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
251 lines
8.9 KiB
ReStructuredText
251 lines
8.9 KiB
ReStructuredText
..
|
|
This file was automatically generated. Do not edit.
|
|
|
|
multimem.st.weak.global.b32
|
|
^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
|
.. code:: cuda
|
|
|
|
// multimem.st.sem.global.b32 [addr], val; // PTX ISA 81, SM_90
|
|
// .sem = { .weak }
|
|
template <typename B32, enable_if_t<sizeof(B32) == 4, bool> = true>
|
|
__device__ static inline void multimem_st(
|
|
cuda::ptx::sem_weak_t,
|
|
B32* addr,
|
|
B32 val);
|
|
|
|
multimem.st.relaxed.cta.global.b32
|
|
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
|
.. code:: cuda
|
|
|
|
// multimem.st.sem.scope.global.b32 [addr], val; // PTX ISA 81, SM_90
|
|
// .sem = { .relaxed, .release }
|
|
// .scope = { .cta, .cluster, .gpu, .sys }
|
|
template <typename B32, enable_if_t<sizeof(B32) == 4, bool> = true, cuda::ptx::dot_sem Sem, cuda::ptx::dot_scope Scope>
|
|
__device__ static inline void multimem_st(
|
|
cuda::ptx::sem_t<Sem> sem,
|
|
cuda::ptx::scope_t<Scope> scope,
|
|
B32* addr,
|
|
B32 val);
|
|
|
|
multimem.st.relaxed.cluster.global.b32
|
|
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
|
.. code:: cuda
|
|
|
|
// multimem.st.sem.scope.global.b32 [addr], val; // PTX ISA 81, SM_90
|
|
// .sem = { .relaxed, .release }
|
|
// .scope = { .cta, .cluster, .gpu, .sys }
|
|
template <typename B32, enable_if_t<sizeof(B32) == 4, bool> = true, cuda::ptx::dot_sem Sem, cuda::ptx::dot_scope Scope>
|
|
__device__ static inline void multimem_st(
|
|
cuda::ptx::sem_t<Sem> sem,
|
|
cuda::ptx::scope_t<Scope> scope,
|
|
B32* addr,
|
|
B32 val);
|
|
|
|
multimem.st.relaxed.gpu.global.b32
|
|
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
|
.. code:: cuda
|
|
|
|
// multimem.st.sem.scope.global.b32 [addr], val; // PTX ISA 81, SM_90
|
|
// .sem = { .relaxed, .release }
|
|
// .scope = { .cta, .cluster, .gpu, .sys }
|
|
template <typename B32, enable_if_t<sizeof(B32) == 4, bool> = true, cuda::ptx::dot_sem Sem, cuda::ptx::dot_scope Scope>
|
|
__device__ static inline void multimem_st(
|
|
cuda::ptx::sem_t<Sem> sem,
|
|
cuda::ptx::scope_t<Scope> scope,
|
|
B32* addr,
|
|
B32 val);
|
|
|
|
multimem.st.relaxed.sys.global.b32
|
|
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
|
.. code:: cuda
|
|
|
|
// multimem.st.sem.scope.global.b32 [addr], val; // PTX ISA 81, SM_90
|
|
// .sem = { .relaxed, .release }
|
|
// .scope = { .cta, .cluster, .gpu, .sys }
|
|
template <typename B32, enable_if_t<sizeof(B32) == 4, bool> = true, cuda::ptx::dot_sem Sem, cuda::ptx::dot_scope Scope>
|
|
__device__ static inline void multimem_st(
|
|
cuda::ptx::sem_t<Sem> sem,
|
|
cuda::ptx::scope_t<Scope> scope,
|
|
B32* addr,
|
|
B32 val);
|
|
|
|
multimem.st.release.cta.global.b32
|
|
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
|
.. code:: cuda
|
|
|
|
// multimem.st.sem.scope.global.b32 [addr], val; // PTX ISA 81, SM_90
|
|
// .sem = { .relaxed, .release }
|
|
// .scope = { .cta, .cluster, .gpu, .sys }
|
|
template <typename B32, enable_if_t<sizeof(B32) == 4, bool> = true, cuda::ptx::dot_sem Sem, cuda::ptx::dot_scope Scope>
|
|
__device__ static inline void multimem_st(
|
|
cuda::ptx::sem_t<Sem> sem,
