diff options
Diffstat (limited to 'offload/plugins-nextgen')
7 files changed, 63 insertions, 4 deletions
diff --git a/offload/plugins-nextgen/amdgpu/dynamic_hsa/hsa_ext_amd.h b/offload/plugins-nextgen/amdgpu/dynamic_hsa/hsa_ext_amd.h index 29cfe78082db..ddfa65c76cf2 100644 --- a/offload/plugins-nextgen/amdgpu/dynamic_hsa/hsa_ext_amd.h +++ b/offload/plugins-nextgen/amdgpu/dynamic_hsa/hsa_ext_amd.h @@ -72,6 +72,7 @@ typedef enum hsa_amd_agent_info_s { HSA_AMD_AGENT_INFO_MAX_WAVES_PER_CU = 0xA00A, HSA_AMD_AGENT_INFO_NUM_SIMDS_PER_CU = 0xA00B, HSA_AMD_AGENT_INFO_COOPERATIVE_QUEUES = 0xA010, + HSA_AMD_AGENT_INFO_UUID = 0xA011, HSA_AMD_AGENT_INFO_TIMESTAMP_FREQUENCY = 0xA016, } hsa_amd_agent_info_t; diff --git a/offload/plugins-nextgen/amdgpu/src/rtl.cpp b/offload/plugins-nextgen/amdgpu/src/rtl.cpp index 0b03ef534d27..928c6cd7569e 100644 --- a/offload/plugins-nextgen/amdgpu/src/rtl.cpp +++ b/offload/plugins-nextgen/amdgpu/src/rtl.cpp @@ -2083,6 +2083,20 @@ struct AMDGPUDeviceTy : public GenericDeviceTy, AMDGenericDeviceTy { return Err; ComputeUnitKind = GPUName; + // From the ROCm HSA documentation: + // Query the UUID of the agent. The value is an Ascii string with a maximum + // of 21 chars including NUL. The string value consists of two parts: header + // and body. The header identifies the device type (GPU, CPU, DSP) while the + // body encodes the UUID as a 16 digit hex string. + // + // Agents that do not support UUID will return the string "GPU-XX" or + // "CPU-XX" or "DSP-XX" depending on their device type. + char UUID[24] = {0}; + if (auto Err = getDeviceAttr(HSA_AMD_AGENT_INFO_UUID, UUID)) + return Err; + if (!StringRef(UUID).ends_with("-XX")) + setDeviceUidFromVendorUid(UUID); + // Get the wavefront size. uint32_t WavefrontSize = 0; if (auto Err = getDeviceAttr(HSA_AGENT_INFO_WAVEFRONT_SIZE, WavefrontSize)) diff --git a/offload/plugins-nextgen/common/include/PluginInterface.h b/offload/plugins-nextgen/common/include/PluginInterface.h index f9bff9abd903..f9dcdea7213f 100644 --- a/offload/plugins-nextgen/common/include/PluginInterface.h +++ b/offload/plugins-nextgen/common/include/PluginInterface.h @@ -791,6 +791,9 @@ struct GenericDeviceTy : public DeviceAllocatorTy { /// this id is not unique between different plugins; they may overlap. int32_t getDeviceId() const { return DeviceId; } + /// Get the unique identifier of the device. + const char *getDeviceUid() const { return DeviceUid.c_str(); } + /// Set the context of the device if needed, before calling device-specific /// functions. Plugins may implement this function as a no-op if not needed. virtual Error setContext() = 0; @@ -989,9 +992,12 @@ struct GenericDeviceTy : public DeviceAllocatorTy { Error syncEvent(void *EventPtr); virtual Error syncEventImpl(void *EventPtr) = 0; + /// Obtain information about the device. + Expected<InfoTreeNode> obtainInfo(); + virtual Expected<InfoTreeNode> obtainInfoImpl() = 0; + /// Print information about the device. Error printInfo(); - virtual Expected<InfoTreeNode> obtainInfoImpl() = 0; /// Return true if the device has work that is either queued or currently /// running @@ -1204,6 +1210,14 @@ protected: /// global device id and is not the device id visible to the OpenMP user. const int32_t DeviceId; + /// The unique identifier of the device. + /// Per default, the unique identifier of the device is set to the device id, + /// combined with the plugin name, since the offload device id may overlap + /// between different plugins. + std::string DeviceUid; + /// Construct the device UID from the vendor (U)UID. + void setDeviceUidFromVendorUid(StringRef VendorUid); + /// The default grid values used for this device. llvm::omp::GV GridValues; @@ -1290,6 +1304,9 @@ struct GenericPluginTy { return UserDeviceIds.at(DeviceId); } + /// Get the UID for the host device. + static constexpr const char *getHostDeviceUid() { return "HOST"; } + /// Get the ELF code to recognize the binary image of this plugin. virtual uint16_t getMagicElfBits() const = 0; diff --git a/offload/plugins-nextgen/common/src/PluginInterface.cpp