From 490b1e45ce16ca91d1c6a1e644f844179b5410eb Mon Sep 17 00:00:00 2001 From: Developer-Ecosystem-Engineering <65677710+Developer-Ecosystem-Engineering@users.noreply.github.com> Date: Tue, 23 Aug 2022 12:39:37 -0700 Subject: ENH: Add SIMD versions of negative NumPy already has SSE2 versions of `negative`. Changes here convert that to universal intrinsics so other architectures can benefit. Previously there was no unroll and SIMD was only used in contiguous cases. We're now unrolling 4x/2x depending on whether destination is contiguous. x86 doesn't perform as well for non-contiguous cases here, so we leave previous implementation / fall back to scalar. Additionally, we've added SIMD versions for ints. --- numpy/core/setup.py | 1 + 1 file changed, 1 insertion(+) (limited to 'numpy/core/setup.py') diff --git a/numpy/core/setup.py b/numpy/core/setup.py index 4001f7ab0..3b34b3865 100644 --- a/numpy/core/setup.py +++ b/numpy/core/setup.py @@ -1005,6 +1005,7 @@ def configuration(parent_package='',top_path=None): join('src', 'umath', 'loops.h.src'), join('src', 'umath', 'loops_utils.h.src'), join('src', 'umath', 'loops.c.src'), + join('src', 'umath', 'loops_unary.dispatch.c.src'), join('src', 'umath', 'loops_unary_fp.dispatch.c.src'), join('src', 'umath', 'loops_arithm_fp.dispatch.c.src'), join('src', 'umath', 'loops_arithmetic.dispatch.c.src'), -- cgit v1.2.1