- Sort Score
- Result 10 results
- Languages All
Results 11 - 15 of 15 for _XlaCompile (0.7 sec)
-
tensorflow/compiler/jit/kernels/xla_ops.cc
.HostMemory("constants") .HostMemory("resources"), XlaLocalLaunchOp); REGISTER_KERNEL_BUILDER(Name("_XlaCompile").Device(DEVICE_CPU), XlaCompileOp); REGISTER_KERNEL_BUILDER(Name("_XlaCompile") .Device(DEVICE_GPU) .HostMemory("constants") .HostMemory("key")
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Fri May 17 22:46:36 UTC 2024 - 41.4K bytes - Viewed (0) -
tensorflow/compiler/jit/mark_for_compilation_pass.cc
namespace tensorflow { namespace { using DeadnessPredicate = DeadnessAnalysis::DeadnessPredicate; using jit::DeviceId; using jit::DeviceSet; // The clusters we create here are eventually lowered into an // _XlaCompile/_XlaRun pair with a TF executor "fallback" that uses the // PartitionedCall op to execute the cluster in the regular graph executor if // need be. PartitionedCall, however, reruns the entire TF graph optimization
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed Feb 21 12:19:41 UTC 2024 - 85.3K bytes - Viewed (0) -
tensorflow/compiler/jit/xla_platform_info.cc
// operations). Such a cluster can fail compilation (in way that // MarkForCompilation could not have detected) if the CPU JIT is not // linked in. // // So bail out of _XlaCompile in this case, and let the executor handle // the situation for us. const Status& status = compiler_for_platform.status(); if (status.code() == error::NOT_FOUND) {
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/tensorflow/ir/tf_ops_n_z.cc
effects.emplace_back(MemoryEffects::Write::get(), ResourceEffects::_XlaRun::get()); // Conservatively mark resource handles as read and write, as without // analyzing _XlaCompile, there is not sufficient information to determine // effects on resources. for (Value value : getArgs()) { MarkResourceAsReadAndWrite(value, effects); } }
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu May 09 22:07:10 UTC 2024 - 170.8K bytes - Viewed (0) -
tensorflow/compiler/mlir/tensorflow/ir/tf_generated_ops.td
node and associated metadata.}]>:$key, Res<TF_BoolTensor, [{If the `must_compile` attr is false the _XlaCompile op can decide not to compile the clusters based on some profitability heuristics. In that case `compilation_successful` is false if _XlaCompile chose not to compile the cluster. If the `must_compile` attr is true then _XlaCompile always attempts to compile the cluster and
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue Jun 11 23:24:08 UTC 2024 - 793K bytes - Viewed (0)