|
|
cuda::ptx::scope_t<Scope> scope,
|
|
B32* addr,
|
|
B32 val);
|
|
|
|
multimem.st.release.cluster.global.b32
|
|
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
|
.. code:: cuda
|
|
|
|
// multimem.st.sem.scope.global.b32 [addr], val; // PTX ISA 81, SM_90
|
|
// .sem = { .relaxed, .release }
|
|
// .scope = { .cta, .cluster, .gpu, .sys }
|
|
template <typename B32, enable_if_t<sizeof(B32) == 4, bool> = true, cuda::ptx::dot_sem Sem, cuda::ptx::dot_scope Scope>
|
|
__device__ static inline void multimem_st(
|
|
cuda::ptx::sem_t<Sem> sem,
|
|
cuda::ptx::scope_t<Scope> scope,
|
|
B32* addr,
|
|
B32 val);
|
|
|
|
multimem.st.release.gpu.global.b32
|
|
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
|
.. code:: cuda
|
|
|
|
// multimem.st.sem.scope.global.b32 [addr], val; // PTX ISA 81, SM_90
|
|
// .sem = { .relaxed, .release }
|
|
// .scope = { .cta, .cluster, .gpu, .sys }
|
|
template <typename B32, enable_if_t<sizeof(B32) == 4, bool> = true, cuda::ptx::dot_sem Sem, cuda::ptx::dot_scope Scope>
|
|
__device__ static inline void multimem_st(
|
|
cuda::ptx::sem_t<Sem> sem,
|
|
cuda::ptx::scope_t<Scope> scope,
|
|
B32* addr,
|
|
B32 val);
|
|
|
|
multimem.st.release.sys.global.b32
|
|
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
|
.. code:: cuda
|
|
|
|
// multimem.st.sem.scope.global.b32 [addr], val; // PTX ISA 81, SM_90
|
|
// .sem = { .relaxed, .release }
|
|
// .scope = { .cta, .cluster, .gpu, .sys }
|
|
template <typename B32, enable_if_t<sizeof(B32) == 4, bool> = true, cuda::ptx::dot_sem Sem, cuda::ptx::dot_scope Scope>
|
|
__device__ static inline void multimem_st(
|
|
cuda::ptx::sem_t<Sem> sem,
|
|
cuda::ptx::scope_t<Scope> scope,
|
|
B32* addr,
|
|
B32 val);
|
|
|
|
multimem.st.weak.global.b64
|
|
^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
|
.. code:: cuda
|
|
|
|
// multimem.st.sem.global.b64 [addr], val; // PTX ISA 81, SM_90
|
|
// .sem = { .weak }
|
|
template <typename B64, enable_if_t<sizeof(B64) == 8, bool> = true>
|
|
__device__ static inline void multimem_st(
|
|
cuda::ptx::sem_weak_t,
|
|
B64* addr,
|
|
B64 val);
|
|
|
|
multimem.st.relaxed.cta.global.b64
|
|
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
|
.. code:: cuda
|
|
|
|
// multimem.st.sem.scope.global.b64 [addr], val; // PTX ISA 81, SM_90
|
|
// .sem = { .relaxed, .release }
|
|
// .scope = { .cta, .cluster, .gpu, .sys }
|
|
template <typename B64, enable_if_t<sizeof(B64) == 8, bool> = true, cuda::ptx::dot_sem Sem, cuda::ptx::dot_scope Scope>
|
|
__device__ static inline void multimem_st(
|
|
cuda::ptx::sem_t<Sem> sem,
|
|
cuda::ptx::scope_t<Scope> scope,
|
|
B64* addr,
|
|
B64 val);
|
|
|
|
multimem.st.relaxed.cluster.global.b64
|
|
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
|
.. code:: cuda
|
|
|
|
// multimem.st.sem.scope.global.b64 [addr], val; // PTX ISA 81, SM_90
|
|
// .sem = { .relaxed, .release }
|
|
// .scope = { .cta, .cluster, .gpu, .sys }
|
|
template <typename B64, enable_if_t<sizeof(B64) == 8, bool> = true, cuda::ptx::dot_sem Sem, cuda::ptx::dot_scope Scope>
|
|
__device__ static inline void multimem_st(
|
|
cuda::ptx::sem_t<Sem> sem,
|
|
cuda::ptx::scope_t<Scope> scope,
|
|
B64* addr,
|
|
B64 val);
|
|
|
|
multimem.st.relaxed.gpu.global.b64
|
|
