frozenleaves/pytorch
1
0
Fork 0
mirror of https://github.com/pytorch/pytorch.git synced 2025-10-20 21:14:14 +08:00
Code Issues Packages Projects Releases Wiki Activity
Files
3a110c9bb209ccd690986d1593b44d261c1174a5
pytorch/docs/source/xpu.md
Yu, Guangye 3a110c9bb2 Add a new API torch.xpu.is_tf32_supported for Intel GPU (#163141) 
# Motivation
Aligned with other backends, this PR introduces a new API `torch.xpu.is_tf32_supported`, which should be used before `torch.backends.mkldnn.allow_tf32=True` or provide hardware capability information to the Triton

# Additional Context
On Intel Xe architecture and newer, TF32 operations can be accelerated through DPAS (Dot Product Accumulate Systolic) instructions. Therefore, TF32 support can be determined by checking whether the device supports subgroup matrix multiply-accumulate operations.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/163141
Approved by: https://github.com/EikanWang
2025-10-12 12:11:57 +00:00

1.5 KiB
Raw Blame History

torch.xpu

.. automodule:: torch.xpu

.. currentmodule:: torch.xpu

.. autosummary::
    :toctree: generated
    :nosignatures:

    StreamContext
    can_device_access_peer
    current_device
    current_stream
    device
    device_count
    device_of
    get_arch_list
    get_device_capability
    get_device_name
    get_device_properties
    get_gencode_flags
    get_stream_from_external
    init
    is_available
    is_bf16_supported
    is_initialized
    is_tf32_supported
    set_device
    set_stream
    stream
    synchronize

Random Number Generator

.. autosummary::
    :toctree: generated
    :nosignatures:

    get_rng_state
    get_rng_state_all
    initial_seed
    manual_seed
    manual_seed_all
    seed
    seed_all
    set_rng_state
    set_rng_state_all

Streams and events

.. autosummary::
    :toctree: generated
    :nosignatures:

    Event
    Stream

.. automodule:: torch.xpu.memory

.. currentmodule:: torch.xpu.memory

Memory management

.. autosummary::
    :toctree: generated
    :nosignatures:

     empty_cache
     max_memory_allocated
     max_memory_reserved
     mem_get_info
     memory_allocated
     memory_reserved
     memory_stats
     memory_stats_as_nested_dict
     reset_accumulated_memory_stats
     reset_peak_memory_stats

.. toctree::
    :hidden:

    xpu.aliases.md