[Libomptarget] Implement a unified kernel entry function

This patch implements a unified kernel entry function that will be
targeted from both teams and non-teams clauses. We introduce a new
interface and make the old functions call in using the new one. A
following patch will include the necessary changes to Clang to call
these new functions instead.

Reviewed By: jdoerfert

Differential Revision: https://reviews.llvm.org/D128549
This commit is contained in:
Joseph Huber 2022-06-23 14:57:59 -04:00
parent 46e984b0bf
commit ad23e4d85f
3 changed files with 76 additions and 53 deletions

View File

@ -109,6 +109,18 @@ enum TargetAllocTy : int32_t {
TARGET_ALLOC_DEFAULT
};
/// This struct contains all of the arguments to a target kernel region launch.
struct __tgt_kernel_arguments {
int32_t Version; // Version of this struct for ABI compatibility.
int32_t NumArgs; // Number of arguments in each input pointer.
void **ArgBasePtrs; // Base pointer of each argument (e.g. a struct).
void **ArgPtrs; // Pointer to the argument data.
int64_t *ArgSizes; // Size of the argument data in bytes.
int64_t *ArgTypes; // Type of the data (e.g. to / from).
void **ArgNames; // Name of the data for debugging, possibly null.
void **ArgMappers; // User-defined mappers, possible null.
};
/// This struct is a record of an entry point or global. For a function
/// entry point the size is expected to be zero
struct __tgt_offload_entry {
@ -345,11 +357,19 @@ int __tgt_target_teams_mapper(ident_t *Loc, int64_t DeviceId, void *HostPtr,
map_var_info_t *ArgNames, void **ArgMappers,
int32_t NumTeams, int32_t ThreadLimit);
int __tgt_target_teams_nowait_mapper(
ident_t *Loc, int64_t DeviceId, void *HostPtr, int32_t ArgNum,
void **ArgsBase, void **Args, int64_t *ArgSizes, int64_t *ArgTypes,
map_var_info_t *ArgNames, void **ArgMappers, int32_t NumTeams,
int32_t ThreadLimit, int32_t DepNum, void *DepList, int32_t NoAliasDepNum,
void *NoAliasDepList);
ident_t *loc, int64_t device_id, void *host_ptr, int32_t arg_num,
void **args_base, void **args, int64_t *arg_sizes, int64_t *arg_types,
map_var_info_t *arg_names, void **arg_mappers, int32_t num_teams,
int32_t thread_limit, int32_t depNum, void *depList, int32_t noAliasDepNum,
void *noAliasDepList);
int __tgt_target_kernel(ident_t *Loc, int64_t DeviceId, int32_t NumTeams,
int32_t ThreadLimit, void *HostPtr,
__tgt_kernel_arguments *Args);
int __tgt_target_kernel_nowait(ident_t *Loc, int64_t DeviceId, int32_t NumTeams,
int32_t ThreadLimit, void *HostPtr,
__tgt_kernel_arguments *Args, int32_t DepNum,
void *DepList, int32_t NoAliasDepNum,
void *NoAliasDepList);
void __kmpc_push_target_tripcount(int64_t DeviceId, uint64_t LoopTripcount);

View File

@ -24,6 +24,8 @@ VERS1.0 {
__tgt_target_data_update_nowait_mapper;
__tgt_target_nowait_mapper;
__tgt_target_teams_nowait_mapper;
__tgt_target_kernel;
__tgt_target_kernel_nowait;
__tgt_mapper_num_components;
__tgt_push_mapper_component;
__kmpc_push_target_tripcount;

