- Sort Score
- Result 10 results
- Languages All
Results 1 - 6 of 6 for embedding_sequencing (0.34 sec)
-
tensorflow/compiler/mlir/tensorflow/transforms/sparsecore/embedding_sequencing.cc
Christian Sigg <******@****.***> 1714060318 -0700
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Apr 25 16:01:03 UTC 2024 - 39.4K bytes - Viewed (0) -
tensorflow/compiler/mlir/tensorflow/tests/embedding_sequencing.mlir
Pat Notz <******@****.***> 1690925009 -0700
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue Aug 01 21:27:49 UTC 2023 - 19.1K bytes - Viewed (0) -
tensorflow/compiler/mlir/tensorflow/transforms/sparsecore/BUILD
"@llvm-project//mlir:Pass", "@llvm-project//mlir:Support", "@llvm-project//mlir:TransformUtils", ], ) cc_library( name = "embedding_sequencing", srcs = ["embedding_sequencing.cc"], hdrs = [ "sparsecore_passes.h", ], deps = [ ":sparsecore_passes_inc_gen", "//tensorflow/compiler/jit:flags_headers",
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Mar 28 23:42:09 UTC 2024 - 3.8K bytes - Viewed (0) -
tensorflow/compiler/jit/flags.h
// TensorCore sequencing will be used. bool tf_xla_disable_full_embedding_pipelining; // Force the WhileOps in embedding_pipelining and embedding_sequencing to use // this many parallel_iterations int tf_xla_embedding_parallel_iterations; }; // Flags for common MLIR configurations. struct MlirCommonFlags {
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed Apr 17 18:52:57 UTC 2024 - 14.5K bytes - Viewed (0) -
tensorflow/compiler/mlir/tf2xla/internal/clustering_bridge_passes.cc
pm.addNestedPass<FuncOp>( mlir::TFTPU::CreateTPUReorderReplicateAndPartitionedInputsPass()); pm.addNestedPass<FuncOp>(mlir::TF::CreateDecomposeReduceDatasetPass()); // Only one of EmbeddingSequencing and EmbeddingPipelining will actually // run and the logic is in EmbeddingPipeliningPass. If the pipelining pass // runs, embedding attributes are stripped and the sequencing pass will have
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue Apr 30 16:09:14 UTC 2024 - 11.2K bytes - Viewed (0) -
tensorflow/compiler/mlir/tensorflow/transforms/sparsecore/embedding_pipelining.cc
} void EmbeddingPipeliningPass::runOnOperation() { LOG(INFO) << "EmbeddingPipeliningPass::runOnOperation()"; ModuleOp module = getOperation(); // We only use one of the EmbeddingPipelining and EmbeddingSequencing passes. if (!UseEmbeddingPipelining(module)) return; SymbolTable symbol_table(module); llvm::SetVector<Operation*> forward_pass_ops; llvm::SetVector<Operation*> backward_pass_ops;
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Apr 25 16:01:03 UTC 2024 - 92.9K bytes - Viewed (0)