NAME

ck_pr_fence_atomic_store —

enforce ordering of atomic read-modify-write operations to store operations

LIBRARY

Concurrency Kit (libck, -lck)

SYNOPSIS

#include <ck_pr.h>

void
ck_pr_fence_atomic_store(void);

void
ck_pr_fence_strict_atomic_store(void);

DESCRIPTION

The ck_pr_fence_atomic_store() function enforces the ordering of any atomic read-modify-write operations relative to any load operations following the function invocation. This function always serve as an implicit compiler barrier. On architectures implementing CK_MD_TSO, this operation only serves as a compiler barrier and no fences are emitted. To force the unconditional emission of a fence, use ck_pr_fence_strict_atomic_store().

EXAMPLE


#include <ck_pr.h>

static int a = 0;
static int b = 0;

void
function(void)
{
	int c;

	ck_pr_fas_int(&a, 1);

	/*
	 * Guarantee that the update to a is completed
	 * with respect to the store into the value pointed
	 * to by b.
	 */
	ck_pr_fence_atomic_store();
	c = ck_pr_store_int(&b, 2);

	return;
}

RETURN VALUES

This function has no return value.