// CHECK: return %[[CONV2D]] : tensor<1x3x3x2x!quant.uniform<i8:f32, 4.000000e+00>>

// -----

func.func @convolution_upstream_srq_non_const_filter(%arg0: tensor<1x3x3x4x!quant.uniform<i8:f32, 1.000000e+0:-100>>, %arg1: tensor<3x3x4x2x!quant.uniform<i8:f32:3, {2.000000e+2, 3.000000e+3}>>) -> tensor<1x3x3x2x!quant.uniform<i8:f32, 4.000000e+0>> {

tensor<2048x!quant.uniform<i32:f32, 1.523437447303877E-7>>, %arg13: tensor<640x2048x!quant.uniform<i8<-127:127>:f32, 0.021174000576138496>>, %arg14: tensor<640x!quant.uniform<i32:f32, 1.601389680352559E-4>>, %arg15: tensor<2048x!quant.uniform<i16:f32, 4.3700000969693065E-4>>, %arg16: tensor<2048x!quant.uniform<i16:f32, 1.1000000085914508E-4>>, %arg17: tensor<2048x!quant.uniform<i16:f32, 1.6799999866634607E-4>>, %arg18: tensor<2048x!quant.uniform<i16:f32, 1.55999994603917E-4>>, %arg19: tensor<1x640x!quant.uniform<i8:f32,...

        self.filters_0 = np.random.uniform(
            low=-1.0, high=1.0, size=(4, 3)
        ).astype('f4')
        self.bias_0 = np.random.uniform(low=-1.0, high=1.0, size=(3,)).astype(
            'f4'
        )

        self.filters_1 = np.random.uniform(
            low=-1.0, high=1.0, size=(4, 3)
        ).astype('f4')
        self.bias_1 = np.random.uniform(low=-1.0, high=1.0, size=(3,)).astype(

//   * Input tensors are per-tensor uniform quantized (i8->f32)
//     tensors (full integer) with shape [..., r_x, c_x] or [..., c_x, r_x].
//   * The filter tensor is a per-tensor uniform quantized (i8->f32) tensor
//     (constant or activation) with shape [..., r_y, c_y] or [..., c_y, r_y].
//   * Output tensors are per-tensor uniform quantized (i8->f32) or
//     per-channel uniform quantized (i32->f32) tensors.
//

  // CHECK-LABEL: fakeQuantArgsTrue
  // CHECK: "tfl.quantize"(%arg0) <{qtype = tensor<8x8x8x8x!quant.uniform<u8<1:255>:f32, 0.001181102379804521:86>>}> : (tensor<8x8x8x8xf32>) -> tensor<8x8x8x8x!quant.uniform<u8<1:255>:f32, 0.001181102379804521:86>>
  // CHECK: %1 = "tfl.dequantize"(%0) : (tensor<8x8x8x8x!quant.uniform<u8<1:255>:f32, 0.001181102379804521:86>>) -> tensor<8x8x8x8xf32>
}

    %1:2 = "tfl.unpack"(%0) {axis = 0 : i32, num = 2 : i32} : (tensor<2x!quant.uniform<u8:f32, 0.007:128>>) -> (tensor<*x!quant.uniform<u8:f32, 0.007:128>>, tensor<*x!quant.uniform<u8:f32, 0.007:128>>)
    func.call @quant_fn(%1#0) : (tensor<*x!quant.uniform<u8:f32, 0.007:128>>) -> ()

    func.return %1#1 : tensor<*x!quant.uniform<u8:f32, 0.007:128>>
  }

  );

  let hasOptions = 1;
}

def TFL_RandomUniformOp : TFL_Op<"random_uniform", []> {
  let summary = "Outputs random values from a uniform distribution.";

  let description = [{
The generated values follow a uniform distribution in the range `[0, 1)`. The
lower bound 0 is included in the range, while the upper bound 1 is excluded.
  }];

  let arguments = (ins

	Send Value     // value to send (for send)
}

// Select executes a select operation described by the list of cases.
// Like the Go select statement, it blocks until at least one of the cases
// can proceed, makes a uniform pseudo-random choice,
// and then executes that case. It returns the index of the chosen case
// and, if that case was a receive operation, the value received and a

n-color.svg\" style=\"height: 50px\"> Istio</a>\n  </div>\n  <div style=\"position: absolute; bottom: 0; right: 0; font-size: 15px\">\n    Istio is an <a href=\"https://github.com/istio/istio\" target=\"_blank\">open platform</a> that provides a uniform way to <a href=\"https://istio.io/docs/concepts/security/\" target=\"_blank\">secure</a>,\n    <a href=\"https://istio.io/docs/concepts/traffic-management/\" target=\"_blank\">connect</a>, and \n    <a href=\"https://istio.io/docs/concepts/observability/\"...

or assignment are not yet evaluated.
</li>

<li>
If one or more of the communications can proceed,
a single one that can proceed is chosen via a uniform pseudo-random selection.
Otherwise, if there is a default case, that case is chosen.
If there is no default case, the "select" statement blocks until
at least one of the communications can proceed.
</li>

<li>