"Michele Russo" <russomiche@yahoo.it> wrote in message 
news:e78kr4$88v$1@news.cineca.it...
> Wilco Dijkstra wrote:
>> That's because you didn't give enough information to answer it.
>> For example, what definition of VLIW do you use in your paper?
>> It is clear that Multiflow was a VLIW (28 instructions per cycle),
>> but when does a LIW become a VLIW (or EPIC for that matter)?
>>
>> If you can also tell us how wide each the above architectures are,
>> we will have enough information to answer your question.
>
> Thank you very much. My paper is about design space exploration of VLIW 
> architectures for embedded systems. In the related section of my paper, I 
> would like to present a list of commercial VLIW targeted for embedded 
> system which can be also classified as ASIP. I'm not sure that the 
> aforementioned VLIWs can be classified as ASIPs and for this reason I 
> wrote to this ng.

I'm not convinced the architectures you mentioned can all be categorized
as VLIW in the first place. For example calling 64-bit instruction packets
VLIW is a bit of a stretch.

> More precisaly this is the sentence I wrote in my paper:
>
> ASIP based on \emph{Very Long Instruction Word} (VLIW)
> architectures~\cite{fisher_isca83} are emerging in the embedded
> domain, especially for multimedia and communication
> appplications. Examples include the TI C6x family, the Agere/Motorola
> StarCore architecture, Sun's MAJC, Fujitsu's FR-V, ST's HP/ST Lx,
> Philips' TriMedia. Architectures based on VLIW processors are
> currently seen as answering the demand for modern, increasingly
> complex embedded multimedia applications, given their capacity to
> exploit high levels of performance while maintaining a reasonable
> trade-off between hardware complexity, cost and power consumption.

But what about codesize?

> A reviewer of the paper states that "My understanding is that the 
> processors listed on page 2 are not actually ASIPs."

If you use a wide definition then most of them are not ASIP as they
were intended as general purpose CPUs geared towards DSP.
With a narrow definition obviously none are ASIPs. Crusoe is a good
example of a ASIP VLIW.

Wilco

Wilco Dijkstra wrote:
> That's because you didn't give enough information to answer it.
> For example, what definition of VLIW do you use in your paper?
> It is clear that Multiflow was a VLIW (28 instructions per cycle),
> but when does a LIW become a VLIW (or EPIC for that matter)?
> 
> If you can also tell us how wide each the above architectures are,
> we will have enough information to answer your question.

Thank you very much. My paper is about design space exploration of VLIW 
architectures for embedded systems. In the related section of my paper, 
I would like to present a list of commercial VLIW targeted for embedded 
system which can be also classified as ASIP. I'm not sure that the 
aforementioned VLIWs can be classified as ASIPs and for this reason I 
wrote to this ng.

More precisaly this is the sentence I wrote in my paper:

ASIP based on \emph{Very Long Instruction Word} (VLIW)
architectures~\cite{fisher_isca83} are emerging in the embedded
domain, especially for multimedia and communication
appplications. Examples include the TI C6x family, the Agere/Motorola
StarCore architecture, Sun's MAJC, Fujitsu's FR-V, ST's HP/ST Lx,
Philips' TriMedia. Architectures based on VLIW processors are
currently seen as answering the demand for modern, increasingly
complex embedded multimedia applications, given their capacity to
exploit high levels of performance while maintaining a reasonable
trade-off between hardware complexity, cost and power consumption.

A reviewer of the paper states that "My understanding is that the 
processors listed on page 2 are not actually ASIPs."

What do you think?

Regards,

Michele

"Michele Russo" <russomiche@yahoo.it> wrote in message 
news:e78ave$450$1@news.cineca.it...
> Jim Stewart wrote:
>> Michele Russo wrote:
>>
>>> Hello all,
>>>
>>> Please, check one or more of the following which can be classified as 
>>> ASIP based on VLIW.
>>>
>>> [ ] TI C6x
>>> [ ] Agere/Motorola StarCore
>>> [ ] Sun MAJC
>>> [ ] Fujitsu FR-V
>>> [ ] ST Lx
>>> [ ] Philips TriMedia
>>
>>
>> Please do your own homework.
>
> It is a pity that nobody in this ng is able to reply to this question.