b/offload/plugins-nextgen/common/src/PluginInterface.cpp index 36d643b65922..d7e5a21600ab 100644 --- a/offload/plugins-nextgen/common/src/PluginInterface.cpp +++ b/offload/plugins-nextgen/common/src/PluginInterface.cpp @@ -715,6 +715,10 @@ GenericDeviceTy::GenericDeviceTy(GenericPluginTy &Plugin, int32_t DeviceId, DeviceId(DeviceId), GridValues(OMPGridValues), PeerAccesses(NumDevices, PeerAccessState::PENDING), PeerAccessesLock(), PinnedAllocs(*this), RPCServer(nullptr) { + // Conservative fall-back to the plugin's device uid for the case that no real + // vendor (u)uid will become available later. + setDeviceUidFromVendorUid(std::to_string(static_cast<uint64_t>(DeviceId))); + #ifdef OMPT_SUPPORT OmptInitialized.store(false); // Bind the callbacks to this device's member functions @@ -1524,15 +1528,22 @@ Error GenericDeviceTy::enqueueHostCall(void (*Callback)(void *), void *UserData, return Err; } +Expected<InfoTreeNode> GenericDeviceTy::obtainInfo() { + auto InfoOrErr = obtainInfoImpl(); + if (InfoOrErr) + InfoOrErr->add("UID", getDeviceUid(), "", DeviceInfo::UID); + return InfoOrErr; +} + Error GenericDeviceTy::printInfo() { - auto Info = obtainInfoImpl(); + auto InfoOrErr = obtainInfo(); // Get the vendor-specific info entries describing the device properties. - if (auto Err = Info.takeError()) + if (auto Err = InfoOrErr.takeError()) return Err; // Print all info entries. - Info->print(); + InfoOrErr->print(); return Plugin::success(); } @@ -1603,6 +1614,10 @@ Expected<bool> GenericDeviceTy::isAccessiblePtr(const void *Ptr, size_t Size) { return isAccessiblePtrImpl(Ptr, Size); } +void GenericDeviceTy::setDeviceUidFromVendorUid(StringRef VendorUid) { + DeviceUid = std::string(Plugin.getName()) + "-" + std::string(VendorUid); +} + Error GenericPluginTy::init() { if (Initialized) return Plugin::success(); diff --git a/offload/plugins-nextgen/cuda/dynamic_cuda/cuda.cpp b/offload/plugins-nextgen/cuda/dynamic_cuda/cuda.cpp index f5b2d074a47e..e7a1ca38b3c1 100644 --- a/offload/plugins-nextgen/cuda/dynamic_cuda/cuda.cpp +++ b/offload/plugins-nextgen/cuda/dynamic_cuda/cuda.cpp @@ -35,6 +35,7 @@ DLWRAP(cuFuncSetAttribute, 3) // Device info DLWRAP(cuDeviceGetName, 3) +DLWRAP(cuDeviceGetUuid, 2) DLWRAP(cuDeviceTotalMem, 2) DLWRAP(cuDriverGetVersion, 1) diff --git a/offload/plugins-nextgen/cuda/dynamic_cuda/cuda.h b/offload/plugins-nextgen/cuda/dynamic_cuda/cuda.h index dec4e33508c6..a470d6df1079 100644 --- a/offload/plugins-nextgen/cuda/dynamic_cuda/cuda.h +++ b/offload/plugins-nextgen/cuda/dynamic_cuda/cuda.h @@ -33,6 +33,9 @@ typedef struct CUfunc_st *CUfunction; typedef void (*CUhostFn)(void *userData); typedef struct CUstream_st *CUstream; typedef struct CUevent_st *CUevent; +typedef struct CUuuid_st { + char bytes[16]; +} CUuuid; #define CU_DEVICE_INVALID ((CUdevice)(-2)) @@ -301,6 +304,7 @@ CUresult cuFuncSetAttribute(CUfunction, CUfunction_attribute, int); // Device info CUresult cuDeviceGetName(char *, int, CUdevice); +CUresult cuDeviceGetUuid(CUuuid *, CUdevice); CUresult cuDeviceTotalMem(size_t *, CUdevice); CUresult cuDriverGetVersion(int *); diff --git a/offload/plugins-nextgen/cuda/src/rtl.cpp b/offload/plugins-nextgen/cuda/src/rtl.cpp index db94f7f2dd99..a9adcc397fb7 100644 --- a/offload/plugins-nextgen/cuda/src/rtl.cpp +++ b/offload/plugins-nextgen/cuda/src/rtl.cpp @@ -25,6 +25,7 @@ #include "PluginInterface.h" #include "Utils/ELF.h" +#include "llvm/ADT/StringExtras.h" #include "llvm/BinaryFormat/ELF.h" #include "llvm/Frontend/OpenMP/OMPConstants.h" #include "llvm/Frontend/OpenMP/OMPGridValues.h" @@ -293,6 +294,12 @@ struct CUDADeviceTy : public GenericDeviceTy { if (auto Err = Plugin::check(Res, "error in cuDeviceGet: %s")) return Err; + CUuuid UUID = {0}; + Res = cuDeviceGetUuid(&UUID, Device); + if (auto Err = Plugin::check(Res, "error in cuDeviceGetUuid: %s")) + return Err; + setDeviceUidFromVendorUid(toHex(UUID.bytes, true)); + // Query the current flags of the primary context and set its flags if // it is inactive. unsigned int FormerPrimaryCtxFlags = 0; |