Skip to content

Add mbarrier wait instructions reportValue #11029

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
fbusato merged 1 commit into from
Aug 27, 2026
Merged

Add mbarrier wait instructions reportValue #11029

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
72 changes: 72 additions & 0 deletions docs/libcudacxx/ptx/instructions/generated/mbarrier_test_wait.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -134,3 +134,75 @@ mbarrier.test_wait.phase_type::primary.relaxed.cluster.shared::cta.b64
bool& isReportSeen,
uint64_t* addr,
uint64_t state);

mbarrier.test_wait.phase_type::primary.acquire.cta.shared::cta.b64
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. code-block:: cuda

// mbarrier.test_wait.phase_type.sem.scope.shared::cta.b64 waitComplete|isReportSeen, reportValue, [addr], state; // PTX ISA 94, SM_90
// .phase_type = { .phase_type::primary }
// .sem = { .acquire, .relaxed }
// .scope = { .cta, .cluster }
template <cuda::ptx::dot_sem Sem, cuda::ptx::dot_scope Scope>
__device__ static inline bool mbarrier_test_wait(
cuda::ptx::mbarrier_phase_primary_t,
cuda::ptx::sem_t<Sem> sem,
cuda::ptx::scope_t<Scope> scope,
bool& isReportSeen,
uint8_t& reportValue,
uint64_t* addr,
uint64_t state);

mbarrier.test_wait.phase_type::primary.acquire.cluster.shared::cta.b64
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. code-block:: cuda

// mbarrier.test_wait.phase_type.sem.scope.shared::cta.b64 waitComplete|isReportSeen, reportValue, [addr], state; // PTX ISA 94, SM_90
// .phase_type = { .phase_type::primary }
// .sem = { .acquire, .relaxed }
// .scope = { .cta, .cluster }
template <cuda::ptx::dot_sem Sem, cuda::ptx::dot_scope Scope>
__device__ static inline bool mbarrier_test_wait(
cuda::ptx::mbarrier_phase_primary_t,
cuda::ptx::sem_t<Sem> sem,
cuda::ptx::scope_t<Scope> scope,
bool& isReportSeen,
uint8_t& reportValue,
uint64_t* addr,
uint64_t state);

mbarrier.test_wait.phase_type::primary.relaxed.cta.shared::cta.b64
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. code-block:: cuda

// mbarrier.test_wait.phase_type.sem.scope.shared::cta.b64 waitComplete|isReportSeen, reportValue, [addr], state; // PTX ISA 94, SM_90
// .phase_type = { .phase_type::primary }
// .sem = { .acquire, .relaxed }
// .scope = { .cta, .cluster }
template <cuda::ptx::dot_sem Sem, cuda::ptx::dot_scope Scope>
__device__ static inline bool mbarrier_test_wait(
cuda::ptx::mbarrier_phase_primary_t,
cuda::ptx::sem_t<Sem> sem,
cuda::ptx::scope_t<Scope> scope,
bool& isReportSeen,
uint8_t& reportValue,
uint64_t* addr,
uint64_t state);

mbarrier.test_wait.phase_type::primary.relaxed.cluster.shared::cta.b64
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. code-block:: cuda

// mbarrier.test_wait.phase_type.sem.scope.shared::cta.b64 waitComplete|isReportSeen, reportValue, [addr], state; // PTX ISA 94, SM_90
// .phase_type = { .phase_type::primary }
// .sem = { .acquire, .relaxed }
// .scope = { .cta, .cluster }
template <cuda::ptx::dot_sem Sem, cuda::ptx::dot_scope Scope>
__device__ static inline bool mbarrier_test_wait(
cuda::ptx::mbarrier_phase_primary_t,
cuda::ptx::sem_t<Sem> sem,
cuda::ptx::scope_t<Scope> scope,
bool& isReportSeen,
uint8_t& reportValue,
uint64_t* addr,
uint64_t state);
73 changes: 73 additions & 0 deletions docs/libcudacxx/ptx/instructions/generated/mbarrier_test_wait_parity.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -135,6 +135,79 @@ mbarrier.test_wait.parity.phase_type::primary.relaxed.cluster.shared::cta.b64
uint64_t* addr,
uint32_t phaseParity);


mbarrier.test_wait.parity.phase_type::primary.acquire.cta.shared::cta.b64
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. code-block:: cuda

