The Future of GPU Computing Wen-mei Hwu University of Illinois, Urbana-Champaign Agenda · · · · Setting the Context Current Victories Coming Battles Conclusion and Outlook NVIDIA HPC Day Moscow State University 2012 CPUs: Latency Oriented Design · Large caches ­ Convert long latency memory accesses to short latency cache accesses ALU Control ALU ALU · Sophisticated control ­ Branch prediction for reduced branch latency ... NVIDIA HPC Day Moscow State University 2012 ...

Еще в разделе: (Показать все результаты (>2) - ccoe.msu.ru/ )

... 9 , 2010 MPI/OpenMP 60 1 2 3 ( PARALLEL) #pragma omp parallel [ [ [, ] ] ...] : default(shared | ... include stdio.h int main () { int n =100000, i; double pi, h, sum , x; h = 1.0 / ( double ) n; sum = 0.0; for (i = 1; i = n; i ++) { x = h * (( double )i - 0.5); sum += (4.0 / (1.0 + x*x)); } pi = h * sum ; printf( pi is approximately %.16f , pi); return 0; } 9 , 2010 MPI / OpenMP 84 1 2 3 OpenMP int main () { int n =100, i; double pi, h, sum , x; h = 1.0 / ( double ) n; ...

352. http://www.imk.msu.ru/Publications/Articles/Smyshlyaev_nyanya.doc

---

Астронет | Научная сеть | ГАИШ МГУ | Поиск по МГУ | О проекте | Авторам

Комментарии, вопросы? Пишите: info@astronet.ru или сюда