this_req = OMP_REQUIRES_UNIFIED_ADDRESS;
else if (!strcmp (p, "unified_shared_memory"))
this_req = OMP_REQUIRES_UNIFIED_SHARED_MEMORY;
+ else if (!strcmp (p, "self_maps"))
+ this_req = OMP_REQUIRES_SELF_MAPS;
else if (!strcmp (p, "dynamic_allocators"))
this_req = OMP_REQUIRES_DYNAMIC_ALLOCATORS;
else if (!strcmp (p, "reverse_offload"))
{
error_at (cloc, "expected %<unified_address%>, "
"%<unified_shared_memory%>, "
+ "%<self_maps%>, "
"%<dynamic_allocators%>, "
"%<reverse_offload%> "
"or %<atomic_default_mem_order%> clause");
this_req = OMP_REQUIRES_UNIFIED_ADDRESS;
else if (!strcmp (p, "unified_shared_memory"))
this_req = OMP_REQUIRES_UNIFIED_SHARED_MEMORY;
+ else if (!strcmp (p, "self_maps"))
+ this_req = OMP_REQUIRES_SELF_MAPS;
else if (!strcmp (p, "dynamic_allocators"))
this_req = OMP_REQUIRES_DYNAMIC_ALLOCATORS;
else if (!strcmp (p, "reverse_offload"))
{
error_at (cloc, "expected %<unified_address%>, "
"%<unified_shared_memory%>, "
+ "%<self_maps%>, "
"%<dynamic_allocators%>, "
"%<reverse_offload%> "
"or %<atomic_default_mem_order%> clause");
enum gfc_omp_requires_kind
{
- /* Keep in sync with gfc_namespace, esp. with omp_req_mem_order. */
+ /* Keep gfc_namespace's omp_requires bitfield size in sync. */
OMP_REQ_ATOMIC_MEM_ORDER_SEQ_CST = 1, /* 001 */
OMP_REQ_ATOMIC_MEM_ORDER_ACQ_REL = 2, /* 010 */
OMP_REQ_ATOMIC_MEM_ORDER_RELAXED = 3, /* 011 */
OMP_REQ_REVERSE_OFFLOAD = (1 << 3),
OMP_REQ_UNIFIED_ADDRESS = (1 << 4),
OMP_REQ_UNIFIED_SHARED_MEMORY = (1 << 5),
- OMP_REQ_DYNAMIC_ALLOCATORS = (1 << 6),
+ OMP_REQ_SELF_MAPS = (1 << 6),
+ OMP_REQ_DYNAMIC_ALLOCATORS = (1 << 7),
OMP_REQ_TARGET_MASK = (OMP_REQ_REVERSE_OFFLOAD
| OMP_REQ_UNIFIED_ADDRESS
- | OMP_REQ_UNIFIED_SHARED_MEMORY),
+ | OMP_REQ_UNIFIED_SHARED_MEMORY
+ | OMP_REQ_SELF_MAPS),
OMP_REQ_ATOMIC_MEM_ORDER_MASK = (OMP_REQ_ATOMIC_MEM_ORDER_SEQ_CST
| OMP_REQ_ATOMIC_MEM_ORDER_ACQ_REL
| OMP_REQ_ATOMIC_MEM_ORDER_RELAXED
unsigned implicit_interface_calls:1;
/* OpenMP requires. */
- unsigned omp_requires:7;
+ unsigned omp_requires:8;
unsigned omp_target_seen:1;
/* Set to 1 if this is an implicit OMP structured block. */
AB_OACC_ROUTINE_LOP_GANG, AB_OACC_ROUTINE_LOP_WORKER,
AB_OACC_ROUTINE_LOP_VECTOR, AB_OACC_ROUTINE_LOP_SEQ,
AB_OACC_ROUTINE_NOHOST,
- AB_OMP_REQ_REVERSE_OFFLOAD, AB_OMP_REQ_UNIFIED_ADDRESS,
+ AB_OMP_REQ_REVERSE_OFFLOAD, AB_OMP_REQ_UNIFIED_ADDRESS, AB_OMP_REQ_SELF_MAPS,
AB_OMP_REQ_UNIFIED_SHARED_MEMORY, AB_OMP_REQ_DYNAMIC_ALLOCATORS,
AB_OMP_REQ_MEM_ORDER_SEQ_CST, AB_OMP_REQ_MEM_ORDER_ACQ_REL,
AB_OMP_REQ_MEM_ORDER_ACQUIRE, AB_OMP_REQ_MEM_ORDER_RELEASE,
minit ("OMP_REQ_REVERSE_OFFLOAD", AB_OMP_REQ_REVERSE_OFFLOAD),
minit ("OMP_REQ_UNIFIED_ADDRESS", AB_OMP_REQ_UNIFIED_ADDRESS),
minit ("OMP_REQ_UNIFIED_SHARED_MEMORY", AB_OMP_REQ_UNIFIED_SHARED_MEMORY),
+ minit ("OMP_REQ_SELF_MAPS", AB_OMP_REQ_SELF_MAPS),
minit ("OMP_REQ_DYNAMIC_ALLOCATORS", AB_OMP_REQ_DYNAMIC_ALLOCATORS),
