ec8f4a38c8
This introduces a remote offloading plugin for libomptarget. This implementation relies on gRPC and protobuf, so this library will only build if both libraries are available on the system. The corresponding server is compiled to `openmp-offloading-server`. This is a large change, but the only way to split this up is into RTL/server but I fear that could introduce an inconsistency amongst them. Ideally, tests for this should be added to the current ones that but that is problematic for at least one reason. Given that libomptarget registers plugin on a first-come-first-serve basis, if we wanted to offload onto a local x86 through a different process, then we'd have to either re-order the plugin list in `rtl.cpp` (which is what I did locally for testing) or find a better solution for runtime plugin registration in libomptarget. Differential Revision: https://reviews.llvm.org/D95314
165 lines
3.3 KiB
Protocol Buffer
165 lines
3.3 KiB
Protocol Buffer
syntax = "proto3";
|
|
|
|
package openmp.libomptarget.remote;
|
|
option cc_enable_arenas = true;
|
|
|
|
service RemoteOffload {
|
|
rpc Shutdown(Null) returns (I32) {}
|
|
|
|
rpc RegisterLib(TargetBinaryDescription) returns (I32) {}
|
|
rpc UnregisterLib(Pointer) returns (I32) {}
|
|
|
|
rpc IsValidBinary(TargetDeviceImagePtr) returns (I32) {}
|
|
rpc GetNumberOfDevices(Null) returns (I32) {}
|
|
|
|
rpc InitDevice(I32) returns (I32) {}
|
|
rpc InitRequires(I64) returns (I32) {}
|
|
|
|
rpc LoadBinary(Binary) returns (TargetTable) {}
|
|
rpc Synchronize(SynchronizeDevice) returns (I32) {}
|
|
|
|
rpc DataAlloc(AllocData) returns (Pointer) {}
|
|
rpc DataDelete(DeleteData) returns (I32) {}
|
|
|
|
rpc DataSubmitAsync(stream SubmitDataAsync) returns (I32) {}
|
|
rpc DataRetrieveAsync(RetrieveDataAsync) returns (stream Data) {}
|
|
|
|
rpc IsDataExchangeable(DevicePair) returns (I32) {}
|
|
rpc DataExchangeAsync(ExchangeDataAsync) returns (I32) {}
|
|
|
|
rpc RunTargetRegionAsync(TargetRegionAsync) returns (I32) {}
|
|
rpc RunTargetTeamRegionAsync(TargetTeamRegionAsync) returns (I32) {}
|
|
}
|
|
|
|
message Null {}
|
|
|
|
message Pointer { uint64 number = 1; }
|
|
|
|
message I32 { int32 number = 1; }
|
|
|
|
message I64 { int64 number = 1; }
|
|
|
|
message DevicePair {
|
|
int32 src_dev_id = 1;
|
|
int32 dst_dev_id = 2;
|
|
}
|
|
|
|
message Binary {
|
|
uint64 image_ptr = 1;
|
|
int32 device_id = 2;
|
|
}
|
|
|
|
message TargetOffloadEntry {
|
|
bytes data = 1;
|
|
string name = 2;
|
|
int32 flags = 3;
|
|
int32 reserved = 4;
|
|
}
|
|
|
|
message DeviceOffloadEntry {
|
|
string name = 1;
|
|
uint64 addr = 2;
|
|
int32 flags = 3;
|
|
int32 reserved = 4;
|
|
int32 size = 5;
|
|
}
|
|
|
|
message TargetTable {
|
|
repeated DeviceOffloadEntry entries = 1;
|
|
repeated uint64 entry_ptrs = 2;
|
|
}
|
|
|
|
message TargetDeviceImagePtr {
|
|
uint64 image_ptr = 1;
|
|
repeated uint64 entry_ptrs = 2;
|
|
}
|
|
|
|
message TargetDeviceImage {
|
|
bytes binary = 1;
|
|
repeated TargetOffloadEntry entries = 2;
|
|
}
|
|
|
|
message ImagePtrs {
|
|
uint64 img_ptr = 1;
|
|
repeated uint64 entry_ptrs = 2;
|
|
}
|
|
|
|
message TargetBinaryDescription {
|
|
repeated ImagePtrs image_ptrs = 1;
|
|
repeated TargetOffloadEntry entries = 2;
|
|
repeated TargetDeviceImage images = 3;
|
|
repeated uint64 entry_ptrs = 4;
|
|
uint64 bin_ptr = 5;
|
|
}
|
|
|
|
message SynchronizeDevice {
|
|
uint64 queue_ptr = 1;
|
|
int32 device_id = 2;
|
|
}
|
|
|
|
message AllocData {
|
|
uint64 size = 1;
|
|
uint64 hst_ptr = 2;
|
|
int32 device_id = 3;
|
|
}
|
|
|
|
message SubmitDataAsync {
|
|
bytes data = 1;
|
|
uint64 hst_ptr = 2;
|
|
uint64 tgt_ptr = 3;
|
|
uint64 queue_ptr = 4;
|
|
uint64 start = 5;
|
|
uint64 size = 6;
|
|
int32 device_id = 7;
|
|
}
|
|
|
|
message RetrieveDataAsync {
|
|
uint64 hst_ptr = 1;
|
|
uint64 tgt_ptr = 2;
|
|
uint64 size = 3;
|
|
uint64 queue_ptr = 4;
|
|
int32 device_id = 5;
|
|
}
|
|
|
|
message Data {
|
|
bytes data = 1;
|
|
uint64 start = 2;
|
|
uint64 size = 3;
|
|
int32 ret = 4;
|
|
}
|
|
|
|
message ExchangeDataAsync {
|
|
uint64 src_dev_id = 1;
|
|
uint64 src_ptr = 2;
|
|
uint64 dst_dev_id = 3;
|
|
uint64 dst_ptr = 4;
|
|
uint64 queue_ptr = 5;
|
|
uint64 size = 6;
|
|
}
|
|
|
|
message DeleteData {
|
|
uint64 tgt_ptr = 1;
|
|
int32 device_id = 2;
|
|
}
|
|
|
|
message TargetRegionAsync {
|
|
repeated uint64 tgt_args = 1;
|
|
repeated int64 tgt_offsets = 2;
|
|
uint64 tgt_entry_ptr = 3;
|
|
uint64 queue_ptr = 4;
|
|
int32 device_id = 5;
|
|
int32 arg_num = 6;
|
|
}
|
|
|
|
message TargetTeamRegionAsync {
|
|
repeated uint64 tgt_args = 1;
|
|
repeated int64 tgt_offsets = 2;
|
|
uint64 tgt_entry_ptr = 3;
|
|
uint64 loop_tripcount = 4;
|
|
uint64 queue_ptr = 5;
|
|
int32 device_id = 6;
|
|
int32 arg_num = 7;
|
|
int32 team_num = 8;
|
|
int32 thread_limit = 9;
|
|
}
|