Article: AMD's Analyst Update
By: David Kanter (dkanter.delete@this.realworldtech.com), February 10, 2012 7:58 pm
Room: Moderated Discussions
Brett (ggtgp@yahoo.com) on 2/10/12 wrote:
---------------------------
>Anon (no@email.com) on 2/10/12 wrote:
>---------------------------
>>Brett (ggtgp@yahoo.com) on 2/10/12 wrote:
>>---------------------------
>>>Apple is rumored to be developing a CPU based on [OpenCL]. (Apple created OpenGL) [and OpenCL]
>>
>>ROTFL, go back and start again, cool aid boy!
>>(sorry, thats a bit personal, but come on...)
>
>Kool-Aid is spelled with a K not a C.
>
>>Next time perhaps put a C in there, not a G!
>
>An easy typo to make, mistake noted.
>
>>And since when did apple matter AT ALL in high performance?
>>it doesnt take much to plan music or videos - do they have any other market these days?
>
>That sort of comment has been made about everything Apple has done, phones, portable
>music players, tablets, x86 desktops, PowerPC desktops, >etc.
There's a big difference. Apple explicitly targeted those markets (music players, phones, etc.) with their products. They have NEVER targeted HPC, and have entirely backed away from anything that looks like a server. So Anon's statement is quite reasonable.
>I can come up with a list of reasons why a Macroscalar >Processor cannot do better
>than any other CPU, and thus is doomed.
>Apple does not ship anything until it is polished and >better than the alternatives,
>bad products don't ship at Apple. If this ships it will be >worth a look.
Uh huh. Like all these:
http://www.networkworld.com/community/node/44206
Apple is good, but they are hardly perfect. Plenty of their products and software have been poor in comparison to the alternatives. But that's true of most companies. Apple excels in that they have a high success rate (not perfect though) and have an uncanny ability to shape how consumer preference (and thus markets) will evolve. That necessarily involves taking risks, which means you sometimes fail.
>>>Apples Macroscalar Processor Architecture
>>>http://www.macrumors.com/2012/02/06/apples-macroscalar-trademark-application-sparks-speculation-on-processor-architecture-advances/
>>>
>>>http://www.appleinsider.com/articles/12/02/06/apple_trademarks_its_patented_macroscalar_code_optimization_technology.html
>>
>>>
>>>http://www.patentlyapple.com/patently-apple/2012/02/apples-macroscalar-architecture-will-it-take-ios-to-the-next-level.html
>>>
>>>Google patents list for Macroscalar
>>>http://www.google.com/search?tbm=pts&tbo=p&hl=en&q=macroscalar
>>
>
>Excuse me for thinking that CPU architecture details are on topic here.
>I will wait for these new features detailed in the above patent docs to be rumored
>for inclusion in the next x86 extension to mention it >again.
It's very much on topic, but it would be good if you didn't hijack the thread. Honestly the topic seems important enough to merit its own thread.
Honestly, I've seen a few macroscalar articles, but they all seem to ignore the ~50 years of previous compiler tricks. Many of which are techniques for aggressively scheduling loops in parallel.
David
---------------------------
>Anon (no@email.com) on 2/10/12 wrote:
>---------------------------
>>Brett (ggtgp@yahoo.com) on 2/10/12 wrote:
>>---------------------------
>>>Apple is rumored to be developing a CPU based on [OpenCL]. (Apple created OpenGL) [and OpenCL]
>>
>>ROTFL, go back and start again, cool aid boy!
>>(sorry, thats a bit personal, but come on...)
>
>Kool-Aid is spelled with a K not a C.
>
>>Next time perhaps put a C in there, not a G!
>
>An easy typo to make, mistake noted.
>
>>And since when did apple matter AT ALL in high performance?
>>it doesnt take much to plan music or videos - do they have any other market these days?
>
>That sort of comment has been made about everything Apple has done, phones, portable
>music players, tablets, x86 desktops, PowerPC desktops, >etc.
There's a big difference. Apple explicitly targeted those markets (music players, phones, etc.) with their products. They have NEVER targeted HPC, and have entirely backed away from anything that looks like a server. So Anon's statement is quite reasonable.
>I can come up with a list of reasons why a Macroscalar >Processor cannot do better
>than any other CPU, and thus is doomed.
>Apple does not ship anything until it is polished and >better than the alternatives,
>bad products don't ship at Apple. If this ships it will be >worth a look.