minit ("OMP_REQ_MEM_ORDER_SEQ_CST", AB_OMP_REQ_MEM_ORDER_SEQ_CST),
minit ("OMP_REQ_MEM_ORDER_ACQ_REL", AB_OMP_REQ_MEM_ORDER_ACQ_REL),
MIO_NAME (ab_attribute) (AB_OMP_REQ_UNIFIED_ADDRESS, attr_bits);
if (gfc_current_ns->omp_requires & OMP_REQ_UNIFIED_SHARED_MEMORY)
MIO_NAME (ab_attribute) (AB_OMP_REQ_UNIFIED_SHARED_MEMORY, attr_bits);
+ if (gfc_current_ns->omp_requires & OMP_REQ_SELF_MAPS)
+ MIO_NAME (ab_attribute) (AB_OMP_REQ_SELF_MAPS, attr_bits);
if (gfc_current_ns->omp_requires & OMP_REQ_DYNAMIC_ALLOCATORS)
MIO_NAME (ab_attribute) (AB_OMP_REQ_DYNAMIC_ALLOCATORS, attr_bits);
if ((gfc_current_ns->omp_requires & OMP_REQ_ATOMIC_MEM_ORDER_MASK)
&gfc_current_locus,
module_name);
break;
+ case AB_OMP_REQ_SELF_MAPS:
+ gfc_omp_requires_add_clause (OMP_REQ_SELF_MAPS,
+ "self_maps",
+ &gfc_current_locus,
+ module_name);
+ break;
case AB_OMP_REQ_DYNAMIC_ALLOCATORS:
gfc_omp_requires_add_clause (OMP_REQ_DYNAMIC_ALLOCATORS,
"dynamic_allocators",
void
gfc_check_omp_requires (gfc_namespace *ns, int ref_omp_requires)
{
+ const char *msg = G_("Program unit at %L has OpenMP device "
+ "constructs/routines but does not set !$OMP REQUIRES %s "
+ "but other program units do");
if (ns->omp_target_seen
&& (ns->omp_requires & OMP_REQ_TARGET_MASK)
!= (ref_omp_requires & OMP_REQ_TARGET_MASK))
gcc_assert (ns->proc_name);
if ((ref_omp_requires & OMP_REQ_REVERSE_OFFLOAD)
&& !(ns->omp_requires & OMP_REQ_REVERSE_OFFLOAD))
- gfc_error ("Program unit at %L has OpenMP device constructs/routines "
- "but does not set !$OMP REQUIRES REVERSE_OFFLOAD but other "
- "program units do", &ns->proc_name->declared_at);
+ gfc_error (msg, &ns->proc_name->declared_at, "REVERSE_OFFLOAD");
if ((ref_omp_requires & OMP_REQ_UNIFIED_ADDRESS)
&& !(ns->omp_requires & OMP_REQ_UNIFIED_ADDRESS))
- gfc_error ("Program unit at %L has OpenMP device constructs/routines "
- "but does not set !$OMP REQUIRES UNIFIED_ADDRESS but other "
- "program units do", &ns->proc_name->declared_at);
+ gfc_error (msg, &ns->proc_name->declared_at, "UNIFIED_ADDRESS");
if ((ref_omp_requires & OMP_REQ_UNIFIED_SHARED_MEMORY)
&& !(ns->omp_requires & OMP_REQ_UNIFIED_SHARED_MEMORY))
- gfc_error ("Program unit at %L has OpenMP device constructs/routines "
- "but does not set !$OMP REQUIRES UNIFIED_SHARED_MEMORY but "
- "other program units do", &ns->proc_name->declared_at);
+ gfc_error (msg, &ns->proc_name->declared_at, "UNIFIED_SHARED_MEMORY");
+ if ((ref_omp_requires & OMP_REQ_SELF_MAPS)
+ && !(ns->omp_requires & OMP_REQ_UNIFIED_SHARED_MEMORY))
+ gfc_error (msg, &ns->proc_name->declared_at, "SELF_MAPS");
}
}
static const char *clauses[] = {"reverse_offload",
"unified_address",
"unified_shared_memory",
+ "self_maps",
"dynamic_allocators",
"atomic_default"};
const char *clause = NULL;
else if (gfc_match (clauses[3]) == MATCH_YES)
{
clause = clauses[3];
+ requires_clause = OMP_REQ_SELF_MAPS;
+ if (requires_clauses & OMP_REQ_SELF_MAPS)
+ goto duplicate_clause;
+ }
