class dry_run_executor

Declaration

class dry_run_executor : public executor { /* full declaration omitted */ };

Description

Executor implementation selected when Celerity performs a dry run, that is, graph generation for debugging purposes without actually allocating memory, launching kernels or issuing data transfers. dry_run_executor still executes horizon-, epoch- and fence instructions to guarantee forward progress in the user application.

Declared at: include/dry_run_executor.h:20

Inherits from: executor

Member Variables

double_buffered_queue<submission> m_submission_queue

std::thread m_thread

Member Aliases

• using host_object_transfer = std::pair< host_object_id, std::unique_ptr<host_object_instance>>;
• using submission = std::variant<std::vector<const instruction*>, host_object_transfer>;

Member Function Overview

• dry_run_executor(executor::delegate * dlg) → explicit
• dry_run_executor(const dry_run_executor &)
• dry_run_executor(dry_run_executor &&)
• get_active_time() const → std::chrono::nanoseconds
• get_starvation_time() const → std::chrono::nanoseconds
• notify_scheduler_idle(bool is_idle) → void
• operator=(const dry_run_executor &) → dry_run_executor &
• operator=(dry_run_executor &&) → dry_run_executor &
• submit(std::vector<const instruction *> instructions, std::vector<outbound_pilot> pilots) → void
• track_host_object_instance(host_object_id hoid, std::unique_ptr<host_object_instance> instance) → void
• track_reducer(reduction_id rid, std::unique_ptr<reducer> reducer) → void
• track_user_allocation(allocation_id aid, void * ptr) → void
• ~dry_run_executor()
• thread_main(executor::delegate * dlg) → void

Inherited from executor:

• public get_active_time
• public get_starvation_time
• public notify_scheduler_idle
• public operator=
• public operator=
• public submit
• public track_host_object_instance
• public track_reducer
• public track_user_allocation

Member Functions

¶explicit dry_run_executor(executor::delegate* dlg)

Description

dlg (optional) receives notifications about reached horizons and epochs from the executor thread.

Declared at: include/dry_run_executor.h:23

Parameters

executor::delegate* dlg

---

¶dry_run_executor(const dry_run_executor&)

Declared at: include/dry_run_executor.h:25

Parameters

const dry_run_executor&

---

¶dry_run_executor(dry_run_executor&&)

Declared at: include/dry_run_executor.h:26

Parameters

dry_run_executor&&

---

¶std::chrono::nanoseconds get_active_time() const

Description

Returns the total time the executor has spent processing instructions.

Declared at: include/dry_run_executor.h:41

---

¶std::chrono::nanoseconds get_starvation_time()
    const

Description

Returns the total time the executor has spent idle waiting for instructions while the scheduler was busy.

Declared at: include/dry_run_executor.h:40

---

¶void notify_scheduler_idle(bool is_idle)

Description

Informs the executor about a change of the scheduler idle state. Required for tracking starvation time.

Declared at: include/dry_run_executor.h:38

Parameters

bool is_idle

---

¶dry_run_executor& operator=(
    const dry_run_executor&)

Declared at: include/dry_run_executor.h:27

Parameters

const dry_run_executor&

---

¶dry_run_executor& operator=(dry_run_executor&&)

Declared at: include/dry_run_executor.h:28

Parameters

dry_run_executor&&

---

¶void submit(
    std::vector<const instruction*> instructions,
    std::vector<outbound_pilot> pilots)

Description

Submits a list of instructions to execute once their dependencies have been fulfilled, and a list of outbound pilots to be transmitted to their recipients as soon as possible. Instructions must be in topological order of dependencies, as must be the concatenation of all vectors passed to subsequent invocations of this function.

Declared at: include/dry_run_executor.h:36

Parameters

std::vector<const instruction*> instructions

std::vector<outbound_pilot> pilots

---

¶void track_host_object_instance(
    host_object_id hoid,
    std::unique_ptr<host_object_instance>
        instance)

Description

Transfer ownership of a host object instance to the executor. The executor will later destroy this instance when executing a matching destroy_host_object_instruction.

Declared at: include/dry_run_executor.h:33

Parameters

host_object_id hoid

std::unique_ptr<host_object_instance> instance

---

¶void track_reducer(
    reduction_id rid,
    std::unique_ptr<reducer> reducer)

Description

Informs the executor about the runtime behavior of a reduction. Will be used by any fill_identity_instruction and reduce_instruction later submitted on the same reduction_id. Reducer instances are removed from executor tracking and destroyed when they later appear in an instruction_garbage list attached to a horizon or epoch instruction.

Declared at: include/dry_run_executor.h:34

Parameters

reduction_id rid

std::unique_ptr<reducer> reducer

---

¶void track_user_allocation(allocation_id aid,
                           void* ptr)

Description

Informs the executor about the runtime address of an allocation on user_memory_id. Must be called before submitting any instruction referring to the allocation id in question. User allocations are later removed from executor tracking as they appear in an instruction_garbage list attached to a horizon or epoch instruction.

Declared at: include/dry_run_executor.h:32

Parameters

allocation_id aid

void* ptr

---

¶~dry_run_executor()

Description

Waits until an epoch with epoch_action::shutdown has executed and the executor thread has exited.

Declared at: include/dry_run_executor.h:30

---

¶void thread_main(executor::delegate* dlg)

Declared at: include/dry_run_executor.h:50

Parameters

executor::delegate* dlg

---