Skip to content

[NFC][SYCL] Speed up slow aspects by caching #18603

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 2 commits into
base: sycl
Choose a base branch
from
Open

[NFC][SYCL] Speed up slow aspects by caching #18603

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
3658da7
[NFC][SYCL] Speed up slow aspects by caching
aelovikov-intel May 21, 2025
d5cc520
Merge branch 'intel:sycl' into more-aspects-caching
aelovikov-intel May 23, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
33 changes: 30 additions & 3 deletions sycl/source/detail/device_impl.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2217,12 +2217,39 @@ class device_impl : public std::enable_shared_from_this<device_impl> {
mutable JointCache<
UREagerCache<UR_DEVICE_INFO_TYPE, UR_DEVICE_INFO_USE_NATIVE_ASSERT,
UR_DEVICE_INFO_EXTENSIONS>, //
URCallOnceCache<UR_DEVICE_INFO_NAME>, //
EagerCache<InfoInitializer>, //
URCallOnceCache<UR_DEVICE_INFO_NAME,
// USM:
UR_DEVICE_INFO_USM_DEVICE_SUPPORT,
UR_DEVICE_INFO_USM_HOST_SUPPORT,
UR_DEVICE_INFO_USM_SINGLE_SHARED_SUPPORT,
UR_DEVICE_INFO_USM_CROSS_SHARED_SUPPORT,
UR_DEVICE_INFO_USM_SYSTEM_SHARED_SUPPORT,
//
UR_DEVICE_INFO_ATOMIC_64>, //
EagerCache<InfoInitializer>, //
CallOnceCache<InfoInitializer,
ext::oneapi::experimental::info::device::architecture>, //
AspectCache<EagerCache, aspect::fp16, aspect::fp64,
aspect::int64_base_atomics, aspect::int64_extended_atomics>>
aspect::int64_base_atomics, aspect::int64_extended_atomics,
aspect::ext_oneapi_atomic16>,
AspectCache<
CallOnceCache,
// Slow, >100ns (for baseline cached ~30..40ns):
aspect::ext_intel_pci_address, aspect::ext_intel_gpu_eu_count,
aspect::ext_intel_free_memory, aspect::ext_intel_fan_speed,
aspect::ext_intel_power_limits,
// medium-slow, 60-90ns (for baseline cached ~30..40ns):
aspect::ext_intel_gpu_eu_simd_width, aspect::ext_intel_gpu_slices,
aspect::ext_intel_gpu_subslices_per_slice,
aspect::ext_intel_gpu_eu_count_per_subslice,
aspect::ext_intel_device_info_uuid,
aspect::ext_intel_gpu_hw_threads_per_eu,
aspect::ext_intel_memory_clock_rate,
aspect::ext_intel_memory_bus_width,
aspect::ext_oneapi_bindless_images,
aspect::ext_oneapi_bindless_images_1d_usm,
aspect::ext_oneapi_bindless_images_2d_usm,
aspect::ext_oneapi_is_composite, aspect::ext_oneapi_is_component>>
MCache;

}; // class device_impl
Expand Down