derek/TheRock
1
0 Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity
Files
1a182e2dac58879f215c0fad0f5f78c76dcafe56
TheRock/math-libs/libhipcxx/docs/libcudacxx/ptx/instructions/generated/tcgen05_cp.rst
T
derek.holloway 7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
Details
CodeQL / Analyze (python) (push) Canceled after 0s
Details
pre-commit / pre-commit (push) Canceled after 0s
Details
Multi-Arch CI / setup (push) Canceled after 0s
Details
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Details
Setup (Multi-Arch) / setup (push) Canceled after 0s
Details
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Details
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
Details
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Details
Multi-Arch CI / CI Summary (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Details
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Details
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
Details
Flatten subprojects into a single base monorepo
2026-09-02 16:34:47 -07:00

435 lines
17 KiB
ReStructuredText
Raw Blame History

..
This file was automatically generated. Do not edit.
tcgen05.cp.cta_group::1.128x256b
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. code:: cuda
// tcgen05.cp.cta_group.128x256b [taddr], s_desc; // PTX ISA 86, SM_100a, SM_101a
// .cta_group = { .cta_group::1, .cta_group::2 }
template <cuda::ptx::dot_cta_group Cta_Group>
__device__ static inline void tcgen05_cp_128x256b(
cuda::ptx::cta_group_t<Cta_Group> cta_group,
uint32_t taddr,
uint64_t s_desc);
tcgen05.cp.cta_group::2.128x256b
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. code:: cuda
// tcgen05.cp.cta_group.128x256b [taddr], s_desc; // PTX ISA 86, SM_100a, SM_101a
// .cta_group = { .cta_group::1, .cta_group::2 }
template <cuda::ptx::dot_cta_group Cta_Group>
__device__ static inline void tcgen05_cp_128x256b(
cuda::ptx::cta_group_t<Cta_Group> cta_group,
uint32_t taddr,
uint64_t s_desc);
tcgen05.cp.cta_group::1.4x256b
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. code:: cuda
// tcgen05.cp.cta_group.4x256b [taddr], s_desc; // PTX ISA 86, SM_100a, SM_101a
// .cta_group = { .cta_group::1, .cta_group::2 }
template <cuda::ptx::dot_cta_group Cta_Group>
__device__ static inline void tcgen05_cp_4x256b(
cuda::ptx::cta_group_t<Cta_Group> cta_group,
uint32_t taddr,
uint64_t s_desc);
tcgen05.cp.cta_group::2.4x256b
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. code:: cuda
// tcgen05.cp.cta_group.4x256b [taddr], s_desc; // PTX ISA 86, SM_100a, SM_101a
// .cta_group = { .cta_group::1, .cta_group::2 }
template <cuda::ptx::dot_cta_group Cta_Group>
__device__ static inline void tcgen05_cp_4x256b(
cuda::ptx::cta_group_t<Cta_Group> cta_group,
uint32_t taddr,
uint64_t s_desc);
tcgen05.cp.cta_group::1.128x128b
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. code:: cuda
// tcgen05.cp.cta_group.128x128b [taddr], s_desc; // PTX ISA 86, SM_100a, SM_101a
// .cta_group = { .cta_group::1, .cta_group::2 }
template <cuda::ptx::dot_cta_group Cta_Group>
__device__ static inline void tcgen05_cp_128x128b(
cuda::ptx::cta_group_t<Cta_Group> cta_group,
uint32_t taddr,
uint64_t s_desc);
tcgen05.cp.cta_group::2.128x128b
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. code:: cuda
// tcgen05.cp.cta_group.128x128b [taddr], s_desc; // PTX ISA 86, SM_100a, SM_101a
// .cta_group = { .cta_group::1, .cta_group::2 }
template <cuda::ptx::dot_cta_group Cta_Group>
__device__ static inline void tcgen05_cp_128x128b(
cuda::ptx::cta_group_t<Cta_Group> cta_group,
