PPC970 Benchmarks in 32bit mode

[Hammer]

Usually, these benchmarks are the weakest for the current Pentium 4 Northwood. They don’t take into an account of the next Prescott core.   One should compare the incoming product vs incoming product not current product vs-incoming product.

Refer to
http://www.chip-architect.com/news/2003_03_26_Prescott_clues_for_Yamhill.html

http://www.chip-architect.com/news/2003_04_20_Looking_at_Intels_Prescott_part2.html

In balance, the other camp will also move their goal post.  

[Hammer]

mdma wrote:
Have you checked the clock speeds Hammer?

Yes, but the PPC 970’s pipeline depth is not as deep as the Pentium 4, thus potential for clock increases may not as positive compared Pentium 4. The current Northwood's transistor switching went as high as ~4.1Ghz via LN2 (liquid nitrogen).

(Not including double speed (poor performing) floating point unit i.e. IF the Northwood is rated 3 Ghz, its floating-point unit would be double pumped to 6 Ghz).

Intel does keep in mind that IPC will play an important role in the near future i.e. refer to Prescott’s architectural improvements.    

1.4 Ghz vs 3Ghz and it still pisses on the P4.

Note that Intel still has IPC bias “Pentium M” (@1.6Ghz) which roughly PR(unofficially)  rated at Pentium 4 @ ~2.5 Ghz ~2.6Ghz for office, legacy floating points and branch extensive applications. It’s pipeline depth is about similar to AMD’s K8.  

Intel has two solutions regards to X86.

IBM (and AMD) may approach chip design from IPC bias then work on the clock speed, while Intel may approach chip design from clock speed bias then work on IPC (the case is true for Pentium 4 family not for Pentium M family). Performance is one factor for comparison but the cost will be another.

Just hope IBM learns from the DEC’s Alpha experience i.e. performance alone doesn’t win the war.

PS Intel's IA-64 department may have duplicated DEC Alpha’s mistake.

I do keep track of the incoming flag chips i.e. IBM’s PPC 970, AMD’s K8 (has been released) and Intel’s Prescott. Just look at my news submissions (via Aorg's  userinfo).

[Hammer]

mdma wrote:

PS Intel's IA-64 department may have duplicated DEC Alpha’s mistake.

Let's hope so, then we might see an end to the Wintel domination of the desktop/low-end server market

We wouldn't see the end of  Wintel domination due to following factors;

1. Intel is known to have a Plan B (Intel's "guidelines to the press" restricts this information).

2. Thanks to IBM’s wisdom(or stupidity; take your pick) during early 80s, AMD will act as back up as the second supplier for X86 market. There are now talks of AMD K9 processor (i.e. includes hyper-treading and double pumped units). Transmeta is now(or soon will be) the second supplier X86-32/AMD64.

3. X86 Linux and Microsoft will ship products for X86 platform.  

4. Massive X86 bias supply channels and ISVs will continue to support X86. Just look at the lackluster support for non-X86 (e.g.. Intel's IA-64).

5. The massive X86 software base. This is the fundamental boat anchor why the world is tied with X86 chips.

6. The PowerPC platform is not foreign for Microsoft’s POV since they have Windows NT 4.0 (up to SP3) running on this platform. Windows XP and Windows Server 2003 are based on NT’s technologies. MS’s dotNET (transparent-re-compiling) ecosystem will enable Microsoft spread it’s wings and avoid the earlier Windows 4.0 mess i.e. the need to have separate edition of  PPC/MIPS/Alpha of MS application products. They just need dotNET edition of MS Office dotNET to run on any machine that has dotNET framework (it should sound like Tao's VP). The support for multiple CPU platform shouldn’t be a problem for MS (now armed with dotNET) except for political reasons.
IF it make business sense for MS, going to PowerPC will not be a barrier.

7. IBM may need to find yet another second vendor for supplying PPC 970 as this may be requirement for some the customers.

8. Economic of scale for X86 market.  

[Hammer]

IBM's 970 is only 1 stage shorter, to begin with.