+ else if (gfc_match (clauses[4]) == MATCH_YES)
+ {
+ clause = clauses[4];
requires_clause = OMP_REQ_DYNAMIC_ALLOCATORS;
if (requires_clauses & OMP_REQ_DYNAMIC_ALLOCATORS)
goto duplicate_clause;
}
else if (gfc_match ("atomic_default_mem_order (") == MATCH_YES)
{
- clause = clauses[4];
+ clause = clauses[5];
if (requires_clauses & OMP_REQ_ATOMIC_MEM_ORDER_MASK)
goto duplicate_clause;
if (gfc_match (" seq_cst )") == MATCH_YES)
gfc_error ("%qs clause at %L specified more than once", clause, &old_loc);
error:
if (!gfc_error_flag_test ())
- gfc_error ("Expected UNIFIED_ADDRESS, UNIFIED_SHARED_MEMORY, "
+ gfc_error ("Expected UNIFIED_ADDRESS, UNIFIED_SHARED_MEMORY, SELF_MAPS, "
"DYNAMIC_ALLOCATORS, REVERSE_OFFLOAD, or "
"ATOMIC_DEFAULT_MEM_ORDER clause at %L", &old_loc);
return MATCH_ERROR;
omp_requires_mask
= (enum omp_requires) (omp_requires_mask
| OMP_REQUIRES_UNIFIED_SHARED_MEMORY);
+ if (omp_requires & OMP_REQ_SELF_MAPS)
+ omp_requires_mask
+ = (enum omp_requires) (omp_requires_mask | OMP_REQUIRES_SELF_MAPS);
if (omp_requires & OMP_REQ_DYNAMIC_ALLOCATORS)
omp_requires_mask = (enum omp_requires) (omp_requires_mask
| OMP_REQUIRES_DYNAMIC_ALLOCATORS);
HOST_WIDE_INT val = ((HOST_WIDE_INT) omp_requires_mask
& (OMP_REQUIRES_UNIFIED_ADDRESS
| OMP_REQUIRES_UNIFIED_SHARED_MEMORY
+ | OMP_REQUIRES_SELF_MAPS
| OMP_REQUIRES_REVERSE_OFFLOAD
| OMP_REQUIRES_TARGET_USED));
/* (Mis)use LTO_symtab_edge for this variable. */
if (requires_mask & GOMP_REQUIRES_UNIFIED_SHARED_MEMORY)
p += snprintf (p, end - p, "%sunified_shared_memory",
(p == buf ? "" : ", "));
+ if (requires_mask & GOMP_REQUIRES_SELF_MAPS)
+ p += snprintf (p, end - p, "%sself_maps",
+ (p == buf ? "" : ", "));
if (requires_mask & GOMP_REQUIRES_REVERSE_OFFLOAD)
p += snprintf (p, end - p, "%sreverse_offload",
(p == buf ? "" : ", "));
OMP_TRAIT_PROPERTY_NONE, true,
NULL
},
+ { "self_maps",
+ (1 << OMP_TRAIT_SET_IMPLEMENTATION),
+ OMP_TRAIT_PROPERTY_NONE, true,
+ NULL
+ },
{ "dynamic_allocators",
(1 << OMP_TRAIT_SET_IMPLEMENTATION),
OMP_TRAIT_PROPERTY_NONE, true,
}
}
break;
+ case OMP_TRAIT_IMPLEMENTATION_SELF_MAPS:
+ if (set == OMP_TRAIT_SET_IMPLEMENTATION)
+ {
+ if (cfun && (cfun->curr_properties & PROP_gimple_any) != 0)
+ break;
+
+ if ((omp_requires_mask
+ & OMP_REQUIRES_SELF_MAPS) == 0)
+ {
+ if (symtab->state == PARSING)
+ ret = -1;
+ else
+ return 0;
+ }
+ }
+ break;
case OMP_TRAIT_IMPLEMENTATION_DYNAMIC_ALLOCATORS:
if (set == OMP_TRAIT_SET_IMPLEMENTATION)
{
OMP_REQUIRES_REVERSE_OFFLOAD = GOMP_REQUIRES_REVERSE_OFFLOAD,
OMP_REQUIRES_ATOMIC_DEFAULT_MEM_ORDER_USED = 0x100,
OMP_REQUIRES_TARGET_USED = GOMP_REQUIRES_TARGET_USED,
+ OMP_REQUIRES_SELF_MAPS = GOMP_REQUIRES_SELF_MAPS
};
extern GTY(()) enum omp_requires omp_requires_mask;
OMP_TRAIT_IMPLEMENTATION_REQUIRES,
OMP_TRAIT_IMPLEMENTATION_UNIFIED_ADDRESS,
OMP_TRAIT_IMPLEMENTATION_UNIFIED_SHARED_MEMORY,
+ OMP_TRAIT_IMPLEMENTATION_SELF_MAPS,
OMP_TRAIT_IMPLEMENTATION_DYNAMIC_ALLOCATORS,
