NAME¶
ck_pr_fence_atomic
—
enforce partial ordering of atomic read-modify-write
operations
LIBRARY¶
Concurrency Kit (libck, -lck)
SYNOPSIS¶
#include
<ck_pr.h>
void
ck_pr_fence_atomic
(
void);
void
ck_pr_fence_strict_atomic
(
void);
DESCRIPTION¶
The
ck_pr_fence_atomic
() function enfores the
ordering of any atomic read-modify-write operations relative to the invocation
of the function. 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. On architectures implementing
CK_MD_PSO and CK_MD_RMO, a store fence is emitted. To force the unconditional
emission of a fence, use
ck_pr_fence_strict_atomic
().
EXAMPLE¶
#include <ck_pr.h>
static int a = 0;
static int b = 0;
static int c = 0;
void
function(void)
{
ck_pr_fas_int(&a, 1);
/*
* Guarantee that the update to a is completed
* with respect to the updates of b and c.
*/
ck_pr_fence_atomic();
ck_pr_fas_int(&b, 2);
ck_pr_fas_int(&c, 2);
return;
}
RETURN VALUES¶
This function has no return value.
SEE ALSO¶
ck_pr_stall(3),
ck_pr_fence_atomic_store(3),
ck_pr_fence_atomic_load(3),
ck_pr_fence_store(3),
ck_pr_fence_load(3),
ck_pr_fence_load_atomic(3),
ck_pr_fence_load_store(3),
ck_pr_fence_load_depends(3),
ck_pr_fence_memory(3),
ck_pr_barrier(3),
ck_pr_fas(3),
ck_pr_load(3),
ck_pr_store(3),
ck_pr_faa(3),
ck_pr_inc(3),
ck_pr_dec(3),
ck_pr_neg(3),
ck_pr_not(3),
ck_pr_add(3),
ck_pr_sub(3),
ck_pr_and(3),
ck_pr_or(3),
ck_pr_xor(3),
ck_pr_cas(3),
ck_pr_btc(3),
ck_pr_bts(3),
ck_pr_btr(3)
Additional information available at
http://concurrencykit.org/