wangtao
/
OpenVML
forked from OSchip/OpenVML
0
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Commit Graph

  • ef53358569 Merge pull request #31 from martin-frbg/master master Zhang Xianyi 2016-12-18 14:49:32 +0800
  • 0089d5ca01 Add detection of Intel Skylake and Kaby Lake Martin Kroeker 2016-12-17 12:32:31 +0100
  • 2cb7cc58ea Merge pull request #30 from xinhuang/sqr Zhang Xianyi 2016-12-06 16:19:02 +0800
  • 5ef9a2fdc9 implement v?Sqr as y =__mm256_mul_pd(a, a) xinhuang 2016-09-10 16:59:11 +0800
  • e31e919a96 generic vsSqr xinhuang 2016-09-10 15:09:08 +0800
  • 4c9919f64b Update ctest. Zhang Xianyi 2016-02-11 14:09:05 -0500
  • d9cc41bd76 [av skip] Update travis ci. Zhang Xianyi 2016-02-12 02:46:16 +0800
  • 6b16b4c495 Update travis ci to trusty image. Zhang Xianyi 2016-02-12 02:18:09 +0800
  • 6a9b65268a Merge branch 'master' of github.com:xianyi/OpenVML Zhang Xianyi 2016-02-11 08:21:04 +0800
  • 597da56ff9 Update ctest.h from github.com:xianyi/ctest.git Zhang Xianyi 2016-02-11 08:20:45 +0800
  • 2ce469bceb Merge pull request #29 from liyancas/master Zhang Xianyi 2015-09-09 11:23:18 -0500
  • e1cfeac534 Add TIME_CPE option for timer function using cycles Yan Li 2015-09-10 00:00:58 +0800
  • aa6f9b0652 Merge branch 'liyancas-master' Fix #28 Zhang Xianyi 2015-08-31 10:27:32 -0500
  • 5a1c20b405 Enable avx kernels for pow, powx, exp, ln, tanh, sin, cos. Zhang Xianyi 2015-08-31 10:24:29 -0500
  • 85ca551449 Change simd_zero to simd_zeros in the arm kernels. Yan Li 2015-08-31 21:07:35 +0800
  • 323dc21f19 Clean the code and add sin, cos and powx. Yan Li 2015-08-31 20:47:13 +0800
  • c26f09972f Use sin, cos for vsincos. Zhang Xianyi 2015-08-27 05:14:34 +0800
  • a147598f8b Add real number tan, asin, acos, atan, atan2 naive implementation. Refs #4. Zhang Xianyi 2015-08-26 12:05:24 -0500
  • 792a6ea601 Fixed sincos bug on Windows. Zhang Xianyi 2015-08-25 23:18:56 -0500
  • 2f54330e29 Add real number sin, cos, sincos. Refs #4. Zhang Xianyi 2015-08-25 23:10:15 -0500
  • b337e1fee7 Add real number Expm1. Refs #2. Zhang Xianyi 2015-08-24 22:00:00 -0500
  • 4a1f8f7eb1 Add Pow2o3 and Pow3o2 by calling Powx. Zhang Xianyi 2015-08-24 21:30:57 -0500
  • 716119b133 Add real number Powx. Zhang Xianyi 2015-08-24 20:59:37 -0500
  • 727078e44a Add const to input vector size n. Zhang Xianyi 2015-08-24 20:36:22 -0500
  • c720f6d39f Add COMPILER_MSVC at openvml_config.h. Zhang Xianyi 2015-08-23 00:06:33 -0500
  • e436e99bdd [av skip] Update readme. Zhang Xianyi 2015-08-20 15:54:33 -0500
  • 6378e465b6 Use Visual Studio 12 2013 on appveyor. Zhang Xianyi 2015-08-20 15:32:19 -0500
  • e743caa24e Fix a bug in appveyor.yml. Zhang Xianyi 2015-08-20 15:29:08 -0500
  • d7883d9308 Add AppVeyor Windows CI. Zhang Xianyi 2015-08-20 15:26:22 -0500
  • cc914f7751 Add travis badge. Zhang Xianyi 2015-08-19 22:53:34 -0500
  • 143be4c889 Add notification of travis. Zhang Xianyi 2015-08-19 22:37:56 -0500
  • d6041ef122 Merge branch 'master' of github.com:xianyi/OpenVML Zhang Xianyi 2015-08-19 22:32:24 -0500
  • d0e9be2ef0 Use gcc-4.8 on travis-ci. Zhang Xianyi 2015-08-19 22:32:12 -0500
