Nvidia Said to Take On Intel in Tablet Computer Chips

On 22 Aug 2010 23:02:44 +0100 (BST), Paul Gotch
wrote:

In comp.arch MitchAlsup wrote:
An advantage so great it has been revoved from the (re)merger of Power
and Power-PC.

The "merger" was mostly marketeering. Power processors, since the Power2, I
think, used the PowerPC architecture.

VMX (IBM call it something different as FreeScale own the AltiVec
trademark) is part of the Power ISA v2.03 and is implemented in POWER
6 and beyond, although before this IBM consistently left it out.

VMX was in the '970 (Apple's G5), which was based on the Power-4.

"Brett Davis" wrote in message
...
In article
,
Robert Myers wrote:

On Aug 17, 1:52 pm, Yousuf Khan wrote:


In most modern implementations of x86, certain common instructions are
considered hard-coded, while others are emulated through microcode. Most
floating point instructions are a series of more basic instructions.


I'll take the word of real computer architects on this one, Yousuf.
Past the decode stage, the ISA doesn't matter. Programmers and others
like to talk about ISA's because that's all they understand. ISA is
irrelevant now. Whatever obstacles there are to "emulating" x86 have
nothing to do with the ISA.

Robert.

You are wrong.

I give you the example of Apple's AltiVec instruction set.
AltiVec at introduction gave the PowerPC chips a 10x speed advantage
on a bunch of important graphical benchmarks, and makes the vector
processor useful in a wide variety of other tasks that are not
normally thought of as vector code. (Filesystem block allocation, etc.)

Ultimately this one innovation alone was not enough for PowerPC to
overcome all the disadvantages of competing against Intel, but it
did level the playing field for a decade.

AltiVec came from a software firm, those "real computer architects"
idea of innovation was Thumb1 and MIPS16, bunch of (CENSORED).

Brett


Not sure if relevant in this discussion but the ISA makes a huge difference to
the code density (discussed in comp.arch.embedded)

See http://www.csl.cornell.edu/~vince/pa...d09/iccd09.pdf

Hans
www.ht-lab.com

In article ,
Brett Davis wrote:

Ultimately this one innovation alone was not enough for PowerPC to
overcome all the disadvantages of competing against Intel, but it
did level the playing field for a decade.

Not really. Witness how many other companies showed an interest;
it wasn't even up to the level of SPARC or MIPS, though I accept
that there were other reasons than performance that dominated.

I call "bull****" on you.
SPARC and MIPS do not have the spare opcode space to implement the
AltiVec permute instructions, and then there is the little issue of
Apple owning the patents.

I was referring to the number of other companies that were interested
in licensing PowerPC, let alone PowerPC+Altivec. Far more pursued
SPARC and MIPS.


Regards,
Nick Maclaren.

HT-Lab wrote:
Not sure if relevant in this discussion but the ISA makes a huge difference to
the code density (discussed in comp.arch.embedded)

If you define "huge difference" as 2X then you're right.

For embedded stuff this can easily be the difference between making it
all fit or not, but it isn't really a _big_ worry for 32-bit platforms.

Terje
(who used to spend weeks getting DOS TSRs as small as possible.)
--
- Terje.Mathisen at tmsw.no
"almost all programming can be viewed as an exercise in caching"

Canada had scored 25 goals in its first four games, 'Bills jerseys'
(http://www.b2bjersey.com/nfl-jerseys...eys-c-1_5.html)
including at least six in every game.To go 59 minutes thereafter with no
more goals was somewhat 'cheap Bills jersey'
(http://www.b2bjersey.com/nfl-jerseys...eys-c-1_5.html)
unexpected, said Burnett 'Panthers jersey' (http://tinyurl.com/2um6xjn)
. There were a lot of 'cheap Panthers jersey'
(http://tinyurl.com/2um6xjn) ups and downs through the first 40 minutes,
but I thought our team really settled down, and we may have only given
up only one quality scoring chance in the third period.




--
tuvw734

In article , wrote:

In article ,
Brett Davis wrote:

Ultimately this one innovation alone was not enough for PowerPC to
overcome all the disadvantages of competing against Intel, but it
did level the playing field for a decade.

