/external/tensorflow/tensorflow/core/kernels/ |
conv_ops_gpu.h | 39 class CudnnScratchAllocator : public perftools::gputools::ScratchAllocator { 44 int64 GetMemoryLimitInBytes(perftools::gputools::Stream* stream) override { 47 perftools::gputools::port::StatusOr<perftools::gputools::DeviceMemory<uint8>> 48 AllocateBytes(perftools::gputools::Stream* stream, int64 byte_size) override { 51 return perftools::gputools::port::Status{ 52 perftools::gputools::port::error::INVALID_ARGUMENT, 56 return perftools::gputools::port::StatusOr< 57 perftools::gputools::DeviceMemory<uint8>>(); 65 return perftools::gputools::port::StatusOr [all...] |
cudnn_pooling_gpu.h | 41 perftools::gputools::dnn::PoolingMode pooling_mode, 55 perftools::gputools::dnn::PoolingMode pooling_mode,
|
pooling_ops_common_gpu.h | 43 perftools::gputools::dnn::PoolingMode pooling_mode, 58 perftools::gputools::dnn::PoolingMode pooling_mode,
|
cudnn_pooling_gpu.cc | 36 perftools::gputools::dnn::PoolingMode pooling_mode, 70 perftools::gputools::dnn::PoolingDescriptor pooling_desc(3); 72 perftools::gputools::dnn::BatchDescriptor input_desc(3); 75 .set_layout(perftools::gputools::dnn::DataLayout::kBatchDepthYX); 76 perftools::gputools::dnn::BatchDescriptor output_desc(3); 79 .set_layout(perftools::gputools::dnn::DataLayout::kBatchDepthYX); 81 const auto dim_i = static_cast<perftools::gputools::dnn::DimIndex>(i); 119 perftools::gputools::dnn::PoolingMode pooling_mode, 125 CHECK((pooling_mode != perftools::gputools::dnn::PoolingMode::kMaximum) || 189 perftools::gputools::dnn::PoolingDescriptor pooling_desc(3) [all...] |
matrix_triangular_solve_op.cc | 37 perftools::gputools::DeviceMemory<Scalar> AsDeviceMemory( 39 perftools::gputools::DeviceMemoryBase wrapped( 41 perftools::gputools::DeviceMemory<Scalar> typed(wrapped); 207 perftools::gputools::blas::UpperLower upper_lower_matrix; 208 perftools::gputools::blas::Transpose transpose_matrix; 210 upper_lower_matrix = perftools::gputools::blas::UpperLower::kUpper; 212 upper_lower_matrix = perftools::gputools::blas::UpperLower::kLower; 216 perftools::gputools::blas::Transpose::kConjugateTranspose; 218 transpose_matrix = perftools::gputools::blas::Transpose::kNoTranspose; 227 perftools::gputools::blas::Side::kRight /*side*/ [all...] |
/external/perf_data_converter/src/ |
perf_data_converter.h | 22 namespace perftools { namespace 78 perftools::profiles::Profile data; 105 } // namespace perftools
|
/external/tensorflow/tensorflow/compiler/xla/service/gpu/ |
copy_thunk.h | 44 perftools::gputools::Stream* stream) override; 68 perftools::gputools::Stream* stream) override;
|
cudnn_convolution_algorithm_picker.h | 37 perftools::gputools::StreamExecutor* stream_exec, 55 perftools::gputools::StreamExecutor* stream_exec_; // never null
|
thunk.h | 87 perftools::gputools::Stream* /*stream*/) { 106 perftools::gputools::Stream* stream) = 0;
|
infeed_thunk.h | 47 perftools::gputools::Stream* stream) override;
|
cudnn_convolution_runner.cc | 25 namespace se = ::perftools::gputools; 218 const Shape& output_shape, perftools::gputools::DeviceMemoryBase input_buf, 219 perftools::gputools::DeviceMemoryBase filter_buf, 220 perftools::gputools::DeviceMemoryBase output_buf, 221 perftools::gputools::DeviceMemoryBase scratch_buf, const Window& window, 223 perftools::gputools::dnn::AlgorithmConfig algorithm, 224 perftools::gputools::Stream* stream, 225 perftools::gputools::dnn::ProfileResult* profile_result) { 235 const Shape& output_shape, perftools::gputools::DeviceMemoryBase input_buf, 236 perftools::gputools::DeviceMemoryBase filter_buf [all...] |
/external/tensorflow/tensorflow/compiler/jit/kernels/ |
xla_launch_op.h | 64 perftools::gputools::Platform::Id platform_id_;
|
/external/tensorflow/tensorflow/compiler/xla/service/cpu/ |
cpu_compiler.h | 56 perftools::gputools::Platform::Id PlatformId() const override; 115 // std::vector<std::vector<perftools::gputools::StreamExecutor*>> 121 perftools::gputools::StreamExecutor* stream_exec, 126 perftools::gputools::StreamExecutor* stream_exec, 133 perftools::gputools::Platform::Id PlatformId() const override;
|
/external/tensorflow/tensorflow/core/common_runtime/gpu/ |
gpu_init.cc | 29 namespace gpu = ::perftools::gputools;
|
/external/tensorflow/tensorflow/stream_executor/cuda/ |
cuda_event.h | 24 namespace perftools { namespace 62 } // namespace perftools
|
/external/tensorflow/tensorflow/stream_executor/ |
event.cc | 22 namespace perftools { namespace 52 } // namespace perftools
|
event.h | 23 namespace perftools { namespace 80 } // namespace perftools
|
scratch_allocator.cc | 21 namespace perftools { namespace 42 } // namespace perftools
|
/external/tensorflow/tensorflow/stream_executor/host/ |
host_stream.h | 27 namespace perftools { namespace 56 } // namespace perftools
|
host_timer.h | 23 namespace perftools { namespace 61 } // namespace perftools
|
/external/tensorflow/tensorflow/stream_executor/lib/ |
demangle.cc | 30 namespace perftools { namespace 53 } // namespace perftools
|
initialize.h | 29 namespace perftools { namespace 53 } // namespace perftools 57 perftools::gputools::port::Initializer google_initializer_##type##_##name( \ 64 extern perftools::gputools::port::Initializer \
|
/external/tensorflow/tensorflow/compiler/xla/service/ |
allocation_tracker.h | 65 perftools::gputools::DeviceMemoryBase device_memory; 88 perftools::gputools::DeviceMemoryBase device_memory, int device_ordinal) 93 Status DecrementRefCount(perftools::gputools::DeviceMemoryBase device_memory,
|
service_executable_run_options.h | 31 std::function<StatusOr<Pool<perftools::gputools::Stream>::SmartPtr>(int)>; 48 perftools::gputools::Stream* stream() const { return run_options_.stream(); } 54 StatusOr<Pool<perftools::gputools::Stream>::SmartPtr> BorrowStream(
|
/external/tensorflow/tensorflow/core/common_runtime/ |
gpu_device_context.h | 22 namespace perftools { namespace 26 } // namespace perftools 30 namespace gpu = ::perftools::gputools; 64 const Tensor* t, perftools::gputools::Stream* stream) const override {}
|