Yeah, but given the choice between being 100% visible on the battlefield and having a Predator style camoflauge, I'll go with the Pred tech thankyouvery much:)
"Many other CPUs do not have built-in hardware rotate instructions and must emulate the operation by (at the very least) two shifts and a logical OR. This handicap is why many non-32bit-Intel [1] and non-PowerPC computers run RC5 slower than one might expect based on real-world benchmarks. It is also the main reason why the RC5 client is a poor benchmark to use in determining the speed or performance of a particular CPU."
It also helps the G4 quite a bit that they have an Altivec crunching core for RC5, whilst there isn't an SSE cruncher for those of us living in x86 world:)
Except that SSE and 3Dnow! aren't double precision... whilst SSE2 is.
Re:Some are happy with a 600 MHz P3 too...
on
PowerPC Goes 64 bit
·
· Score: 2
actually, a 700Mhz Sahara should be able to smack a 600Mhz Coppermine P3 around quite handily.. not only is it based on the original 4-stage G3/G4 pipeline (which is higher IPC than Motorola's current 7-stage G4's) but it also has a half meg of L2 cache on the die with a 256Bit link to the processor core.
OTOH, an IBM 750FX @ 800Mhz uses less than 5w and performs _better_ than a Motorola 7455 per clock (unless the Altivec hardware on the G4 comes into play)
Even in terms of numerically power, the Athlons with SSE2 are faster than the AltiVec (SSE2 does double precision, AltiVec doesn't), for similar money.
Uh, Athlon's don't have SSE2, they have "3DNow! Pro" which includes instructions that just so happen to be identical to SSE, but not SSE2 support.
SSE2 = Pentium 4 or AMD Opteron (which isn't out yet)
I find it frustrating that I can't wring out every last bit of performance from whatever CPU I'm coding for. Um, isn't one of the key selling points of Java portability?, allowing programmers to write code for a specific (family of) cpus would utterly break that..
It would be extremely non-elegant, and if the 68k / PPC hackjobs for the Amiga are anything to go by, it would be hellishly slow too..
Maintaining cache coherency between two processors that are opposite-endian... eek *shudder* it was bad enough with the 300+ _Micro_second context switches on Amiga's with PPC accelerators
That was my point, the Xserve has more memory bandwidth, although the FSB is the same, it seems be better equipped to keep the processor fully fed whilst also servicing the NIC/disk controllers etc.
(and AFAIK the CPU northbridge on the Xserve was still 133Mhz SDR? )
The Altivec hardware in the G4 is still _extremely_ impressive, but it seems bandwidth limited.
I seem to recall some Xserve benches that showed a single processor Xserve being right on the heels of a DP Quicksilver in some processor intensive tests?
Can't remember where, was a german website I think?
My wishful-thinking-cap is still firmly pointing at Apple ditching Motorola and going to IBM for their processors.
a POWER4-Lite would be vaguely feasible (eg, pair of G3 cores + SMP logic + Altivec execution hardware + 1MB of L2 cache) on.13, and I'd reckon it would be rather rapid:)
Of course, the chances of that happening are something like my chances of winning the lottery, which incidentally is also the only way in hell I could afford a PowerMac equipped to my liking:p
Re:You're assuming too much
on
More MS EULA Fun
·
· Score: 1, Troll
I have a large collection of mp3's ripped from CD's that I OWN
I'd appreciate it if Microsoft can not being able to delete the mp3's I spent hours ripping and normalising.
I use either Sasami or "THE PLAYA" as I'm Win32 here, either way it's frickin' annoying. especially when it wouldn't be _that_ difficult to fix it so workarounds weren't needed..
I mean, comeon, they can compress video to a fraction of it's normal size, but they can't work out how to keep that synced to audio?.. bah.
it's not my machine, it can play a file straight through without problems.. the problem is when you try to jump to a specific point, and you get audio lagged behind (or running ahead of) the video.
(and since when is a 1.5Ghz AthlonXP with a gig of DDR ram a _slow_ computer?)
*takes 3200x2400 Terragen render* *resizes to 1600x1200*
In jpeg format, it's 922KB @ 100% quality (from Photoshop 7) In PNG (run through PNGCrush with -brute -l 9 -reduce) it's *waits for PNGCrush to finish* 1.72MB
I'd post links to the two samples of the image, but I'd prefer it if my 32KB/s DSL upload weren't raped by/.'ers
Slashdot Mirror
Yeah, but given the choice between being 100% visible on the battlefield and having a Predator style camoflauge, I'll go with the Pred tech thankyouvery much :)
*ahem*
:)
They themselves state that RC5 is a poor overall CPU performance benchmark
"Many other CPUs do not have built-in hardware rotate instructions and must emulate the operation by (at the very least) two shifts and a logical OR. This handicap is why many non-32bit-Intel [1] and non-PowerPC computers run RC5 slower than one might expect based on real-world benchmarks. It is also the main reason why the RC5 client is a poor benchmark to use in determining the speed or performance of a particular CPU."
