News for hackers. Stuff that matters.
Re:Bug 1283585 – Fix Intel's AES-GCM code to not depend on AVX by protomyth on Sunday October 02, 2016 @10:53PM (#12625326)
Can someone give a bit of the why on this one? Is there something wrong with AVX or is this a run on other chips thing? I'm at a bit of a loss on the history.
Re:Bug 1283585 – Fix Intel's AES-GCM code to not depend on AVX by yuhong on Sunday October 02, 2016 @10:54PM (#12625328)
AVX is normally 256-bit, but it also allows 128-bit instructions with a VEX prefix. Benefits of that include three operands and unaligned access, as well as higher performance when mixed with 256-bit instructions. Of course, you need a AVX-capable CPU and an OS that support AVX XSAVE to be able to use them.
Re:Bug 1283585 – Fix Intel's AES-GCM code to not depend on AVX by glandium on Monday October 03, 2016 @01:56AM (#12625690)
Why don't you write that information in the bug you filed?
Re:Bug 1283585 – Fix Intel's AES-GCM code to not depend on AVX by creshal on Monday October 03, 2016 @03:37AM (#12625900)
Sooo… why move away from AVX? What CPUs support AESNI, but not AVX, and actually matter?
Re:Bug 1283585 – Fix Intel's AES-GCM code to not depend on AVX by pdw on Monday October 03, 2016 @04:02AM (#12625956)
According to Wikipedia, most Celerons and Pentiums lack AVX but have the AES instructions.
Re:Bug 1283585 – Fix Intel's AES-GCM code to not depend on AVX by yuhong on Monday October 03, 2016 @10:37AM (#12627696)
Westmere
Re:Bug 1283585 – Fix Intel's AES-GCM code to not depend on AVX by DeepYogurt on Monday October 03, 2016 @03:56AM (#12625943)
The issue might be due to not all intel chips have AVX support. That said, many have hardware AES support so.... alternate code path?
Re:Bug 1283585 – Fix Intel's AES-GCM code to not depend on AVX by dogma1138 on Monday October 03, 2016 @04:57AM (#12626101)
AES-NI and AVX were proposed by AMD and Intel at the same time, and were introduced in the same generation of CPUs. I have a strong feeling that they are interconnected.