/aosp_15_r20/external/tensorflow/tensorflow/compiler/xla/service/gpu/ |
H A D | nvptx_compiler.cc | 72 HloModule* hlo_module, se::StreamExecutor* stream_exec, in OptimizeHloConvolutionCanonicalization() 120 HloModule* hlo_module, se::StreamExecutor* stream_exec, in OptimizeHloPostLayoutAssignment() 323 GpuVersion NVPTXCompiler::GetGpuVersion(se::StreamExecutor* stream_exec) { in GetGpuVersion() 331 se::StreamExecutor* stream_exec, in CompileTargetBinary() 380 se::StreamExecutor* stream_exec, const std::string& ptx, in CompileGpuAsmOrGetCachedResult() 488 se::StreamExecutor* stream_exec, in LinkModules()
|
H A D | gpu_compiler.cc | 202 se::StreamExecutor* stream_exec) in GpuBfloat16Support() 337 HloModule* hlo_module, se::StreamExecutor* stream_exec, in OptimizeHloModule() 723 HloModule* hlo_module, se::StreamExecutor* stream_exec, in OptimizeHloPostLayoutAssignment() 825 std::unique_ptr<HloModule> module, se::StreamExecutor* stream_exec, in RunHloPasses() 881 se::StreamExecutor* stream_exec) { in LowerToJitRt() 974 se::StreamExecutor* stream_exec = nullptr) { in CompileModuleToLlvmIrImpl() 1100 se::StreamExecutor* stream_exec, in CompileToTargetBinary() 1328 std::unique_ptr<HloModule> module, se::StreamExecutor* stream_exec, in RunBackend() 1441 auto stream_exec = options.executor(); in CompileAheadOfTime() local 1613 absl::string_view entry_function_name, se::StreamExecutor* stream_exec, in CompileLmhloToExecutable()
|
H A D | amdgpu_compiler.cc | 77 HloModule* hlo_module, se::StreamExecutor* stream_exec, in OptimizeHloConvolutionCanonicalization() 109 HloModule* hlo_module, se::StreamExecutor* stream_exec, in OptimizeHloPostLayoutAssignment() 129 GpuVersion AMDGPUCompiler::GetGpuVersion(se::StreamExecutor* stream_exec) { in GetGpuVersion() 137 se::StreamExecutor* stream_exec, in CompileTargetBinary()
|
H A D | stream_executor_util.cc | 313 absl::Mutex& GetGpuMutex(const se::StreamExecutor* stream_exec) { in GetGpuMutex() 333 absl::Span<const uint8_t> cubin_data, se::StreamExecutor* stream_exec) { in CreateKernel()
|
H A D | gpu_device_info.cc | 21 GpuDeviceInfo GetGpuDeviceInfo(stream_executor::StreamExecutor* stream_exec) { in GetGpuDeviceInfo()
|
H A D | gemm_algorithm_picker.h | 33 GemmAlgorithmPicker(se::StreamExecutor* stream_exec, in GemmAlgorithmPicker()
|
H A D | gpu_conv_algorithm_picker.h | 45 GpuConvAlgorithmPicker(se::StreamExecutor* stream_exec, in GpuConvAlgorithmPicker()
|
H A D | gpu_conv_algorithm_picker.cc | 121 se::StreamExecutor* stream_exec = stream->parent(); in GetAlgorithms() local 189 se::StreamExecutor* stream_exec, in GetMIOpenAlgorithms()
|
H A D | gpu_compiler.h | 151 se::StreamExecutor* stream_exec, in LinkModules()
|
H A D | precompiled_kernels.cc | 107 se::StreamExecutor* stream_exec) { in Get()
|
/aosp_15_r20/external/tensorflow/tensorflow/core/common_runtime/gpu/ |
H A D | gpu_debug_allocator_test.cc | 49 auto stream_exec = ExecutorForPlatformDeviceId(platform_device_id); in TEST() local 151 auto stream_exec = ExecutorForPlatformDeviceId(platform_device_id); in TEST() local 195 auto stream_exec = ExecutorForPlatformDeviceId(platform_device_id); in TEST() local 240 auto stream_exec = ExecutorForPlatformDeviceId(platform_device_id); in TEST() local 252 auto stream_exec = ExecutorForPlatformDeviceId(platform_device_id); in TEST() local