According to Ars Technica. The PPC 970 has 16-stages (integer). Current Northwood  core has 20 stages deep.  AMD K8 has 17 stages deep (floating point).

This makes for a top Mhz rating of around 5Ghz on the next-generation process

Note that Intel has 6 Ghz units (double pumped) as of this moment (from 3Ghz Northwood) using the current process.

Just to break your line of thought, Ars Technica doesn’t even consider the incoming Prescott core. One has to look at http://www.chip-architect.com  

But IBM did something Intel didn't:  But IBM
did something Intel didn't: It made the pipes WIDE. IBM's throwing upwards of 12 instructions down the pipes at once!

Intel architecture has feature called "packed instructions".

[Hammer]

pipeline depth may not be as great, but the volume is much bigger. 200 instructions as against 132 instructions from the last time I looked.
Even if this is wrong we are talking about a 1.4 ghz vs a 3ghz so the Pentium will need a much bigger increase in speed to match a small increase in the 970 to maintain the performance level.

Note that Prescott's "Instructions in Flight" is at 256.  

http://www.chip-architect.com/news/2003_03_26_Prescott_clues_for_Yamhill.html

IS your POV comparing yet-to-be-release CPU with the current CPU? (Just analyze what you have stated).

[Hammer]

This means over
200 instructions are flying through this thing's pipes.

Note that Prescott  has 256 "Instructions in Flight".

Then there's the thuroughput issue. Intel's still using the shared-bus approach it pioneered so many years ago to save pin count, assuming that a single, wide bus would be faster. In truth, it is
only cheaper than two smaller dedicated-route busses as done up in older machines such as the Cray.

The price of the machine (purchasing) will play a big part in the desktop PC arena. Money just doesn’t magically appear in people’s pockets…

IBM's got the edge in I/O handling,
being able to both send *AND* recieve instructions on the same cycle.

Full duplex would be the term to use. I wouldn’t comment on Intel's CPU duplex issues.

now, let's add in IBM's multiple processor approach, seperate channels
per-processor verses Intel's shared-bus approach. Means that if you
provide a large enough memory pipe that IBM MP approaches will be
zooming past anything Intel can throw at it.

Due to the nature of X86 market i.e. no single X86 CPU vendor has the edge for very given segment. AMD would be the current flag bearer for the X86 multi-processor market (AMD 's Opteron class platform).

I don’t think your average citizen (western level incomes) can afford dual processors based machine. Majority of them can’t even afford the current dual PPC G4 let alone >2-way PPC 970 machines.    

Note that, it's not the first time that Intel has been blown away by the competition in regards to large scale multi-processors e.g. DEC's Alpha based platform is one example in the mid 90s.    

[Hammer]

IonDeluxe wrote:
My POV is simply that this is a promising processor and that any pissing contestes between it and new intel\AMD CPU's to be developed will just have to wait.

Note that AMD's Opteron is available since 22nd April 2003.

I dont have anything against AMD\intel per se, but an improvement as big as this is great for those many people who want to get away from M$ dominated arena's,

Just hating something is childish It must make business sense for them.

It would interesting on what proportion would be the X86 Linux users VS PPC Linux users. Does anyone has sales the data from United Linux and Red Hat Linux?    

and at the moment, M$ is dictating to AMD\intel where they should be going for the x86 platform.

There’s business reason for this i.e. majority of Intel/AMD's revenues is obtained from MS based solutions.

With this new processor some very competitive preformance that has been sorely needed is being brought back to the PPC, and in combination with Mac, Linux and Amiga products perhaps it will begin a bit of an exodous from wintel systems

Are you saying that going PPC will guard against MS?  Don't you know dotNET ecosystem is currently being ported to Linux?

All MS has to do (IF it make business sense for going into PPC in MS's POV) is to rehash PowerPC edition Windows NT x.0 with dotNET ecosystem.

and make M$ pull its monopolistic head in.

Note that the Mac**, Amiga** and Atari** were a monopoly within their own markets. **During the reign of 68K.

Microsoft has made the X86 platform a commodity (against the wishes of  IBM), thus crushing the non-commodity platforms.  