  • 1af867960e Merge pull request #25 from gitter-badger/gitter-badge Zhang Xianyi 2015-08-19 22:25:53 -0500
  • 5a71c19ddb Added Gitter badge The Gitter Badger 2015-08-20 03:21:24 +0000
  • 967cc772c1 Fix travis-ci avx2 bug. Zhang Xianyi 2015-08-19 22:16:36 -0500
  • 6e8d6c2a2a Build sandybridge and haswell kernels on travis. Zhang Xianyi 2015-08-20 05:36:32 +0800
  • 19f1ff74a1 Use container on travis. Zhang Xianyi 2015-08-20 05:18:35 +0800
  • ee01a6c4f8 Only link rt on Linux. Zhang Xianyi 2015-08-20 04:46:48 +0800
  • 45c2c1f88a Modified test output. Add -lrt. Zhang Xianyi 2015-08-20 04:33:50 +0800
  • 52b11a9e81 Return the numboer of failures. Zhang Xianyi 2015-08-20 03:33:26 +0800
  • bbb748e255 Install cmake manully on travis. Zhang Xianyi 2015-08-20 03:04:35 +0800
  • 40357af529 Test install cmake on travis. Zhang Xianyi 2015-08-20 01:09:10 +0800
  • 2627ce9f8f Update cmake travis ppa. Zhang Xianyi 2015-08-20 01:04:45 +0800
  • 73b0170c72 Add required cmake 2.8.12. Zhang Xianyi 2015-08-20 00:49:50 +0800
  • c4b3eb41b9 Test cmake version. Zhang Xianyi 2015-08-20 00:38:46 +0800
  • df9a49903d Install the new cmake on travis. Zhang Xianyi 2015-08-19 11:10:30 -0500
  • 0e2bfe2114 Enable Travis CI. Zhang Xianyi 2015-08-19 10:59:12 -0500
  • ab505c340c Merge pull request #24 from datalayout/master Zhang Xianyi 2015-08-18 10:24:35 -0500
  • 6750b95915 Fix a bug in the vml_test.h Yan Li 2015-08-15 21:49:37 +0800
  • a4c8bb43bb Using relative error for accurary testing and fix bugs in neon kernels. Yan Li 2015-08-15 21:44:10 +0800
  • 20e53089ed Update doc for test. Zhang Xianyi 2015-08-14 21:18:07 +0000
  • f01323cada Enable floor neon version for ARM Cortex-A15. Zhang Xianyi 2015-08-14 20:56:27 +0000
  • 845518ee64 Refs #7. Add Floor function. Zhang Xianyi 2015-08-14 20:48:06 +0000
  • fc91a45073 Update doc Zhang Xianyi 2015-08-14 20:09:32 +0000
  • 2e7f3f0b95 Disable OpenMP at kernel code. Deleted unused header. Zhang Xianyi 2015-08-14 20:02:11 +0000
  • 265d609153 Fixed the build bug for x86_64. Zhang Xianyi 2015-08-14 14:44:06 -0500
  • 8834bc3aca Update ignore files for cmake Update ignore files for CMake. Zhang Xianyi 2015-08-14 11:44:25 -0500
  • 6c18ca40aa Deleted unused files. Zhang Xianyi 2015-08-14 11:39:04 -0500
  • 1f566bf881 Merge pull request #22 from liyancas/master Yan Li 2015-08-13 21:41:53 +0800
  • 3c9d54145d clean the code. Yan Li 2015-08-13 21:40:04 +0800
  • cb54f20a68 Merge pull request #21 from liyancas/master Yan Li 2015-08-13 21:04:04 +0800
  • 4b477f7cde Add the boundary check for exp function. Yan Li 2015-08-13 20:59:56 +0800
  • ae04cfa9ba Merge pull request #20 from liyancas/master Yan Li 2015-08-13 15:45:32 +0800
  • d8102f9493 delete the useless files. Yan Li 2015-08-13 15:30:03 +0800
  • 1ec8e42496 Add performance results about neon fucntions to the test dir. Yan Li 2015-08-13 15:22:10 +0800
  • 2d56703d0f Using arm neon simd instructions to optimize tanh, exp, pow and log functions. Yan Li 2015-08-13 15:07:51 +0800
