Matthias Kretz

43e534d improves the situation by using less optimization passes with GCC, Clang, and ICC (i.e. `-O2` instead of `-O3`). This will, of course, miss failures due to optimizer bugs, so...

`native_test_types` does not follow `TEST_TYPES` for the non-full ABIs. This is especially relevant for the `knl` builds which instantiate more templates than intended and test some functions three times.

Maybe PCH can help. Have to try https://github.com/sakra/cotire/

I tried PCH manually with GCC6 and saw no reduction in compilation time for the datapar test. Since almost every test requires different compiler flags (the same flags are used...

## should assertions depend on a macro (1.b)? The following considerations are relevant: 1. If the assertion function is implemented using an unlikely branch (`if (!cond) [[unlikely]] abort();`), then the...

At this point it's as simple as "I want to release something that's a full implementation, correct, and optimized" to show off the TS. Verifying more than one compiler makes...

Hi. First of all, I'm happy to hear that you had good success with Vc. And I understand that you want to make use of the portability promise now and...

Right, `exp` and `log` are next on my list for vectorization in std-simd. Note however that I'll have to implement them with high precision in the complete input range. So...

I just pushed `hmin` and `hmax`. I have an `exp` implementation waiting in another dev branch; I still need to benchmark it. It's precise with a max error of 1ULP.

The internal API doesn't have to be as precise as the public API. For `_SimdImplX86` I added the following function: ```c++ template _GLIBCXX_SIMD_INTRINSIC static _SimdWrapper _S_gather(const _Tp* __mem, const _IdxV&...