Home
last modified time | relevance | path

Searched refs:GetDeviceDescription (Results 1 – 25 of 34) sorted by relevance

12

/external/tensorflow/tensorflow/compiler/xla/service/gpu/tests/
Dreduction_vectorization_test.cc57 executor->GetDeviceDescription().cuda_compute_capability(&cc_major, in TEST_F()
105 executor->GetDeviceDescription().cuda_compute_capability(&cc_major, in TEST_F()
153 executor->GetDeviceDescription().cuda_compute_capability(&cc_major, in TEST_F()
237 executor->GetDeviceDescription().cuda_compute_capability(&cc_major, in TEST_F()
340 backend().default_stream_executor()->GetDeviceDescription(); in TEST_F()
Dgpu_atomic_test.cc113 backend().default_stream_executor()->GetDeviceDescription(); in TEST_F()
Dmlir_gpu_test_base.cc59 stream_exec->GetDeviceDescription().cuda_compute_capability( in CompileMlirModule()
/external/tensorflow/tensorflow/stream_executor/rocm/
Drocm_platform.cc51 min_numa_node_ = exec->GetDeviceDescription().numa_node(); in InspectNumaNodes()
55 std::min(min_numa_node_, exec->GetDeviceDescription().numa_node()); in InspectNumaNodes()
57 limit_numa_node_, exec->GetDeviceDescription().numa_node() + 1); in InspectNumaNodes()
72 return exec->GetDeviceDescription().numa_node() - min_numa_node_; in DeviceToBus()
/external/tensorflow/tensorflow/compiler/xla/service/gpu/
Damdgpu_compiler.cc97 if (!stream_exec->GetDeviceDescription().rocm_amdgpu_isa_version( in GetGpuVersion()
104 stream_exec->GetDeviceDescription().rocm_amdgpu_gcn_arch_name(); in GetGpuVersion()
105 if (gcn_arch_name == stream_exec->GetDeviceDescription().kUndefinedString) { in GetGpuVersion()
Dbuffer_comparator.cc610 executor->GetDeviceDescription().threads_per_block_limit(); in DeviceCompare()
612 executor->GetDeviceDescription().threads_per_warp(); in DeviceCompare()
614 executor->GetDeviceDescription().shared_memory_per_block(); in DeviceCompare()
616 executor->GetDeviceDescription().threads_per_core_limit(); in DeviceCompare()
617 gpu_device_info.core_count = executor->GetDeviceDescription().core_count(); in DeviceCompare()
Dgpu_compiler.cc872 stream_exec->GetDeviceDescription().cuda_compute_capability( in RunBackend()
886 stream_exec->GetDeviceDescription().memory_bandwidth()); in RunBackend()
966 stream_exec->GetDeviceDescription().threads_per_block_limit(); in GetGpuDeviceInfo()
968 stream_exec->GetDeviceDescription().threads_per_warp(); in GetGpuDeviceInfo()
970 stream_exec->GetDeviceDescription().shared_memory_per_block(); in GetGpuDeviceInfo()
972 stream_exec->GetDeviceDescription().threads_per_core_limit(); in GetGpuDeviceInfo()
973 gpu_device_info.core_count = stream_exec->GetDeviceDescription().core_count(); in GetGpuDeviceInfo()
Dhlo_execution_profiler.cc62 clock_rate_ghz_ = stream->parent()->GetDeviceDescription().clock_rate_ghz(); in HloExecutionProfiler()
Dgpu_conv_algorithm_picker.cc182 stream_executor->GetDeviceDescription().cuda_compute_capability(&cc_major, in GetComputeCapability()
191 const auto& desc = se->GetDeviceDescription(); in PrintPlatformInfo()
596 stream_exec_->GetDeviceDescription().pci_bus_id()); in PickBestAlgorithmNoCacheCuda()
Dgpu_executable.cc102 main_stream->parent()->GetDeviceDescription().rocm_amdgpu_isa_version( in CheckCompatibilityWithServiceExecutableRunOptions()
