openmp

问题 I got a problem that my following code runs slower with openmp: chunk = nx/nthreads; int i, j; for(int t = 0; t < n; t++){ #pragma omp parallel for default(shared) private(i, j) schedule(static,chunk) for(i = 1; i < nx/2+1; i++){ for(j = 1; j < nx-1; j++){ T_c[i][j] =0.25*(T_p[i-1][j] +T_p[i+1][j]+T_p[i][j-1]+T_p[i][j+1]); T_c[nx-i+1][j] = T_c[i][j]; } } copyT(T_p, T_c, nx); } print2file(T_c, nx, file); The problem is when I run more than one threads, the computational time will be much

问题 for (int i = 0; i < x_res; i++){ #pragma omp parallel for for (int j = 0; j < y_res; j++) { Ray hit = s.kd_tree->intersect(rays[i][j]); } } Why is this code not working in parallel? I cannot find the reason. The backtrace outputs this: #0 0x00007fff8ce03bf2 in __psynch_mutexwait () #1 0x00007fff8cd331a1 in pthread_mutex_lock () #2 0x00000001000027e4 in gomp_barrier_destroy () #3 0x000000010000247b in gomp_team_end () 回答1: Download the last gcc (4.8 for now) from http://hpc.sourceforge.net/ .

问题 I want to know how much time each thread is using in the for loop. I want time_taken to be private for each thread so they can append their own time there. Best cast i would like the total time for each thread, instead of the time for each iteration in the while-loop. double time_taken = 0.0; while(delta >= epsilon) { delta = 0.0; double wtime = omp_get_wtime(); #pragma omp parallel for reduction(+:delta) for (i = 0; i < workSize; i++) { #do some work and change delta } time_taken += omp_get

问题 In this answer to Multiprocessing.Pool makes Numpy matrix multiplication slower the author of the answer recommends in the second paragraph to recompile Numpy with enabled OpenMP directives. So my questions are: How do you do that? What could be negative side effects? Would you recommend that? Searching SO I found following post OpenMP and Python, where the answers explain why there is no use for OpenMP in general Python due to the GIL. But I assume Numpy is a different issue. 回答1: While

问题 So from what I understand, either of these are correct in ALL versions of openmp: //int i declared in loop, explicitly private #pragma omp parallel for for (int i = 0; i < NUMEL; i++) { foo(i); } //int i declared outsize loop, but is the iterated value, implicitly private int i; #pragma omp parallel for for (i = 0; i < NUMEL; i++) { foo(i); } However, I more commonly see the second than the first. Why is that? 回答1: Because not everybody writes in C++ or targets a C99-compliant C compiler.

问题 This question already has answers here : Closed 8 years ago . Possible Duplicates: C/C++ pragma in define macro Conditional “pragma omp” How can I use an OpenMP pragmas inside a macro definition? E.g. #define A() { \ ...a lot of code... \ #pragma omp for \ for(..) \ ..do_for.. \ ...another a lot of code \ } 回答1: As it was answered here Conditional "pragma omp" C99 has the _Pragma keyword that allows you to place what otherwise would be #pragma inside macros. Something like #define OMP_PARA

问题 Consider the following minimal C code example. When compiling and executing with export OMP_NUM_THREADS=4 && gcc -fopenmp minimal2.c && ./a.out (homebrew GCC 5.2.0 on OS X 10.11), this usually produces the correct behavior, i.e. seven lines with the same number. But sometimes, this happens: [ ] bsum=1.893293142303100e+03 [1] asum=1.893293142303100e+03 [2] asum=1.893293142303100e+03 [0] asum=1.893293142303100e+03 [3] asum=3.786586284606200e+03 [ ] bsum=1.893293142303100e+03 [ ] asum=3

问题 I'm in a situation where on one computer (cluster with high perf nodes) a code compiles but on my personal computer it doesn't. The error is 'var' declared 'threadprivate' after first use. #pragma omp threadprivate(var) The related line in the code is in a header file and looks like this extern const int var; #pragma omp threadprivate(var); I haven't written the code so it is difficult to give a minimal example of the problem. Here are some specification of the computer I use : cluster

问题 I am running the following fortran code in parallel using openmp, but only one processor is working. I added some of the execution routines like OMP_SET_NUM_THREADS and OMP_GET_NUM_THREADS to the code to follow the parallel-processing. Here is the relevant part of the code: integer a,b,omp_get_num_procs,omp_get_max_threads, & omp_get_num_threads open( unit=10 , file='threads' , status='new' ) a=4 call omp_set_num_threads(a) write(10,*) 'num_proc=',omp_get_num_procs() write(10,*) 'max_threads=

问题 I have this code: #pragma omp parallel { #pragma omp single { for (int i=0; i<given_number; ++i) myBuffer_1[i] = myObject_1->myFunction(); } #pragma omp single { for (int i=0; i<given_number; ++i) myBuffer_2[i] = myObject_2->myFunction(); } } // and so on... up to 5 or 6 of myObject_x // Then I sum up the buffers and do something with them float result; for (int i=0; i<given_number; ++i) result = myBuffer_1[i] + myBuffer_2[i]; // do something with result If I run this code, I get what I