void
GOACC_update (int device, const void *offload_table, size_t mapnum,
void **hostaddrs, size_t *sizes, unsigned short *kinds,
int async, int num_waits, ...)
{
bool host_fallback = device == GOMP_DEVICE_HOST_FALLBACK;
size_t i;
select_acc_device (device);
struct goacc_thread *thr = goacc_thread ();
struct gomp_device_descr *acc_dev = thr->dev;
if ((acc_dev->capabilities & GOMP_OFFLOAD_CAP_SHARED_MEM)
|| host_fallback)
return;
if (num_waits > 0)
{
va_list ap;
va_start (ap, num_waits);
goacc_wait (async, num_waits, ap);
va_end (ap);
}
acc_dev->openacc.async_set_async_func (async);
for (i = 0; i < mapnum; ++i)
{
unsigned char kind = kinds[i] & 0xff;
switch (kind)
{
case GOMP_MAP_POINTER:
case GOMP_MAP_TO_PSET:
break;
case GOMP_MAP_FORCE_TO:
acc_update_device (hostaddrs[i], sizes[i]);
break;
case GOMP_MAP_FORCE_FROM:
acc_update_self (hostaddrs[i], sizes[i]);
break;
default:
gomp_fatal (">>>> GOACC_update UNHANDLED kind 0x%.2x", kind);
break;
}
}
acc_dev->openacc.async_set_async_func (acc_async_sync);
}
void
GOACC_wait (int async, int num_waits, ...)
{
va_list ap;
va_start (ap, num_waits);
goacc_wait (async, num_waits, ap);
va_end (ap);
}
void
GOACC_wait (int async, int num_waits, ...)
{
if (num_waits)
{
va_list ap;
va_start (ap, num_waits);
goacc_wait (async, num_waits, &ap);
va_end (ap);
}
else if (async == acc_async_sync)
acc_wait_all ();
else if (async == acc_async_noval)
goacc_thread ()->dev->openacc.async_wait_all_async_func (acc_async_noval);
}
void
GOACC_parallel (int device, void (*fn) (void *), const void *offload_table,
size_t mapnum, void **hostaddrs, size_t *sizes,
unsigned short *kinds,
int num_gangs, int num_workers, int vector_length,
int async, int num_waits, ...)
{
bool host_fallback = device == GOMP_DEVICE_HOST_FALLBACK;
va_list ap;
struct goacc_thread *thr;
struct gomp_device_descr *acc_dev;
struct target_mem_desc *tgt;
void **devaddrs;
unsigned int i;
struct splay_tree_key_s k;
splay_tree_key tgt_fn_key;
void (*tgt_fn);
if (num_gangs != 1)
gomp_fatal ("num_gangs (%d) different from one is not yet supported",
num_gangs);
if (num_workers != 1)
gomp_fatal ("num_workers (%d) different from one is not yet supported",
num_workers);
gomp_debug (0, "%s: mapnum=%zd, hostaddrs=%p, sizes=%p, kinds=%p, async=%d\n",
__FUNCTION__, mapnum, hostaddrs, sizes, kinds, async);
select_acc_device (device);
thr = goacc_thread ();
acc_dev = thr->dev;
/* Host fallback if "if" clause is false or if the current device is set to
the host. */
if (host_fallback)
{
goacc_save_and_set_bind (acc_device_host);
fn (hostaddrs);
goacc_restore_bind ();
return;
}
else if (acc_device_type (acc_dev->type) == acc_device_host)
{
fn (hostaddrs);
return;
}
va_start (ap, num_waits);
if (num_waits > 0)
goacc_wait (async, num_waits, ap);
va_end (ap);
acc_dev->openacc.async_set_async_func (async);
if (!(acc_dev->capabilities & GOMP_OFFLOAD_CAP_NATIVE_EXEC))
{
k.host_start = (uintptr_t) fn;
k.host_end = k.host_start + 1;
gomp_mutex_lock (&acc_dev->mem_map.lock);
tgt_fn_key = splay_tree_lookup (&acc_dev->mem_map.splay_tree, &k);
gomp_mutex_unlock (&acc_dev->mem_map.lock);
if (tgt_fn_key == NULL)
gomp_fatal ("target function wasn't mapped");
tgt_fn = (void (*)) tgt_fn_key->tgt->tgt_start;
}
else
tgt_fn = (void (*)) fn;
tgt = gomp_map_vars (acc_dev, mapnum, hostaddrs, NULL, sizes, kinds, true,
false);
devaddrs = alloca (sizeof (void *) * mapnum);
for (i = 0; i < mapnum; i++)
devaddrs[i] = (void *) (tgt->list[i]->tgt->tgt_start
+ tgt->list[i]->tgt_offset);
acc_dev->openacc.exec_func (tgt_fn, mapnum, hostaddrs, devaddrs, sizes, kinds,
num_gangs, num_workers, vector_length, async,
tgt);
/* If running synchronously, unmap immediately. */
if (async < acc_async_noval)
gomp_unmap_vars (tgt, true);
else
{
gomp_copy_from_async (tgt);
acc_dev->openacc.register_async_cleanup_func (tgt);
}
acc_dev->openacc.async_set_async_func (acc_async_sync);
}
void
GOACC_enter_exit_data (int device, const void *offload_table, size_t mapnum,
void **hostaddrs, size_t *sizes, unsigned short *kinds,
int async, int num_waits, ...)
