8000 ENH: Use AVX for float32 implementation of np.sin & np.cos by r-devulap · Pull Request #13368 · numpy/numpy · GitHub
[go: up one dir, main page]
Skip to content

ENH: Use AVX for float32 implementation of np.sin & np.cos #13368

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
merged 11 commits into from
Aug 18, 2019
Merged

ENH: Use AVX for float32 implementation of np.sin & np.cos #13368

Changes from 1 commit
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
bd2c82b
ENH: Use AVX for float32 implementation of np.sin & np.cos
Mar 20, 2019
e50e725
BUG: fixing NAN handling and adding tests for sin/cos
May 1, 2019
d56fbfd
BUG: sin and cos cast float16 to float32
May 7, 2019
bca9628
TEST: adding tests to validate AVX sin/cos implementation
May 20, 2019
9cae09c
BUG: use strides and process strided arrays using AVX
May 22, 2019
cd9f1a8
BUG: AVX2 impl of sin/cos requires an FMA
May 22, 2019
8589d48
TEST: Rounding max tolerable ulp error to an int
May 23, 2019
0f78154
BUG: eliminate unsed variables warning in cpuid
May 23, 2019
44d14ab
MAINT: using an enum to switch between sin/cos
May 29, 2019
6f34f5f
TEST: improving test coverage for sin/cos for input > 117435.992f
May 30, 2019
457b3e6
BUG: rename avx2_scalef_ps to fma_scalef_ps
Aug 3, 2019
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
BUG: rename avx2_scalef_ps to fma_scalef_ps
  • Loading branch information
Raghuveer Devulapalli committed Aug 3, 2019
commit 457b3e6979d84677b860cf1a7c22d1190ba9d895
2 changes: 1 addition & 1 deletion 2 numpy/core/src/umath/simd.inc.src
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1252,7 +1252,7 @@ fma_get_mantissa(__m256 x)
}

static NPY_INLINE NPY_GCC_OPT_3 NPY_GCC_TARGET_AVX2 __m256
avx2_scalef_ps(__m256 poly, __m256 quadrant)
fma_scalef_ps(__m256 poly, __m256 quadrant)
{
/*
* Handle denormals (which occur when quadrant <= -125):
Expand Down
0