Having a logic netlist is only part of the battle when it comes to designing a microprocessor. It will be up to the user to do all of the physical design work. Since the wire delays between gates are becoming more significant than the gate delays, it can be argued that the physical design is the more difficult part of the problem. It is time consuming and expensive work, and needs to be repeated for each different fab.
It's cool that they were able to load it into a xilinx part and get it working at 100 MHz. But a microprocessor inside a PLD will never be competitive in terms of cost or speed with a custom design.
This may compete with the synthesizable core supplied by MIPS and others, but synthesizable cores are not the mainstay of their business.
It is likely that MIPS and ARM will protect their intellectual property. MIPS probably hasn't acted yet because their lawyers haven't had time to digest this yet.
It's time to change the mind-set about these attacks. The attacks wouldn't be possible without plentiful insecure machines to use as zombies. The organizations which are failing to use good security practices on their machines are a significant part of the problem, not innocent victims. Perhaps there should be some sort of penalty for lax security which allows your machine to be used in a DDOS attack. This might be a way to get security to be taken more seriously.
MIPS is not longer owned by SGI. SGI still uses MIPS processors, and has one in design, but they are not in the business of supplying processors to other companies. MIPS Inc and other suppliers do sell MIPS processors, but they tend to concentrate on the embedded market. So it seems quite unlikely that SGI is working on porting any MAC OS to MIPS.
The suggestion that AMD would create a version of the Athlon to run MAC OS also seems very unlikely. The story make it sound like a simple matter to remove X86 "emulation" from the Athlon. This is nonsense. It would be a huge redesign. The Athlon is an x86 processor, not an emulator.
For use on earth this seems to be limited by the fact that you need to put energy in to the system, and most of our energy generation involves the production of co2.
However, energy is one of the things which is not in short supply when you're in orbit, but carbon is. This might be a useful part of the life support system of a space habitat. Allowing co2 to be recycled as methanol using plentiful solar energy.
The next questions is: what do you do with the methanol?
The 3120 chip is a bit large at 77mmsq for its target market. This makes it significantly more expensive than the competition. Competing chips in this market are more on the order of $20 and 20-30mmsq. Transmeta has compared the 3120 to PII and PIII in their release, but it is important to note that PII and PIII are not important players in the much more cost sensitive embedded market which the 3120 is intended to address.
BTW, S3 recently acquired Diamond, so I don't think S3 has a separate project going with Transmeta.
The reviewer mentions that he'd like to see experiments with human computers like the calculor.
It turns out that, they used something similar to the calculor during the Manhattan project. A room full of people with mechanical calculators working on the same problem. They passed partial results to each other on pieces of paper according to a sort of program.
Your statements regarding metal widths are not inaccurate.
I have worked with three different 0.18 micron processes, and the minimum metal width for lower metals is between 0.26 and 0.28 microns. The minimum wire widths are process limits, not RC limits. An 0.18 wide wire would be about 50 % more resistive than than an 0.28 wide wire, but would have lower capacitance. If the fabs could make wires this narrow, they probably would.
DES is about to be obsoleted and replaced by AES. Will this chip be able to adopt new standards when they come out? It should be possible to build a chip which is a general Feistal network engine which could run both DES and newer algorithms such as twofish, which is an AES candidate. This chip does not appear to have such flexibility.
You're likely to get a better deal through a group policy. A co-worker of mine had a nice PPO policy through the IEEE. It was basically the same policy as was provided by our employer. You need to be a member of IEEE, but there are other benefits such as lower conference fees and book discounts which make the membership fee worthwhile. It's likely that there are policies available through other professional organizations as well (ACM?). This may even be worth doing if you have company coverage, in order to have portable insurance. You can usually get your employer to pay for your outside group policy rather than theirs.
Re:Someone Wanna Grab that Palm Pilot?
on
Password Overload
·
· Score: 1
There's a nice freeware encryption package for the pilot call cipher. It uses IDEA (128 bit keys).
I looked up Infineon, and found that it's the recently spun off Siemens Semiconductor operation. Infineon say they'll have 0.17u EDRAM at about the same time the Glaze is supposed to be available. It's likely that they still have lots of design work to do before this chip tapes out.
Every graphics chip supplier will need EDRAM for the next generation, and from what I've heard, they're all working on it.
Slashdot Mirror
The mechanisms by which genes code for structure
are reasonably well understood. There's no need
to invoke mysterious fractal magic to explain
it.
A good non-technical book on the subject
is:
"The Art of Genes: How Organisms Make Themselves"
by Enrico Coen
The fact that he wants to invoke fractals in
introns to explain structure suggests that
he dosen't know the molecular biology very
well.