{
struct goacc_thread *thr;
struct gomp_device_descr *acc_dev;
bool host_fallback = device == GOMP_DEVICE_HOST_FALLBACK;
bool data_enter = false;
size_t i;
select_acc_device (device);
thr = goacc_thread ();
acc_dev = thr->dev;
if ((acc_dev->capabilities & GOMP_OFFLOAD_CAP_SHARED_MEM)
|| host_fallback)
return;
if (num_waits > 0)
{
va_list ap;
va_start (ap, num_waits);
goacc_wait (async, num_waits, ap);
va_end (ap);
}
acc_dev->openacc.async_set_async_func (async);
/* Determine if this is an "acc enter data". */
for (i = 0; i < mapnum; ++i)
{
unsigned char kind = kinds[i] & 0xff;
if (kind == GOMP_MAP_POINTER || kind == GOMP_MAP_TO_PSET)
continue;
if (kind == GOMP_MAP_FORCE_ALLOC
|| kind == GOMP_MAP_FORCE_PRESENT
|| kind == GOMP_MAP_FORCE_TO)
{
data_enter = true;
break;
}
if (kind == GOMP_MAP_FORCE_DEALLOC
|| kind == GOMP_MAP_FORCE_FROM)
break;
gomp_fatal (">>>> GOACC_enter_exit_data UNHANDLED kind 0x%.2x",
kind);
}
if (data_enter)
{
for (i = 0; i < mapnum; i++)
{
unsigned char kind = kinds[i] & 0xff;
/* Scan for PSETs. */
int psets = find_pset (i, mapnum, kinds);
if (!psets)
{
switch (kind)
{
case GOMP_MAP_POINTER:
gomp_acc_insert_pointer (1, &hostaddrs[i], &sizes[i],
&kinds[i]);
break;
case GOMP_MAP_FORCE_ALLOC:
acc_create (hostaddrs[i], sizes[i]);
break;
case GOMP_MAP_FORCE_PRESENT:
acc_present_or_copyin (hostaddrs[i], sizes[i]);
break;
case GOMP_MAP_FORCE_TO:
acc_present_or_copyin (hostaddrs[i], sizes[i]);
break;
default:
gomp_fatal (">>>> GOACC_enter_exit_data UNHANDLED kind 0x%.2x",
kind);
break;
}
}
else
{
gomp_acc_insert_pointer (3, &hostaddrs[i], &sizes[i], &kinds[i]);
/* Increment 'i' by two because OpenACC requires fortran
arrays to be contiguous, so each PSET is associated with
one of MAP_FORCE_ALLOC/MAP_FORCE_PRESET/MAP_FORCE_TO, and
one MAP_POINTER. */
i += 2;
}
}
}
else
for (i = 0; i < mapnum; ++i)
{
unsigned char kind = kinds[i] & 0xff;
int psets = find_pset (i, mapnum, kinds);
if (!psets)
{
switch (kind)
{
case GOMP_MAP_POINTER:
gomp_acc_remove_pointer (hostaddrs[i], (kinds[i] & 0xff)
== GOMP_MAP_FORCE_FROM,
async, 1);
break;
case GOMP_MAP_FORCE_DEALLOC:
acc_delete (hostaddrs[i], sizes[i]);
break;
case GOMP_MAP_FORCE_FROM:
acc_copyout (hostaddrs[i], sizes[i]);
break;
default:
gomp_fatal (">>>> GOACC_enter_exit_data UNHANDLED kind 0x%.2x",
kind);
break;
}
}
else
{
gomp_acc_remove_pointer (hostaddrs[i], (kinds[i] & 0xff)
== GOMP_MAP_FORCE_FROM, async, 3);
/* See the above comment. */
i += 2;
}
}
acc_dev->openacc.async_set_async_func (acc_async_sync);
}
void
GOACC_parallel_keyed (int device, void (*fn) (void *),
size_t mapnum, void **hostaddrs, size_t *sizes,
unsigned short *kinds, ...)
