Skip to content

Elementwise functions tuning #1889

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

Merged
ndgrigorian merged 13 commits into from
Nov 22, 2024
Merged

Elementwise functions tuning #1889

Changes from 1 commit
Commits
Show all changes
13 commits
Select commit Hold shift + click to select a range
870daa1
Add UL suffix literal integral value
oleksandr-pavlyk Oct 21, 2024
02a7c5a
Do not use sg.get_local_range
oleksandr-pavlyk Oct 21, 2024
19837bf
Fix for test failure on AMD CPU.
oleksandr-pavlyk Oct 28, 2024
6748a18
More specializations for hyperparameters of add_contig_impl
oleksandr-pavlyk Nov 12, 2024
040af7a
cabs_impl function changed to use select over branching
oleksandr-pavlyk Nov 12, 2024
840ac69
Add changelog entry for tuning of elementwise functions
oleksandr-pavlyk Nov 12, 2024
281cb7b
Corrected text in the license/description header
oleksandr-pavlyk Nov 12, 2024
041f528
Introduce SYCL utilities sub_group_load/sub_group_store
oleksandr-pavlyk Nov 18, 2024
7d22eac
Replace sg.load/sg.store with sub_group_load/sub_group_store utilities
oleksandr-pavlyk Nov 18, 2024
8809be2
Replaced missed instance of sg.store with sub_group_store
oleksandr-pavlyk Nov 18, 2024
57065ff
Define USE_GROUP_LOAD_STORE variable
oleksandr-pavlyk Nov 18, 2024
2531261
Bump minimal version of __INTEL_LLVM_COMPILER needed to enable group_…
oleksandr-pavlyk Nov 19, 2024
88c3e1a
Do not use group_load/group_store with 2025.1.0 just yet
oleksandr-pavlyk Nov 21, 2024
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
Prev Previous commit
Next Next commit
Corrected text in the license/description header
  • Loading branch information
@oleksandr-pavlyk
oleksandr-pavlyk committed Nov 21, 2024
commit 281cb7b9fc5c8a84213f07adc8903c6302fac0de
7 changes: 3 additions & 4 deletions dpctl/tensor/libtensor/include/kernels/elementwise_functions/vec_size_util.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,4 @@
//=== tanh.hpp - Unary function TANH ------
//*-C++-*--/===//
//=== vec_size_utils.hpp - -------/ /*-C++-*--/===//
//
// Data Parallel Control (dpctl)
//
Expand All @@ -20,8 +19,8 @@
//===---------------------------------------------------------------------===//
///
/// \file
/// This file defines utilities for dispatching elementwise dedicated kernels
// for contiguous inputs.
/// This file defines utilities for selection of hyperparameters for kernels
/// implementing unary and binary elementwise functions for contiguous inputs
//===---------------------------------------------------------------------===//

#pragma once
Expand Down