package norm

import "unicode/utf8"

type input struct {
	str   string
	bytes []byte
}

func inputBytes(str []byte) input {
	return input{bytes: str}
}

func inputString(str string) input {
	return input{str: str}
}

func (in *input) setBytes(str []byte) {
	in.str = ""
	in.bytes = str
}

func (in *input) setString(str string) {
	in.str = str
	in.bytes = nil
}

 * limitations under the License.
 */
package org.gradle.api.tasks;

import java.lang.annotation.*;

/**
 * <p>Attached to a task property to indicate that the property specifies some input value for the task.</p>
 *
 * <p>This annotation should be attached to the getter method in Java or the property in Groovy.
 * Annotations on setters or just the field in Java are ignored.</p>
 *

// RUN: tac-translate -input-mlir -output-mlir -device-specs=GPU %s -o - 2>&1 | FileCheck %s

module {
func.func @main(%arg0: tensor<1xf32>, %arg1: tensor<1xf32>, %arg2: tensor<1xf32>, %arg3: tensor<1xf32>) -> tensor<2x1xf32> attributes {tf.entry_function = {inputs = "input0,input1,input2,input3", outputs = "output"}} {
  %0 = "tfl.add"(%arg0, %arg1) {fused_activation_function = "RELU6"} : (tensor<1xf32>, tensor<1xf32>) -> tensor<1xf32>

  %10 = "tf.opK"() : () -> tensor<*xi16>
  %11 = "tf.opL"() : () -> tensor<*xi64>
  tf_device.replicate([%0, %1, %2] as %input0: tensor<*xi1>, %9 as %input1: tensor<*xi8>, %10 as %input2: tensor<*xi16>, [%3, %4, %5] as %input3: tensor<*xi32>, [%6, %7, %8] as %input4: tensor<*xf32>, %11 as %input5: tensor<*xi64>) {n = 3 : i32} {
    tf_device.return
  }
  func.return

// CHECK:      %[[OP_A:[a-z0-9]*]] = "tf.opA"

# RUN: tf_tfl_translate -tf-input-arrays=input0,input1 \
# RUN:                  -tf-input-shapes=4:4 \
# RUN:                  -tf-input-data-types=DT_FLOAT,DT_FLOAT \
# RUN:                  -tf-output-arrays=Add \
# RUN:                  -tf-inference-type=DT_QUINT8 \
# RUN:                  -tf-input-min-values='-2,-3' \
# RUN:                  -tf-input-max-values='2,3' \
# RUN:                  --quant-stats=%s.stats \

    def setup() {
        INVOCATION_COUNT.set(0)
    }

    def "input artifact selection is restored when using the in-memory cache"() {
        def transform = registerTransform(IdentityTransform)

        def inputArtifact1 = file("input1/input.txt")
        inputArtifact1.text = "Hello"

        def inputArtifact2 = file("input2/input.txt")
        inputArtifact2.text = "Hello"

        expect:

    }

    def "out-of-date when input file changes"() {
        given:
        def inputFile = file("input.txt")
        inputFile.text = "foo"
        buildFile << """
            ${keyInfo.addAsPropertiesScript()}
            signing {
                ${signingConfiguration()}
            }
            task signCustomFile(type: Sign) {
                sign(file("input.txt"))
            }
        """

// RUN: tf-opt -split-input-file -verify-diagnostics -tf-tpu-annotate-dynamic-shape-inputs %s | FileCheck %s

// Test that annotate the inputs of the cluster func to be dynamic shaped.

module attributes {tf.devices = ["/job:worker/replica:0/task:0/device:CPU:0", "/job:worker/replica:0/task:0/device:TPU_SYSTEM:0", "/job:worker/replica:0/task:0/device:TPU:0"]} {
   func.func @main(
      %arg0: tensor<2048xi64> {tf.device = "/job:localhost/replica:0/task:0/device:CPU:0"},

  %weight_zps = "tf.Const"() { value = dense<3> : tensor<i32> } : () -> tensor<i32>

  // CHECK: "tf.AddV2"
  // CHECK: mhlo.constant
  // CHECK-SAME{LITERAL}: dense<[[1, 2], [3, 4]]> : tensor<2x2xi8>
  %0 = "tf.AddV2"(%input, %input) : (tensor<?x?xf32>, tensor<?x?xf32>) -> tensor<?x?xf32>

  // CHECK: "mhlo.dot"
  // CHECK-SAME: (tensor<?x?xf32>, tensor<2x2x!quant.uniform<i8:f32, 1.000000e+00:3>>) -> tensor<?x?xf32>

Anis Eleuch <******@****.***> 1712232280 +0100