News for hackers. Stuff that matters.
Re:A tale of an impossible bug: big.LITTLE and caching by sangnoir on Tuesday September 13, 2016 @07:47AM (#12487179)
> Samsung's design breaks correctly written user-land code. Hence, they're 100% at fault.

This is similar to blaming OS/BIOS manufaturers for Y2K breaking "correctly written code" at the turn of the millenium.The code was incorrect in this instance because it assumed the cache size would be the same for all cores, Samsung simply manufactured a SOC that breaks that faulty assumption.

Re:A tale of an impossible bug: big.LITTLE and caching by oshepherd on Tuesday September 13, 2016 @07:58AM (#12487278)
The architecture states that CTR_EL0 reports the _minimum_ ICache line size across all cores.

In this system, that would be 64 bytes.

Re:A tale of an impossible bug: big.LITTLE and caching by pawadu on Tuesday September 13, 2016 @08:07AM (#12487353)
Can you point me to the manual that does say so? This is all I could find on the subject

> [3:0] IminLine Log 2 of the number of words in the smallest cache line of all the Instruction Caches that the processor controls.

> This values is:

> 0x4

> Smallest Instruction Cache line size is 16 words.

Re:A tale of an impossible bug: big.LITTLE and caching by gcp on Tuesday September 13, 2016 @08:04AM (#12487331)
The assumption isn't faulty, it's guaranteed to be right. And it has to be, or there's no way to write functional code for ARM.
Re:A tale of an impossible bug: big.LITTLE and caching by abysmallyideal on Friday September 16, 2016 @01:13AM (#12511987)
That is a bit far-fetched, as it seems to mostly affect how mono and gcc(?) JIT is designed.