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
184 lines
7.0 KiB
ReStructuredText
184 lines
7.0 KiB
ReStructuredText
..
|
|
This file was automatically generated. Do not edit.
|
|
|
|
red.async.relaxed.cluster.shared::cluster.mbarrier::complete_tx::bytes.inc.u32
|
|
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
|
.. code:: cuda
|
|
|
|
// red.async.relaxed.cluster.shared::cluster.mbarrier::complete_tx::bytes.op.type [dest], value, [remote_bar]; // PTX ISA 81, SM_90
|
|
// .type = { .u32 }
|
|
// .op = { .inc }
|
|
template <typename = void>
|
|
__device__ static inline void red_async(
|
|
cuda::ptx::op_inc_t,
|
|
uint32_t* dest,
|
|
const uint32_t& value,
|
|
uint64_t* remote_bar);
|
|
|
|
red.async.relaxed.cluster.shared::cluster.mbarrier::complete_tx::bytes.dec.u32
|
|
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
|
.. code:: cuda
|
|
|
|
// red.async.relaxed.cluster.shared::cluster.mbarrier::complete_tx::bytes.op.type [dest], value, [remote_bar]; // PTX ISA 81, SM_90
|
|
// .type = { .u32 }
|
|
// .op = { .dec }
|
|
template <typename = void>
|
|
__device__ static inline void red_async(
|
|
cuda::ptx::op_dec_t,
|
|
uint32_t* dest,
|
|
const uint32_t& value,
|
|
uint64_t* remote_bar);
|
|
|
|
red.async.relaxed.cluster.shared::cluster.mbarrier::complete_tx::bytes.min.u32
|
|
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
|
.. code:: cuda
|
|
|
|
// red.async.relaxed.cluster.shared::cluster.mbarrier::complete_tx::bytes.op.type [dest], value, [remote_bar]; // PTX ISA 81, SM_90
|
|
// .type = { .u32 }
|
|
// .op = { .min }
|
|
template <typename = void>
|
|
__device__ static inline void red_async(
|
|
cuda::ptx::op_min_t,
|
|
uint32_t* dest,
|
|
const uint32_t& value,
|
|
uint64_t* remote_bar);
|
|
|
|
red.async.relaxed.cluster.shared::cluster.mbarrier::complete_tx::bytes.max.u32
|
|
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
|
.. code:: cuda
|
|
|
|
// red.async.relaxed.cluster.shared::cluster.mbarrier::complete_tx::bytes.op.type [dest], value, [remote_bar]; // PTX ISA 81, SM_90
|
|
// .type = { .u32 }
|
|
// .op = { .max }
|
|
template <typename = void>
|
|
__device__ static inline void red_async(
|
|
cuda::ptx::op_max_t,
|
|
uint32_t* dest,
|
|
const uint32_t& value,
|
|
uint64_t* remote_bar);
|
|
|
|
red.async.relaxed.cluster.shared::cluster.mbarrier::complete_tx::bytes.add.u32
|
|
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
|
.. code:: cuda
|
|
|
|
// red.async.relaxed.cluster.shared::cluster.mbarrier::complete_tx::bytes.op.type [dest], value, [remote_bar]; // PTX ISA 81, SM_90
|
|
// .type = { .u32 }
|
|
// .op = { .add }
|
|
template <typename = void>
|
|
__device__ static inline void red_async(
|
|
cuda::ptx::op_add_t,
|
|
uint32_t* dest,
|
|
const uint32_t& value,
|
|
uint64_t* remote_bar);
|
|
|
|
red.async.relaxed.cluster.shared::cluster.mbarrier::complete_tx::bytes.min.s32
|
|
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
|
.. code:: cuda
|
|
|
|
// red.async.relaxed.cluster.shared::cluster.mbarrier::complete_tx::bytes.op.type [dest], value, [remote_bar]; // PTX ISA 81, SM_90
|
|
// .type = { .s32 }
|
|
// .op = { .min }
|
|
template <typename = void>
|
|
__device__ static inline void red_async(
|
|
cuda::ptx::op_min_t,
|
|
int32_t* dest,
|
|
const int32_t& value,
|
|
uint64_t* remote_bar);
|
|
|
|
red.async.relaxed.cluster.shared::cluster.mbarrier::complete_tx::bytes.max.s32
|
|
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
|
.. code:: cuda
|
|
|
|