It also helps the G4 quite a bit that they have an Altivec crunching core for RC5, whilst there isn't an SSE cruncher for those of us living in x86 world
Like this you mean?
3dnow Pro! is standard 3dnow with the addition of SSE compatability..
:)
Could be that you're just seeing the raw brute force the Athlon core can bring to bare
Except that SSE and 3Dnow! aren't double precision... whilst SSE2 is.
actually, a 700Mhz Sahara should be able to smack a 600Mhz Coppermine P3 around quite handily.. not only is it based on the original 4-stage G3/G4 pipeline (which is higher IPC than Motorola's current 7-stage G4's) but it also has a half meg of L2 cache on the die with a 256Bit link to the processor core.
OTOH, an IBM 750FX @ 800Mhz uses less than 5w and performs _better_ than a Motorola 7455 per clock (unless the Altivec hardware on the G4 comes into play)
Even in terms of numerically power, the Athlons with SSE2 are faster than the AltiVec (SSE2 does double precision, AltiVec doesn't), for similar money. Uh, Athlon's don't have SSE2, they have "3DNow! Pro" which includes instructions that just so happen to be identical to SSE, but not SSE2 support. SSE2 = Pentium 4 or AMD Opteron (which isn't out yet)
PowerPC 750FX for you then!
I find it frustrating that I can't wring out every last bit of performance from whatever CPU I'm coding for.
Um, isn't one of the key selling points of Java portability?, allowing programmers to write code for a specific (family of) cpus would utterly break that..
It would be extremely non-elegant, and if the 68k / PPC hackjobs for the Amiga are anything to go by, it would be hellishly slow too..
Maintaining cache coherency between two processors that are opposite-endian... eek *shudder*
it was bad enough with the 300+ _Micro_second context switches on Amiga's with PPC accelerators
...
That was my point, the Xserve has more memory bandwidth, although the FSB is the same, it seems be better equipped to keep the processor fully fed whilst also servicing the NIC/disk controllers etc.
(and AFAIK the CPU northbridge on the Xserve was still 133Mhz SDR? )
Just FYI, Apple currently ship IBM processors, the IBM "Sahara" PowerPC 750FX (G3) is used in the iBook
:)
They are quite sweet little chips too
No, calculations != cycles
Different processors can handle a different number of instructions per cycle.
and hence, require a different number of cycles to perform the same calculation.
The Altivec hardware in the G4 is still _extremely_ impressive, but it seems bandwidth limited.
I seem to recall some Xserve benches that showed a single processor Xserve being right on the heels of a DP Quicksilver in some processor intensive tests?
Can't remember where, was a german website I think?
My wishful-thinking-cap is still firmly pointing at Apple ditching Motorola and going to IBM for their processors.
.13, and I'd reckon it would be rather rapid :)
:p
a POWER4-Lite would be vaguely feasible (eg, pair of G3 cores + SMP logic + Altivec execution hardware + 1MB of L2 cache) on
Of course, the chances of that happening are something like my chances of winning the lottery, which incidentally is also the only way in hell I could afford a PowerMac equipped to my liking
I have a large collection of mp3's ripped from CD's that I OWN I'd appreciate it if Microsoft can not being able to delete the mp3's I spent hours ripping and normalising.
Nope, Windows XP identifies itself as Windows NT 5.1 in it's about dialogs.
I use either Sasami or "THE PLAYA" as I'm Win32 here, either way it's frickin' annoying. especially when it wouldn't be _that_ difficult to fix it so workarounds weren't needed..
I mean, comeon, they can compress video to a fraction of it's normal size, but they can't work out how to keep that synced to audio?.. bah.
it's not my machine, it can play a file straight through without problems.. the problem is when you try to jump to a specific point, and you get audio lagged behind (or running ahead of) the video.
(and since when is a 1.5Ghz AthlonXP with a gig of DDR ram a _slow_ computer?)
# MIPS:
Um, I was under the impression that RiscOS was written for the ARM processor(s)? ARM processor(s)?* RiscOS, mips-*-riscos*
Did somebody just turn two pages at once?
DIVX ;-) kinda needs better audio/video syncronisation IMO
The obvious answer is to ramraid^H^H^H^H^H^stamp on the local convenience store with the Timberwolf.
Maxtor are doing 7200rpm FDB disks. :)
as are Seagate
*hugs BarracudaIV*
*takes 3200x2400 Terragen render*
/.'ers
*resizes to 1600x1200*
In jpeg format, it's 922KB @ 100% quality (from Photoshop 7)
In PNG (run through PNGCrush with -brute -l 9 -reduce) it's *waits for PNGCrush to finish* 1.72MB
I'd post links to the two samples of the image, but I'd prefer it if my 32KB/s DSL upload weren't raped by