- Sort Score
- Result 10 results
- Languages All
Results 21 - 30 of 104 for HLO (0.05 sec)
-
tensorflow/compiler/mlir/tf2xla/transforms/legalize_tf_patterns.td
// This pattern converts TensorFlow axis format to HLO axis format which // doesn't wrap around like TensorFlow and is always positive. For this // conversion, use the first input to get inputs rank. Other inputs need not be // ranked. // Defining op for `axis` is TensorFlow constant op in the pattern as during // the conversion, original Concat op operands still refers to the old ops even
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Mon May 06 18:46:23 UTC 2024 - 34.8K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/stablehlo/transforms/passes.h
std::unique_ptr<OperationPass<ModuleOp>> CreateCompositeLoweringPass(); // Adds the HLO to TF rewrite patterns to the specified pattern list. void PopulateLegalizeHloToTfPatterns(RewritePatternSet* patterns, MLIRContext* context); // Adds the HLO to TFLite rewrite patterns to the specified pattern list. void PopulateLegalizeHloToTFLitePatterns(RewritePatternSet* patterns,
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Apr 25 21:59:06 UTC 2024 - 3.2K bytes - Viewed (0) -
tensorflow/compiler/mlir/tf2xla/transforms/legalize_tf.cc
}; // Converts tf.RandomShuffle op into a series of XLA HLO ops. // // tf.RandomShuffle shuffles tensors along the first dimension. If the input // tensor's rank is 1, then it is translated into HLO sort op(s) according to // indices randomly generated via HLO rng_uniform ops. Otherwise, it is // translated into an HLO while op to first emulate shuffling indices using // HLO dynamic_slice and dynamic_update_slice ops, then finally HLO gather
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue Jun 11 20:00:43 UTC 2024 - 291.8K bytes - Viewed (0) -
tensorflow/compiler/mlir/runlit.cfg.py
config.name = 'MLIR ' + os.path.basename(config.mlir_test_dir) config.test_format = lit.formats.ShTest(not llvm_config.use_lit_shell) # suffixes: A list of file extensions to treat as test files. config.suffixes = ['.cc', '.hlo', '.json', '.mlir', '.pbtxt', '.py'] # test_source_root: The root path where tests are located. config.test_source_root = config.mlir_test_dir # test_exec_root: The root path where tests should be run.
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Mon Jun 10 18:52:19 UTC 2024 - 3.3K bytes - Viewed (0) -
tensorflow/compiler/mlir/tf2xla/internal/legalize_tf_mlir.h
namespace internal { // Compiles a serialized MLIR module and returns a serialized MLIR module of the // result of running all the MLIR Bridge passes. If compile_to_xla_hlo is true // 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,
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/mlir/lite/tests/flatbuffer2mlir/composite_op_round_trip.mlir
// RUN: tf_tfl_translate --enable-hlo-to-tf-conversion --input-mlir %s -o - | flatbuffer_translate --tflite-flatbuffer-to-mlir - -o - | FileCheck %s --check-prefix=CHECK-ROUNDTRIP module { func.func public @main( %arg0: tensor<i64>) -> tensor<i64> { %0 = func.call @test_add_roundtrip(%arg0) : (tensor<i64>) -> tensor<i64> return %0 : tensor<i64> } // CHECK-LABEL: func.func private @test_add_roundtrip
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed Apr 24 03:40:50 UTC 2024 - 1.1K bytes - Viewed (0) -
tensorflow/compiler/mlir/tensorflow/transforms/tf_test_passes.td
let options = [ Option<"default_patterns_", "default-patterns", "bool", /*default=*/"true", "Activate the default TF->TF patterns">, Option<"pre_hlo_patterns_", "pre-hlo-patterns", "bool", /*default=*/"true", "Activate the pre-HLO TF->TF patterns">, ]; } def TestResourceAliasAnalysis : Pass<"tf-test-resource-alias-analysis", "mlir::func::FuncOp"> {
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Fri Mar 03 00:21:29 UTC 2023 - 4K bytes - Viewed (0) -
tensorflow/compiler/mlir/tf2xla/internal/passes/lowering_passes.td
let description = [{ Gathers metrics about the input MLIR to Phase 2 of the TFXLA Bridge, which does a strict semantic lowering from Tensorflow ops to XLA HLO. }]; let constructor = "tensorflow::tf2xla::internal::CreateInputLoweringMetricsPass()";
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed Feb 21 19:49:04 UTC 2024 - 1.2K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/common/tfl_pass_config.h
// Whether to enable the hlo/stablehlo to tf conversion. This also supports // the case where a saved model contains both TF module and serialized // StableHLO module. bool enable_hlo_to_tf_conversion = false; // Whether to disable the direct hlo/stablehlo to Tensorflow Lite conversion. // // This prevents from directly converting from HLO to TFLite without going
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed May 08 19:05:30 UTC 2024 - 6.5K bytes - Viewed (0) -
tensorflow/compiler/mlir/tf2xla/internal/legalize_tf_mlir.cc
std::vector<ShardingAndIndex>* arg_core_mapping, std::vector<std::vector<xla::Shape>>* per_core_arg_shapes) { LOG_FIRST_N(INFO, 1) << "Compiling MLIR computation to XLA HLO using MLIR tf2xla bridge in " "the op by op fallback mode. This is Phase 2 of the TF2XLA Bridge. " "Old (non-MLIR) bridge may be used in case of unsupported feature "
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Sun Apr 14 20:29:34 UTC 2024 - 6.1K bytes - Viewed (0)