// red.async.relaxed.cluster.shared::cluster.mbarrier::complete_tx::bytes.op.type [dest], value, [remote_bar]; // PTX ISA 81, SM_90
|
|
// .type = { .s32 }
|
|
// .op = { .max }
|
|
template <typename = void>
|
|
__device__ static inline void red_async(
|
|
cuda::ptx::op_max_t,
|
|
int32_t* dest,
|
|
const int32_t& value,
|
|
uint64_t* remote_bar);
|
|
|
|
red.async.relaxed.cluster.shared::cluster.mbarrier::complete_tx::bytes.add.s32
|
|
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
|
.. code:: cuda
|
|
|
|
// red.async.relaxed.cluster.shared::cluster.mbarrier::complete_tx::bytes.op.type [dest], value, [remote_bar]; // PTX ISA 81, SM_90
|
|
// .type = { .s32 }
|
|
// .op = { .add }
|
|
template <typename = void>
|
|
__device__ static inline void red_async(
|
|
cuda::ptx::op_add_t,
|
|
int32_t* dest,
|
|
const int32_t& value,
|
|
uint64_t* remote_bar);
|
|
|
|
red.async.relaxed.cluster.shared::cluster.mbarrier::complete_tx::bytes.and.b32
|
|
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
|
.. code:: cuda
|
|
|
|
// red.async.relaxed.cluster.shared::cluster.mbarrier::complete_tx::bytes.op.type [dest], value, [remote_bar]; // PTX ISA 81, SM_90
|
|
// .type = { .b32 }
|
|
// .op = { .and }
|
|
template <typename B32, enable_if_t<sizeof(B32) == 4, bool> = true>
|
|
__device__ static inline void red_async(
|
|
cuda::ptx::op_and_op_t,
|
|
B32* dest,
|
|
const B32& value,
|
|
uint64_t* remote_bar);
|
|
|
|
red.async.relaxed.cluster.shared::cluster.mbarrier::complete_tx::bytes.or.b32
|
|
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
|
.. code:: cuda
|
|
|
|
// red.async.relaxed.cluster.shared::cluster.mbarrier::complete_tx::bytes.op.type [dest], value, [remote_bar]; // PTX ISA 81, SM_90
|
|
// .type = { .b32 }
|
|
// .op = { .or }
|
|
template <typename B32, enable_if_t<sizeof(B32) == 4, bool> = true>
|
|
__device__ static inline void red_async(
|
|
cuda::ptx::op_or_op_t,
|
|
B32* dest,
|
|
const B32& value,
|
|
uint64_t* remote_bar);
|
|
|
|
red.async.relaxed.cluster.shared::cluster.mbarrier::complete_tx::bytes.xor.b32
|
|
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
|
.. code:: cuda
|
|
|
|
// red.async.relaxed.cluster.shared::cluster.mbarrier::complete_tx::bytes.op.type [dest], value, [remote_bar]; // PTX ISA 81, SM_90
|
|
// .type = { .b32 }
|
|
// .op = { .xor }
|
|
template <typename B32, enable_if_t<sizeof(B32) == 4, bool> = true>
|
|
__device__ static inline void red_async(
|
|
cuda::ptx::op_xor_op_t,
|
|
B32* dest,
|
|
const B32& value,
|
|
uint64_t* remote_bar);
|
|
|
|
red.async.relaxed.cluster.shared::cluster.mbarrier::complete_tx::bytes.add.u64
|
|
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
|
.. code:: cuda
|
|
|
|
// red.async.relaxed.cluster.shared::cluster.mbarrier::complete_tx::bytes.op.type [dest], value, [remote_bar]; // PTX ISA 81, SM_90
|
|
// .type = { .u64 }
|
|
// .op = { .add }
|
|
template <typename = void>
|
|
__device__ static inline void red_async(
|
|
cuda::ptx::op_add_t,
|
|
uint64_t* dest,
|
|
const uint64_t& value,
|
|
uint64_t* remote_bar);
|
|
|
|
red.async.relaxed.cluster.shared::cluster.mbarrier::complete_tx::bytes.add.u64
|
|
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
|
.. code:: cuda
|
|
|
|
// red.async.relaxed.cluster.shared::cluster.mbarrier::complete_tx::bytes.op.u64 [dest], value, [remote_bar]; // .u64 intentional PTX ISA 81, SM_90
|
|
// .op = { .add }
|
|
template <typename = void>
|
|
__device__ static inline void red_async(
|
|
cuda::ptx::op_add_t,
|
|
int64_t* dest,
|
|
const int64_t& value,
|
|
int64_t* remote_bar);
|