Not really. Witness how many other companies showed an interest;
it wasn't even up to the level of SPARC or MIPS, though I accept
that there were other reasons than performance that dominated.

I call "bull****" on you.
SPARC and MIPS do not have the spare opcode space to implement the
AltiVec permute instructions, and then there is the little issue of
Apple owning the patents.

I was referring to the number of other companies that were interested
in licensing PowerPC, let alone PowerPC+Altivec. Far more pursued
SPARC and MIPS.

The car you drive probably has close to a dozen PowerPC chips in it.
MOT is a $20 billion a year electronics company, and most of those
chips have PowerPC hidden in them.
IBM sells the PowerPC chips in your Tivo/DVR and all three consoles.
(Playstation3, XBox360, and Wii.)

ARMH is a far distant second in sales at ~$600 million a year.
(Pre-iPhone I remember them being a ~$200 million a year company...)

MIPS has yearly sales of $70 million. Used to be twice that?
(Hard to fund a design teem and stay relevant/solvent at that size...)

SPARC as snot for sales outside of SUN/JAVA and Fujitsu.

AltiVec has clearly mattered in making PowerPC the dominate RISC chip.
MIPS used to be significant, the Playstation1 and 2 were MIPS based.

PowerPC has ~90% market share in the 32bit market, and ~99% of the
64bit embedded market. (Dollar share, not unit share.)
Up from zero a decade ago.

If PowerPC was just another RISC chip this could not have happened.
Being late to the market with a me-too product would not have worked.
PowerPC dominates because of AltiVec and the bitfield extract and
other cool useful instructions that give good performance and good
inner loop code density.

Programmers LIKE PowerPC, whereas MIPS and ARM are tolerated.
(This is a major reason PowerPC dominates, pity the fool manager
that picks MIPS and cant find good programmers to work for him.)

ISA does matter, just not the way you think it does.

Brett - Actually working on ARM code right now.

On 24.8.2010 8:32, Brett Davis wrote:
The car you drive probably has close to a dozen PowerPC chips in it.
MOT is a $20 billion a year electronics company, and most of those
chips have PowerPC hidden in them.

The semiconductor business of MOT was transferred to Freescale
Semiconductor in 2004, which is a 3.5B company.

PowerPC dominates because of AltiVec and the bitfield extract and
other cool useful instructions that give good performance and good
inner loop code density.

I would say PowerPC is big in the embedded market due to the
good spectrum of different chips that have rich set of peripherials.
The processor itself is not that critical, all the support logic around
is (memory controllers,i2c, ethernet, accelerators, flash, usb etc.).
This is where Intel for example has problems with their Atom.

--Kim

On Aug 24, 1:32*am, Brett Davis wrote:


Programmers LIKE PowerPC, whereas MIPS and ARM are tolerated.
(This is a major reason PowerPC dominates, pity the fool manager
that picks MIPS and cant find good programmers to work for him.)


Always good to have insightful advice about programming from a
programmer in a hardware forum.

The original context, which you destroyed by your cross-post, has been
completely lost.

Have you heard of comp.arch.embedded?

Robert.

In article ,
Kim Enkovaara wrote:
On 24.8.2010 8:32, Brett Davis wrote:

PowerPC dominates because of AltiVec and the bitfield extract and
other cool useful instructions that give good performance and good
inner loop code density.

I would say PowerPC is big in the embedded market due to the
good spectrum of different chips that have rich set of peripherials.
The processor itself is not that critical, all the support logic around
is (memory controllers,i2c, ethernet, accelerators, flash, usb etc.).
This is where Intel for example has problems with their Atom.

Perhaps. It's not my area. What I do know is that it was taken up
by the embedded market long before Aptivec was invented, so the
claim that it was taken up because of Aptivec is more than a little
erroneous.


Regards,
Nick Maclaren.

On Aug 24, 6:22*am, Paul Gotch wrote:

There are over 1 billion ARM cores across all architecture profiles
shipped per quarter.

I suspect that if you include mobile devices in the "embedded" world,
Power and/or PowerPC don't even make the top 10 core-units.

Mitch