HomeSort by relevance Sort by last modified time
    Searched refs:perftools (Results 201 - 225 of 314) sorted by null

1 2 3 4 5 6 7 891011>>

  /external/tensorflow/tensorflow/compiler/xla/service/
hlo_runner.h 44 HloRunner(::perftools::gputools::Platform* platform);
executable.h 94 perftools::gputools::StreamExecutor* executor) {
allocation_tracker.cc 159 perftools::gputools::DeviceMemoryBase device_memory, int device_ordinal) {
171 perftools::gputools::DeviceMemoryBase device_memory, int device_ordinal) {
  /external/tensorflow/tensorflow/contrib/image/kernels/
adjust_hsv_in_yiq_op_gpu.cu.cc 62 auto no_transpose = perftools::gputools::blas::Transpose::kNoTranspose;
  /external/tensorflow/tensorflow/core/kernels/
cuda_device_array.h 83 perftools::gputools::DeviceMemoryBase output_values_base{
conv_ops.cc 477 perftools::gputools::dnn::AlgorithmConfig>
486 using perftools::gputools::dnn::AlgorithmConfig;
487 using perftools::gputools::dnn::AlgorithmDesc;
488 using perftools::gputools::dnn::ProfileResult;
516 auto no_transpose = perftools::gputools::blas::Transpose::kNoTranspose;
545 auto no_transpose = perftools::gputools::blas::Transpose::kNoTranspose;
631 perftools::gputools::dnn::BatchDescriptor input_desc;
636 .set_layout(perftools::gputools::dnn::DataLayout::kBatchDepthYX);
637 perftools::gputools::dnn::BatchDescriptor output_desc;
642 .set_layout(perftools::gputools::dnn::DataLayout::kBatchDepthYX)
    [all...]
fused_batch_norm_op.cc 254 perftools::gputools::DeviceMemory<T> y_ptr;
282 perftools::gputools::dnn::BatchDescriptor x_desc;
287 .set_layout(perftools::gputools::dnn::DataLayout::kBatchDepthYX);
289 perftools::gputools::dnn::BatchDescriptor scale_offset_desc;
294 .set_layout(perftools::gputools::dnn::DataLayout::kBatchDepthYX);
311 using perftools::gputools::DeviceMemory;
393 perftools::gputools::DeviceMemory<T> x_backprop_ptr;
436 perftools::gputools::dnn::BatchDescriptor x_desc;
441 .set_layout(perftools::gputools::dnn::DataLayout::kBatchDepthYX);
443 perftools::gputools::dnn::BatchDescriptor scale_offset_desc
    [all...]
conv_grad_filter_ops.cc 532 perftools::gputools::dnn::AlgorithmConfig>
636 using perftools::gputools::dnn::AlgorithmConfig;
637 using perftools::gputools::dnn::AlgorithmDesc;
638 using perftools::gputools::dnn::ProfileResult;
721 ->ThenBlasGemm(perftools::gputools::blas::Transpose::kNoTranspose,
722 perftools::gputools::blas::Transpose::kTranspose, n,
    [all...]
conv_grad_input_ops.cc 604 perftools::gputools::dnn::AlgorithmConfig>
705 using perftools::gputools::dnn::AlgorithmConfig;
706 using perftools::gputools::dnn::AlgorithmDesc;
707 using perftools::gputools::dnn::ProfileResult;
    [all...]
lrn_op.cc 190 perftools::gputools::dnn::BatchDescriptor dimensions_desc;
195 .set_layout(perftools::gputools::dnn::DataLayout::kBatchYXDepth);
197 perftools::gputools::dnn::NormalizeDescriptor normalize_desc;
407 perftools::gputools::dnn::BatchDescriptor dimensions_desc;
412 .set_layout(perftools::gputools::dnn::DataLayout::kBatchYXDepth);
414 perftools::gputools::dnn::NormalizeDescriptor normalize_desc;
  /external/tensorflow/tensorflow/stream_executor/cuda/
cuda_fft.h 29 namespace perftools { namespace
137 } // namespace perftools
  /external/tensorflow/tensorflow/stream_executor/
executor_cache.cc 20 namespace perftools { namespace
108 } // namespace perftools
platform.cc 25 namespace perftools { namespace
128 } // namespace perftools
plugin_registry.h 31 namespace perftools { namespace
164 } // namespace perftools
temporary_memory_manager.cc 24 namespace perftools { namespace
128 } // namespace perftools
  /external/tensorflow/tensorflow/compiler/xla/tests/
compute_constant_test.cc 47 perftools::gputools::Platform* platform = nullptr)
54 Client* ClientOrDie(::perftools::gputools::Platform* platform,
99 perftools::gputools::Platform* platform_;
  /external/tensorflow/tensorflow/contrib/nccl/kernels/
nccl_manager_test.cc 72 perftools::gputools::DeviceMemory<Scalar> AsDeviceMemory(
74 perftools::gputools::DeviceMemoryBase wrapped(
76 perftools::gputools::DeviceMemory<Scalar> typed(wrapped);
  /external/tensorflow/tensorflow/compiler/aot/
compile.cc 90 namespace gpu = perftools::gputools;
  /external/tensorflow/tensorflow/compiler/xla/client/
local_client.h 161 perftools::gputools::Platform* platform() const;
  /external/tensorflow/tensorflow/compiler/xla/service/cpu/
cpu_executable.cc 48 namespace se = ::perftools::gputools;
78 std::vector<perftools::gputools::DeviceMemoryBase>* buffers) {
250 tensorflow::gtl::ArraySlice<perftools::gputools::DeviceMemoryBase>
325 auto* host_stream = dynamic_cast<perftools::gputools::host::HostStream*>(
  /external/tensorflow/tensorflow/compiler/xla/service/gpu/
convolution_thunk.cc 28 namespace se = ::perftools::gputools;
kernel_thunk.cc 26 namespace se = ::perftools::gputools;
  /external/tensorflow/tensorflow/compiler/xla/service/interpreter/
executable.cc 41 namespace se = ::perftools::gputools;
executor.cc 22 namespace perftools { namespace
122 } // namespace perftools
  /external/tensorflow/tensorflow/stream_executor/lib/
statusor.h 16 // IWYU pragma: private, include "perftools/gputools/executor/stream_executor.h"
83 namespace perftools { namespace
252 } // namespace perftools

Completed in 295 milliseconds

1 2 3 4 5 6 7 891011>>