原始文献 / 论坛帖 / Re: 4 hashes parallel on SSE2 CPUs for 0.3.6
Re: 4 hashes parallel on SSE2 CPUs for 0.3.6
Bitcointalk · 2010-08-02 19:02:46 UTC
AuthorSatoshi Nakamoto
TitleRe: 4 hashes parallel on SSE2 CPUs for 0.3.6
Date2010-08-02 19:02:46 UTC
ForumBitcointalk · 原文
在 AMD 上是快 2 倍，在 Intel 上是慢一半吗？
【引用 tcatm 于 2010年7月31日 10:12:38（https://bitcointalk.org/index.php?topic=648.msg6797#msg6797）】
"顺便问下，既然 __attribute__ ((aligned (16))) 就能告诉编译器在编译时对齐，你为什么还用 alignup<16> 这个函数？"
试过了，但对栈上的东西不起作用。我做过测试。
它甚至不会报错，就是不对齐。
英文原文
Is it 2x fast on AMD and 1/2 fast on Intel?
【引用 tcatm on July 31, 2010, 10:12:38 AM（https://bitcointalk.org/index.php?topic=648.msg6797#msg6797）】
"Btw. Why are you using this alignup<16> function when __attribute__ ((aligned (16))) will tell the compiler to align at compiletime?
"
Tried that, but it doesn't work for things on the stack. I ran some tests.
It doesn't even cause an error, it just doesn't align it.