derek.holloway
7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
208 lines
7.0 KiB
ReStructuredText
208 lines
7.0 KiB
ReStructuredText
..
|
|
This file was automatically generated. Do not edit.
|
|
|
|
mbarrier.arrive.shared.b64
|
|
^^^^^^^^^^^^^^^^^^^^^^^^^^
|
|
.. code:: cuda
|
|
|
|
// mbarrier.arrive.shared.b64 state, [addr]; // 1. PTX ISA 70, SM_80
|
|
template <typename = void>
|
|
__device__ static inline uint64_t mbarrier_arrive(
|
|
uint64_t* addr);
|
|
|
|
mbarrier.arrive.shared::cta.b64
|
|
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
|
.. code:: cuda
|
|
|
|
// mbarrier.arrive.shared::cta.b64 state, [addr], count; // 2. PTX ISA 78, SM_90
|
|
template <typename = void>
|
|
__device__ static inline uint64_t mbarrier_arrive(
|
|
uint64_t* addr,
|
|
const uint32_t& count);
|
|
|
|
mbarrier.arrive.release.cta.shared::cta.b64
|
|
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
|
.. code:: cuda
|
|
|
|
// mbarrier.arrive.sem.scope.space.b64 state, [addr]; // 3a. PTX ISA 80, SM_90
|
|
// .sem = { .release }
|
|
// .scope = { .cta, .cluster }
|
|
// .space = { .shared::cta }
|
|
template <cuda::ptx::dot_scope Scope>
|
|
__device__ static inline uint64_t mbarrier_arrive(
|
|
cuda::ptx::sem_release_t,
|
|
cuda::ptx::scope_t<Scope> scope,
|
|
cuda::ptx::space_shared_t,
|
|
uint64_t* addr);
|
|
|
|
mbarrier.arrive.release.cluster.shared::cta.b64
|
|
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
|
.. code:: cuda
|
|
|
|
// mbarrier.arrive.sem.scope.space.b64 state, [addr]; // 3a. PTX ISA 80, SM_90
|
|
// .sem = { .release }
|
|
// .scope = { .cta, .cluster }
|
|
// .space = { .shared::cta }
|
|
template <cuda::ptx::dot_scope Scope>
|
|
__device__ static inline uint64_t mbarrier_arrive(
|
|
cuda::ptx::sem_release_t,
|
|
cuda::ptx::scope_t<Scope> scope,
|
|
cuda::ptx::space_shared_t,
|
|
uint64_t* addr);
|
|
|
|
mbarrier.arrive.release.cta.shared::cta.b64
|
|
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
|
.. code:: cuda
|
|
|
|
// mbarrier.arrive.sem.scope.space.b64 state, [addr], count; // 3b. PTX ISA 80, SM_90
|
|
// .sem = { .release }
|
|
// .scope = { .cta, .cluster }
|
|
// .space = { .shared::cta }
|
|
template <cuda::ptx::dot_scope Scope>
|
|
__device__ static inline uint64_t mbarrier_arrive(
|
|
cuda::ptx::sem_release_t,
|
|
cuda::ptx::scope_t<Scope> scope,
|
|
cuda::ptx::space_shared_t,
|
|
uint64_t* addr,
|
|
const uint32_t& count);
|
|
|
|
mbarrier.arrive.release.cluster.shared::cta.b64
|
|
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
|
.. code:: cuda
|
|
|
|
// mbarrier.arrive.sem.scope.space.b64 state, [addr], count; // 3b. PTX ISA 80, SM_90
|
|
// .sem = { .release }
|
|
// .scope = { .cta, .cluster }
|
|
// .space = { .shared::cta }
|
|
template <cuda::ptx::dot_scope Scope>
|
|
__device__ static inline uint64_t mbarrier_arrive(
|
|
cuda::ptx::sem_release_t,
|
|
cuda::ptx::scope_t<Scope> scope,
|
|
cuda::ptx::space_shared_t,
|
|
uint64_t* addr,
|
|
const uint32_t& count);
|
|
|
|
mbarrier.arrive.release.cluster.shared::cluster.b64
|
|
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
|
.. code:: cuda
|
|
|
|
// mbarrier.arrive.sem.scope.space.b64 _, [addr]; // 4a. PTX ISA 80, SM_90
|
|
// .sem = { .release }
|
|
// .scope = { .cluster }
|
|
// .space = { .shared::cluster }
|
|
template <typename = void>
|
|
__device__ static inline void mbarrier_arrive(
|
|
cuda::ptx::sem_release_t,
|
|
cuda::ptx::scope_cluster_t,
|
|
cuda::ptx::space_cluster_t,
|
|
uint64_t* addr);
|
|
|
|
mbarrier.arrive.release.cluster.shared::cluster.b64
|
|
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
|