// mbarrier.test_wait.parity.phase_type.sem.scope.shared::cta.b64 waitComplete|isReportSeen, reportValue, [addr], phaseParity; // PTX ISA 94, SM_90
// .phase_type = { .phase_type::primary }
// .sem = { .acquire, .relaxed }
// .scope = { .cta, .cluster }
template <cuda::ptx::dot_sem Sem, cuda::ptx::dot_scope Scope>
__device__ static inline bool mbarrier_test_wait_parity(
cuda::ptx::mbarrier_phase_primary_t,
cuda::ptx::sem_t<Sem> sem,
cuda::ptx::scope_t<Scope> scope,
bool& isReportSeen,
uint8_t& reportValue,
uint64_t* addr,
uint32_t phaseParity);

mbarrier.test_wait.parity.phase_type::primary.acquire.cluster.shared::cta.b64
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. code-block:: cuda

// mbarrier.test_wait.parity.phase_type.sem.scope.shared::cta.b64 waitComplete|isReportSeen, reportValue, [addr], phaseParity; // PTX ISA 94, SM_90
// .phase_type = { .phase_type::primary }
// .sem = { .acquire, .relaxed }
// .scope = { .cta, .cluster }
template <cuda::ptx::dot_sem Sem, cuda::ptx::dot_scope Scope>
__device__ static inline bool mbarrier_test_wait_parity(
cuda::ptx::mbarrier_phase_primary_t,
cuda::ptx::sem_t<Sem> sem,
cuda::ptx::scope_t<Scope> scope,
bool& isReportSeen,
uint8_t& reportValue,
uint64_t* addr,
uint32_t phaseParity);

mbarrier.test_wait.parity.phase_type::primary.relaxed.cta.shared::cta.b64
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. code-block:: cuda

// mbarrier.test_wait.parity.phase_type.sem.scope.shared::cta.b64 waitComplete|isReportSeen, reportValue, [addr], phaseParity; // PTX ISA 94, SM_90
// .phase_type = { .phase_type::primary }
// .sem = { .acquire, .relaxed }
// .scope = { .cta, .cluster }
template <cuda::ptx::dot_sem Sem, cuda::ptx::dot_scope Scope>
__device__ static inline bool mbarrier_test_wait_parity(
cuda::ptx::mbarrier_phase_primary_t,
cuda::ptx::sem_t<Sem> sem,
cuda::ptx::scope_t<Scope> scope,
bool& isReportSeen,
uint8_t& reportValue,
uint64_t* addr,
uint32_t phaseParity);

mbarrier.test_wait.parity.phase_type::primary.relaxed.cluster.shared::cta.b64
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. code-block:: cuda

// mbarrier.test_wait.parity.phase_type.sem.scope.shared::cta.b64 waitComplete|isReportSeen, reportValue, [addr], phaseParity; // PTX ISA 94, SM_90
// .phase_type = { .phase_type::primary }
// .sem = { .acquire, .relaxed }
// .scope = { .cta, .cluster }
template <cuda::ptx::dot_sem Sem, cuda::ptx::dot_scope Scope>
__device__ static inline bool mbarrier_test_wait_parity(
cuda::ptx::mbarrier_phase_primary_t,
cuda::ptx::sem_t<Sem> sem,
cuda::ptx::scope_t<Scope> scope,
bool& isReportSeen,
uint8_t& reportValue,
uint64_t* addr,
uint32_t phaseParity);

mbarrier.test_wait.parity.phase_type::conditional.acquire.cta.shared::cta.b64
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. code-block:: cuda
Expand Down
149 changes: 149 additions & 0 deletions docs/libcudacxx/ptx/instructions/generated/mbarrier_try_wait.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -206,6 +206,79 @@ mbarrier.try_wait.phase_type::primary.relaxed.cluster.shared::cta.b64
uint64_t* addr,
uint64_t state);


mbarrier.try_wait.phase_type::primary.acquire.cta.shared::cta.b64
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. code-block:: cuda