OMP_TRAIT_IMPLEMENTATION_REVERSE_OFFLOAD,
OMP_TRAIT_USER_CONDITION,
int foo (int, int, int *);
int bar (int, int, int *);
+int foobar (int, int, int *);
#pragma omp declare variant (foo) \
match (construct={parallel,for},\
device={isa(avx512f,avx512vl),kind(host,cpu)},\
implementation={vendor(score(0):gnu),unified_shared_memory},\
user={condition(score(0):0)})
+#pragma omp declare variant (foo) \
+ match (construct={parallel,for},\
+ device={isa(avx512f,avx512vl),kind(host,cpu)},\
+ implementation={vendor(score(0):gnu),self_maps},\
+ user={condition(score(0):0)})
#pragma omp declare variant (bar) \
match (device={arch(x86_64,powerpc64),isa(avx512f,popcntb)}, \
implementation={atomic_default_mem_order(seq_cst),made_up_selector("foo", 13, "bar")}, \
#pragma omp requires unified_shared_memory,unified_shared_memory /* { dg-error "too many 'unified_shared_memory' clauses" } */
#pragma omp requires unified_address unified_address /* { dg-error "too many 'unified_address' clauses" } */
#pragma omp requires reverse_offload reverse_offload /* { dg-error "too many 'reverse_offload' clauses" } */
-#pragma omp requires foobarbaz /* { dg-error "expected 'unified_address', 'unified_shared_memory', 'dynamic_allocators', 'reverse_offload' or 'atomic_default_mem_order' clause" } */
+#pragma omp requires foobarbaz /* { dg-error "expected 'unified_address', 'unified_shared_memory', 'self_maps', 'dynamic_allocators', 'reverse_offload' or 'atomic_default_mem_order' clause" } */
#pragma omp requires dynamic_allocators , dynamic_allocators /* { dg-error "too many 'dynamic_allocators' clauses" } */
#pragma omp requires atomic_default_mem_order(seq_cst) atomic_default_mem_order(seq_cst) /* { dg-error "too many 'atomic_default_mem_order' clauses" } */
#pragma omp requires atomic_default_mem_order (seq_cst) /* { dg-error "more than one 'atomic_default_mem_order' clause in a single compilation unit" } */
#pragma omp requires unified_shared_memory /* { dg-error "'unified_shared_memory' clause used lexically after first target construct or offloading API" } */
#pragma omp requires unified_address /* { dg-error "'unified_address' clause used lexically after first target construct or offloading API" } */
#pragma omp requires reverse_offload /* { dg-error "'reverse_offload' clause used lexically after first target construct or offloading API" } */
+#pragma omp requires self_maps /* { dg-error "'self_maps' clause used lexically after first target construct or offloading API" } */
subroutine f45 ()
!$omp declare variant (f13) match (implementation={unified_shared_memory})
end subroutine
+ subroutine f45a ()
+ !$omp declare variant (f13) match (implementation={self_maps})
+ end subroutine
subroutine f46 ()
!$omp declare variant (f13) match (implementation={unified_address})
end subroutine
!$omp requires unified_shared_memory,unified_shared_memory ! { dg-error "specified more than once" }