This kind of rhetoric (naming calling and negative labeling) doesn’t wash i.e. since I’m old enough to recall the once monopolistic IBM during early 80s. Not one companies you mentioned is an angel in regards monopolistic tendencies.

[Hammer]

None of those companies has been found guilty in an antitrust case have they?

IBM (1956). It lasted for 40 years (ended at ~1996 ).

Have you looked at microsoft lisencing policies and costs?

Almost everyday.

In Aust to buy a simple system $450 windows,

Looking at "DIY Computer Market"(Parramatta) price list...

OEM Windows XP Home Edition cost $185 AUD.
Security hologram seems to be genuine....

A Volume License purchases is a lot cheaper than that (i.e. lower per unit). The famed “Corporate Edition”.

$1000 for office.Thats more than the PC to run it in most cases.

Looking at "DIY Computer Market"(Parramatta) price...

MS Office XP Professional OEM $480 AUD.  
Security hologram seems to be genuine....

.NET is a move towards paying a subsricption to use M$ software...and you still have to buy the software to begin with.

It's an option.  An example MS’s 2003 product line up i.e. I recall, MS Windows Server 2003 (a.k.a dotNET server) is still being sold as a box (i.e. not as a subscription).

[Hammer]

The added advantages is that it provides an alternaive to the wintel which is very important to alot of people.  There are alot of people who have grown more than dissatisfied with what the x86 offers, and can no longer trust M$.

(Sigh) Have you statistically tested "There are alot of people who have grown more than dissatisfied with what the x86 offers"?

I am one of those people, I make no bones about it.

There's no point staying in dreamland i.e. one has to do a SWOT analysis for the said product.

However, if you believe, like you seem to do, that x86 and M$ is the way to go,

That's your assumption.

 then I think you may find that you are in the wrong place.

Such statements are completely irrelevant to the topic at hand. Please the personality out of this.

[Hammer]

Then when they reach 100 stage 1 instruction wide

Not quite 1 instruction wide. Note that Northwood's ALU throughput has four 32 bit ops/cycle.
 

bazillion gigahertz, they can compensate their instruction/cache misses (SNIP)

Increase in trace cache was one solution for  deeper pipelines related problems. Not just clock speed.

The advent of netbox.co.uk/set-tops should aleviate some of this.
 

Note that it’s VIA C3 powered based machine...
http://www.netbox.co.uk/netbox/html/techspecs.htm

As such, it may not have the performance to compete with thin and light "Pentium M" based boxes. Then again, Netbox has to compete with Shuttle branded PCs (they offer Athlon/nForce2 and Pentium/845based solutions).

[Hammer]

Yeah, I did make an assumtion, you have said nothing to the contrary of that assumption.

Did you missed Windows Server 2003 for 2003 product line up example? DotNET is just an ecosystem i.e. a platform to target (refer to Visual Studio dotNET).
 

If .NET and x86 technology is not what you are supporting, then what are you supporting?

Is that relevant?

Aust Govt has issued directives to move to more cost effective use of software resulting in several key departments changing to linux

"Nothing new under the sun" in regards Oz Gov's use of *nix based OS. Did you miss the statement in regards to the level of “proportion”. Note that those Linux boxes would be X86 powered box.

Note that X86 Linux can run some of the Windows based software investments (half the performance penalty is not such a big deal when people can buy 3Ghz machines).

Pick up a magazine and with each issue you see more and more linux related articles(and software on the CD).

More of the same; majority of cover mounted CD/DVDs Magazines continue to contain large proportion of Windows based titles.

They just encourage dual boot scenarios and interconnectivity between the two OS platforms.
The mentality is to run as many applications on a single box. The purpose of a PC is a general machine not tied into a specific role.

My sample size;
1. Australia's PowerPlay DVD.
2. UK's PCFormat.
3. UK's PCPlus.
4. Australian PC User.
5. Australian Personal Computer (APC).
6. Australian PC World.
7. Australian PC Authority.
8. Computer Music.
9. PC Basics/PC Projects.
10. UK's PC Answers.
11. Australia's Computer Market.

