1 |
On 3/30/06, Mike Myers <fluffymikey@×××××.com> wrote: |
2 |
> Just my .02c, but it seems like the 64-bit processors come with more |
3 |
> hype than benefits. Not that the 64-bit move is a bad thing at all, |
4 |
> but I mean it just seems like people tend to expect much more out of |
5 |
> them than what they should. |
6 |
|
7 |
You're very close to the mark, actually. |
8 |
|
9 |
> It would seem like a more accurate, but oversimplified explaination |
10 |
> would be that it simply allows for other improvements within the |
11 |
> computer, but it does not improve anything on it's own. For instance, |
12 |
|
13 |
Yes, you're very close. It does allow for one major thing OTTOH. |
14 |
With a 64-bit wide word, more precise calculations take half the time |
15 |
they would on a 32-bit chip. They don't give any other real major |
16 |
64-bit exclusive benefits though. The advantages of a 64-bit variable |
17 |
isn't really relevant for most uses though. Things like MatLab are |
18 |
greatly benefitted, however, normal desktop use isn't. Some video |
19 |
games are now being made 64-bit, so they'll benefit from more precise |
20 |
gameplay at higher speeds, however, you are right: 64-bit en se |
21 |
doesn't give any other amazing benefit. |
22 |
|
23 |
> allowing >4GB ram, which in turn gives better performance. From what |
24 |
> I've read, there are improvements in certain things that are specific |
25 |
> to number crunching, like a database with mathematical formulas. |
26 |
|
27 |
Yup. |
28 |
|
29 |
> However, for a desktop processor, the difference is going to be barely |
30 |
> noticeable, if any, especially since most desktops don't use more than |
31 |
> 4 gigs of ram. |
32 |
|
33 |
True. However, sticking to 32-bit for the rest of forever isn't a |
34 |
terribly good idea, now is it? |
35 |
|
36 |
> It definitely seems to be a difficult thing to explain though due to |
37 |
> the nature of the processor. Most people think simply 'more numbers = |
38 |
> more speed', but that's not really case, and surely not the point. |
39 |
> Since around the mid 90's, processor speeds have steadily increased, |
40 |
> but in the last couple of years, that increase has halted. |
41 |
|
42 |
Not really. AMD is still making their chips more efficient and |
43 |
faster, though the new fad is to add more cores. However, eventually |
44 |
this will still limit threads to the speed of one core, which'll |
45 |
prompt more and more rapid speed increases. Just be patient; you |
46 |
don't need all that number-crunching power right now, do you? ; ) |
47 |
|
48 |
> Supposedly, the speeds have been maxed out for the size of the |
49 |
> processors, so that's why the manufacturers are trying different |
50 |
> routes, like hyperthreading, dual core, multi-core, and 64-bit. None |
51 |
|
52 |
Well, they also need to make the thing smaller. We're still on what? |
53 |
95 nanometre? Smaller means more transistors in the same area. |
54 |
|
55 |
> of these features directly improve performance, but they do increase |
56 |
> it's capabilities. More specifically, they allow the computer to do |
57 |
> MORE tasks better, instead of focusing on speeding up tasks. That's |
58 |
> not a bad thing really, because it's nice to be able to do multiple |
59 |
> things simultaneously, like burning a cd while listening to mp3s and |
60 |
> playing games on a LAMP server that's running emerge -u world without |
61 |
> any degradation in performance in any of the processes. |
62 |
|
63 |
People who do that scare me. |
64 |
|
65 |
> That kind of performance seems to be what is intended with these |
66 |
> different avenues that the chip makers are taking. That is not to say |
67 |
> that single tasks will perform any better, and I think the lack of |
68 |
> discerning the difference is causing a lot of confusion for most |
69 |
> people, especially when they aren't familiar with low level |
70 |
> programming. |
71 |
|
72 |
