SHMEM\_LONG\_WAIT(3) Open MPI SHMEM\_LONG\_WAIT(3) shmem\_int\_wait <#shmem-int-wait>(3), shmem\_int\_wait <#shmem-int-wait>(3)\_until, [shmem\_int4\_wait(3)](/man/enterprise-packages/openmpi-cuda-13.2/shmem_int4_wait.3), [shmem\_int4\_wait(3)](/man/enterprise-packages/openmpi-cuda-13.2/shmem_int4_wait.3)\_until, [shmem\_int8\_wait(3)](/man/enterprise-packages/openmpi-cuda-13.2/shmem_int8_wait.3), [shmem\_int8\_wait(3)](/man/enterprise-packages/openmpi-cuda-13.2/shmem_int8_wait.3)\_until, [shmem\_long\_wait(3)](/man/enterprise-packages/openmpi-cuda-13.2/shmem_long_wait.3), [shmem\_long\_wait(3)](/man/enterprise-packages/openmpi-cuda-13.2/shmem_long_wait.3)\_until, shmem\_longlong\_wait <#shmem-longlong-wait>(3), shmem\_longlong\_wait <#shmem-longlong-wait>(3)\_until, shmem\_short\_wait <#shmem-short-wait>(3), shmem\_short\_wait <#shmem-short-wait>(3)\_until, shmem\_wait <#shmem-wait>(3), shmem\_wait <#shmem-wait>(3)\_until - Waits for a variable on the local processing element (PE) to change # [SYNOPSIS](#SYNOPSIS) C or C++: ``` #include void shmem_int_wait(volatile int *var, int value) void shmem_int_wait_until(volatile int *var, int cond, int value) void shmem_long_wait(volatile long *var, long value) void shmem_long_wait_until(volatile long *var, int cond, long value) void shmem_longlong_wait(volatile long long *var, long long value) void shmem_longlong_wait_until(volatile long long *var, int cond, long long value) void shmem_short_wait(volatile short *var, short value) void shmem_short_wait_until(volatile short *var, int cond, short value) void shmem_wait(volatile long *ivar, long cmp_value) void shmem_wait_until(volatile long *ivar, int cmp, long value) ``` Fortran: ``` INCLUDE "mpp/shmem.fh" CALL SHMEM_INT4_WAIT(ivar, cmp_value) CALL SHMEM_INT4_WAIT_UNTIL(ivar, cmp, cmp_value) CALL SHMEM_INT8_WAIT(ivar, cmp_value) CALL SHMEM_INT8_WAIT_UNTIL(ivar, cmp, cmp_value) CALL SHMEM_WAIT(ivar, cmp_value) CALL SHMEM_WAIT_UNTIL(ivar, cmp, cmp_value) ``` # [DESCRIPTION](#DESCRIPTION) shmem\_wait <#shmem-wait> and shmem\_wait\_until <#shmem-wait-until> wait for **ivar** to be changed by a remote write or atomic swap issued by a different processor. These routines can be used for point-to- point directed synchronization. A call to shmem\_wait <#shmem-wait> does not return until some other processor writes a value, not equal to cmp\_value, into **ivar** on the waiting processor. A call to shmem\_wait\_until <#shmem-wait-until> does not return until some other processor changes **ivar** to satisfy the condition implied by cmp and cmp\_value. This mechanism is useful when a processor needs to tell another processor that it has completed some action. The arguments are as follows: [**ivar**](#ivar) A remotely accessible integer variable that is being updated by another PE. If you are using C/C++, the type of ivar should match that implied in the SYNOPSIS section. If you are using Fortran, ivar must be a specific sized integer type according to the function being called, as follows: shmem\_wait <#shmem-wait>, shmem\_wait\_until <#shmem-wait-until>:\** default INTEGER shmem\_int4\_wait, shmem\_int4\_wait\_until:\** INTEGER\*4 shmem\_int8\_wait, shmem\_int8\_wait\_until:\** INTEGER\*8 [**cmp**](#cmp) The compare operator that compares ivar with cmp\_value. cmp must be of type integer. If you are using Fortran, it must be of default kind. If you are using C/C++, the type of cmp should match that implied in the SYNOPSIS section. The following cmp values are supported: [**SHMEM\_CMP\_EQ**](#SHMEM_CMP_EQ) Equal [**SHMEM\_CMP\_NE**](#SHMEM_CMP_NE) Not equal [**SHMEM\_CMP\_GT**](#SHMEM_CMP_GT) Greater than [**SHMEM\_CMP\_LE**](#SHMEM_CMP_LE) Less than or equal to [**SHMEM\_CMP\_LT**](#SHMEM_CMP_LT) Less than [**SHMEM\_CMP\_GE**](#SHMEM_CMP_GE) Greater than or equal to [**cmp\_value**](#cmp_value) cmp\_value must be of type integer. If you are using C/C++, the type of cmp\_value should match that implied in the SYNOPSIS section. If you are using Fortran, cmp\_value must be an integer of the same size and kind as ivar. The shmem\_wait <#shmem-wait> routines return when ivar is no longer equal to cmp\_value. The shmem\_wait\_until <#shmem-wait-until> routines return when the compare condition is true. The compare condition is defined by the ivar argument compared with the cmp\_value using the comparison operator, cmp. # [EXAMPLES](#EXAMPLES) **Example 1:** The following call returns when variable ivar is not equal to 100: ``` INTEGER*8 IVAR CALL SHMEM_INT8_WAIT(IVAR, INT8(100)) ``` **Example 2:** The following call to SHMEM\_INT8\_WAIT\_UNTIL is equivalent to the call to SHMEM\_INT8\_WAIT in example 1: ``` INTEGER*8 IVAR CALL SHMEM_INT8_WAIT_UNTIL(IVAR, SHMEM_CMP_NE, INT8(100)) ``` **Example 3:** The following C/C++ call waits until the sign bit in ivar is set by a transfer from a remote PE: ``` int ivar; shmem_int_wait_until(&ivar, SHMEM_CMP_LT, 0); ``` **Example 4:** The following Fortran example is in the context of a subroutine: ``` SUBROUTINE EXAMPLE() INTEGER FLAG_VAR COMMON/FLAG/FLAG_VAR . . . FLAG_VAR = FLAG_VALUE ! initialize the event variable . . . IF (FLAG_VAR .EQ. FLAG_VALUE) THEN CALL SHMEM_WAIT(FLAG_VAR, FLAG_VALUE) ENDIF FLAG_VAR = FLAG_VALUE ! reset the event variable for next time . . . END ``` **See also:** [*intro\_shmem*(3)](/man/enterprise-packages/openmpi-cuda-13.2/intro_shmem.3) [*shmem\_put*(3)](/man/enterprise-packages/openmpi-cuda-13.2/shmem_put.3) # [Copyright](#Copyright) 2003-2026, The Open MPI Community October 9, 2026 --- Document: shmem_long_wait(3) from openmpi-cuda-13.2 5.0.11-r1 (Chainguard OS) Source: https://github.com/open-mpi/ompi