<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/tensorflow/probability/blob/v0.25.0/tensorflow_probability/python/experimental/auto_batching/instructions.py) |

Instruction language for auto-batching virtual machine.

#### View aliases


**Main aliases**

[`tfp.experimental.auto_batching.frontend.instructions`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/auto_batching/instructions), [`tfp.experimental.auto_batching.frontend.st.inst`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/auto_batching/instructions), [`tfp.experimental.auto_batching.frontend.stack.inst`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/auto_batching/instructions), [`tfp.experimental.auto_batching.stack_optimization.inst`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/auto_batching/instructions), [`tfp.experimental.auto_batching.stackless.inst`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/auto_batching/instructions)

<br />

## Classes

[`class Block`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/auto_batching/instructions/Block): A basic block.

[`class BranchOp`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/auto_batching/instructions/BranchOp): A conditional.

[`class ControlFlowGraph`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/auto_batching/instructions/ControlFlowGraph): A control flow graph (CFG).

[`class Function`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/auto_batching/instructions/Function): A function subject to auto-batching, callable with `FunctionCallOp`.

[`class FunctionCallOp`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/auto_batching/instructions/FunctionCallOp): Call a `Function`.

[`class GotoOp`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/auto_batching/instructions/GotoOp): An unconditional jump.

[`class IndirectGotoOp`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/auto_batching/instructions/IndirectGotoOp): Jump to the address in the reserved "program counter" variable.

[`class PopOp`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/auto_batching/instructions/PopOp): Restore the given variables from their stacks.

[`class PrimOp`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/auto_batching/instructions/PrimOp): An arbitrary already-batched computation, a 'primitive operation'.

[`class Program`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/auto_batching/instructions/Program): An auto-batchable program.

[`class PushGotoOp`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/auto_batching/instructions/PushGotoOp): Save an address for `IndirectGotoOp` and unconditionally jump to another.

[`class TensorType`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/auto_batching/TensorType): TensorType(dtype, shape)

[`class Type`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/auto_batching/Type): Type(tensors,)

[`class VariableAllocation`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/auto_batching/instructions/VariableAllocation): A token indicating how to allocate memory for an autobatched variable.

## Functions

[`extract_referenced_variables(...)`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/auto_batching/instructions/extract_referenced_variables): Extracts a set of the variable names referenced by the node in question.

[`halt_op(...)`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/auto_batching/instructions/halt_op): Returns a control transfer `Op` that means "exit this graph".

[`interpret(...)`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/auto_batching/instructions/interpret): Interprets a program in this instruction language and returns the result.

[`push_op(...)`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/auto_batching/instructions/push_op): Returns an `Op` that pushes values from `vars_in` into `vars_out`.

<br />

<br />

<br />

| ## Other Members ||
|---|---|
| pc_var | `'__program_counter__'` |

<br />