| /external/tensorflow/tensorflow/compiler/xla/service/gpu/ |
| D | amdgpu_compiler.cc | 74 HloModule* hlo_module, se::StreamExecutor* stream_exec, in OptimizeHloConvolutionCanonicalization()
95 GpuVersion AMDGPUCompiler::GetGpuVersion(se::StreamExecutor* stream_exec) { in GetGpuVersion()
117 se::StreamExecutor* stream_exec, in CompileTargetBinary()
|
| D | nvptx_compiler.cc | 108 HloModule* hlo_module, se::StreamExecutor* stream_exec, in OptimizeHloConvolutionCanonicalization()
161 HloModule* hlo_module, se::StreamExecutor* stream_exec, in OptimizeHloPostLayoutAssignment()
287 GpuVersion NVPTXCompiler::GetGpuVersion(se::StreamExecutor* stream_exec) { in GetGpuVersion()
304 se::StreamExecutor* stream_exec, in CompileTargetBinary()
342 se::StreamExecutor* stream_exec, const string& ptx, int cc_major, in CompileGpuAsmOrGetCachedResult()
447 se::StreamExecutor* stream_exec, std::vector<std::vector<uint8>> modules) { in LinkModules()
|
| D | gemm_algorithm_picker.h | 32 GemmAlgorithmPicker(se::StreamExecutor* stream_exec, in GemmAlgorithmPicker()
|
| D | gpu_conv_algorithm_picker.h | 40 GpuConvAlgorithmPicker(se::StreamExecutor* stream_exec, in GpuConvAlgorithmPicker()
|
| D | gpu_compiler.cc | 150 HloModule* hlo_module, se::StreamExecutor* stream_exec, in OptimizeHloModule()
403 HloModule* hlo_module, se::StreamExecutor* stream_exec, in OptimizeHloPostLayoutAssignment()
490 std::unique_ptr<HloModule> module, se::StreamExecutor* stream_exec, in RunHloPasses()
678 se::StreamExecutor* stream_exec, in CompileToTargetBinary()
856 std::unique_ptr<HloModule> module, se::StreamExecutor* stream_exec, in RunBackend()
963 GpuDeviceInfo GetGpuDeviceInfo(se::StreamExecutor* stream_exec) { in GetGpuDeviceInfo()
1100 absl::string_view entry_function_name, se::StreamExecutor* stream_exec, in CompileLmhloToExecutable()
|
| D | gpu_compiler.h | 130 se::StreamExecutor* stream_exec, in LinkModules()
|
| D | stream_executor_util.cc | 177 tensorflow::mutex_lock LockGpu(const se::StreamExecutor* stream_exec) { in LockGpu()
196 absl::Span<const uint8> cubin_data, se::StreamExecutor* stream_exec) { in CreateKernel()
|
| D | gpu_conv_algorithm_picker.cc | 103 se::StreamExecutor* stream_exec) { in GetAlgorithms()
127 se::DeviceMemoryBase result_buffer, se::StreamExecutor* stream_exec, in GetMIOpenAlgorithms()
|
| /external/tensorflow/tensorflow/core/common_runtime/gpu/ |
| D | gpu_debug_allocator_test.cc | 49 auto stream_exec = ExecutorForPlatformGpuId(platform_gpu_id); in TEST() local
145 auto stream_exec = ExecutorForPlatformGpuId(platform_gpu_id); in TEST() local
187 auto stream_exec = ExecutorForPlatformGpuId(platform_gpu_id); in TEST() local
|
| /external/tensorflow/tensorflow/compiler/xla/ |
| D | device_util.h | 32 string DeviceIdentifier(se::StreamExecutor* stream_exec) { in DeviceIdentifier()
|
| /external/tensorflow/tensorflow/compiler/xla/service/interpreter/ |
| D | compiler.cc | 105 std::unique_ptr<HloModule> hlo_module, se::StreamExecutor* stream_exec, in RunBackend()