That's because you didn't give enough information to answer it.
For example, what definition of VLIW do you use in your paper?
It is clear that Multiflow was a VLIW (28 instructions per cycle),
but when does a LIW become a VLIW (or EPIC for that matter)?

If you can also tell us how wide each the above architectures are,
we will have enough information to answer your question.

Wilco

Jim Stewart wrote:
> Michele Russo wrote:
> 
>> Hello all,
>>
>> Please, check one or more of the following which can be classified as 
>> ASIP based on VLIW.
>>
>> [ ] TI C6x
>> [ ] Agere/Motorola StarCore
>> [ ] Sun MAJC
>> [ ] Fujitsu FR-V
>> [ ] ST Lx
>> [ ] Philips TriMedia
> 
> 
> Please do your own homework.

It is a pity that nobody in this ng is able to reply to this question.

At any rate I adjure that I'm not a student!

Regards,

Michele

CBFalconer wrote:
> My opinion is that you are still trying to get out of homework, and
> your instructor marked you down for faking an earlier paper.

Thank you very much fou your kindly answer. Your comments are very useful!

Michele Russo wrote:
> CBFalconer wrote:
>> Michele Russo wrote:
>>
>>> Please, check one or more of the following which can be classified
>>> as ASIP based on VLIW.
>>>
>>> [ ] TI C6x
>>> [ ] Agere/Motorola StarCore
>>> [ ] Sun MAJC
>>> [ ] Fujitsu FR-V
>>> [ ] ST Lx
>>> [ ] Philips TriMedia
>>
>> You omitted your instructors email address.
> 
> No. I'm an assistant researcher. A reviewer of a paper of mine
> said that "the processors listed above are not actually ASIPs."
> 
> I would like to know your opinion about that.

My opinion is that you are still trying to get out of homework, and
your instructor marked you down for faking an earlier paper.

-- 
"If you want to post a followup via groups.google.com, don't use
 the broken "Reply" link at the bottom of the article.  Click on 
 "show options" at the top of the article, then click on the 
 "Reply" at the bottom of the article headers." - Keith Thompson
More details at: <http://cfaj.freeshell.org/google/>
Also see <http://www.safalra.com/special/googlegroupsreply/>

Michele Russo wrote:

> Hello all,
> 
> Please, check one or more of the following which can be classified as 
> ASIP based on VLIW.
> 
> [ ] TI C6x
> [ ] Agere/Motorola StarCore
> [ ] Sun MAJC
> [ ] Fujitsu FR-V
> [ ] ST Lx
> [ ] Philips TriMedia

Please do your own homework.

CBFalconer wrote:
> Michele Russo wrote:
> 
>>Please, check one or more of the following which can be classified
>>as ASIP based on VLIW.
>>
>>[ ] TI C6x
>>[ ] Agere/Motorola StarCore
>>[ ] Sun MAJC
>>[ ] Fujitsu FR-V
>>[ ] ST Lx
>>[ ] Philips TriMedia
> 
> 
> You omitted your instructors email address.
> 

No. I'm an assistant researcher. A reviewer of a paper of mine said that 
"the processors listed above are not actually ASIPs."

I would like to know your opinion about that.

Regards,

Michele

Michele Russo wrote:
> 
> Please, check one or more of the following which can be classified
> as ASIP based on VLIW.
> 
> [ ] TI C6x
> [ ] Agere/Motorola StarCore
> [ ] Sun MAJC
> [ ] Fujitsu FR-V
> [ ] ST Lx
> [ ] Philips TriMedia

You omitted your instructors email address.

-- 
 "A man who is right every time is not likely to do very much."
                           -- Francis Crick, co-discover of DNA
 "There is nothing more amazing than stupidity in action."
                                             -- Thomas Matthews