uint32_t taddr,
uint64_t s_desc);
tcgen05.cp.cta_group::1.64x128b.warpx2::02_13
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. code:: cuda
// tcgen05.cp.cta_group.64x128b.warpx2::02_13 [taddr], s_desc; // PTX ISA 86, SM_100a, SM_101a
// .cta_group = { .cta_group::1, .cta_group::2 }
template <cuda::ptx::dot_cta_group Cta_Group>
__device__ static inline void tcgen05_cp_64x128b_warpx2_02_13(
cuda::ptx::cta_group_t<Cta_Group> cta_group,
uint32_t taddr,
uint64_t s_desc);
tcgen05.cp.cta_group::2.64x128b.warpx2::02_13
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. code:: cuda
// tcgen05.cp.cta_group.64x128b.warpx2::02_13 [taddr], s_desc; // PTX ISA 86, SM_100a, SM_101a
// .cta_group = { .cta_group::1, .cta_group::2 }
template <cuda::ptx::dot_cta_group Cta_Group>
__device__ static inline void tcgen05_cp_64x128b_warpx2_02_13(
cuda::ptx::cta_group_t<Cta_Group> cta_group,
uint32_t taddr,
uint64_t s_desc);
tcgen05.cp.cta_group::1.64x128b.warpx2::01_23
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. code:: cuda
// tcgen05.cp.cta_group.64x128b.warpx2::01_23 [taddr], s_desc; // PTX ISA 86, SM_100a, SM_101a
// .cta_group = { .cta_group::1, .cta_group::2 }
template <cuda::ptx::dot_cta_group Cta_Group>
__device__ static inline void tcgen05_cp_64x128b_warpx2_01_23(
cuda::ptx::cta_group_t<Cta_Group> cta_group,
uint32_t taddr,
uint64_t s_desc);
tcgen05.cp.cta_group::2.64x128b.warpx2::01_23
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. code:: cuda
// tcgen05.cp.cta_group.64x128b.warpx2::01_23 [taddr], s_desc; // PTX ISA 86, SM_100a, SM_101a
// .cta_group = { .cta_group::1, .cta_group::2 }
template <cuda::ptx::dot_cta_group Cta_Group>
__device__ static inline void tcgen05_cp_64x128b_warpx2_01_23(
cuda::ptx::cta_group_t<Cta_Group> cta_group,
uint32_t taddr,
uint64_t s_desc);
tcgen05.cp.cta_group::1.32x128b.warpx4
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. code:: cuda
// tcgen05.cp.cta_group.32x128b.warpx4 [taddr], s_desc; // PTX ISA 86, SM_100a, SM_101a
// .cta_group = { .cta_group::1, .cta_group::2 }
template <cuda::ptx::dot_cta_group Cta_Group>
__device__ static inline void tcgen05_cp_32x128b_warpx4(
cuda::ptx::cta_group_t<Cta_Group> cta_group,
uint32_t taddr,
uint64_t s_desc);
tcgen05.cp.cta_group::2.32x128b.warpx4
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. code:: cuda
// tcgen05.cp.cta_group.32x128b.warpx4 [taddr], s_desc; // PTX ISA 86, SM_100a, SM_101a
// .cta_group = { .cta_group::1, .cta_group::2 }
template <cuda::ptx::dot_cta_group Cta_Group>
__device__ static inline void tcgen05_cp_32x128b_warpx4(
cuda::ptx::cta_group_t<Cta_Group> cta_group,
uint32_t taddr,
uint64_t s_desc);
tcgen05.cp.cta_group::1.128x256b.b8x16.b6x16_p32
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. code:: cuda
// tcgen05.cp.cta_group.128x256b.b8x16.b6x16_p32 [taddr], s_desc; // PTX ISA 86, SM_100a, SM_101a
// .cta_group = { .cta_group::1, .cta_group::2 }
template <cuda::ptx::dot_cta_group Cta_Group>
__device__ static inline void tcgen05_cp_128x256b_b8x16_b6x16_p32(
cuda::ptx::cta_group_t<Cta_Group> cta_group,
uint32_t taddr,
uint64_t s_desc);
tcgen05.cp.cta_group::2.128x256b.b8x16.b6x16_p32
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. code:: cuda
// tcgen05.cp.cta_group.128x256b.b8x16.b6x16_p32 [taddr], s_desc; // PTX ISA 86, SM_100a, SM_101a
// .cta_group = { .cta_group::1, .cta_group::2 }
template <cuda::ptx::dot_cta_group Cta_Group>
