- Sort Score
- Result 10 results
- Languages All
Results 11 - 20 of 56 for lowerings (0.17 sec)
-
tensorflow/compiler/mlir/tfrt/runtime_fallback/runtime_fallback_executor.cc
using ::tensorflow::thread::ThreadPoolInterface; using ::tensorflow::tfrt_stub::FallbackTensor; // -------------------------------------------------------------------------- // // Run function via the TF->TFRT fallback lowering. // -------------------------------------------------------------------------- // namespace { // Thread pool for running `intra-op` tasks scheduled by the fallback kernels.
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed May 08 00:18:59 UTC 2024 - 9.1K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/stablehlo/transforms/composite_lowering_pass.cc
target.addLegalDialect<arith::ArithDialect>(); if (failed(applyPartialConversion(getOperation(), target, std::move(patterns)))) { getOperation().emitError("Composite lowering pass failed."); signalPassFailure(); } } } // namespace // Creates an instance of the pass. std::unique_ptr<OperationPass<ModuleOp>> CreateCompositeLoweringPass() {
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue May 28 23:16:05 UTC 2024 - 3K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/stablehlo/transforms/composite_lowering_patterns.td
See the License for the specific language governing permissions and limitations under the License. ==============================================================================*/ // Pattern definition file for direct lowering of mhlo composites to tflite ops. include "mlir/IR/OpBase.td" include "mlir/Dialect/Arith/IR/ArithOps.td" include "mlir/Dialect/Func/IR/FuncOps.td" include "mhlo/IR/hlo_ops.td"
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Jun 06 18:45:51 UTC 2024 - 4.6K bytes - Viewed (0) -
tensorflow/compiler/mlir/tf2xla/api/v1/compile_mlir_util.h
// passes for backend-specific ops. // lower_to_xla_hlo: Temporary parameter to be removed in imminent update. If // true, includes legalization and MHLO lowering passes. // allow_partial_conversion: when this is true, allow operations that can't be // legalized. ABSL_DEPRECATED("Use v2/legalize_tf.h::LegalizeMlirToHlo instead.") void CreateConvertMlirToXlaHloPipeline(
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue May 21 17:24:39 UTC 2024 - 10.4K bytes - Viewed (0) -
tensorflow/compiler/mlir/tfrt/tests/tf_to_corert/attributes.mlir
// RUN: tf-tfrt-opt -tf-to-tfrt %s | FileCheck %s --dump-input=fail // _output_shapes and f.* attributes are removed during tf-to-tfrt lowering. // CHECK-LABEL: func @remove_unused_attr func.func @remove_unused_attr() { // CHECK: %out_op_chain = tfrt_fallback_async.executeop.seq(%arg0) key(0) cost({{.*}}) device("/device:CPU:0") "tf.SomeOp2"()
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed May 08 00:18:59 UTC 2024 - 4.8K bytes - Viewed (0) -
tensorflow/compiler/mlir/tensorflow/transforms/decompose_reduce_dataset.cc
/*parallel_iterations=*/10, false, /*shape_invariant=*/false); // `_lower_using_switch_merge` is the default for While ops created // in TensorFlow and allows lowering to V1 control flow for loop // parallelization. dataset_while->setAttr("_lower_using_switch_merge", builder.getBoolAttr(true)); return dataset_while; }
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Apr 25 16:01:03 UTC 2024 - 14K bytes - Viewed (0) -
tensorflow/compiler/jit/xla_platform_info.cc
platform_info.device_type() == DEVICE_GPU) { // We do not need to (and cannot) build a real device compiler for GPU // if the platform ID is null. We just return a placeholder for supporting // cross platform lowering. *xla_device_compiler = new XlaDeviceCompiler(/*persistor=*/nullptr, /*compiler_client=*/nullptr); return absl::OkStatus(); }
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu May 02 17:23:27 UTC 2024 - 17.4K bytes - Viewed (0) -
tensorflow/compiler/mlir/tf2xla/transforms/legalize_tf_collective.cc
See the License for the specific language governing permissions and limitations under the License. ==============================================================================*/ // This file implements logic for lowering TensorFlow dialect's collective // ops (TF/XLA) to the HLO dialect. #include <numeric> #include <string> #include <utility> #include "llvm/ADT/StringRef.h"
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Apr 25 16:01:03 UTC 2024 - 16K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/stablehlo/transforms/passes.td
let summary = "Replaces a splat constant tensor with a BroadcastInDim op."; let constructor = "mlir::odml::CreateUnfoldSplatConstantPass()"; } def CompositeLoweringPass : Pass<"composite-lowering", "ModuleOp"> { let summary = "Lowers mhlo composites directly to tflite ops (when possible)."; let dependentDialects = ["mlir::mhlo::MhloDialect", "TFL::TensorFlowLiteDialect"];
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Apr 25 21:59:06 UTC 2024 - 5.6K bytes - Viewed (0) -
tensorflow/compiler/mlir/tf2xla/transforms/legalize_tf_patterns.td
//===----------------------------------------------------------------------===// // Relu op patterns. //===----------------------------------------------------------------------===// // TODO(hinsu): Make these patterns to TF to TF lowering. Relu6 lowering will // require HLO canonicalization of min and max on a tensor to ClampOp. // TODO(hinsu): Lower quantized types after supporting them in GetScalarOfType. def : Pat<(TF_ReluOp AnyTensor:$input),
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Mon May 06 18:46:23 UTC 2024 - 34.8K bytes - Viewed (0)