SHMEM_UDCFLUSH_LINE(3)

💅 SHMEM_UDCFLUSH_LINE(3) — Open MPI, bestie edition 🫶

okay so this is the Open MPI page for a whole lil squad of cache-control routines, and yes, the title says SHMEM_UDCFLUSH_LINE(3) but there's like six functions crashing this party. Let's get into it ✨

---

🎀 NAME

shmem_clear_cache_inv(3), shmem_set_cache_inv(3), shmem_set_cache_line_inv(3), shmem_udcflush(3), shmem_udcflush_line(3) — Controls data cache utilities

(yes, shmem_clear_cache_line_inv is in the synopsis too, we see you girl 👀)

---

🌸 SYNOPSIS

C or C++:

#include <mpp/shmem.h>

void shmem_clear_cache_inv(void)
void shmem_clear_cache_line_inv(void *target)
void shmem_set_cache_inv(void)
void shmem_set_cache_line_inv(void *target)
void shmem_udcflush(void)
void shmem_udcflush_line(void *target)

Fortran:

INCLUDE "mpp/shmem.fh"

CALL SHMEM_CLEAR_CACHE_INV
CALL SHMEM_CLEAR_CACHE_LINE_INV(target)
CALL SHMEM_SET_CACHE_INV
CALL SHMEM_SET_CACHE_LINE_INV(target)

CALL SHMEM_UDCFLUSH
CALL SHMEM_UDCFLUSH_LINE(target)

---

✨ DESCRIPTION

ok so first, the one argument that the cache line control routines take — bestie, meet target 🥺

• target — a data object that is local to the processing element (PE). target can be of any noncharacter type. If you're doing Fortran, it can be of any kind. (kind girl summer 💐)

now the routines themselves, one by one, no skipping:

• shmem_clear_cache_inv — disables automatic cache coherency mode that was previously enabled by shmem_set_cache_inv or shmem_set_cache_line_inv. basically it's the "nvm, turn it back off" button 🔘
• shmem_clear_cache_line_inv — disables automatic cache coherency mode for the cache line associated with the address of target only. just that one line. not the whole vibe, just that line ✂️
• shmem_set_cache_inv — enables the OpenSHMEM API to automatically decide the best strategy for cache coherency. it's giving "you handle it, i trust you" 🤝
• shmem_set_cache_line_inv — enables automatic cache coherency mode for the cache line associated with the address of target only. same one-line-only energy 💅
• shmem_clear_cache_inv — yeah it's literally right here again in the original: disables automatic cache coherency mode previously enabled by shmem_set_cache_inv or shmem_set_cache_line_inv. it's listed twice, we're keeping it twice, no cap 💀
• shmem_udcflush — makes the entire user data cache coherent. whole cache. full send 🌊
• shmem_udcflush_line — makes coherent the cache line that corresponds with the address specified by target. one line, squeaky clean 🧼

---

🦋 NOTES

these routines have been retained for improved backward compatibility with legacy architectures. so like yeah, they're here for the old-school girlies 🕰️👑

SEE ALSO: intro_shmem(3) shmem_put(3) shmem_swap(3)

---

👑 COPYRIGHT

2003-2026, The Open MPI Community

---

that's the whole page, you ate that 🍓💖 — signing off from May 14, 2026, source and version: Open MPI's own SHMEM_UDCFLUSH_LINE(3) page. iykyk 🌈⭐