我是ArrayFire和CUDA开发的新手,几天前我在惨败使用Thrust后才开始使用ArrayFire。
我正在构建一个基于ArrayFire的算法,该算法应该在存储在设备内存中的数十万个32x32帧的数据库中搜索单个32x32像素帧。
首先,我初始化一个矩阵,该矩阵具有1024 + 1个像素行(我需要一个额外的像素来保留帧组ID)和预定义数量的帧(在这种情况下为1000个),以coloumn为索引。
如果我取消注释“ pixels_uint32 = device_frame_ptr [pixel_group_idx];”,这是执行搜索的功能。程序崩溃。该指针似乎是有效的,所以我不明白为什么会发生这种情况。关于以这种方式访问设备内存,也许有些我不知道的东西?
#include <iostream>
#include <stdio.h>
#include <sys/types.h>
#include <arrayfire.h>
#include "utils.h"
using namespace af;
using namespace std;
/////////////////////////// CUDA settings ////////////////////////////////
#define TEST_DEBUG false
#define MAX_NUMBER_OF_FRAMES 1000 // maximum (2499999 frames) X (1024 + 1 pixels per frame) x (2 bytes per pixel) = 5.124.997.950 bytes (~ 5GB)
#define BLOB_FINGERPRINT_SIZE 1024 //32x32
//percentage of macroblocks that should match: 0.9 means 90%
#define MACROBLOCK_COMPARISON_OVERALL_THRESHOLD 768 //1024 * 0.75
//////////////////////// End of CUDA settings ////////////////////////////
array search_frame(array d_db_vec)
{
try {
uint number_of_uint32_for_frame = BLOB_FINGERPRINT_SIZE / 2;
// create one-element array to hold the result of the computation
array frame_found(1,MAX_NUMBER_OF_FRAMES, u32);
frame_found = 0;
gfor (array frame_idx, MAX_NUMBER_OF_FRAMES) {
// get the blob id it's the last coloumn of the matrix
array blob_id = d_db_vec(number_of_uint32_for_frame, frame_idx); // addressing with (pixel_idx, frame_idx)
// define some hardcoded pixel to search for
uint8_t searched_r = 0x0;
uint8_t searched_g = 0x3F;
uint8_t searched_b = 0x0;
uint8_t b1 = 0;
uint8_t g1 = 0;
uint8_t r1 = 0;
uint8_t b2 = 0;
uint8_t g2 = 0;
uint8_t r2 = 0;
uint32_t sum1 = 0;
uint32_t sum2 = 0;
uint32_t *device_frame_ptr = NULL;
uint32_t pixels_uint32 = 0;
uint pixel_match_counter = 0;
//uint pixel_match_counter = 0;
array frame = d_db_vec(span, frame_idx);
device_frame_ptr = frame.device<uint32_t>();
for (uint pixel_group_idx = 0; pixel_group_idx < number_of_uint32_for_frame; pixel_group_idx++) {
// test to see if the whole matrix is traversed
// d_db_vec(pixel_group_idx, frame_idx) = 0;
/////////////////////////////// PROBLEMATIC CODE ///////////////////////////////////
pixels_uint32 = 0x7E007E0;
//pixels_uint32 = device_frame_ptr[pixel_group_idx]; //why does this crash the program?
// if I uncomment the above line the program tries to copy the u32 frame into the pixels_uint32 variable
// something goes wrong, since the pointer device_frame_ptr is not NULL and the elements should be there judging by the lines above
////////////////////////////////////////////////////////////////////////////////////
// splitting the first pixel into its components
b1 = (pixels_uint32 & 0xF8000000) >> 27; //(input & 11111000000000000000000000000000)
g1 = (pixels_uint32 & 0x07E00000) >> 21; //(input & 00000111111000000000000000000000)
r1 = (pixels_uint32 & 0x001F0000) >> 16; //(input & 00000000000111110000000000000000)
// splitting the second pixel into its components
b2 = (pixels_uint32 & 0xF800) >> 11; //(input & 00000000000000001111100000000000)
g2 = (pixels_uint32 & 0x07E0) >> 5; //(input & 00000000000000000000011111100000)
r2 = (pixels_uint32 & 0x001F); //(input & 00000000000000000000000000011111)
// checking if they are a match
sum1 = abs(searched_r - r1) + abs(searched_g - g1) + abs(searched_b - b1);
sum2 = abs(searched_r - r2) + abs(searched_g - g2) + abs(searched_b - b2);
// if they match, increment the local counter
pixel_match_counter = (sum1 <= 16) ? pixel_match_counter + 1 : pixel_match_counter;
pixel_match_counter = (sum2 <= 16) ? pixel_match_counter + 1 : pixel_match_counter;
}
bool is_found = pixel_match_counter > MACROBLOCK_COMPARISON_OVERALL_THRESHOLD;
