ANDNL (R11), R9, DX                     // c4c230f213
	ANDNL DX, R9, DX                        // c4e230f2d2
	ANDNL R11, R9, DX                       // c4c230f2d3
	ANDNL (BX), R9, R11                     // c46230f21b
	ANDNL (R11), R9, R11                    // c44230f21b
	ANDNL DX, R9, R11                       // c46230f2da
	ANDNL R11, R9, R11                      // c44230f2db

030+\323\314\212\301\320?\014\364\342\212\212\320\305?\244\352~!o\233\347?t\202GyI\357\347?<a\rq\310\345\304?t\346K\266\235C\327?\242\201-\024v\277\356?\346F\313A\214\310\350?\224\221vT}\032\356?\316\364t{\177\253\323?;\305\316\306Q\000\357?`\2127\"DX\247?\032\020/\370\317\376\321?1rp\300\233\025\354? \014\350\010\\=\333?\361\017\013=b\'\353?4W?\347<\231\323?\257`\342\344\241\216\340?\350\330wZ7&\352?\000\2602Jrr\223?\220\213q\337\345\364\276?`\361@\033/w\300?\242\257\034C\355\337\341?1;\311\272...

		{"Regs386.BP", Field, 0},
		{"Regs386.BX", Field, 0},
		{"Regs386.CS", Field, 0},
		{"Regs386.CX", Field, 0},
		{"Regs386.DI", Field, 0},
		{"Regs386.DS", Field, 0},
		{"Regs386.DX", Field, 0},
		{"Regs386.ES", Field, 0},
		{"Regs386.FLAGS", Field, 0},
		{"Regs386.FS", Field, 0},
		{"Regs386.GS", Field, 0},
		{"Regs386.IP", Field, 0},
		{"Regs386.SI", Field, 0},

  }];

  let description = [{
tensors.

This op can be used to override the gradient for complicated functions. For
example, suppose y = f(x) and we wish to apply a custom function g for backprop
such that dx = g(dy). In Python,

```python
with tf.get_default_graph().gradient_override_map(
    {'IdentityN': 'OverrideGradientWithG'}):
  y, _ = identity_n([f(x), x])

@tf.RegisterGradient('OverrideGradientWithG')