pranith

Great investigative work! The stack structure you refer to here is called the Return Address Stack (RAS).

Even cows are extremely intelligent and emotional animals. Did you stop eating them?

Very well explained.. its a really interesting idea.

Wishing him good luck and healthy life.

Graviton2 is using Ares core IP from ARM.

Looking forward to seeing a high performance dev-board from SiFive.

True, but the design is licensed from ARM and tuned to AWS's requirements.

If they are good enough for internal use, they should be good enough for public use. Not really sure what is stopping them from exposing it to the public... I am sure there is _some_ demand for it.

I am sure the software is multi-arch ready but I wonder if they are evaluating ARM servers either for use internally or to launch in the cloud...

I wonder when and how Azure and Google Cloud will compete with AWS in this market.

They could buy ARM processors available in the market, but I doubt they will be able to get them as cheap as AWS who builds their own.

Would you please tell what the specifications are and how much it cost you?

The long term extended support release might be a suitable option for you in that case...

https://www.mozilla.org/en-US/firefox/enterprise/

Ah, forgot Amazon. They are a sink for OSS. Apple, it appears, is much better than I knew.

Microsoft has come a long way lately when it comes to open source. Apple seems to be the only major company that is still not an enthusiastic participant.

For those having trouble accessing the page:

https://web.archive.org/web/20170512030315/http://www.alex-i...

> Properly coded applications will be using some form of sync primitives to shared data structures. So, when the emulator hits a LOCK xxx instruction

This is not always true. See [1] for an example. Because of the semantics of the x86 memory model a sequentially consistent load does not generate a lock'd instruction. When such loads are translated to ARM64, you need to introduce barriers or use a ldacq instruction.

[1] https://www.cl.cam.ac.uk/~pes20/cpp/cpp0xmappings.html

Since there are no publicly available details, I would guess this is solved in hardware. The Qualcomm processor can be made to support stronger memory model for translated instructions similar to how the Power processors support strong-access ordering for efficient x86 emulation[1].

[1] https://www.google.com/patents/WO2012101538A1?cl=en

Google is putting quite some effort to get Clang to build the linux kernel. Once it is at that stage, they can stop depending on gcc in AOSP. They already use clang for everything but the kernel.

And the latest available version on the most recent ubuntu and debian releases is... 5.7.1 from 6 years ago!!

https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=574947

https://bugs.launchpad.net/ubuntu/+source/global/+bug/127502...

There were plans not to disable the on-chip GPU and use it as a power saving feature. When the gpu work load can be handled by the on-chip GPU, disabling the external GPU saves you quite a lot of energy.