Commit message (Collapse) | Author | Age | |
---|---|---|---|
* | fix warning | 2019-01-09 | |
| | |||
* | bug #1652: implements a much more accurate version of vectorized sin/cos. ↵ | 2019-01-09 | |
| | | | | | | | This new version achieve same speed for SSE/AVX, and is slightly faster with FMA. Guarantees are as follows: - no FMA: 1ULP up to 3pi, 2ULP up to sin(25966) and cos(18838), fallback to std::sin/cos for larger inputs - FMA: 1ULP up to sin(117435.992) and cos(71476.0625), fallback to std::sin/cos for larger inputs | ||
* | Implement a faster fix for sin/cos of large entries that also correctly ↵ | 2018-12-23 | |
| | | | | handle INF input. | ||
* | Make sure that psin/pcos return number in [-1,1] for large inputs (though ↵ | 2018-12-23 | |
| | | | | sin/cos on large entries is quite useless because it's inaccurate) | ||
* | Fix plog(+INF): it returned ~87 instead of +INF | 2018-12-23 | |
| | |||
* | bug #1615: slightly increase the default unrolling limit to compensate for ↵ | 2018-12-13 | |
| | | | | | | | changeset 101ea26f5e18919972b321b5f7e3ef4e07be3fd6 . This solves a performance regression with clang and 3x3 matrix products. | ||
* | Extend the generic psin_float code to handle cosine and make SSE and AVX use ↵ | 2018-11-30 | |
| | | | | it (-> this adds pcos for AVX) | ||
* | bug #1631: fix compilation with ARM NEON and clang, and cleanup the weird ↵ | 2018-11-27 | |
| | | | | pshiftright_and_cast and pcast_and_shiftleft functions. | ||
* | Update pshiftleft to pass the shift as a true compile-time integer. | 2018-11-27 | |
| | |||
* | Unify SSE/AVX psin functions. | 2018-11-27 | |
| | | | | | | | | It is based on the SSE version which is much more accurate, though very slightly slower. This changeset also includes the following required changes: - add packet-float to packet-int type traits - add packet float<->int reinterpret casts - add faster pselect for AVX based on blendv | ||
* | Unify SSE and AVX pexp for double. | 2018-11-26 | |
| | |||
* | Unify SSE and AVX implementation of pexp | 2018-11-26 | |
| | |||
* | First step toward a unification of packet log implementation, currently only ↵ | 2018-11-26 | |
| | | | | | | SSE and AVX are unified. To this end, I added the following functions: pzero, pcmp_*, pfrexp, pset1frombits functions. | ||
* | bug #1436: fix compilation of Jacobi rotations with ARM NEON, some ↵ | 2017-06-15 | |
| | | | | specializations of internal::conj_helper were missing. | ||
* | bug #1167: simplify installation of header files using cmake's ↵ | 2016-08-29 | |
| | | | | install(DIRECTORY ...) command. | ||
* | Automatic relicensing to MPL2 using Keirs script. Manual fixup follows. | 2012-07-13 | |
| | |||
* | Remove all references to EIGEN_TUNE_CPU_CACHE_SIZE. | 2011-02-04 | |
| | | | | | This macro is no longer used as of revision 0212eec23f4cb64e8426bf32568156df302f8fcf . | ||
* | forgot to remove a #endif | 2010-08-13 | |
| | |||
* | fix determination of number of registers on sse: | 2010-08-13 | |
| | | | | | | __i386__ was not defined by MSVC 2010. fixed as (2*sizeof(void*)). also move that to SSE/ and let the default for unknown arch's be just 8. | ||
* | email change | 2010-06-24 | |
| | |||
* | Add a proof concept API to configure the blocking parameters at runtime. | 2010-06-07 | |
| | | | | After validation of the final API I'll update the other products to use it. | ||
* | add missing cmake directives for arch/Default | 2010-03-08 | |
| | |||
* | make the number of registers easier to configure per architectures | 2010-03-04 | |
| | |||
* | factorize default performance related settings to a single file | 2010-03-03 | |
included after the architecture specific files such that they can be adapted by each platform. |