|
/aosp_15_r20/external/tensorflow/tensorflow/compiler/xla/tests/ |
H A D | llvm_compiler_test.cc | 47 HloModule* hlo_module, se::StreamExecutor* stream_exec, in OptimizeHloConvolutionCanonicalization() 53 HloModule* hlo_module, se::StreamExecutor* stream_exec, in OptimizeHloPostLayoutAssignment() 64 GpuVersion gpu_version, se::StreamExecutor* stream_exec, bool relocatable, in CompileTargetBinary()
|
/aosp_15_r20/external/tensorflow/tensorflow/compiler/xla/service/interpreter/ |
H A D | compiler.cc | 110 std::unique_ptr<HloModule> hlo_module, se::StreamExecutor* stream_exec, in RunBackend() 135 std::vector<std::vector<se::StreamExecutor*>> stream_exec, in Compile()
|
/aosp_15_r20/external/tensorflow/tensorflow/compiler/xla/stream_executor/cuda/ |
H A D | redzone_allocator_test.cc | 55 StreamExecutor* stream_exec = platform->ExecutorForDevice(0).ValueOrDie(); in TEST() local 129 StreamExecutor* stream_exec = platform->ExecutorForDevice(0).ValueOrDie(); in TEST() local
|
/aosp_15_r20/external/tensorflow/tensorflow/core/kernels/ |
H A D | gpu_utils.cc | 146 se::StreamExecutor* stream_exec, in LogConvAutotuneResults() 190 se::StreamExecutor* stream_exec, absl::Span<const AutotuneResult> results) { in LogFusedConvForwardAutotuneResults()
|
/aosp_15_r20/external/tensorflow/tensorflow/core/common_runtime/device/ |
H A 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 439 auto stream_exec = GPUMachineManager()->ExecutorForDevice(0).ValueOrDie(); in BM_no_ops() local
|
H A D | device_host_allocator.h | 29 explicit DeviceHostAllocator(se::StreamExecutor* stream_exec, int numa_node, in DeviceHostAllocator()
|
H A D | device_mem_allocator.h | 31 explicit DeviceMemAllocator(se::StreamExecutor* stream_exec, in DeviceMemAllocator()
|
/aosp_15_r20/external/tensorflow/tensorflow/compiler/xla/ |
H A D | device_util.h | 32 std::string DeviceIdentifier(se::StreamExecutor* stream_exec) { in DeviceIdentifier()
|
/aosp_15_r20/external/tensorflow/tensorflow/compiler/xla/stream_executor/ |
H A D | event.cc | 24 Event::Event(StreamExecutor* stream_exec) in Event()
|
/aosp_15_r20/external/tensorflow/tensorflow/compiler/xla/stream_executor/gpu/ |
H A D | gpu_activation.cc | 34 StreamExecutor* stream_exec) in ScopedActivateExecutorContext()
|
H A D | gpu_executor.h | 434 inline GpuExecutor* ExtractGpuExecutor(StreamExecutor* stream_exec) { in ExtractGpuExecutor()
|
/aosp_15_r20/external/tensorflow/tensorflow/compiler/xla/service/gpu/tests/ |
H A D | mlir_gpu_test_base.cc | 57 se::StreamExecutor* stream_exec = stream->parent(); in CompileMlirModule() local
|
/aosp_15_r20/external/tensorflow/tensorflow/compiler/xla/stream_executor/tpu/ |
H A D | tpu_executable_interface.cc | 59 auto stream_exec = stream->parent(); in AllocateOutputMemoryWithInputReuse() local
|
/aosp_15_r20/external/tensorflow/tensorflow/core/tpu/ |
H A D | tpu_on_demand_compiler.cc | 113 std::vector<std::vector<stream_executor::StreamExecutor*>> stream_exec, in Compile()
|