__device__ static inline void tcgen05_cp_128x256b_b8x16_b6x16_p32(
cuda::ptx::cta_group_t<Cta_Group> cta_group,
uint32_t taddr,
uint64_t s_desc);
tcgen05.cp.cta_group::1.4x256b.b8x16.b6x16_p32
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. code:: cuda
// tcgen05.cp.cta_group.4x256b.b8x16.b6x16_p32 [taddr], s_desc; // PTX ISA 86, SM_100a, SM_101a
// .cta_group = { .cta_group::1, .cta_group::2 }
template <cuda::ptx::dot_cta_group Cta_Group>
__device__ static inline void tcgen05_cp_4x256b_b8x16_b6x16_p32(
cuda::ptx::cta_group_t<Cta_Group> cta_group,
uint32_t taddr,
uint64_t s_desc);
tcgen05.cp.cta_group::2.4x256b.b8x16.b6x16_p32
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. code:: cuda
// tcgen05.cp.cta_group.4x256b.b8x16.b6x16_p32 [taddr], s_desc; // PTX ISA 86, SM_100a, SM_101a
// .cta_group = { .cta_group::1, .cta_group::2 }
template <cuda::ptx::dot_cta_group Cta_Group>
__device__ static inline void tcgen05_cp_4x256b_b8x16_b6x16_p32(
cuda::ptx::cta_group_t<Cta_Group> cta_group,
uint32_t taddr,
uint64_t s_desc);
tcgen05.cp.cta_group::1.128x128b.b8x16.b6x16_p32
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. code:: cuda
// tcgen05.cp.cta_group.128x128b.b8x16.b6x16_p32 [taddr], s_desc; // PTX ISA 86, SM_100a, SM_101a
// .cta_group = { .cta_group::1, .cta_group::2 }
template <cuda::ptx::dot_cta_group Cta_Group>
__device__ static inline void tcgen05_cp_128x128b_b8x16_b6x16_p32(
cuda::ptx::cta_group_t<Cta_Group> cta_group,
uint32_t taddr,
uint64_t s_desc);
tcgen05.cp.cta_group::2.128x128b.b8x16.b6x16_p32
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. code:: cuda
// tcgen05.cp.cta_group.128x128b.b8x16.b6x16_p32 [taddr], s_desc; // PTX ISA 86, SM_100a, SM_101a
// .cta_group = { .cta_group::1, .cta_group::2 }
template <cuda::ptx::dot_cta_group Cta_Group>
__device__ static inline void tcgen05_cp_128x128b_b8x16_b6x16_p32(
cuda::ptx::cta_group_t<Cta_Group> cta_group,
uint32_t taddr,
uint64_t s_desc);
tcgen05.cp.cta_group::1.64x128b.warpx2::02_13.b8x16.b6x16_p32
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. code:: cuda
// tcgen05.cp.cta_group.64x128b.warpx2::02_13.b8x16.b6x16_p32 [taddr], s_desc; // PTX ISA 86, SM_100a, SM_101a
// .cta_group = { .cta_group::1, .cta_group::2 }
template <cuda::ptx::dot_cta_group Cta_Group>
__device__ static inline void tcgen05_cp_64x128b_warpx2_02_13_b8x16_b6x16_p32(
cuda::ptx::cta_group_t<Cta_Group> cta_group,
uint32_t taddr,
uint64_t s_desc);
tcgen05.cp.cta_group::2.64x128b.warpx2::02_13.b8x16.b6x16_p32
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. code:: cuda
// tcgen05.cp.cta_group.64x128b.warpx2::02_13.b8x16.b6x16_p32 [taddr], s_desc; // PTX ISA 86, SM_100a, SM_101a
// .cta_group = { .cta_group::1, .cta_group::2 }
template <cuda::ptx::dot_cta_group Cta_Group>
__device__ static inline void tcgen05_cp_64x128b_warpx2_02_13_b8x16_b6x16_p32(
cuda::ptx::cta_group_t<Cta_Group> cta_group,
uint32_t taddr,
uint64_t s_desc);
tcgen05.cp.cta_group::1.64x128b.warpx2::01_23.b8x16.b6x16_p32
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. code:: cuda
// tcgen05.cp.cta_group.64x128b.warpx2::01_23.b8x16.b6x16_p32 [taddr], s_desc; // PTX ISA 86, SM_100a, SM_101a
// .cta_group = { .cta_group::1, .cta_group::2 }
template <cuda::ptx::dot_cta_group Cta_Group>
__device__ static inline void tcgen05_cp_64x128b_warpx2_01_23_b8x16_b6x16_p32(
cuda::ptx::cta_group_t<Cta_Group> cta_group,
uint32_t taddr,
uint64_t s_desc);
tcgen05.cp.cta_group::2.64x128b.warpx2::01_23.b8x16.b6x16_p32
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. code:: cuda