  • c5ed13f948 Merge pull request #19 from xinhuang/ln Zhang Xianyi 2015-05-26 14:29:08 -0500
  • e175968d2e AVX implementation of (s/d)log1p Xin Huang 2015-05-17 17:34:39 +0800
  • 9661ef6396 Merge pull request #18 from xinhuang/log10 Zhang Xianyi 2015-05-15 14:33:43 -0500
  • fce1bcfe57 AVX SIMD implementation for ln Xin Huang 2015-05-15 20:18:34 +0800
  • 25a76515d6 fix configuration for arm/Kernel_generic.txt Xin Huang 2015-05-15 19:55:07 +0800
  • 0f0992667c avx implementation for (s/d)log10 Xin Huang 2015-05-15 18:32:36 +0800
  • 13278d3fef Change the compiler option for ARM. Zhang Xianyi 2015-05-04 19:41:36 +0000
  • 0ce95b55ec Include avx_mathfun.h from http://software-lisc.fbk.eu/avx_mathfun/ Zhang Xianyi 2015-05-01 16:44:46 -0500
  • b9a4068eef Add ARM and AARCH64 config. Zhang Xianyi 2015-05-01 20:24:07 +0000
  • 2ed622c582 Use intrinsic for x86_64 kernels. Enable detecting the CPU core on Windows. Zhang Xianyi 2015-05-02 00:26:49 +0800
  • 66df69e11d Enable Release by default. Zhang Xianyi 2015-05-01 05:46:04 +0800
  • 6a7fa5d450 Fix the test compiling warning. Update ctest.h. Zhang Xianyi 2015-04-30 15:14:36 -0500
  • 5bb6623f14 Enable export macro for reference. Zhang Xianyi 2015-04-30 15:08:23 -0500
  • 3974edef2e Temp to use low precise timer on windows. Zhang Xianyi 2015-04-27 13:39:21 -0500
  • 98d1a59f95 Modify reference impl for MSVC. Zhang Xianyi 2015-04-27 13:20:34 -0500
  • 210cdd3dcb Use ctest.h from https://github.com/xianyi/ctest Zhang Xianyi 2015-04-27 13:08:32 -0500
  • 18710d7b3c Fix dll export bug on MSVC. Turnoff building static library and test on MSVC. Zhang Xianyi 2015-04-23 14:39:00 -0500
  • 758d327522 Only build generic kernel with MSVC. Zhang Xianyi 2015-04-23 14:38:00 -0500
  • 2fe4f9a14b Add detecting 32 or 64 bit. Try to build the library with MSVC. Fix cpuid issue with MSVC. Zhang Xianyi 2015-04-23 12:52:35 -0500
  • a4d6de264d Add openvml_get_config function. Zhang Xianyi 2015-04-23 11:03:35 -0500
  • b0843f728d Add avx kernel for vsub. Zhang Xianyi 2015-04-22 13:02:12 -0500
  • 5008870893 Add CPU auto-detecting feature. Zhang Xianyi 2015-04-21 14:26:39 -0500
  • 70731aa312 Add Sandy Bridge kernel config file. Zhang Xianyi 2015-04-21 14:07:39 -0500
  • 6e325f5a9e Add x86_64 haswell target. Add avx kernel for vadd. Zhang Xianyi 2015-04-21 12:23:56 -0500
  • e073130e66 Change the display of time. Zhang Xianyi 2015-04-21 11:22:02 -0500
  • 15c7a5a3aa Merge branch 'master' of github.com:xianyi/OpenVML Zhang Xianyi 2015-04-20 23:34:28 -0500
  • 28d864ed2d Change the input parameter name. Zhang Xianyi 2015-04-20 23:34:19 -0500
  • 0d91994225 Fix the build warning on OSX. Zhang Xianyi 2015-04-17 00:52:06 -0500
  • 4f16144857 Add test for real number exp and tanh functions. Zhang Xianyi 2015-04-17 08:48:59 -0500
  • d406a6df62 Add test for real number pow functions. Zhang Xianyi 2015-04-17 08:31:35 -0500
  • c045c22d13 Add license header. Zhang Xianyi 2015-04-17 08:02:34 -0500
  • 840088a6b6 Add vsub test. Zhang Xianyi 2015-04-17 08:01:30 -0500
  • 26e52f4bc4 Add test flags. Zhang Xianyi 2015-04-17 07:53:43 -0500