Jukka Larja (roskakori2006@gmail.com) on 10/2/09 wrote:
---------------------------
>[Sorry, I haven't proof-read this message. I'm somewhat ill and just too tired to do that.]
>
>AM (myname4rwt@jee.male) on 10/1/09 wrote:
>---------------------------
>
>> I seriously doubt I said that. Are you sure?
>> I recall I mentioned on several occasions
>> that I don't dispute power and die overheads
>> (have you seen those?).
>
>I think its up to you to define what you meant, and its pointless to argue about
>how something you wrote can be interpreted. It is now obvious that I misunderstood you.

OK

>(More on this further down.)
>
>> If this is the whole reason why you keep
>> posting to "correct my misunderstanding",
>> I'd like to see the post+sentence you're
>> talking about.
>
>I think here's pretty fundamental difference between us. I'm not interested whether
>what you wrote was badly worded or whether it is perfect English and I just read
>it wrong. That's why I won't be searching for and posting any quotes. The bottom
>line is that I misunderstood it, and the good thing is that it is now resolved. Bad thing is that it took this long.

Actually, all you had to do is simply ask whether your understanding was correct -- that, I think, is a civilized and the shortest way to resolve misunderstandings.

>> No, I don't believe I stated OoO is free.
>> On the contrary, you should be able to
>> find me saying that OoOE needs to be
>> justified, or doesn't contribute to
>> higher performance on certain class of
>> workloads regardless of how well-designed
>> and advanced it is.
>
>Yes. If I recall correctly, part of the problem was that what you wrote seemed
>(to me that is) contradict your earlier statements.
>
>>> I think I have stated before that your
>>> facts aren't the problem, just the
>>> meaning you assign to them (or more
>>> accurately, the meaning you assign to
>>> facts of other people).
>>
>>What are those?
>
>For example that you seem to think that Jouni's arguments have no value unless
>he can point out some actual design that clearly demonstrates them.
>
>The word "fact" may not be a best fit here, but I couldn't come up anything better.

Meaning and value are quite different things imo. If someone refers to a book, it's natural to ask for pages (H&P is available on books.google.com as I told him). Normal practice, actually.

>>> I think the bound and must may be a
>>> problem here. I'm just trying to say
>>> that if there is a cost and you
>>> choose not to pay it in anywhere
>>> else, then you have to pay it in
>>> clockspeed.
>>
>> No, no, this is a very... well,
>> primitive look. As primitive as Jouni
>> arguing that since 603ev clocked
>> higher than original 603, then it
>> must have had a longer pipeline.
>
>Primitive, simplified, what's the difference?

Just trying to tell you that clock rate is by far not the only way to bring down power consumption -- both in practice and theory. (You seem to be somehow fixed in this understanding).

>> You don't need to wait until someday, mate.
>> I'm asking you today: what's the logic
>> behind fixing the power envelope ("not a
>> nanowatt more", IIRC), but allowing the die
>> space?
>
>Well, for me that's closer to "everything else being equal" than requiring same
>die space. In a latter case you have to specify what is going to get removed and
>how that is going to affect other parameters (performance being pretty important
>in practise). You know, all those hard practical issues.

But if you allow extra space for more transistors, then why fix the power envelope ("not a nanowatt more")? You can't be serious about judging the value of any design feature on the grounds of zero cost, even if it's just power consumption in a chip. What people look at is what the feature brings (perf, power savings, ..) vs what it costs (die, power, design complexity ..).

>> Then I'd like to see what exactly you mean
>> as requested above.
>
>That's written below.
>
>> If you read the thread indeed, how can it
>> be unknown to you that I never disputed
>> power and die costs etc.?
>
>[KLIP]
>
>> And it was brought up when I requested
>> some clarity on the obvious contradiction
>> in your own text (smth. about the waste
>> in OoOE). Remember?
>
>Actually, the statements were made by you (as I had understood them) and the point
>was to show you that you make contradictory arguments. Now it is obvious that I
>just understood one of your statements wrong, but back then I was totally lost.

OK

>> IIRC, your statement was something about
>> theoretical standpoint. As such, it's an
>> empty point as long as there's no
>> theoretical substantiation -- and I
>> haven't seen one.
>
>I think there was lot's of theoretical support for Jouni's claim but a lack of
>practical one. But perhaps we just see that level of support differently, not the matter.

No. For a reference to a book it's quite normal to ask for pages containing the proof.

>> No need to analyze or interpret, just take
>> it for what it is.
>
>Um, that way you're never going to understand anyone's point if its sufficiently
>different from yours. Language simply isn't precise tool and to expect "just take
>it for what it is" to yield complete results is lunatic.

So do you think analyzis and interpretation is something that works better? No way to make an even worse mistake when trying to interpret what the other says?

>> What ref. is it?
>
>Nothing too important (= I don't feel like finding exact quote). Its just that
>your answered like you didn't understand why he brought up debating at all, although
>for me it was quite clear, something I had thought even before Jouni wrote about it.