// tcgen05.cp.cta_group.64x128b.warpx2::01_23.b8x16.b6x16_p32 [taddr], s_desc; // PTX ISA 86, SM_100a, SM_101a
// .cta_group = { .cta_group::1, .cta_group::2 }
template <cuda::ptx::dot_cta_group Cta_Group>
__device__ static inline void tcgen05_cp_64x128b_warpx2_01_23_b8x16_b6x16_p32(
cuda::ptx::cta_group_t<Cta_Group> cta_group,
uint32_t taddr,
uint64_t s_desc);
tcgen05.cp.cta_group::1.32x128b.warpx4.b8x16.b6x16_p32
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. code:: cuda
// tcgen05.cp.cta_group.32x128b.warpx4.b8x16.b6x16_p32 [taddr], s_desc; // PTX ISA 86, SM_100a, SM_101a
// .cta_group = { .cta_group::1, .cta_group::2 }
template <cuda::ptx::dot_cta_group Cta_Group>
__device__ static inline void tcgen05_cp_32x128b_warpx4_b8x16_b6x16_p32(
cuda::ptx::cta_group_t<Cta_Group> cta_group,
uint32_t taddr,
uint64_t s_desc);
tcgen05.cp.cta_group::2.32x128b.warpx4.b8x16.b6x16_p32
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. code:: cuda
// tcgen05.cp.cta_group.32x128b.warpx4.b8x16.b6x16_p32 [taddr], s_desc; // PTX ISA 86, SM_100a, SM_101a
// .cta_group = { .cta_group::1, .cta_group::2 }
template <cuda::ptx::dot_cta_group Cta_Group>
__device__ static inline void tcgen05_cp_32x128b_warpx4_b8x16_b6x16_p32(
cuda::ptx::cta_group_t<Cta_Group> cta_group,
uint32_t taddr,
uint64_t s_desc);
tcgen05.cp.cta_group::1.128x256b.b8x16.b4x16_p64
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. code:: cuda
// tcgen05.cp.cta_group.128x256b.b8x16.b4x16_p64 [taddr], s_desc; // PTX ISA 86, SM_100a, SM_101a
// .cta_group = { .cta_group::1, .cta_group::2 }
template <cuda::ptx::dot_cta_group Cta_Group>
__device__ static inline void tcgen05_cp_128x256b_b8x16_b4x16_p64(
cuda::ptx::cta_group_t<Cta_Group> cta_group,
uint32_t taddr,
uint64_t s_desc);
tcgen05.cp.cta_group::2.128x256b.b8x16.b4x16_p64
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. code:: cuda
// tcgen05.cp.cta_group.128x256b.b8x16.b4x16_p64 [taddr], s_desc; // PTX ISA 86, SM_100a, SM_101a
// .cta_group = { .cta_group::1, .cta_group::2 }
template <cuda::ptx::dot_cta_group Cta_Group>
__device__ static inline void tcgen05_cp_128x256b_b8x16_b4x16_p64(
cuda::ptx::cta_group_t<Cta_Group> cta_group,
uint32_t taddr,
uint64_t s_desc);
tcgen05.cp.cta_group::1.4x256b.b8x16.b4x16_p64
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. code:: cuda
// tcgen05.cp.cta_group.4x256b.b8x16.b4x16_p64 [taddr], s_desc; // PTX ISA 86, SM_100a, SM_101a
// .cta_group = { .cta_group::1, .cta_group::2 }
template <cuda::ptx::dot_cta_group Cta_Group>
__device__ static inline void tcgen05_cp_4x256b_b8x16_b4x16_p64(
cuda::ptx::cta_group_t<Cta_Group> cta_group,
uint32_t taddr,
uint64_t s_desc);
tcgen05.cp.cta_group::2.4x256b.b8x16.b4x16_p64
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. code:: cuda
// tcgen05.cp.cta_group.4x256b.b8x16.b4x16_p64 [taddr], s_desc; // PTX ISA 86, SM_100a, SM_101a
// .cta_group = { .cta_group::1, .cta_group::2 }
template <cuda::ptx::dot_cta_group Cta_Group>
__device__ static inline void tcgen05_cp_4x256b_b8x16_b4x16_p64(
cuda::ptx::cta_group_t<Cta_Group> cta_group,
uint32_t taddr,
uint64_t s_desc);
tcgen05.cp.cta_group::1.128x128b.b8x16.b4x16_p64
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. code:: cuda
// tcgen05.cp.cta_group.128x128b.b8x16.b4x16_p64 [taddr], s_desc; // PTX ISA 86, SM_100a, SM_101a
// .cta_group = { .cta_group::1, .cta_group::2 }
template <cuda::ptx::dot_cta_group Cta_Group>
__device__ static inline void tcgen05_cp_128x128b_b8x16_b4x16_p64(
cuda::ptx::cta_group_t<Cta_Group> cta_group,
