- Sort Score
- Result 10 results
- Languages All
Results 1 - 8 of 8 for _xla_outside_compilation (0.25 sec)
-
tensorflow/compiler/mlir/tensorflow/tests/mark_ops_for_outside_compilation.mlir
func.func @variant_input_output_already_marked() { // CHECK: "tf.opA" // CHECK-SAME: _xla_outside_compilation = "0" // CHECK: "tf.opB" // CHECK-SAME: _xla_outside_compilation = "0" "tf_device.cluster"() ({ %1= "tf.opA"() {_xla_outside_compilation = "0"} : () -> tensor<!tf_type.variant<tensor<f32>>> "tf.opB"(%1) {_xla_outside_compilation = "0"} : (tensor<!tf_type.variant<tensor<f32>>>) -> () tf_device.return
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed Apr 24 16:22:32 UTC 2024 - 29.5K bytes - Viewed (0) -
tensorflow/compiler/mlir/tensorflow/tests/extract_head_tail_outside_compilation.mlir
// CHECK-NEXT: %[[A_OUT:.*]] = "tf.A" // CHECK-NOT: _xla_outside_compilation // CHECK-NEXT: %[[B_OUT:.*]] = "tf.B"(%[[A_OUT]]) // CHECK-NOT: _xla_outside_compilation // CHECK-NEXT: %[[C_OUT:.*]] = "tf.C"(%[[B_OUT]], %arg0) // CHECK-NOT: _xla_outside_compilation // CHECK-NEXT: tf_device.return %[[C_OUT]] // // CHECK: "tf_device.cluster"
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue Oct 31 08:59:10 UTC 2023 - 29.1K bytes - Viewed (0) -
tensorflow/compiler/mlir/tf2xla/internal/passes/clustering_passes.td
For example, the following tf_device.cluster with an op marked for `xla_outside_compilation`: ```mlir func @outside_compilation() -> tensor<f32> { %0 = "tf_device.cluster"() ( { %1 = "tf.Const"() {_xla_outside_compilation = "0", value = dense<1.0> : tensor<f32>} : () -> (tensor<f32>) %2 = "tf.Identity"(%1) {_xla_outside_compilation = "0"} : (tensor<f32>) -> (tensor<f32>)
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue Apr 30 02:01:13 UTC 2024 - 19.8K bytes - Viewed (0) -
tensorflow/compiler/mlir/tf2xla/api/v1/compile_tf_graph_test.cc
tensor<1120x?xi32>, tensor<2xi32>) {\0A %0 = \22tf.Reshape\22(%arg0, %arg1) {_xla_outside_compilation = \220\22} : (tensor<3360x?xi32>, tensor<3xi32>) -> tensor<3x1120x?xi32> loc(#loc9)\0A %1:3 = \22tf.Split\22(%arg2, %0) {_xla_outside_compilation = \220\22} : (tensor<i32>, tensor<3x1120x?xi32>) -> (tensor<1x1120x?xi32>, tensor<1x1120x?xi32>, tensor<1x1120x?xi32>) loc(#loc10)\0A %2 = \22tf.Reshape\22(%1#0, %arg3) {_xla_outside_compilation = \220\22} : (tensor<1x1120x?xi32>, tensor<2xi32>) -> tensor<1120x?xi32>...
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Sat Apr 13 08:08:57 UTC 2024 - 11.7K bytes - Viewed (0) -
tensorflow/compiler/mlir/tensorflow/transforms/tf_device_passes.td
let summary = "Verifies that after Outside Compilation passes complete, there are no more _xla_outside_compilation attributes and no tf_device.launch ops."; let description = [{ This pass takes iterates over ops and ensures that _xla_outside_compilation and tf_device.launch ops no longer exist and have been removed. This happens after Outside Compilation passes have completed. }];
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/tf2xla/internal/passes/mark_ops_for_outside_compilation.cc
// Automatically marked ops for outside compilation have // `_xla_outside_compilation` attribute value of "auto" plus // an increasing counter. Manually marked ops for outside compilation only // have an increasing counteri for the attribute value. Therefore there is no // collision in // `_xla_outside_compilation` attribute between automatically and manually // marking ops.
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Apr 25 16:01:03 UTC 2024 - 21.4K bytes - Viewed (0) -
tensorflow/compiler/mlir/tf2xla/internal/passes/extract_head_tail_outside_compilation.cc
#include "tensorflow/compiler/mlir/tensorflow/utils/tpu_rewrite_device_util.h" namespace tensorflow { namespace tf2xla { namespace internal { // This pass extracts a CPU computation cluster with `_xla_outside_compilation` // annotation from the head or tail of a TPU cluster. namespace { using mlir::Block; using mlir::BlockArgument; using mlir::BoolAttr; using mlir::ModuleOp; using mlir::OpBuilder;
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/tensorflow/transforms/passes.h
// attribute on the `tf_device.launch`. std::unique_ptr<OperationPass<func::FuncOp>> CreateLaunchToDeviceAttributePass( bool legacy_graph_export = true); // Creates a pass to ensure that the `_xla_outside_compilation` and // tf_device.launch op no longer exist after Outside Compilation is complete. std::unique_ptr<OperationPass<func::FuncOp>> CreateVerifyNoOutsideCompilationMarkersPass();
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed Jun 12 21:18:05 UTC 2024 - 31.8K bytes - Viewed (0)