{
bool host_fallback = device == GOMP_DEVICE_HOST_FALLBACK;
va_list ap;
struct goacc_thread *thr;
struct gomp_device_descr *acc_dev;
struct target_mem_desc *tgt;
void **devaddrs;
unsigned int i;
struct splay_tree_key_s k;
splay_tree_key tgt_fn_key;
void (*tgt_fn);
int async = GOMP_ASYNC_SYNC;
unsigned dims[GOMP_DIM_MAX];
unsigned tag;
#ifdef HAVE_INTTYPES_H
gomp_debug (0, "%s: mapnum=%"PRIu64", hostaddrs=%p, size=%p, kinds=%p\n",
__FUNCTION__, (uint64_t) mapnum, hostaddrs, sizes, kinds);
#else
gomp_debug (0, "%s: mapnum=%lu, hostaddrs=%p, sizes=%p, kinds=%p\n",
__FUNCTION__, (unsigned long) mapnum, hostaddrs, sizes, kinds);
#endif
goacc_lazy_initialize ();
thr = goacc_thread ();
acc_dev = thr->dev;
/* Host fallback if "if" clause is false or if the current device is set to
the host. */
if (host_fallback)
{
goacc_save_and_set_bind (acc_device_host);
fn (hostaddrs);
goacc_restore_bind ();
return;
}
else if (acc_device_type (acc_dev->type) == acc_device_host)
{
fn (hostaddrs);
return;
}
va_start (ap, kinds);
/* TODO: This will need amending when device_type is implemented. */
while ((tag = va_arg (ap, unsigned)) != 0)
{
if (GOMP_LAUNCH_DEVICE (tag))
gomp_fatal ("device_type '%d' offload parameters, libgomp is too old",
GOMP_LAUNCH_DEVICE (tag));
switch (GOMP_LAUNCH_CODE (tag))
{
case GOMP_LAUNCH_DIM:
{
unsigned mask = GOMP_LAUNCH_OP (tag);
for (i = 0; i != GOMP_DIM_MAX; i++)
if (mask & GOMP_DIM_MASK (i))
dims[i] = va_arg (ap, unsigned);
}
break;
case GOMP_LAUNCH_ASYNC:
{
/* Small constant values are encoded in the operand. */
async = GOMP_LAUNCH_OP (tag);
if (async == GOMP_LAUNCH_OP_MAX)
async = va_arg (ap, unsigned);
break;
}
case GOMP_LAUNCH_WAIT:
{
unsigned num_waits = GOMP_LAUNCH_OP (tag);
if (num_waits)
goacc_wait (async, num_waits, &ap);
break;
}
default:
gomp_fatal ("unrecognized offload code '%d',"
" libgomp is too old", GOMP_LAUNCH_CODE (tag));
}
}
va_end (ap);
acc_dev->openacc.async_set_async_func (async);
if (!(acc_dev->capabilities & GOMP_OFFLOAD_CAP_NATIVE_EXEC))
{
k.host_start = (uintptr_t) fn;
k.host_end = k.host_start + 1;
gomp_mutex_lock (&acc_dev->lock);
tgt_fn_key = splay_tree_lookup (&acc_dev->mem_map, &k);
gomp_mutex_unlock (&acc_dev->lock);
if (tgt_fn_key == NULL)
gomp_fatal ("target function wasn't mapped");
tgt_fn = (void (*)) tgt_fn_key->tgt_offset;
}
else
tgt_fn = (void (*)) fn;
tgt = gomp_map_vars (acc_dev, mapnum, hostaddrs, NULL, sizes, kinds, true,
GOMP_MAP_VARS_OPENACC);
devaddrs = gomp_alloca (sizeof (void *) * mapnum);
for (i = 0; i < mapnum; i++)
devaddrs[i] = (void *) (tgt->list[i].key->tgt->tgt_start
+ tgt->list[i].key->tgt_offset);
acc_dev->openacc.exec_func (tgt_fn, mapnum, hostaddrs, devaddrs,
async, dims, tgt);
/* If running synchronously, unmap immediately. */
if (async < acc_async_noval)
gomp_unmap_vars (tgt, true);
else
{
gomp_copy_from_async (tgt);
acc_dev->openacc.register_async_cleanup_func (tgt);
}
acc_dev->openacc.async_set_async_func (acc_async_sync);
}
