Search Options

Results per page
Sort
Preferred Languages
Advance

Results 1 - 2 of 2 for MulNoNan (0.19 sec)

  1. tensorflow/compiler/mlir/tensorflow/tests/canonicalize.mlir

      %res1 = "tf.MulNoNan"(%arg0, %comp1) {device = "/job:localhost/replica:0/task:0/device:GPU:0"} : (tensor<2xcomplex<f32>>, tensor<2xcomplex<f32>>) -> tensor<2xcomplex<f32>>
      %res2 = "tf.DivNoNan"(%arg0, %comp2) : (tensor<2xcomplex<f32>>, tensor<2xcomplex<f32>>) -> tensor<2xcomplex<f32>>
      %res3 = "tf.MulNoNan"(%arg0, %comp3) : (tensor<2xcomplex<f32>>, tensor<2xcomplex<f32>>) -> tensor<2xcomplex<f32>>
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Thu May 09 22:07:10 UTC 2024
    - 132.1K bytes
    - Viewed (0)
  2. tensorflow/compiler/mlir/tensorflow/ir/tf_ops_a_m.cc

    /// Canonicalization template for tf.DivNoNan and tf.MulNoNan:
    /// If the op is tf.DivNoNan and the divisor is a constant tensor (with all the
    /// elements of any allowed type: float or complex), rewrite the op to the
    /// divisor if all the elements of the divisor are zero and to tf.Div if all the
    /// elements of the divisor are non-zero.
    
    /// Similarly, if the op is tf.MulNoNan and the multiplier is a constant tensor
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Thu Apr 25 16:01:03 UTC 2024
    - 146.7K bytes
    - Viewed (0)
Back to top