LonelyStrange

Oh, I can run it well sometimes, maybe it is related to the compiler option. As I now don't use `-O3`, it gets right.

 @slice4e It seems that the `_mm512_load_epi64` func would cause `Segmentation fault`, on my cascade lake machine My complier CXXFLAGS is `g++ -std=c++17 -march=cascadelake -mprefer-vector-width=512`

> @lrg11 - after some thought, I belive it will be prudent to first understand what fraction of the execution time we are spending in the "vectorizable" code. This limits...

> @slice4e @lrg11 thanks both for your interest 🙏 > > My 2 cents: if you take a look at our paper (see [here](http://pages.di.unipi.it/pibiri/papers/SPIRE21.pdf)) we found out that on average...

OK, anyway, Could you provide me with the dataset in the TSXor paper, which can accelerate my developing and evaluating  1256765829 ***@***.***   ------------------ 原始邮件 ------------------ 发件人: "Yang ***@***.***>; 发送时间: 2023年5月18日(星期四) 下午2:58 收件人: ***@***.***>;...

OK, I'm evaluating the new paper dataset! Thanks   1256765829 ***@***.***   ------------------ 原始邮件 ------------------ 发件人: "Yang ***@***.***>; 发送时间: 2023年5月18日(星期四) 下午3:13 收件人: ***@***.***>; 抄送: ***@***.***>; ***@***.***>; 主题: Re: [andybbruno/TSXor] Vectorization (Issue #2)...