In the end this might degenerate to a "programmer's rating" thing. |
73 |
IE: one standardised benchmark. |
74 |
|
75 |
> On 3/29/06, Richard Fish <bigfish@××××××××××.org> wrote: |
76 |
> > On 3/29/06, Lord Sauron <lordsauronthegreat@×××××.com> wrote: |
77 |
> > > www.alienware.com I beg to differ. I could have sworn I saw a laptop |
78 |
> > > with more than 2G... where was it... wow! You appear to be right! |
79 |
> > > Darn.. I could have SWORN I saw something with > 2G... |
80 |
> > |
81 |
> > Actually, you are right. I neglected the monstrous Clevo laptop. Its |
82 |
> > an AMD X2 with capacity for 2 optical drives plus 2 hard drives, up to |
83 |
> > 3G of memory, and a 200W power adapter. Weighs 12-15 lbs, _not_ |
84 |
> > counting the power adapter! This is acutally a Clevo design, sold by |
85 |
> > Sager, AGearnotebooks, and many others. Alienware got it with a |
86 |
> > customized case. All of the reviews I read on it basically said |
87 |
> > "incredible performance, excellent display, but heavy, noisy, and |
88 |
> > really hard to describe how large it really is". |
89 |
> > |
90 |
> > I was actually considering purchasing this beast...but the noise |
91 |
> > factor scared me off. Not really appropriate for a shared office or |
92 |
> > conference room. |
93 |
> > |
94 |
> > > compiler helps with the 64-bit part. It gets a bit technical, but |
95 |
> > > there is a big difference between something made from the ground up as |
96 |
> > > 64-bit versus something that was made 32-bit and just recompiled |
97 |
> > > 64-bit. |
98 |
> > |
99 |
> > For most applications, this is not true. The vast majority of C/C++ |
100 |
> > code that runs on a desktop system couldn't care less whether longs |
101 |
> > and pointers are 32-bits or 64-bits in size. It is a compiler |
102 |
> > function to deal with that. And it is also a compiler function to |
103 |
> > determine whether 64-bit or 32-bit registers should be used for a |
104 |
> > particular operation. FYI, gcc has supported non-x86 64-bit CPUs for |
105 |
> > a long time, so gcc's 64-bit support is probably more mature than you |
106 |
> > think. So are the applications...many open source applications were |
107 |
> > ported and adapted (if necessary) to 64-bit sparc and alpha processors |
108 |
> > back in the late 90s. |
109 |
> > |
110 |
> > There are opportunities for some programs to take advantage of special |
111 |
> > processor operations through assembly instructions. This is very |
112 |
> > similar to how 3Dnow, MMX, SSE, et. al. make programs faster. So |
113 |
> > there may be some specific optimizations for some operations that can |
114 |
> > be improved over time. |
115 |
> > |
116 |
> > An example of an application domain that could benefit from 64-bit is |
117 |
> > encryption, because for key setups you need to calculate very large |
118 |
> > numbers. Such numbers could be calculated about twice as fast with |
119 |
> > 64-bit operations vs 32-bit. *BUT*, this does almost nothing for the |
120 |
> > actual data encryption itself. |
121 |
> > |
122 |
> > A good resource on the 64-bit vs 32-bit issues is to look at AMDs |
123 |
> > optimization guide for software developers. Chapter 3 is particularly |
124 |
> > relevant: |
125 |
> > |
126 |
> > http://www.amd.com/us-en/assets/content_type/white_papers_and_tech_docs/25112.PDF |
127 |
> > |
128 |
> > -Richard |
129 |
> > |
130 |
> > -- |
131 |
> > gentoo-user@g.o mailing list |
132 |
> > |
133 |
> > |
134 |
> |
135 |
> |
136 |
> -- |
137 |
> Mike Myers |
138 |
> mike@××××.us |
139 |
> http://www.yaay.us |
140 |
> |
141 |
> -- |
142 |
> gentoo-user@g.o mailing list |
143 |
> |
144 |
> |
145 |
|
146 |
|
147 |
-- |
148 |
========== GCv3.12 ========== |
149 |
GCS d-(++) s+: a? C++ UL+>++++ P+ |
150 |
L++ E--- W+(+++) N++ o? K? w--- O? M+ |
151 |
V? PS- PE+ Y-(--) PGP- t+++ 5? X R tv-- b+ |
152 |
DI+++ D+ G e* h- !r !y |
153 |
========= END GCv3.12 ======== |
154 |
|
155 |
-- |
156 |
gentoo-user@g.o mailing list |