- Sort Score
- Result 10 results
- Languages All
Results 11 - 20 of 239 for Computation (0.28 sec)
-
tensorflow/compiler/mlir/tf2xla/api/v1/compile_tf_graph.cc
} if (output_to_input_alias.empty()) return absl::OkStatus(); xla::HloModuleProto* module_proto = compilation_result->computation->mutable_proto(); absl::StatusOr<xla::ProgramShape> program_shape_or_status = compilation_result->computation->GetProgramShape(); TF_RET_CHECK(program_shape_or_status.ok()); xla::ProgramShape& program_shape = program_shape_or_status.value();
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed Jun 12 22:19:26 UTC 2024 - 14K bytes - Viewed (0) -
tensorflow/compiler/mlir/tensorflow/transforms/tf_device_passes.td
// TF device dialect passes. def ResourceOpLiftingPass : Pass<"tf-resource-op-lifting", "ModuleOp"> { let summary = "Lifting resource operations out of device computation"; let description = [{ This pass lifts resource variable operations outside of device computation. This is useful because a lot of accelerator devices can not interact with resource variables directly..
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed Apr 17 18:52:57 UTC 2024 - 12.5K bytes - Viewed (0) -
tensorflow/compiler/mlir/tensorflow/transforms/tpu_host_computation_expansion.cc
return llvm::isa<TF::CastOp, TF::IdentityOp>(op); } // Adds outside compilation attributes to unary ops such as Identity/Cast ops // at the head of TPU computation that is used only by other outside compiled // ops. Identity ops and Cast ops is commonly added to the start of TPU // computation. Adding/expanding outside compilation attributes to these ops // will ensure that head outside compiled ops are correctly located and moved to // host.
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Apr 25 16:01:03 UTC 2024 - 5.1K bytes - Viewed (0) -
tensorflow/compiler/mlir/tensorflow/utils/tf_xla_mlir_translate.cc
xla::XlaComputation computation, return_value.valid() ? builder.Build(return_value) : builder.Build()); auto hlo_module = computation.proto(); xla::HloProto hlo_proto; hlo_proto.mutable_hlo_module()->Swap(&hlo_module); compilation_result->computation = std::make_shared<xla::XlaComputation>(); xla::XlaComputation* xla_computation = compilation_result->computation.get();
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Apr 25 16:01:03 UTC 2024 - 18.8K bytes - Viewed (0) -
tensorflow/compiler/mlir/tf2xla/internal/passes/extract_head_tail_outside_compilation.cc
} // Returns a set of ops that are outside compiled and can be extracted to before // the TPU computation. These ops are either connected to the inputs of the TPU // computation or other ops that can be extracted, and have no operands from // other ops in the TPU computation that cannot be extracted. llvm::SmallVector<Operation*, 4> FindOutsideCompiledOpsAtHead(
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Apr 25 16:01:03 UTC 2024 - 20.6K bytes - Viewed (0) -
tensorflow/compiler/mlir/tf2xla/internal/legalize_tf_mlir.h
// then those passes include all the Legalization to XLA HLO which is returned // in the compilation_result. absl::StatusOr<std::string> CompileFromMlirToXlaHlo( bool lower_to_xla_hlo, const tpu::MlirToHloArgs& computation, const tpu::TPUCompileMetadataProto& metadata, llvm::StringRef device_type, const XlaShapeLayoutHelpers::ShapeDeterminationFns& shape_determination_fns,
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Sun Apr 14 20:29:34 UTC 2024 - 2.8K bytes - Viewed (0) -
tensorflow/compiler/jit/encapsulate_xla_computations_pass.h
// Rewrites computations generated by the xla.compile() Python code into // XlaLaunch nodes. // // xla.compile() does two main things: // a) marks operators that make up an XLA computation with the attribute // _xla_compile_id=XYZ, where XYZ is a unique key. // b) adds XlaClusterOutput nodes to represent outputs of the computation. // These nodes are not marked with the _xla_compile_id attribute.
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Feb 22 06:59:07 UTC 2024 - 3.6K bytes - Viewed (0) -
tensorflow/compiler/mlir/tf2xla/transforms/tf2xla_rewriter.cc
XlaComputation& computation) { xla::DebugOptions debug_options; TF_ASSIGN_OR_RETURN(auto hlo_module_config, xla::HloModule::CreateModuleConfigFromProto( computation.proto(), debug_options)); TF_ASSIGN_OR_RETURN( std::unique_ptr<xla::HloModule> hlo_module, xla::HloModule::CreateFromProto(computation.proto(), hlo_module_config));
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu May 02 09:16:07 UTC 2024 - 18.9K bytes - Viewed (0) -
tensorflow/compiler/mlir/tensorflow/tests/tpu_rewrite.mlir
%add_result = "tf.Add"(%computation, %computation) : (tensor<i32>, tensor<i32>) -> tensor<i32> // expected-error@+1 {{Input of TPUPartitionedOutputV2 must be in tpu computation.}} %partitioned_output:2 = "tf.TPUPartitionedOutputV2"(%add_result) {N = 2 : i64, partition_dims = []} : (tensor<i32>) -> (tensor<i32>, tensor<i32>)
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu May 02 22:03:30 UTC 2024 - 172.9K bytes - Viewed (0) -
tensorflow/compiler/jit/xla_device_compiler_client.cc
xla::ExecutableBuildOptions build_options = GetExecutableBuildOptions( options, result, client_->default_device_ordinal()); TF_ASSIGN_OR_RETURN( auto executables, client_->Compile(*result.computation, argument_layouts, build_options)); TF_RET_CHECK(executables.size() == 1); return std::move(executables[0]); } absl::StatusOr<std::string> XlaDeviceCompilerClient::SerializeExecutable(
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed Feb 21 09:53:30 UTC 2024 - 4.1K bytes - Viewed (0)