// write down if the frame is a match or not
frame_found(0,frame_idx) = is_found ? frame_found(0,frame_idx) : blob_id;
}
// test to see if the whole matrix is traversed - this has to print zeroes
if (TEST_DEBUG)
print(d_db_vec);
// return the matches array
return frame_found;
} catch (af::exception& e) {
fprintf(stderr, "%s\n", e.what());
throw;
}
}
// make 2 green pixels
uint32_t make_test_pixel_group() {
uint32_t b1 = 0x0; //11111000000000000000000000000000
uint32_t g1 = 0x7E00000; //00000111111000000000000000000000
uint32_t r1 = 0x0; //00000000000111110000000000000000
uint32_t b2 = 0x0; //00000000000000001111100000000000
uint32_t g2 = 0x7E0; //00000000000000000000011111100000
uint32_t r2 = 0x0; //00000000000000000000000000011111
uint32_t green_pix = b1 | g1 | r1 | b2 | g2 | r2;
return green_pix;
}
int main(int argc, char ** argv)
{
info();
/////////////////////////////////////// CREATE THE DATABASE ///////////////////////////////////////
uint number_of_uint32_for_frame = BLOB_FINGERPRINT_SIZE / 2;
array d_db_vec(number_of_uint32_for_frame + 1, // fingerprint size + 1 extra u32 for blob id
MAX_NUMBER_OF_FRAMES, // number of frames
u32); // type of elements is 32-bit unsigned integer (unsigned) with the configuration RGBRGB (565565)
if (TEST_DEBUG == true) {
for (uint frame_idx = 0; frame_idx < MAX_NUMBER_OF_FRAMES; frame_idx++) {
for (uint pix_idx = 0; pix_idx < number_of_uint32_for_frame; pix_idx++) {
d_db_vec(pix_idx, frame_idx) = make_test_pixel_group(); // fill everything with green :D
}
}
} else {
d_db_vec = rand(number_of_uint32_for_frame + 1, MAX_NUMBER_OF_FRAMES);
}
cout << "Setting blob ids. \n\n";
for (uint frame_idx = 0; frame_idx < MAX_NUMBER_OF_FRAMES; frame_idx++) {
// set the blob id to 123456
d_db_vec(number_of_uint32_for_frame, frame_idx) = 123456; // blob_id = 123456
}
if (TEST_DEBUG)
print(d_db_vec);
cout << "Done setting blob ids. \n\n";
//////////////////////////////////// CREATE THE SEARCHED FRAME ///////////////////////////////////
// to be done, for now we use the hardcoded values at line 37-39 to simulate the searched pixel:
//37 uint8_t searched_r = 0x0;
//38 uint8_t searched_g = 0x3F;
//39 uint8_t searched_b = 0x0;
///////////////////////////////////////////// SEARCH /////////////////////////////////////////////
clock_t timer = startTimer();
for (int i = 0; i< 1000; i++) {
array frame_found = search_frame(d_db_vec);
if (TEST_DEBUG)
print(frame_found);
}
stopTimer(timer);
return 0;
}
这是带有注释行的控制台输出:
arrayfire / examples / helloworld $ ./helloworld
ArrayFire v1.9.1(64位Linux,内部版本9af23ea)
许可证:服务器([email protected])
CUDA工具包5.0,驱动程序304.54
GPU0 Tesla C2075,5376 MB,计算2.0
内存使用:5312 MB可用空间(总计5376 MB)
设置Blob ID。
完成设置Blob ID。
时间:0.03秒。
这是控制台输出,其行未注释:
arrayfire / examples / helloworld $ ./helloworld
ArrayFire v1.9.1(64位Linux,内部版本9af23ea)
许可证:服务器([email protected])
CUDA工具包5.0,驱动程序304.54
GPU0 Tesla C2075,5376 MB,计算2.0
内存使用:5312 MB可用空间(总计5376 MB)
设置Blob ID。
完成设置Blob ID。
分段故障
在此先感谢您的任何帮助。我真的尝试了一切,但没有成功。
最佳答案
免责声明:我是arrayfire的首席开发人员。我看到您也有posted on AccelerEyes forums,但我将在此发布以清除代码中的一些常见问题。
不要在gfor循环中使用.device()、. host()、. scalar()。这将导致GFOR循环内部出现分歧,而GFOR并不是为此而设计的。
您不能索引到设备指针。指针指向GPU上的位置。当您执行device_frame_ptr[pixel_group_idx];
时,系统正在寻找CPU上的等效位置。这是您的细分错误的原因。
使用向量化代码。例如,您不需要gfor的内部for循环。您可以执行b1 = (pixels_uint32 & 0xF8000000) >> 27;
,而不是在for循环中执行array B1 = (frame & 0xF800000000) >> 27;
。也就是说,您不是在将数据返回到CPU并使用for循环,而是在GPU内部进行了整个操作。
不要在GFOR中使用if-else或三元运算符。这些再次引起分歧。例如,pixel_match_counter = sum(sum1 <= 16) + sum(sum2 < 16);
和found(0, found_idx) = is_found * found(0, found_idx) + (1 - is_found) * blob_id
。
我已经回答了您面临的特定问题。如果您有任何后续问题,请在我们的论坛和/或我们的支持电子邮件中跟进。 Stackoverflow非常适合提出一个特定的问题,但不能调试整个程序。