%0 = "tf.Conv2D"(%arg0, %cst0) {T = "tfdtype$DT_FLOAT", data_format = "NHWC", dilations = [1, 2, 3, 1], padding = "SAME", strides = [1, 4, 5, 1]} : (tensor<1x112x112x3xf32>, tensor<1x3x3x2xf32>) -> tensor<1x28x23x2xf32>
  %1 = "tf.Mul"(%0, %cst2) : (tensor<1x28x23x2xf32>, tensor<2xf32>) -> tensor<1x28x23x2xf32>

  func.return %1 : tensor<1x28x23x2xf32>
  // CHECK: %[[CST:.*]] = "tf.Const{{.*}} dense<

  %9 = "tf.AddV2"(%8, %cst_6) : (tensor<1x98x98x1xf32>, tensor<1xf32>) -> tensor<1x98x98x1xf32>
  %10 = "tf.Mul"(%9, %cst_5) : (tensor<1x98x98x1xf32>, tensor<1xf32>) -> tensor<1x98x98x1xf32>
  %11 = "tf.AddV2"(%10, %cst_8) : (tensor<1x98x98x1xf32>, tensor<f32>) -> tensor<1x98x98x1xf32>

  Output input_b = ops::Placeholder(s.WithOpName("shape_b"), DT_FLOAT,
                                    ops::Placeholder::Attrs{});
  Output mul = ops::Mul(s.WithOpName("mul"), input_b, input_b);
  Output shape_of_mul = ops::Shape(s.WithOpName("shape_of_mul"), mul);

  Output shape = ops::Add(s.WithOpName("shape"), shape_of_mul, input_a);

  Output reshape_input = ops::Placeholder(s.WithOpName("reshape_input"),

	return e
}

// Sub sets e = t1 - t2, and returns e.
func (e *P256Element) Sub(t1, t2 *P256Element) *P256Element {
	p256Sub(&e.x, &t1.x, &t2.x)
	return e
}

// Mul sets e = t1 * t2, and returns e.
func (e *P256Element) Mul(t1, t2 *P256Element) *P256Element {
	p256Mul(&e.x, &t1.x, &t2.x)
	return e
}

// Square sets e = t * t, and returns e.
func (e *P256Element) Square(t *P256Element) *P256Element {

// Calibration used to determine thresholds for using
// different algorithms.  Ideally, this would be converted
// to go generate to create thresholds.go

// This file prints execution times for the Mul benchmark
// given different Karatsuba thresholds. The result may be
// used to manually fine-tune the threshold constant. The
// results are somewhat fragile; use repeated runs to get
// a clear picture.

				}
			}
		}

		n := new(big.Int).Set(bigOne)
		totient := new(big.Int).Set(bigOne)
		pminus1 := new(big.Int)
		for _, prime := range primes {
			n.Mul(n, prime)
			pminus1.Sub(prime, bigOne)
			totient.Mul(totient, pminus1)
		}
		if n.BitLen() != bits {
			// This should never happen for nprimes == 2 because
			// crypto/rand should set the top two bits in each prime.

	"LL",
	"LLV",
	"LUI",
	"MOVB",
	"MOVBU",
	"MOVD",
	"MOVDF",
	"MOVDW",
	"MOVF",
	"MOVFD",
	"MOVFW",
	"MOVH",
	"MOVHU",
	"MOVW",
	"MOVWD",
	"MOVWF",
	"MOVWL",
	"MOVWR",
	"MUL",
	"MULD",
	"MULF",
	"MULU",
	"MULH",
	"MULHU",
	"MULW",
	"NEGD",
	"NEGF",
	"NEGW",
	"NEGV",
	"NOOP",
	"NOR",
	"OR",
	"REM",
	"REMU",
	"RFE",
	"SC",
	"SCV",
	"SGT",

  func.return %6 : tensor<!tf_type.variant>
}

func.func @"__inference_Dataset_map_<lambda>_80"(%arg0: tensor<*xi32>) -> tensor<*xi32> {
  %0 = "tf.Const"() {value = dense<2> : tensor<i32>} : () -> tensor<i32>
  %1 = "tf.Mul"(%arg0, %0) {device = ""} : (tensor<*xi32>, tensor<i32>) -> tensor<*xi32>
  %2 = "tf.Identity"(%1) {device = ""} : (tensor<*xi32>) -> tensor<*xi32>
  func.return %2 : tensor<*xi32>
}

	MOVW	R4, F5			// 85a41401
	MOVW	F4, R5			// 85b41401
	MOVV	R4, F5			// 85a81401
	MOVV	F4, R5			// 85b81401
	WORD	$74565			// 45230100
	BREAK				// 00002a00
	UNDEF				// 00002a00

	// mul
	MUL	R4, R5	  		// a5101c00
	MUL	R4, R5, R6	  	// a6101c00
	MULV	R4, R5	   		// a5901d00
	MULV	R4, R5, R6	   	// a6901d00
	MULVU	R4, R5			// a5901d00
	MULVU	R4, R5, R6		// a6901d00
	MULHV	R4, R5			// a5101e00

}

Status MulModel(AbstractContext* ctx,
                absl::Span<AbstractTensorHandle* const> inputs,
                absl::Span<AbstractTensorHandle*> outputs) {
  return ops::Mul(ctx, inputs[0], inputs[1], &outputs[0], "Mul");
}

// TODO(vnvo2409): Add more tests from `python/ops/gradient_checker_v2_test.py`.
// These tests should not be confused with `[*]_grad_test` which compare the