Thanks for that explanation. I can't speak for the OP (or anyone else), but my take on the difference between them is that euthanasia is suicide, but only once all other options have been exhausted.
I don't see "simple suicide" (i.e. not in the face of terminal disease) as immoral or wrong. The tragedy though, is how often it happens because of poor social support systems, such as lack of access to mental health support systems or, in some parts of the world, bad debts to loan sharks.
These are often relatively spur of the moment, avoidable situations and, IMO, more of an indictment of society than a moral failing of the person. Euthanasia is different in that it is usually a well-considered decision, once there is little hope of any change for the better. I don't see any value in forcing people to live through misery without anyone having a clue on how to improve their life.
(I don't expect you to necessarily agree with this point of view, but I hope it helps understand another perspective.)
Thanks - yeah, I agree, we need better palliative care, better social support in general. I understand your perspective, but I do have trouble following it through - I need to be able to say "at this point, a life loses that value, and it becomes permissible to kill". I don't see that happening with consent, because dueling to the death is rightly illegal. I also don't see how we can get somewhere by counting up something (like suffering, failure to contribute back to society, whatever) that then makes it permissible to kill a person. And if I try to combine both, I end up with rules that are still problematic, but make it easier to kill the elderly, the dying, and other vulnerable people, which is a bad sign.
For what its worth, I think we're approaching this question from opposite ends of the spectrum. Rather than asking when it is permissible to kill, I look at it as "when is overriding free will (on victimless actions) for societal good permissible"? Forcing terminally ill patients to live through the misery doesn't meet my bar on that front.
I realise that you're drawing a distinction between taking your life and having someone else take it for you, but to me, in this case the difference is largely academic since the agency remains with the patient at all times.
The objections to dueling were, as I understand, more around the social pressures which required one to participate making the idea of consent much more fuzzy.
Interestingly, family pressure to euthanize is a major practical concern for countries with euthanasia.
The point is actually that there is no distinction between taking your life own or someone else's. If consent is our metric, dueling is permissible (with societal pressure safeguards, if you'd like). Consent is irrelevant, the issue is that intentional killing should be a relic of a more barbaric past. The cure (resolving psychological distress over having a painful death by being willingly poisoned, often in front of your family) is worse than the disease.
Ultimately, you're saying that it's permissible to kill when a terminally ill patient would "live through misery", where someone who is not the patient defines what constitutes "misery". Am I understanding that correctly? On what grounds would that not apply to, for example, a severely depressed homeless person suffering from substance abuse, who a doctor might judge has much more suffering in store for them than a cancer patient with access to painkillers?
> "... family pressure to euthanize is a major practical concern..."
Agreed, and this is one of my major reservations about euthanasia. I still think it is overall for the best, but this aspect absolutely needs monitoring. I can only hope that better social services and support help reduce the financial burden on families (which is often one of the biggest reasons for pressure). The emotional aspect, of course, is another story.
> "The point is actually that there is no distinction between taking your life own or someone else's."
Here I have to disagree. Only one of these is an action on one's own body (which one should have relative autonomy). I think consent is absolutely key -- personally, I'm not opposed to the idea of legalizing dueling, as long as we have adequate societal safeguards against it. We don't outright ban other dangerous things that could end up killing people (tobacco, alcohol, free climbing...)
> "The cure ... is worse than the disease."
This is not a determination I am comfortable making for anyone else. Unless there is significant societal/family pressure which means that people are not making this choice themselves, I think they should have that right. If there is extensive pressure, there should be safeguards against that, as opposed to banning the practice?
I see a similar kind of argument in the anti-abortion debate -- there are folks who wouldn't opt for it themselves, but want others to have that right, while others feel that it should be banned for everyone because it is overall a societal ill.
I realise that this is a different question, but is this the kind of angle you are coming from?
> ... not the patient defines what constitutes "misery".
In the long run, it should absolutely be the patient who determines what constitutes misery and makes the choice. Unfortunately, there is entirely too much risk of it being used as a way for society to ignore people we should be helping ("if we wait long enough, maybe they'll just go away") for it to be practical to use it that way yet.
Terminally ill patients are a relatively well-defined set where there is less risk of society starting to ignore the problem (I don't see interest in cancer research drying up just because of this option), so it seems like a reasonable place to start?
I haven't gotten around to trying it myself yet, but OpenFastpath+OpenDataplane supposedly has a userspace port of the FreeBSD stack that runs on DPDK through ODP-DPDK.