View File

@ -278,36 +278,9 @@ EXTERN int __tgt_target_mapper(ident_t *Loc, int64_t DeviceId, void *HostPtr,
int64_t *ArgSizes, int64_t *ArgTypes,
map_var_info_t *ArgNames, void **ArgMappers) {
TIMESCOPE_WITH_IDENT(Loc);
DP("Entering target region with entry point " DPxMOD " and device Id %" PRId64
"\n",
DPxPTR(HostPtr), DeviceId);
if (checkDeviceAndCtors(DeviceId, Loc)) {
DP("Not offloading to device %" PRId64 "\n", DeviceId);
return OMP_TGT_FAIL;
}
if (getInfoLevel() & OMP_INFOTYPE_KERNEL_ARGS)
printKernelArguments(Loc, DeviceId, ArgNum, ArgSizes, ArgTypes, ArgNames,
"Entering OpenMP kernel");
#ifdef OMPTARGET_DEBUG
for (int I = 0; I < ArgNum; ++I) {
DP("Entry %2d: Base=" DPxMOD ", Begin=" DPxMOD ", Size=%" PRId64
", Type=0x%" PRIx64 ", Name=%s\n",
I, DPxPTR(ArgsBase[I]), DPxPTR(Args[I]), ArgSizes[I], ArgTypes[I],
(ArgNames) ? getNameFromMapping(ArgNames[I]).c_str() : "unknown");
}
#endif
DeviceTy &Device = *PM->Devices[DeviceId];
AsyncInfoTy AsyncInfo(Device);
int Rc =
target(Loc, Device, HostPtr, ArgNum, ArgsBase, Args, ArgSizes, ArgTypes,
ArgNames, ArgMappers, 0, 0, false /*team*/, AsyncInfo);
if (Rc == OFFLOAD_SUCCESS)
Rc = AsyncInfo.synchronize();
handleTargetOutcome(Rc == OFFLOAD_SUCCESS, Loc);
assert(Rc == OFFLOAD_SUCCESS && "__tgt_target_mapper unexpected failure!");
return OMP_TGT_SUCCESS;
__tgt_kernel_arguments KernelArgs{1, ArgNum, ArgsBase, Args,
ArgSizes, ArgTypes, ArgNames, ArgMappers};
return __tgt_target_kernel(Loc, DeviceId, -1, 0, HostPtr, &KernelArgs);
}
EXTERN int __tgt_target_nowait_mapper(
@ -352,50 +325,78 @@ EXTERN int __tgt_target_teams_mapper(ident_t *Loc, int64_t DeviceId,
map_var_info_t *ArgNames,
void **ArgMappers, int32_t TeamNum,
int32_t ThreadLimit) {
TIMESCOPE_WITH_IDENT(Loc);
__tgt_kernel_arguments KernelArgs{1, ArgNum, ArgsBase, Args,
ArgSizes, ArgTypes, ArgNames, ArgMappers};
return __tgt_target_kernel(Loc, DeviceId, TeamNum, ThreadLimit, HostPtr,
&KernelArgs);
}
/// Implements a kernel entry that executes the target region on the specified
/// device.
///
/// \param Loc Source location associated with this target region.
/// \param DeviceId The device to execute this region, -1 indicated the default.
/// \param NumTeams Number of teams to launch the region with, -1 indicates a
/// non-teams region and 0 indicates it was unspecified.
/// \param ThreadLimit Limit to the number of threads to use in the kernel
/// launch, 0 indicates it was unspecified.
/// \param HostPtr The pointer to the host function registered with the kernel.
/// \param Args All arguments to this kernel launch (see struct definition).
EXTERN int __tgt_target_kernel(ident_t *Loc, int64_t DeviceId, int32_t NumTeams,
int32_t ThreadLimit, void *HostPtr,
__tgt_kernel_arguments *Args) {
TIMESCOPE_WITH_IDENT(Loc);
DP("Entering target region with entry point " DPxMOD " and device Id %" PRId64
"\n",
DPxPTR(HostPtr), DeviceId);
if (Args->Version != 1) {
DP("Unexpected ABI version: %d\n", Args->Version);
}
if (checkDeviceAndCtors(DeviceId, Loc)) {
DP("Not offloading to device %" PRId64 "\n", DeviceId);
return OMP_TGT_FAIL;
}
if (getInfoLevel() & OMP_INFOTYPE_KERNEL_ARGS)
printKernelArguments(Loc, DeviceId, ArgNum, ArgSizes, ArgTypes, ArgNames,
printKernelArguments(Loc, DeviceId, Args->NumArgs, Args->ArgSizes,
Args->ArgTypes, Args->ArgNames,
"Entering OpenMP kernel");
#ifdef OMPTARGET_DEBUG
for (int I = 0; I < ArgNum; ++I) {
for (int I = 0; I < Args->NumArgs; ++I) {
DP("Entry %2d: Base=" DPxMOD ", Begin=" DPxMOD ", Size=%" PRId64
", Type=0x%" PRIx64 ", Name=%s\n",
I, DPxPTR(ArgsBase[I]), DPxPTR(Args[I]), ArgSizes[I], ArgTypes[I],
(ArgNames) ? getNameFromMapping(ArgNames[I]).c_str() : "unknown");
I, DPxPTR(Args->ArgBasePtrs[I]), DPxPTR(Args->ArgPtrs[I]),
Args->ArgSizes[I], Args->ArgTypes[I],
(Args->ArgNames) ? getNameFromMapping(Args->ArgNames[I]).c_str()
: "unknown");
}
#endif
bool IsTeams = NumTeams != -1;
if (!IsTeams)
NumTeams = 0;
DeviceTy &Device = *PM->Devices[DeviceId];
AsyncInfoTy AsyncInfo(Device);
int Rc = target(Loc, Device, HostPtr, ArgNum, ArgsBase, Args, ArgSizes,
ArgTypes, ArgNames, ArgMappers, TeamNum, ThreadLimit,
true /*team*/, AsyncInfo);
int Rc = target(Loc, Device, HostPtr, Args->NumArgs, Args->ArgBasePtrs,
Args->ArgPtrs, Args->ArgSizes, Args->ArgTypes, Args->ArgNames,
Args->ArgMappers, NumTeams, ThreadLimit, IsTeams, AsyncInfo);
if (Rc == OFFLOAD_SUCCESS)
Rc = AsyncInfo.synchronize();
handleTargetOutcome(Rc == OFFLOAD_SUCCESS, Loc);
assert(Rc == OFFLOAD_SUCCESS &&
"__tgt_target_teams_mapper unexpected failure!");
assert(Rc == OFFLOAD_SUCCESS && "__tgt_target_kernel unexpected failure!");
return OMP_TGT_SUCCESS;
}
EXTERN int __tgt_target_teams_nowait_mapper(
ident_t *Loc, int64_t DeviceId, void *HostPtr, int32_t ArgNum,
void **ArgsBase, void **Args, int64_t *ArgSizes, int64_t *ArgTypes,
map_var_info_t *ArgNames, void **ArgMappers, int32_t TeamNum,
int32_t ThreadLimit, int32_t DepNum, void *DepList, int32_t NoAliasDepNum,
void *NoAliasDepList) {
EXTERN int __tgt_target_kernel_nowait(
ident_t *Loc, int64_t DeviceId, int32_t NumTeams, int32_t ThreadLimit,
void *HostPtr, __tgt_kernel_arguments *Args, int32_t DepNum, void *DepList,
int32_t NoAliasDepNum, void *NoAliasDepList) {
TIMESCOPE_WITH_IDENT(Loc);
return __tgt_target_teams_mapper(Loc, DeviceId, HostPtr, ArgNum, ArgsBase,
Args, ArgSizes, ArgTypes, ArgNames,
ArgMappers, TeamNum, ThreadLimit);
return __tgt_target_kernel(Loc, DeviceId, NumTeams, ThreadLimit, HostPtr,
Args);
}
// Get the current number of components for a user-defined mapper.