xinhuang
|
5ef9a2fdc9
|
implement v?Sqr as y =__mm256_mul_pd(a, a)
|
2016-09-13 20:29:31 +08:00 |
|
xinhuang
|
e31e919a96
|
generic vsSqr
|
2016-09-10 15:09:08 +08:00 |
|
Zhang Xianyi
|
5a1c20b405
|
Enable avx kernels for pow, powx, exp, ln, tanh, sin, cos.
Fix MSVC compiling bug.
|
2015-08-31 10:24:29 -05:00 |
|
Zhang Xianyi
|
a147598f8b
|
Add real number tan, asin, acos, atan, atan2 naive implementation. Refs #4.
|
2015-08-26 12:05:24 -05:00 |
|
Zhang Xianyi
|
2f54330e29
|
Add real number sin, cos, sincos. Refs #4.
|
2015-08-25 23:10:15 -05:00 |
|
Zhang Xianyi
|
b337e1fee7
|
Add real number Expm1. Refs #2.
|
2015-08-24 22:00:00 -05:00 |
|
Zhang Xianyi
|
4a1f8f7eb1
|
Add Pow2o3 and Pow3o2 by calling Powx.
|
2015-08-24 21:30:57 -05:00 |
|
Zhang Xianyi
|
716119b133
|
Add real number Powx.
|
2015-08-24 20:59:37 -05:00 |
|
Zhang Xianyi
|
727078e44a
|
Add const to input vector size n.
|
2015-08-24 20:36:22 -05:00 |
|
Zhang Xianyi
|
c720f6d39f
|
Add COMPILER_MSVC at openvml_config.h.
|
2015-08-23 00:06:33 -05:00 |
|
Zhang Xianyi
|
845518ee64
|
Refs #7. Add Floor function.
|
2015-08-14 20:48:06 +00:00 |
|
Zhang Xianyi
|
2e7f3f0b95
|
Disable OpenMP at kernel code. Deleted unused header.
|
2015-08-14 20:02:11 +00:00 |
|
Zhang Xianyi
|
6c18ca40aa
|
Deleted unused files.
|
2015-08-14 11:39:04 -05:00 |
|
Yan Li
|
2d56703d0f
|
Using arm neon simd instructions to optimize tanh, exp, pow and log functions.
|
2015-08-13 15:07:51 +08:00 |
|
Xin Huang
|
e175968d2e
|
AVX implementation of (s/d)log1p
|
2015-05-17 17:35:55 +08:00 |
|
Xin Huang
|
fce1bcfe57
|
AVX SIMD implementation for ln
|
2015-05-15 20:18:34 +08:00 |
|
Xin Huang
|
0f0992667c
|
avx implementation for (s/d)log10
|
2015-05-15 19:54:45 +08:00 |
|
Zhang Xianyi
|
2fe4f9a14b
|
Add detecting 32 or 64 bit.
Try to build the library with MSVC. Fix cpuid issue with MSVC.
|
2015-04-23 12:52:35 -05:00 |
|
Zhang Xianyi
|
a4d6de264d
|
Add openvml_get_config function.
|
2015-04-23 11:03:35 -05:00 |
|
Zhang Xianyi
|
d406a6df62
|
Add test for real number pow functions.
|
2015-04-17 08:31:35 -05:00 |
|
Zhang Xianyi
|
2ac453aeba
|
Add basic performance and correct test.
|
2015-04-17 00:25:33 -05:00 |
|
Zhang Xianyi
|
fd711810d7
|
Add tanh for real numbers.
|
2015-01-08 14:56:38 +08:00 |
|
Zhang Xianyi
|
40d5f98efc
|
Add exp for real numbers.
|
2015-01-08 14:48:21 +08:00 |
|
Zhang Xianyi
|
90e9c3f456
|
Add pow for real numbers.
|
2015-01-08 14:39:52 +08:00 |
|
Zhang Xianyi
|
f077906fbc
|
Add fake smp server.
|
2015-01-08 14:24:26 +08:00 |
|
Zhang Xianyi
|
36bd1b9d8b
|
redefine kernel interface.
|
2015-01-08 11:38:50 +08:00 |
|
Zhang Xianyi
|
ce814b9c26
|
add and sub for complex number.
|
2015-01-08 01:41:25 +08:00 |
|
Zhang Xianyi
|
6d2e036873
|
BSD-2 Clause.
|
2015-01-08 01:00:17 +08:00 |
|
Zhang Xianyi
|
ed26fc047c
|
rewrite add and sub for generic.
|
2015-01-07 17:35:37 +08:00 |
|
Zhang Xianyi
|
15580f4a86
|
Add cmake, add, sub interface.
|
2015-01-06 22:05:39 +08:00 |