.. code:: cuda
|
|
|
|
// mbarrier.arrive.sem.scope.space.b64 _, [addr], count; // 4b. PTX ISA 80, SM_90
|
|
// .sem = { .release }
|
|
// .scope = { .cluster }
|
|
// .space = { .shared::cluster }
|
|
template <typename = void>
|
|
__device__ static inline void mbarrier_arrive(
|
|
cuda::ptx::sem_release_t,
|
|
cuda::ptx::scope_cluster_t,
|
|
cuda::ptx::space_cluster_t,
|
|
uint64_t* addr,
|
|
const uint32_t& count);
|
|
|
|
mbarrier.arrive.relaxed.cta.shared::cta.b64
|
|
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
|
.. code:: cuda
|
|
|
|
// mbarrier.arrive.sem.scope.space.b64 state, [addr], count; // PTX ISA 86, SM_90
|
|
// .sem = { .relaxed }
|
|
// .scope = { .cta, .cluster }
|
|
// .space = { .shared::cta }
|
|
template <cuda::ptx::dot_scope Scope>
|
|
__device__ static inline uint64_t mbarrier_arrive(
|
|
cuda::ptx::sem_relaxed_t,
|
|
cuda::ptx::scope_t<Scope> scope,
|
|
cuda::ptx::space_shared_t,
|
|
uint64_t* addr,
|
|
const uint32_t& count);
|
|
|
|
mbarrier.arrive.relaxed.cluster.shared::cta.b64
|
|
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
|
.. code:: cuda
|
|
|
|
// mbarrier.arrive.sem.scope.space.b64 state, [addr], count; // PTX ISA 86, SM_90
|
|
// .sem = { .relaxed }
|
|
// .scope = { .cta, .cluster }
|
|
// .space = { .shared::cta }
|
|
template <cuda::ptx::dot_scope Scope>
|
|
__device__ static inline uint64_t mbarrier_arrive(
|
|
cuda::ptx::sem_relaxed_t,
|
|
cuda::ptx::scope_t<Scope> scope,
|
|
cuda::ptx::space_shared_t,
|
|
uint64_t* addr,
|
|
const uint32_t& count);
|
|
|
|
mbarrier.arrive.relaxed.cta.shared::cta.b64
|
|
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
|
.. code:: cuda
|
|
|
|
// mbarrier.arrive.sem.scope.space.b64 state, [addr]; // PTX ISA 86, SM_90
|
|
// .sem = { .relaxed }
|
|
// .scope = { .cta, .cluster }
|
|
// .space = { .shared::cta }
|
|
template <cuda::ptx::dot_scope Scope>
|
|
__device__ static inline uint64_t mbarrier_arrive(
|
|
cuda::ptx::sem_relaxed_t,
|
|
cuda::ptx::scope_t<Scope> scope,
|
|
cuda::ptx::space_shared_t,
|
|
uint64_t* addr);
|
|
|
|
mbarrier.arrive.relaxed.cluster.shared::cta.b64
|
|
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
|
.. code:: cuda
|
|
|
|
// mbarrier.arrive.sem.scope.space.b64 state, [addr]; // PTX ISA 86, SM_90
|
|
// .sem = { .relaxed }
|
|
// .scope = { .cta, .cluster }
|
|
// .space = { .shared::cta }
|
|
template <cuda::ptx::dot_scope Scope>
|
|
__device__ static inline uint64_t mbarrier_arrive(
|
|
cuda::ptx::sem_relaxed_t,
|
|
cuda::ptx::scope_t<Scope> scope,
|
|
cuda::ptx::space_shared_t,
|
|
uint64_t* addr);
|
|
|
|
mbarrier.arrive.relaxed.cluster.shared::cluster.b64
|
|
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
|
.. code:: cuda
|
|
|
|
// mbarrier.arrive.sem.scope.space.b64 _, [addr], count; // PTX ISA 86, SM_90
|
|
// .sem = { .relaxed }
|
|
// .scope = { .cluster }
|
|
// .space = { .shared::cluster }
|
|
template <typename = void>
|
|
__device__ static inline void mbarrier_arrive(
|
|
cuda::ptx::sem_relaxed_t,
|
|
cuda::ptx::scope_cluster_t,
|
|
cuda::ptx::space_cluster_t,
|
|
uint64_t* addr,
|
|
const uint32_t& count);
|
|
|
|
mbarrier.arrive.relaxed.cluster.shared::cluster.b64
|
|
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
|
.. code:: cuda
|
|
|
|
// mbarrier.arrive.sem.scope.space.b64 _, [addr]; // PTX ISA 86, SM_90
|
|
// .sem = { .relaxed }
|
|
// .scope = { .cluster }
|
|
// .space = { .shared::cluster }
|
|
template <typename = void>
|
|
__device__ static inline void mbarrier_arrive(
|
|
cuda::ptx::sem_relaxed_t,
|
|
cuda::ptx::scope_cluster_t,
|
|
cuda::ptx::space_cluster_t,
|
|
uint64_t* addr);
|