111 main_stream->parent()->GetDeviceDescription().cuda_compute_capability( in CheckCompatibilityWithServiceExecutableRunOptions()
Dnvptx_compiler.cc289 if (!stream_exec->GetDeviceDescription().cuda_compute_capability(&cc_major, in GetGpuVersion()
Dstream_executor_util.cc43 CHECK(stream_executor.GetDeviceDescription().cuda_compute_capability(&major, in IsVoltaOrLater()
/external/tensorflow/tensorflow/stream_executor/cuda/
Dcuda_platform.cc89 min_numa_node_ = exec->GetDeviceDescription().numa_node(); in InspectNumaNodes()
93 std::min(min_numa_node_, exec->GetDeviceDescription().numa_node()); in InspectNumaNodes()
95 limit_numa_node_, exec->GetDeviceDescription().numa_node() + 1); in InspectNumaNodes()
110 return exec->GetDeviceDescription().numa_node() - min_numa_node_; in DeviceToBus()
/external/tensorflow/tensorflow/core/kernels/
Dgpu_utils.cc117 stream_executor->GetDeviceDescription().cuda_compute_capability(&cc_major, in GetComputeCapability()
154 log.set_device_pci_bus_id(stream_exec->GetDeviceDescription().pci_bus_id()); in LogConvAutotuneResults()
201 log.set_device_pci_bus_id(stream_exec->GetDeviceDescription().pci_bus_id()); in LogFusedConvForwardAutotuneResults()
Dconv_ops_gpu.h37 .GetDeviceDescription() in IsVoltaOrLater()
/external/tensorflow/tensorflow/compiler/xla/service/
Dbackend.cc193 return (executor_a->GetDeviceDescription().name() == in devices_equivalent()
194 executor_b->GetDeviceDescription().name()); in devices_equivalent()
Dhlo_execution_profile_test.cc69 ->GetDeviceDescription() in TEST_F()
Dplatform_util.cc131 const auto& description = executor->GetDeviceDescription(); in IsDeviceSupported()
Dexecutable.cc268 &stream->parent()->GetDeviceDescription(); in ExecuteWrapperAfterExecution()
/external/tensorflow/tensorflow/stream_executor/
Dstream_executor_pimpl.cc234 const DeviceDescription &StreamExecutor::GetDeviceDescription() const { in GetDeviceDescription() function in stream_executor::StreamExecutor
272 GetDeviceDescription().cuda_compute_capability(&cc_major, &cc_minor); in GetConvolveAlgorithms()
313 GetDeviceDescription().cuda_compute_capability(&cc_major, &cc_minor); in GetConvolveBackwardDataAlgorithms()
326 GetDeviceDescription().cuda_compute_capability(&cc_major, &cc_minor); in GetConvolveBackwardFilterAlgorithms()
/external/tensorflow/tensorflow/compiler/xla/client/
Dlocal_client.cc99 build_executor->GetDeviceDescription().name(), in ValidateExecutionOptions()
101 run_executor->GetDeviceDescription().name()); in ValidateExecutionOptions()
/external/tensorflow/tensorflow/stream_executor/gpu/
Dredzone_allocator.cc224 executor->GetDeviceDescription().threads_per_block_limit(), num_elements); in RunRedzoneChecker()
/external/tensorflow/tensorflow/core/common_runtime/gpu/
Dgpu_process_state.cc76 int numa_node = se->GetDeviceDescription().numa_node(); in BusIdForGPU()
/external/tensorflow/tensorflow/compiler/xla/pjrt/
Dgpu_device.cc235 local_device->executor()->GetDeviceDescription(); in BuildLocalDevices()
/external/tensorflow/tensorflow/compiler/xla/tests/
Dxla_hlo_profile_test.cc185 executor->GetDeviceDescription().clock_rate_ghz()); in ExecuteAndFetchProfile()

12