130 std::vector<std::vector<se::StreamExecutor*>> stream_exec, in Compile()
|
| /external/tensorflow/tensorflow/compiler/xla/tests/ |
| D | llvm_compiler_test.cc | 45 HloModule* hlo_module, se::StreamExecutor* stream_exec, in OptimizeHloConvolutionCanonicalization()
51 HloModule* hlo_module, se::StreamExecutor* stream_exec, in OptimizeHloPostLayoutAssignment()
62 GpuVersion gpu_version, se::StreamExecutor* stream_exec, bool relocatable, in CompileTargetBinary()
|
| /external/tensorflow/tensorflow/stream_executor/cuda/ |
| D | redzone_allocator_test.cc | 55 StreamExecutor* stream_exec = platform->ExecutorForDevice(0).ValueOrDie(); in TEST() local
130 StreamExecutor* stream_exec = platform->ExecutorForDevice(0).ValueOrDie(); in TEST() local
|
| /external/tensorflow/tensorflow/stream_executor/ |
| D | event.cc | 24 Event::Event(StreamExecutor* stream_exec) in Event()
|
| D | stream_executor_pimpl.cc | 75 ScopedTracer(StreamExecutor *stream_exec, BeginCallT begin_call, in ScopedTracer()
116 MakeScopedTracer(StreamExecutor *stream_exec, BeginCallT begin_call, in MakeScopedTracer()
|
| /external/tensorflow/tensorflow/stream_executor/gpu/ |
| D | gpu_activation.cc | 34 StreamExecutor* stream_exec) in ScopedActivateExecutorContext()
|
| /external/tensorflow/tensorflow/core/kernels/ |
| D | conv_ops_gpu.h | 34 inline bool IsVoltaOrLater(const se::StreamExecutor& stream_exec) { in IsVoltaOrLater()
164 se::StreamExecutor* stream_exec) const { in ShouldIncludeWinogradNonfusedAlgo()
|
| D | gpu_utils.cc | 135 se::StreamExecutor* stream_exec, in LogConvAutotuneResults()
179 se::StreamExecutor* stream_exec, absl::Span<const AutotuneResult> results) { in LogFusedConvForwardAutotuneResults()
|
| /external/tensorflow/tensorflow/core/common_runtime/device/ |
| D | device_host_allocator.h | 29 explicit DeviceHostAllocator(se::StreamExecutor* stream_exec, int numa_node, in DeviceHostAllocator()
|
| D | device_mem_allocator.h | 31 explicit DeviceMemAllocator(se::StreamExecutor* stream_exec, in DeviceMemAllocator()
|
| D | device_event_mgr_test.cc | 112 auto stream_exec = GPUMachineManager()->ExecutorForDevice(0).ValueOrDie(); in TEST() local
121 auto stream_exec = GPUMachineManager()->ExecutorForDevice(0).ValueOrDie(); in TEST() local
443 auto stream_exec = GPUMachineManager()->ExecutorForDevice(0).ValueOrDie(); in BM_no_ops() local
|
| /external/tensorflow/tensorflow/stream_executor/tpu/ |
| D | tpu_executable_interface.cc | 59 auto stream_exec = stream->parent(); in AllocateOutputMemoryWithInputReuse() local
|
| /external/tensorflow/tensorflow/compiler/xla/service/gpu/tests/ |
| D | mlir_gpu_test_base.cc | 53 se::StreamExecutor* stream_exec = stream->parent(); in CompileMlirModule() local
|
| /external/tensorflow/tensorflow/compiler/xla/service/ |
| D | compiler.h | 233 std::vector<std::vector<se::StreamExecutor*>> stream_exec, in Compile()
|
| /external/tensorflow/tensorflow/core/tpu/ |
| D | tpu_on_demand_compiler.cc | 277 std::vector<std::vector<stream_executor::StreamExecutor*>> stream_exec, in Compile()
|