SHMEM_SHORT_P(3)
π SHMEM_SHORT_P π
okay so bestie, welcome to the <p>-suffix corner of Open MPI's shmem world β this is the shmem_short_p(3) page (and like, it's literally a whole friend group of pages all sharing one doc), straight out of Open MPI. Buckle up, we're putting tiny little values on remote PEs and we're doing it fast. π¦
πΈ NAME πΈ
shmem_char_p(3), shmem_float_p(3), shmem_int_p(3), shmem_long_p(3), shmem_short_p(3), shmem_longlong_p(3), shmem_longdouble_p(3)
These routines provide a low latency mechanism to write basic types (char, short, int, float, double, long, long long, long double) to symmetric data objects on remote PEs. it's giving "small put, big energy" β¨
π SYNOPSIS π
C or C++:
#include <mpp/shmem.h>
void shmem_char_p(char *addr, char value, int pe)
void shmem_short_p(short *addr, short value, int pe)
void shmem_int_p(int *addr, int value, int pe)
void shmem_long_p(long *addr, long value, int pe)
void shmem_longlong_p(long long *addr, long long value, int pe)
void shmem_float_p(float *addr, float value, int pe)
void shmem_double_p(double *addr, double value, int pe)
void shmem_longdouble_p(long double *addr, long double value, int pe)
like, pick your type, pick your PE, that's the whole vibe π
π DESCRIPTION π
These routines provide a very low latency put capability for single elements of most basic types. not a whole array, not a whole vibe β one element, delivered with main character energy π
The arguments are as follows:
addrβ the remotely accessible array element or scalar data object which will receive the data on the remote PE. it's the landing spot, the destination, the receiving end of the friendship π«Άvalueβ the value to be transferred toaddron the remote PE. this is the actual thing you're yeeting over there πpeβ the number of the remote PE. yes bestie, you gotta say which PE, we're not mind readers π
β οΈ okay important one: as withshmem_put(3), these functions start the remote transfer and may return before the data is delivered to the remote PE. so likeβ¦ it left your hands, doesn't mean it's arrived. useshmem_quiet(3)to force completion of all remote PUT transfers. no cap, don't skip the quiet if you actually need the data to be there. π₯
π SEE ALSO: π
intro_shmem(3)shmem_put(3)
π COPYRIGHT π
2003-2026, The Open MPI Community
and that's the page bestie!! π mwah, go forth and put your little shorts on remote PEs responsibly π
~ with love from the Open MPI squad, dated May 14, 2026 β catch you in the next manpage, iykyk β
π¦ where this page comes from
- arch rolling: nvhpc-comm-libs 26.9-1 Β· LicenseRef-NVIDIA-HPC-SDK
- π girlified by deepseek-ai/DeepSeek-V4.1-Flash-1017 on : a language model's rewrite of the original, under its terms