Unfortunately I don't remember what was that, but let me ask: if I misunderstood him, why didn't he simply correct me and clarify what he meant?

>But this is just my interpretation. I don't know what your answer was supposed
>to sound like or whether or not debatish tones in your arguments are just a coincidence or result of different cultures.
>
>>So, are you just exercising in debating?
>
>No, no, no! We don't have debating culture in Finland. I've only debated twice,
>and although it can be quite funny to watch or even participate in, I don't think
>it has practically anything to do with who is right. My view is typical to Finns,
>we loath people who bring debating tactics to actual discussions (in case we notice
>that. Often we are just wondering what the heck the other guy is talking about).
>
>So, just to make sure I don't insult you, I don't think your just debating regardless
>of facts. But your style does have some aspects that could be interpreted that way, if I wanted to.

So what is your understanding of the best (debateless?) way to resolve disputes or differences of opinions? I gave examples, asked for examples and asked for sources (you) and pages from H&P (him) to support the claims after both referred to theory or H&P. What do you find to be inappropriate(?) about this style?

>>> I'm not sure whether dispute is a right word,
>>> but what I wanted to dispute was your
>>> interpretation of the point Jouni was trying
>>> to make.
>>
>> Then -- in case you're really trying to help
>> communication -- I look forward to seeing
>> above-requested examples.
>
>Well, to quote what Jouni (later) wrote: "Its about design decision of adding OoO.
>Not about two different teams, but effect on result should a team chooce OoO or
>inorder , and comparing different teams or different times is just approximation
>of it." I think that every time you took the discussion to actual designs, you were missing the point.
>
>(That is, when discussing with Jouni. I don't remember what the state of the discussion
>was when Jouni joined in or which of his messages started the dialogue between you
>and him. The thing is, contexts evolve. Sometimes even the subject is changed. There's nothing special about that.)

Actually, when one starts out with claims about OoOE in general, I think it's perfectly OK to consider best-vs-best examples. E.g. there are many situations when it's hard or downright impossible to choose between two options by means of direct matching (e.g. what to use for particular task -- plane or chopper), and the only thing that works is best vs best from available designs.

One is likely to complain about such approach if he or she is unable to find a good match vs the opponent's best shot. Which, apparently, has happened.

Btw, I don't know what he thinks abot #stages b/w IF and EX in EV6, it was indeed one of the points of discussion, but on a closer look it seems that one stage simply does nothing (used to move data across).

>> Well, if you feel you misunderstood me,
>> what's the point in continuing this
>> discussion?
>
>There wouldn't be any point continuing if I didn't know would there? I wasn't sure
>whether I had misunderstood. Competing theory (sorry, hypothesis) was that you were
>conviniently changing your argument depending on what you wanted to prove.

And you spent so much time in obscure arguments instead of simply asking for clarification?

>> I just suspect that even this will not be
>> enough and will likely result in yet
>> another post from you how I seem to not
>> respect context, not listen to what
>> others say etc.
>
>We just have very different view on how you should listen to other people. You
>"just take it for what it is", while I think that 99 % of people often make mistakes
>in both writing and reading, or more generally, communicating. You have several
>times interpreted what I wrote wrong. I'm not trying to assign blame here. Since
>I'm obviously less proficient in English than you, it is by definition more probable that I was to blame.
>
>But it happened. We miscommunicated. I'm asking you to deal it differently than
>you do. Not acting like the fact that there was a miscommunication proves that the other guy is an idiot.

I don't think I do.

>> I think you admitted that the context you
>> introduced differed significantly. No?
>
>From the Jouni's context, yes. Not that much from the one that had evolved after
>after I joined in (how that was born, I cannot answer without reading the messages
>again, but I don't suppose there was anything special going on).

Usually if you want to discuss something else (or change the context), you don't make direct connections to prior discussion as if the context remains the same.

>> Prescott is just a particular (but telling)
>> example. The context -- no, it's you who
>> thinks of different context etc.
>
>Perhaps we should just agree to disagree at this point.
>
>> I don't try to repeat myself, it comes naturally.
>
>Yeah, it would for me too if I was writing in Finnish. It's considered bad style
>here. As far as I understand, there are different guidelines in English.

So, just to clarify: repeating oneself is bad style, but made-up "facts" and made-up "theory" are just fine?

>> Or just defended your friend not caring much
>> about the subject and essence of the
>> discussion?
>
>Well, I don't know him (outside this board) and don't usually agree with him, but
>do find his style, well, homely. So maybe that was a factor.

Ah, the *style*. OK, I think you can find quite many examples of arguing in this style on this board. Feel free to defend anyone else from my (or similar) "trolling" then. :)

>> Like the whole example was meant to yield
>> a response and then show how easily I can
>> misunderstand what was "really" meant?
>> Ah, geddit now.
>
>You must be kidding? How about I didn't care writing about something I didn't expect
>you to reply and that wasn't terribly relevant to anything anyway? Especially after two hours of writing.
>
>I guess it's just how you think of other people.

Heh, if I had really thought that way about you, I would have ignored the whole part.

>-JLarja