uint32_t taddr,
uint64_t s_desc);
tcgen05.cp.cta_group::2.128x128b.b8x16.b4x16_p64
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. code:: cuda
// tcgen05.cp.cta_group.128x128b.b8x16.b4x16_p64 [taddr], s_desc; // PTX ISA 86, SM_100a, SM_101a
// .cta_group = { .cta_group::1, .cta_group::2 }
template <cuda::ptx::dot_cta_group Cta_Group>
__device__ static inline void tcgen05_cp_128x128b_b8x16_b4x16_p64(
cuda::ptx::cta_group_t<Cta_Group> cta_group,
uint32_t taddr,
uint64_t s_desc);
tcgen05.cp.cta_group::1.64x128b.warpx2::02_13.b8x16.b4x16_p64
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. code:: cuda
// tcgen05.cp.cta_group.64x128b.warpx2::02_13.b8x16.b4x16_p64 [taddr], s_desc; // PTX ISA 86, SM_100a, SM_101a
// .cta_group = { .cta_group::1, .cta_group::2 }
template <cuda::ptx::dot_cta_group Cta_Group>
__device__ static inline void tcgen05_cp_64x128b_warpx2_02_13_b8x16_b4x16_p64(
cuda::ptx::cta_group_t<Cta_Group> cta_group,
uint32_t taddr,
uint64_t s_desc);
tcgen05.cp.cta_group::2.64x128b.warpx2::02_13.b8x16.b4x16_p64
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. code:: cuda
// tcgen05.cp.cta_group.64x128b.warpx2::02_13.b8x16.b4x16_p64 [taddr], s_desc; // PTX ISA 86, SM_100a, SM_101a
// .cta_group = { .cta_group::1, .cta_group::2 }
template <cuda::ptx::dot_cta_group Cta_Group>
__device__ static inline void tcgen05_cp_64x128b_warpx2_02_13_b8x16_b4x16_p64(
cuda::ptx::cta_group_t<Cta_Group> cta_group,
uint32_t taddr,
uint64_t s_desc);
tcgen05.cp.cta_group::1.64x128b.warpx2::01_23.b8x16.b4x16_p64
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. code:: cuda
// tcgen05.cp.cta_group.64x128b.warpx2::01_23.b8x16.b4x16_p64 [taddr], s_desc; // PTX ISA 86, SM_100a, SM_101a
// .cta_group = { .cta_group::1, .cta_group::2 }
template <cuda::ptx::dot_cta_group Cta_Group>
__device__ static inline void tcgen05_cp_64x128b_warpx2_01_23_b8x16_b4x16_p64(
cuda::ptx::cta_group_t<Cta_Group> cta_group,
uint32_t taddr,
uint64_t s_desc);
tcgen05.cp.cta_group::2.64x128b.warpx2::01_23.b8x16.b4x16_p64
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. code:: cuda
// tcgen05.cp.cta_group.64x128b.warpx2::01_23.b8x16.b4x16_p64 [taddr], s_desc; // PTX ISA 86, SM_100a, SM_101a
// .cta_group = { .cta_group::1, .cta_group::2 }
template <cuda::ptx::dot_cta_group Cta_Group>
__device__ static inline void tcgen05_cp_64x128b_warpx2_01_23_b8x16_b4x16_p64(
cuda::ptx::cta_group_t<Cta_Group> cta_group,
uint32_t taddr,
uint64_t s_desc);
tcgen05.cp.cta_group::1.32x128b.warpx4.b8x16.b4x16_p64
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. code:: cuda
// tcgen05.cp.cta_group.32x128b.warpx4.b8x16.b4x16_p64 [taddr], s_desc; // PTX ISA 86, SM_100a, SM_101a
// .cta_group = { .cta_group::1, .cta_group::2 }
template <cuda::ptx::dot_cta_group Cta_Group>
__device__ static inline void tcgen05_cp_32x128b_warpx4_b8x16_b4x16_p64(
cuda::ptx::cta_group_t<Cta_Group> cta_group,
uint32_t taddr,
uint64_t s_desc);
tcgen05.cp.cta_group::2.32x128b.warpx4.b8x16.b4x16_p64
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. code:: cuda
// tcgen05.cp.cta_group.32x128b.warpx4.b8x16.b4x16_p64 [taddr], s_desc; // PTX ISA 86, SM_100a, SM_101a
// .cta_group = { .cta_group::1, .cta_group::2 }
template <cuda::ptx::dot_cta_group Cta_Group>
__device__ static inline void tcgen05_cp_32x128b_warpx4_b8x16_b4x16_p64(
cuda::ptx::cta_group_t<Cta_Group> cta_group,
uint32_t taddr,
uint64_t s_desc);
Reference in new issue View Git Blame Copy Permalink