This is by far my favourite post in this entire thread -- I don't think I've ever seen Seymour Cray referenced as an authority in this manner before :)
Not specifically to OP, but for everyone unhappy about the use of performant: Pretty happy to concede that it isn't our finest bit of writing. Pretentiousness? Lack of technical nous? A bit of hurried/careless wording? I'll let you folks decide...
I don't think CAT can be used to partition kernel and userspace -- I'm not even sure how you'd go about doing that given that you can (and do) have shared pages between them.
That being said, from our experiments, if you're using userspace network and NVMe drivers the context switch and associated cache pollution is not a problem, since it is happening pretty infrequently (primarily just timer interrupts, and those can be turned off, but we haven't needed to).
Not sure exactly what OP is referring to, but CSS-trees [1] are a classic example of cache-aware indexing structures that fetch entire pages into cache and arrange data so that most of the comparisons happen on cached data. In most cases, they significantly outperform binary trees. Masstree [2] is a more recent example of this.
Yes. Even the persistent memories that attach to the memory bus are currently quite a bit slower than DRAM (5-7x from estimates I've seen), while the difference with PCIe-attached ones is even more.
I'm not sure what the future holds in terms of latencies for non-volatile storage but sub-DRAM levels aren't within reach yet.
On a side note, it's interesting to me that emerging memory technologies currently seem to be mainly focused on addressing the "from-DRAM-to-disk" part of the memory hierarchy.
That is, as you mentioned, not directly competing with DRAM, and consistently on the same side of the 1 microsecond dividing line between memory and storage; as in:
As far as the other side of the line is concerned, I think I've only seen proposals for hybrid-cache architectures (HCA) -- other than http://link.springer.com/chapter/10.1007%2F978-1-4419-9551-3... -- with a hybrid approach (e.g., combining SRAM/eDRAM/STT-RAM/PCRAM) probably making sense due to latency/endurance/bandwidth trade-offs.
If anything, there seems to be more development on the DRAM interface itself -- with multiple candidates for the (or a) DDR4's successor, so far involving Wide I/O (Samsung), Hybrid Memory Cube (Intel, Micron), High Bandwidth Memory (SK Hynix, AMD, Nvidia): http://www.extremetech.com/computing/197720-beyond-ddr4-unde...
It's fairly recent development, though, and it remains to be seen how is it going to fare.
Other than the above, there doesn't really seem to be much progress around competing with/improving SRAM. However, this may become increasingly important, since some of the technological process scaling issues apply to SRAM, too.
Wrapping a bunch of replies into one: Absolutely agree that we need to view fast storage as something other than disk behind a block interface and slow memory, especially with all the different flavours of fast persistent storage that seem to be on the horizon. For the one's that attach to the memory bus, the PMFS-style [1] approach of treating them like a file-system for discoverability and then mmaping to allow them to be accessed as memory is pretty attractive.
I'm not sure a dedicated storage processing unit is the way to go though; I think we could equally well see bits of functionality being offloaded to smarter controllers (kind of like checksum, VLANs, etc are on network adapters) while the CPU remains in charge of orchestrating the different bits.
Also agree on the fact that it is an interesting data structure problem -- a lot of the work we do involves examining what the right data structures are for things once seeks are free and cache locality is the dominant factor for operations.
Disclaimer: I'm not in SF, nor am I familiar with HR policies at large companies. That being said,
> "If that happens before I've proven myself as a good engineer, I won't feel like I deserve seeing doctors or going > to appointments on facebook's dime."
I certainly hope this is not the attitude that most companies take to your well-being: RSI is almost an occupational hazard for tech workers, and it is absolutely in everyone's best interests to try and ensure that you're pain free.
If it does crop up, please don't hesitate in at least talking to people around you and getting a sense as to what the best options available are. Good luck!
I don't see "simple suicide" (i.e. not in the face of terminal disease) as immoral or wrong. The tragedy though, is how often it happens because of poor social support systems, such as lack of access to mental health support systems or, in some parts of the world, bad debts to loan sharks.
These are often relatively spur of the moment, avoidable situations and, IMO, more of an indictment of society than a moral failing of the person. Euthanasia is different in that it is usually a well-considered decision, once there is little hope of any change for the better. I don't see any value in forcing people to live through misery without anyone having a clue on how to improve their life.
(I don't expect you to necessarily agree with this point of view, but I hope it helps understand another perspective.)