// mbarrier.try_wait.phase_type.sem.scope.shared::cta.b64 waitComplete|isReportSeen, reportValue, [addr], state; // PTX ISA 94, SM_90
// .phase_type = { .phase_type::primary }
// .sem = { .acquire, .relaxed }
// .scope = { .cta, .cluster }
template <cuda::ptx::dot_sem Sem, cuda::ptx::dot_scope Scope>
__device__ static inline bool mbarrier_try_wait(
cuda::ptx::mbarrier_phase_primary_t,
cuda::ptx::sem_t<Sem> sem,
cuda::ptx::scope_t<Scope> scope,
bool& isReportSeen,
uint8_t& reportValue,
uint64_t* addr,
uint64_t state);

mbarrier.try_wait.phase_type::primary.acquire.cluster.shared::cta.b64
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. code-block:: cuda

// mbarrier.try_wait.phase_type.sem.scope.shared::cta.b64 waitComplete|isReportSeen, reportValue, [addr], state; // PTX ISA 94, SM_90
// .phase_type = { .phase_type::primary }
// .sem = { .acquire, .relaxed }
// .scope = { .cta, .cluster }
template <cuda::ptx::dot_sem Sem, cuda::ptx::dot_scope Scope>
__device__ static inline bool mbarrier_try_wait(
cuda::ptx::mbarrier_phase_primary_t,
cuda::ptx::sem_t<Sem> sem,
cuda::ptx::scope_t<Scope> scope,
bool& isReportSeen,
uint8_t& reportValue,
uint64_t* addr,
uint64_t state);

mbarrier.try_wait.phase_type::primary.relaxed.cta.shared::cta.b64
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. code-block:: cuda

// mbarrier.try_wait.phase_type.sem.scope.shared::cta.b64 waitComplete|isReportSeen, reportValue, [addr], state; // PTX ISA 94, SM_90
// .phase_type = { .phase_type::primary }
// .sem = { .acquire, .relaxed }
// .scope = { .cta, .cluster }
template <cuda::ptx::dot_sem Sem, cuda::ptx::dot_scope Scope>
__device__ static inline bool mbarrier_try_wait(
cuda::ptx::mbarrier_phase_primary_t,
cuda::ptx::sem_t<Sem> sem,
cuda::ptx::scope_t<Scope> scope,
bool& isReportSeen,
uint8_t& reportValue,
uint64_t* addr,
uint64_t state);

mbarrier.try_wait.phase_type::primary.relaxed.cluster.shared::cta.b64
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. code-block:: cuda

// mbarrier.try_wait.phase_type.sem.scope.shared::cta.b64 waitComplete|isReportSeen, reportValue, [addr], state; // PTX ISA 94, SM_90
// .phase_type = { .phase_type::primary }
// .sem = { .acquire, .relaxed }
// .scope = { .cta, .cluster }
template <cuda::ptx::dot_sem Sem, cuda::ptx::dot_scope Scope>
__device__ static inline bool mbarrier_try_wait(
cuda::ptx::mbarrier_phase_primary_t,
cuda::ptx::sem_t<Sem> sem,
cuda::ptx::scope_t<Scope> scope,
bool& isReportSeen,
uint8_t& reportValue,
uint64_t* addr,
uint64_t state);

mbarrier.try_wait.phase_type::primary.acquire.cta.shared::cta.b64
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. code-block:: cuda
Expand Down Expand Up @@ -277,3 +350,79 @@ mbarrier.try_wait.phase_type::primary.relaxed.cluster.shared::cta.b64
uint64_t* addr,
uint64_t state,
uint32_t suspendTimeHint);

mbarrier.try_wait.phase_type::primary.acquire.cta.shared::cta.b64
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. code-block:: cuda