This same idea is used in Greg Egan's SF novel
'Distress', published in June 1997.
All they are providing is a logical design.
Having a logic netlist is only part of the battle when it comes to
designing a microprocessor. It will be up to the user to do all of
the physical design work. Since the wire delays between gates are
becoming more significant than the gate delays, it can be argued that
the physical design is the more difficult part of the problem. It is
time consuming and expensive work, and needs to be repeated for each
different fab.
It's cool that they were able to load it into a xilinx part and get
it working at 100 MHz. But a microprocessor inside a PLD will never
be competitive in terms of cost or speed with a custom design.
This may compete with the synthesizable core supplied by MIPS and
others, but synthesizable cores are not the mainstay of their business.
It is likely that MIPS and ARM will protect their intellectual
property. MIPS probably hasn't acted yet because their lawyers
haven't had time to digest this yet.
It's time to change the mind-set about these attacks. The attacks
wouldn't be possible without plentiful insecure machines to use as
zombies. The organizations which are failing to use good security
practices on their machines are a significant part of the problem, not
innocent victims. Perhaps there should be some sort of penalty for
lax security which allows your machine to be used in a DDOS attack.
This might be a way to get security to be taken more seriously.
MIPS is not longer owned by SGI. SGI still uses MIPS processors, and
has one in design, but they are not in the business of supplying
processors to other companies. MIPS Inc and other suppliers do sell
MIPS processors, but they tend to concentrate on the embedded market.
So it seems quite unlikely that SGI is working on porting any MAC OS
to MIPS.
The suggestion that AMD would create a version of the Athlon to run
MAC OS also seems very unlikely. The story make it sound like a
simple matter to remove X86 "emulation" from the Athlon. This is
nonsense. It would be a huge redesign. The Athlon is an x86
processor, not an emulator.
For use on earth this seems to be limited by the fact that you need to
put energy in to the system, and most of our energy generation
involves the production of co2.
However, energy is one of the things which is not in short supply when
you're in orbit, but carbon is. This might be a useful part of the
life support system of a space habitat. Allowing co2 to be recycled
as methanol using plentiful solar energy.
The next questions is: what do you do with the methanol?
The 3120 chip is a bit large at 77mmsq for its target market. This
makes it significantly more expensive than the competition. Competing
chips in this market are more on the order of $20 and 20-30mmsq.
Transmeta has compared the 3120 to PII and PIII in their release, but
it is important to note that PII and PIII are not important players in
the much more cost sensitive embedded market which the 3120 is
intended to address.
BTW, S3 recently acquired Diamond, so I don't think S3 has a separate
project going with Transmeta.
The reviewer mentions that he'd like to see experiments with human
computers like the calculor.
It turns out that, they used something similar to the calculor during
the Manhattan project. A room full of people with mechanical
calculators working on the same problem. They passed partial results
to each other on pieces of paper according to a sort of program.
Your statements regarding metal widths are not inaccurate.
I have worked with three different 0.18 micron processes, and the minimum
metal width for lower metals is between 0.26 and 0.28 microns. The minimum
wire widths are process limits, not RC limits. An 0.18 wide wire would be
about 50 % more resistive than than an 0.28 wide wire, but would have lower
capacitance. If the fabs could make wires this narrow, they probably would.
DES is about to be obsoleted and replaced by AES. Will this chip be able to
adopt new standards when they come out? It should be possible to build a
chip which is a general Feistal network engine which could run both DES and
newer algorithms such as twofish, which is an AES candidate. This chip does not
appear to have such flexibility.
You're likely to get a better deal through a group
policy. A co-worker of mine had a nice PPO policy
through the IEEE. It was basically the same policy as was provided by our employer. You need
to be a member of IEEE, but there are other benefits such as lower conference fees and book
discounts which make the membership fee worthwhile. It's likely
that there are policies available through other
professional organizations as well (ACM?).
This may even be worth doing if you have company
coverage, in order to have portable insurance. You
can usually get your employer to pay for your
outside group policy rather than theirs.
There's a nice freeware encryption package for the
pilot call cipher. It uses IDEA (128 bit keys).
I use it to encrypt passwords on my pilot
I looked up Infineon, and found that it's the
recently spun off Siemens Semiconductor operation.
Infineon say they'll have 0.17u EDRAM at about the
same time the Glaze is supposed to be available.
It's likely that they still have lots of design work to do before this chip tapes out.
Every graphics chip supplier will need EDRAM for the next generation, and from what I've heard,
they're all working on it.
We'll see who has it first.