Ever since APC’s release of Redhat 6 to Red Hat 8(inc. Mandrake 9) on pocket books series the Linux article’s proportions compared Windows remained much of the same.

X86 Linux developed it’s own market niche. On the entertainment side of things, the situation didn’t change much.  As one of slashdot user would say***, it’s all about games, games, games…  ***One of the reason why MS wouldn’t die.

[Hammer]

Nevertheless, the IBM 970 will give the PPC platform a boost in the performance area exactly when it is badly needed which will give people more options and will make the market more competetive which is good for all consumers.

I didn't state that the IBM's PPC 970 product is bad for consumers.

If these benchmarks are fake I guess time will tell.

Just make sure IBM delivers the product and it’s cost competitive, NOT just performance competitive.

I doubt IBM would produce a CPU that was crap as there would be no money in it, and they have a knack of making money.

Did you forget IBM's PS/2 era venture. The PS/2 era regime almost killed IBM.

Of course IBM will/or attempt to produce a product that is competitive. A scenario not much different to PPC 601 vs Pentium Classic days.  

[Hammer]

Yes it is relevant, without a clear POV no-one can see where you are arguing from,

Follow the thread.

I dont particularly care what magazines encourage,

IF that’s your intentions.  

the fact is that 5 years ago these magazines had much less linux related product included in them if ANY.

Some of those magazines also contained (and cover mounted) OS/2 Warp, QNX and X86 BeOS. There’s nothing new under the sun.   Refer back to what magazines encouraged.

The TCPA issue is also forcing a choice between windows and linux.

Microsoft's implementation of TCPA is the Palladium. This particular implementation is quite lame in Longhorn.

Operating system discussions (e.g. Linux vs Windows) is outside of this topic.

[Hammer]

Have you looked at microsoft lisencing policies and costs?

Just hope you have the experience in dealing (selling) with Microsoft products to corporate clients and volume buyers. The cost you quoted for per unit basis at volume amount is wrong. The amount quoted is not the amount.

(This not the amount which I buy from wholesale/volume (e.g. best buy)). The quoted OEM prices refer to end-users price.

There is much business sense in moving away from those kinds of costs, especially for the home user.

You are forgetting the soft skills factor…

With TCPA M$ is forcing people to use thier products or become incompatible...even with earlier windows products.
.

Such statement contradicts Microsoft's David Cutler (NT’s top banana) in regards to the importance of software investment protection.    

It is also an attempt to kill GPL as you cant afford to get certification. All this on the x86 platform.
.

Careful with "It is also an attempt to kill GPL as you cant afford to get certification. All this on the x86 platform." statement.

Reference;
http://search.amd.com/amd_query.html?col=spec1&col=a4&col=a2&col=a3&col=a1&col=a5&charset=utf-8&ht=0&qp=url%3A%2Fus-en%2F+url%3A%2Fgb-uk%2F+url%3A%2Fepd%2F&qt=Linux+Future&qs=+%7C+language%3Aen&qc=&pw=100%25&ws=1&la=en&qm=0&st=1&nh=10&lk=1&rf=0&rq=0&si=0

Hector Ruiz has stated that their future is with Linux and Windows. Linux would be fine under AMD's processors.

Note that Intel/HP directly supports OpenVMS for IA-64.

Also refer to;
http://www.computerworld.co.nz/webhome.nsf/UNID/C6D47647C87E74CFCC256C040081D748!opendocument

TCPA is backed by industry heavyweights such as Intel, Compaq/HP, IBM and of course Microsoft. It and Palladium are both seen as business enabling technologies

Notice IBM.

For Palladium to work; both HW and SW must be aware with another. Note that the Longhorn beta works with the current x86 HW...

anyway, all of this is speculation until it all happens, maybe we should take about it again in 5-10 years.

Try again.

[Hammer]

the fact is that 5 years ago these magazines had much less linux related product included in them if ANY.This shows a clear move away from windows.

To illustrate the proportion of the world _desktop_ users (as of 2002);
Linux has 0.25%
MacOS has 4%
 
Source: Paul Robinson and Dan Corkery, Operating In Linux - 3rd Edition, Next Publishing, 2002.