIDIA end user license agreement (EULA)
* associated with this source code for terms and conditions that govern
* your use of this NVIDIA software.
*
*/
#ifndef __BOOK_H__
#define __BOOK_H__
#include <stdio.h>
static void HandleError( cudaError_t err,
const char *file,
int line ) {
if (err != cudaSuccess) {
printf( "%s in %s at line %d\n", cudaGetErrorString( err ),
file, line );
exit( EXIT_FAILURE );
}
}
#define HANDLE_ERROR( err ) (HandleError( err, __FILE__, __LINE__ ))
#define HANDLE_NULL( a ) {if (a == NULL) { \
printf( "Host memory failed in %s at line %d\n", \
__FILE__, __LINE__ ); \
exit( EXIT_FAILURE );}}
template< typename T >
void swap( T& a, T& b ) {
T t = a;
a = b;
b = t;
}
void* big_random_block( int size ) {
unsigned char *data = (unsigned char*)malloc( size );
HANDLE_NULL( data );
for (int i=0; i<size; i++)
data[i] = rand();
return data;
}
int* big_random_block_int( int size ) {
int *data = (int*)malloc( size * sizeof(int) );
HANDLE_NULL( data );
for (int i=0; i<size; i++)
data[i] = rand();
return data;
}
// a place for common kernels - starts here
__device__ unsigned char value( float n1, float n2, int hue ) {
if (hue > 360) hue -= 360;
else if (hue < 0) hue += 360;
if (hue < 60)
return (unsigned char)(255 * (n1 + (n2-n1)*hue/60));
if (hue < 180)
return (unsigned char)(255 * n2);
if (hue < 240)
return (unsigned char)(255 * (n1 + (n2-n1)*(240-hue)/60));
return (unsigned char)(255 * n1);
}
__global__ void float_to_color( unsigned char *optr,
const float *outSrc ) {
// map from threadIdx/BlockIdx to pixel position
int x = threadIdx.x + blockIdx.x * blockDim.x;
int y = threadIdx.y + blockIdx.y * blockDim.y;
int offset = x + y * blockDim.x * gridDim.x;
float l = outSrc[offset];
float s = 1;
int h = (180 + (int)(360.0f * outSrc[offset])) % 360;
float m1, m2;
if (l <= 0.5f)
m2 = l * (1 + s);
else
m2 = l + s - l * s;
m1 = 2 * l - m2;
optr[offset*4 + 0] = value( m1, m2, h+120 );
optr[offset*4 + 1] = value( m1, m2, h );
optr[offset*4 + 2] = value( m1, m2, h -120 );
optr[offset*4 + 3] = 255;
}
__global__ void float_to_color( uchar4 *optr,
const float *outSrc ) {
// map from threadIdx/BlockIdx to pixel position
int x = threadIdx.x + blockIdx.x * blockDim.x;
int y = threadIdx.y + blockIdx.y * blockDim.y;
int offset = x + y * blockDim.x * gridDim.x;
float l = outSrc[offset];
float s = 1;
int h = (180 + (int)(360.0f * outSrc[offset])) % 360;
float m1, m2;
if (l <= 0.5f)
m2 = l * (1 + s);
else
m2 = l + s - l * s;
m1 = 2 * l - m2;
optr[offset].x = value( m1, m2, h+120 );
optr[offset].y = value( m1, m2, h );
optr[offset].z = value( m1, m2, h -120 );
optr[offset].w = 255;
}
#if _WIN32
//Windows threads.
#include <windows.h>
typedef HANDLE CUTThread;
typedef unsigned (WINAPI *CUT_THREADROUTINE)(void *);
#define CUT_THREADPROC unsigned WINAPI
#define CUT_THREADEND return 0
#else
//POSIX threads.
#include <pthread.h>
typedef pthread_t CUTThread;
typedef void *(*CUT_THREADROUTINE)(void *);
#define CUT_THREADPROC void
#define CUT_THREADEND
#endif
//Create thread.
CUTThread start_thread( CUT_THREADROUTINE, void *data );
//Wait for thread to finish.
void end_thread( CUTThread thread );
//Destroy thread.
void destroy_thread( CUTThread thread );
//Wait for multiple threads.
void wait_for_threads( const CUTThread *threads, int num );
#if _WIN32
//Create thread
CUTThread start_thread(CUT_THREADROUTINE func, void *data){
return CreateThread(NULL, 0, (LPTHREAD_START_ROUTINE)func, data, 0, NULL);
}
//Wait for thread to finish
void end_thread(CUTThread thread){
WaitForSingleObject(thread, INFINITE);
CloseHandle(thread);
}
//Destroy thread
void destroy_thread( CUTThread thread ){
TerminateThread(thread, 0);
CloseHandle(thread);
}
//Wait for multiple threads
void wait_for_threads(const CUTThread * threads, int num){
WaitForMultipleObjects(num, threads, true, INFINITE);
for(int i = 0; i < num; i++)
CloseHandle(threads[i]);
}
#else
//Create thread
CUTThread start_thread(CUT_THREADROUTINE func, void * data){
pthread_t thread;
pthread_create(&thread, NULL, func, data);
return thread;
}
//Wait for thread to finish
void end_thread(CUTThread thread){
pthread_join(thread, NULL);
}
//Destroy thread
void destroy_thread( CUTThread thread ){
pthread_cancel(thread);
}
//Wait for multiple threads
void wait_for_threads(const CUTThread * threads, int num){
for(int i = 0; i < num; i++)
end_thread( threads[i] );
}
#endif
#endif // __BOOK_H__