!$omp requires unified_address unified_address ! { dg-error "specified more than once" }
!$omp requires reverse_offload reverse_offload ! { dg-error "specified more than once" }
-!$omp requires foobarbaz ! { dg-error "Expected UNIFIED_ADDRESS, UNIFIED_SHARED_MEMORY, DYNAMIC_ALLOCATORS, REVERSE_OFFLOAD, or ATOMIC_DEFAULT_MEM_ORDER clause" }
+!$omp requires foobarbaz ! { dg-error "Expected UNIFIED_ADDRESS, UNIFIED_SHARED_MEMORY, SELF_MAPS, DYNAMIC_ALLOCATORS, REVERSE_OFFLOAD, or ATOMIC_DEFAULT_MEM_ORDER clause" }
!$omp requires dynamic_allocators , dynamic_allocators ! { dg-error "specified more than once" }
!$omp requires atomic_default_mem_order(seq_cst) atomic_default_mem_order(seq_cst) ! { dg-error "specified more than once" }
!$omp requires atomic_default_mem_order (seq_cst)
--- /dev/null
+! { dg-do compile { target skip-all-targets } }
+
+! used by requires-self-maps.f90
+
+module m2
+ implicit none
+contains
+ integer function g()
+ !$omp target map(from:g)
+ g = 99
+ !$omp end target
+ end
+end
+
+program main
+ use m
+ use m2
+end
--- /dev/null
+! { dg-do link }
+! { dg-additional-sources "requires-self-maps-aux.f90" }
+
+module m
+ !$omp requires self_maps
+ implicit none
+contains
+ integer function f()
+ !$omp target map(from:f)
+ f = 42
+ !$omp end target
+ end
+end
+
+! This shows up in line 5 of requires-self-maps-aux.f90, but adding dg-error there is ignored when
+! invoked as additional files – but this file needs to come first in order to create the .mod file:
+! { dg-error "Program unit at .1. has OpenMP device constructs/routines but does not set !.OMP REQUIRES SELF_MAPS but other program units do" "" { target *-*-* } 0 }
#define GOMP_DEPEND_INOUTSET 5
/* Flag values for OpenMP 'requires' directive features. */
+// compiler use only: OMP_REQUIRES_ATOMIC_DEFAULT_MEM_ORDER 0xf
#define GOMP_REQUIRES_UNIFIED_ADDRESS 0x10
#define GOMP_REQUIRES_UNIFIED_SHARED_MEMORY 0x20
+// compiler use only: OMP_REQUIRES_DYNAMIC_ALLOCATORS 0x40
#define GOMP_REQUIRES_REVERSE_OFFLOAD 0x80
+// compiler use only: OMP_REQUIRES_ATOMIC_DEFAULT_MEM_ORDER_USED 0x100
#define GOMP_REQUIRES_TARGET_USED 0x200
+#define GOMP_REQUIRES_SELF_MAPS 0x400
/* Interop foreign-runtime data. */
#define GOMP_INTEROP_IFR_LAST 7
@item Scope requirement changes for @code{declare_target} @tab N @tab
@item @code{message} and @code{severity} clauses to @code{parallel} directive
@tab N @tab
-@item @code{self_maps} clause to @code{requires} directive @tab N @tab
+@item @code{self_maps} clause to @code{requires} directive @tab Y @tab
@item @code{no_openmp_constructs} assumptions clause @tab N @tab
@item Restriction for @code{ordered} regarding loop-transforming directives
@tab N @tab
&& ((omp_requires_mask
& ~(GOMP_REQUIRES_UNIFIED_ADDRESS
| GOMP_REQUIRES_UNIFIED_SHARED_MEMORY
+ | GOMP_REQUIRES_SELF_MAPS
| GOMP_REQUIRES_REVERSE_OFFLOAD)) != 0))
return -1;
/* Check whether host page access is supported; this is per system level