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
|
.. code:: cuda
|
|
|
|
// multimem.st.sem.scope.global.b64 [addr], val; // PTX ISA 81, SM_90
|
|
// .sem = { .relaxed, .release }
|
|
// .scope = { .cta, .cluster, .gpu, .sys }
|
|
template <typename B64, enable_if_t<sizeof(B64) == 8, bool> = true, cuda::ptx::dot_sem Sem, cuda::ptx::dot_scope Scope>
|
|
__device__ static inline void multimem_st(
|
|
cuda::ptx::sem_t<Sem> sem,
|
|
cuda::ptx::scope_t<Scope> scope,
|
|
B64* addr,
|
|
B64 val);
|
|
|
|
multimem.st.relaxed.sys.global.b64
|
|
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
|
.. code:: cuda
|
|
|
|
// multimem.st.sem.scope.global.b64 [addr], val; // PTX ISA 81, SM_90
|
|
// .sem = { .relaxed, .release }
|
|
// .scope = { .cta, .cluster, .gpu, .sys }
|
|
template <typename B64, enable_if_t<sizeof(B64) == 8, bool> = true, cuda::ptx::dot_sem Sem, cuda::ptx::dot_scope Scope>
|
|
__device__ static inline void multimem_st(
|
|
cuda::ptx::sem_t<Sem> sem,
|
|
cuda::ptx::scope_t<Scope> scope,
|
|
B64* addr,
|
|
B64 val);
|
|
|
|
multimem.st.release.cta.global.b64
|
|
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
|
.. code:: cuda
|
|
|
|
// multimem.st.sem.scope.global.b64 [addr], val; // PTX ISA 81, SM_90
|
|
// .sem = { .relaxed, .release }
|
|
// .scope = { .cta, .cluster, .gpu, .sys }
|
|
template <typename B64, enable_if_t<sizeof(B64) == 8, bool> = true, cuda::ptx::dot_sem Sem, cuda::ptx::dot_scope Scope>
|
|
__device__ static inline void multimem_st(
|
|
cuda::ptx::sem_t<Sem> sem,
|
|
cuda::ptx::scope_t<Scope> scope,
|
|
B64* addr,
|
|
B64 val);
|
|
|
|
multimem.st.release.cluster.global.b64
|
|
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
|
.. code:: cuda
|
|
|
|
// multimem.st.sem.scope.global.b64 [addr], val; // PTX ISA 81, SM_90
|
|
// .sem = { .relaxed, .release }
|
|
// .scope = { .cta, .cluster, .gpu, .sys }
|
|
template <typename B64, enable_if_t<sizeof(B64) == 8, bool> = true, cuda::ptx::dot_sem Sem, cuda::ptx::dot_scope Scope>
|
|
__device__ static inline void multimem_st(
|
|
cuda::ptx::sem_t<Sem> sem,
|
|
cuda::ptx::scope_t<Scope> scope,
|
|
B64* addr,
|
|
B64 val);
|
|
|
|
multimem.st.release.gpu.global.b64
|
|
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
|
.. code:: cuda
|
|
|
|
// multimem.st.sem.scope.global.b64 [addr], val; // PTX ISA 81, SM_90
|
|
// .sem = { .relaxed, .release }
|
|
// .scope = { .cta, .cluster, .gpu, .sys }
|
|
template <typename B64, enable_if_t<sizeof(B64) == 8, bool> = true, cuda::ptx::dot_sem Sem, cuda::ptx::dot_scope Scope>
|
|
__device__ static inline void multimem_st(
|
|
cuda::ptx::sem_t<Sem> sem,
|
|
cuda::ptx::scope_t<Scope> scope,
|
|
B64* addr,
|
|
B64 val);
|
|
|
|
multimem.st.release.sys.global.b64
|
|
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
|
.. code:: cuda
|
|
|
|
// multimem.st.sem.scope.global.b64 [addr], val; // PTX ISA 81, SM_90
|
|
// .sem = { .relaxed, .release }
|
|
// .scope = { .cta, .cluster, .gpu, .sys }
|
|
template <typename B64, enable_if_t<sizeof(B64) == 8, bool> = true, cuda::ptx::dot_sem Sem, cuda::ptx::dot_scope Scope>
|
|
__device__ static inline void multimem_st(
|
|
cuda::ptx::sem_t<Sem> sem,
|
|
cuda::ptx::scope_t<Scope> scope,
|
|
B64* addr,
|
|
B64 val);
|