// mbarrier.try_wait.phase_type.sem.scope.shared::cta.b64 waitComplete|isReportSeen, reportValue, [addr], state, suspendTimeHint; // PTX ISA 94, SM_90
// .phase_type = { .phase_type::primary }
// .sem = { .acquire, .relaxed }
// .scope = { .cta, .cluster }
template <cuda::ptx::dot_sem Sem, cuda::ptx::dot_scope Scope>
__device__ static inline bool mbarrier_try_wait(
cuda::ptx::mbarrier_phase_primary_t,
cuda::ptx::sem_t<Sem> sem,
cuda::ptx::scope_t<Scope> scope,
bool& isReportSeen,
uint8_t& reportValue,
uint64_t* addr,
uint64_t state,
uint32_t suspendTimeHint);

mbarrier.try_wait.phase_type::primary.acquire.cluster.shared::cta.b64
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. code-block:: cuda

// mbarrier.try_wait.phase_type.sem.scope.shared::cta.b64 waitComplete|isReportSeen, reportValue, [addr], state, suspendTimeHint; // PTX ISA 94, SM_90
// .phase_type = { .phase_type::primary }
// .sem = { .acquire, .relaxed }
// .scope = { .cta, .cluster }
template <cuda::ptx::dot_sem Sem, cuda::ptx::dot_scope Scope>
__device__ static inline bool mbarrier_try_wait(
cuda::ptx::mbarrier_phase_primary_t,
cuda::ptx::sem_t<Sem> sem,
cuda::ptx::scope_t<Scope> scope,
bool& isReportSeen,
uint8_t& reportValue,
uint64_t* addr,
uint64_t state,
uint32_t suspendTimeHint);

mbarrier.try_wait.phase_type::primary.relaxed.cta.shared::cta.b64
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. code-block:: cuda

// mbarrier.try_wait.phase_type.sem.scope.shared::cta.b64 waitComplete|isReportSeen, reportValue, [addr], state, suspendTimeHint; // PTX ISA 94, SM_90
// .phase_type = { .phase_type::primary }
// .sem = { .acquire, .relaxed }
// .scope = { .cta, .cluster }
template <cuda::ptx::dot_sem Sem, cuda::ptx::dot_scope Scope>
__device__ static inline bool mbarrier_try_wait(
cuda::ptx::mbarrier_phase_primary_t,
cuda::ptx::sem_t<Sem> sem,
cuda::ptx::scope_t<Scope> scope,
bool& isReportSeen,
uint8_t& reportValue,
uint64_t* addr,
uint64_t state,
uint32_t suspendTimeHint);

mbarrier.try_wait.phase_type::primary.relaxed.cluster.shared::cta.b64
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. code-block:: cuda

// mbarrier.try_wait.phase_type.sem.scope.shared::cta.b64 waitComplete|isReportSeen, reportValue, [addr], state, suspendTimeHint; // PTX ISA 94, SM_90
// .phase_type = { .phase_type::primary }
// .sem = { .acquire, .relaxed }
// .scope = { .cta, .cluster }
template <cuda::ptx::dot_sem Sem, cuda::ptx::dot_scope Scope>
__device__ static inline bool mbarrier_try_wait(
cuda::ptx::mbarrier_phase_primary_t,
cuda::ptx::sem_t<Sem> sem,
cuda::ptx::scope_t<Scope> scope,
bool& isReportSeen,
uint8_t& reportValue,
uint64_t* addr,
uint64_t state,
uint32_t suspendTimeHint);
Loading
Loading