(all GPUs supported by HSA). While intrinsically true for APUs, it
requires XNACK support for discrete GPUs. */
if (hsa_context.agent_count > 0
- && (omp_requires_mask & GOMP_REQUIRES_UNIFIED_SHARED_MEMORY))
+ && (omp_requires_mask
+ & (GOMP_REQUIRES_UNIFIED_SHARED_MEMORY | GOMP_REQUIRES_SELF_MAPS)))
{
bool b;
hsa_system_info_t type = HSA_AMD_SYSTEM_INFO_SVM_ACCESSIBLE_BY_DEFAULT;
if (num_devices > 0
&& ((omp_requires_mask
& ~(GOMP_REQUIRES_UNIFIED_ADDRESS
+ | GOMP_REQUIRES_SELF_MAPS
| GOMP_REQUIRES_UNIFIED_SHARED_MEMORY
| GOMP_REQUIRES_REVERSE_OFFLOAD)) != 0))
return -1;
if so, enable USM. Currently, capabilities is per device type, hence,
check all devices. */
if (num_devices > 0
- && (omp_requires_mask & GOMP_REQUIRES_UNIFIED_SHARED_MEMORY))
+ && (omp_requires_mask
+ & (GOMP_REQUIRES_UNIFIED_SHARED_MEMORY | GOMP_REQUIRES_SELF_MAPS)))
for (int dev = 0; dev < num_devices; dev++)
{
int pi;
if (requires_mask & GOMP_REQUIRES_UNIFIED_SHARED_MEMORY)
p += snprintf (p, end - p, "%sunified_shared_memory",
(p == buf ? "" : ", "));
+ if (requires_mask & GOMP_REQUIRES_SELF_MAPS)
+ p += snprintf (p, end - p, "%sself_maps",
+ (p == buf ? "" : ", "));
if (requires_mask & GOMP_REQUIRES_REVERSE_OFFLOAD)
p += snprintf (p, end - p, "%sreverse_offload",
(p == buf ? "" : ", "));
if (omp_req && omp_requires_mask && omp_requires_mask != omp_req)
{
char buf1[sizeof ("unified_address, unified_shared_memory, "
- "reverse_offload")];
+ "self_maps, reverse_offload")];
char buf2[sizeof ("unified_address, unified_shared_memory, "
- "reverse_offload")];
+ "self_maps, reverse_offload")];
gomp_requires_to_name (buf2, sizeof (buf2),
omp_req != GOMP_REQUIRES_TARGET_USED
? omp_req : omp_requires_mask);
/* If USM has been requested and is supported by all devices
of this type, set the capability accordingly. */
- if (omp_requires_mask & GOMP_REQUIRES_UNIFIED_SHARED_MEMORY)
+ if (omp_requires_mask
+ & (GOMP_REQUIRES_UNIFIED_SHARED_MEMORY | GOMP_REQUIRES_SELF_MAPS))
current_device.capabilities |= GOMP_OFFLOAD_CAP_SHARED_MEM;
devs = realloc (devs, (num_devs + new_num_devs)
--- /dev/null
+! Basic test whether self_maps work
+
+module m
+ !$omp requires self_maps
+ implicit none (type, external)
+ type t
+ integer :: val
+ type(t), pointer :: next
+ end type t
+contains
+ subroutine init(p)
+ integer :: i
+ type(t), pointer :: p, x
+ allocate(x)
+ p => x
+ do i = 1, 5
+ x%val = i
+ if (i < 5) then
+ allocate(x%next)
+ x => x%next
+ end if
+ end do
+ end subroutine
+
+ subroutine check(p)
+ !$omp declare target enter(check)
+ integer :: i
+ type(t), pointer :: p, x
+ x => p
+ do i = 1, 5
+ if (x%val /= i) stop 1
+ x => x%next
+ end do
+end subroutine
+end module
+
+use omp_lib
+use m
+implicit none (type, external)
+type(t), pointer :: linked
+integer :: i
+
+call init(linked)
+do i = 0, omp_get_num_devices()
+ !$omp target device(i)
+ call check(linked)
+ !$omp end target
+end do
+end