Uh huh. Like all these:
http://www.networkworld.com/community/node/44206
Apple is good, but they are hardly perfect. Plenty of their products and software have been poor in comparison to the alternatives. But that's true of most companies. Apple excels in that they have a high success rate (not perfect though) and have an uncanny ability to shape how consumer preference (and thus markets) will evolve. That necessarily involves taking risks, which means you sometimes fail.
>>>Apples Macroscalar Processor Architecture
>>>http://www.macrumors.com/2012/02/06/apples-macroscalar-trademark-application-sparks-speculation-on-processor-architecture-advances/
>>>
>>>http://www.appleinsider.com/articles/12/02/06/apple_trademarks_its_patented_macroscalar_code_optimization_technology.html
>>
>>>
>>>http://www.patentlyapple.com/patently-apple/2012/02/apples-macroscalar-architecture-will-it-take-ios-to-the-next-level.html
>>>
>>>Google patents list for Macroscalar
>>>http://www.google.com/search?tbm=pts&tbo=p&hl=en&q=macroscalar
>>
>
>Excuse me for thinking that CPU architecture details are on topic here.
>I will wait for these new features detailed in the above patent docs to be rumored
>for inclusion in the next x86 extension to mention it >again.
It's very much on topic, but it would be good if you didn't hijack the thread. Honestly the topic seems important enough to merit its own thread.
Honestly, I've seen a few macroscalar articles, but they all seem to ignore the ~50 years of previous compiler tricks. Many of which are techniques for aggressively scheduling loops in parallel.
David
Topic | Posted By | Date |
---|---|---|
Fused Multiply-Add and HSA | Richard H. | 2012/02/07 06:29 PM |
Fused Multiply-Add and HSA | David Kanter | 2012/02/07 10:54 PM |
"CUDA is on its way out" | pk | 2012/02/09 04:37 AM |
"CUDA is on its way out" | David Kanter | 2012/02/09 10:49 AM |
"CUDA is on its way out" | Bryan Catanzaro | 2012/02/09 11:44 AM |
"CUDA is on its way out" | David Kanter | 2012/02/09 04:48 PM |
"CUDA is on its way out" | Anon | 2012/02/09 06:11 PM |
"CUDA is on its way out" | David Kanter | 2012/02/09 11:00 PM |
"CUDA is on its way out" | Michael S | 2012/02/10 03:54 AM |
"CUDA is on its way out" | Anon | 2012/02/10 05:42 PM |
Proprietary SW interfaces and hardware vendors | David Kanter | 2012/02/10 08:07 PM |
Proprietary SW interfaces and hardware vendors | Anon | 2012/02/11 03:08 AM |
Proprietary SW interfaces and hardware vendors | Anon | 2012/02/11 03:12 AM |
Proprietary SW interfaces and hardware vendors | Del | 2012/02/11 07:39 AM |
"CUDA is on its way out" | Del | 2012/02/11 07:33 AM |
"NVIDIA is on its way out" | Brendan | 2012/02/10 09:42 PM |
"NVIDIA is on its way out" | anonymous | 2012/02/11 10:37 AM |
"CUDA is on its way out" | Del | 2012/02/11 07:22 AM |
"CUDA is on its way out" | Anon | 2012/02/11 03:11 PM |
ispc on GPUs | Matt Pharr | 2012/02/12 09:02 AM |
ispc on GPUs | Anon | 2012/02/13 02:34 PM |
"CUDA is on its way out" | Erwin Coumans | 2012/02/09 08:39 PM |
"CUDA is on its way out" | Brett | 2012/02/10 11:54 AM |
"CUDA is on its way out" | David Kanter | 2012/02/10 03:00 PM |
"CUDA is on its way out" | Anon | 2012/02/10 05:45 PM |
"CUDA is on its way out" | Brett | 2012/02/10 07:20 PM |
"CUDA is on its way out" | David Kanter | 2012/02/10 07:58 PM |
"CUDA is on its way out" | Brett | 2012/02/11 06:15 AM |
Macroscalar | none | 2012/02/11 07:40 AM |
"CUDA is on its way out" | Anon | 2012/02/10 05:39 PM |
"CUDA is on its way out" | David Kanter | 2012/02/10 08:19 PM |
"CUDA is on its way out" | Anon | 2012/02/11 03:33 AM |
"CUDA is on its way out" | NN | 2012/02/14 03:24 PM |
"CUDA is on its way out" | Anon | 2012/02/15 03:16 PM |
"CUDA is on its way out" | bakaneko | 2012/02/11 04:31 AM |
"CUDA is on its way out" | Aaron Spink | 2012/02/09 11:29 PM |
Fused Multiply-Add and HSA | EduardoS | 2012/02/08 02:11 PM |
Fused Multiply-Add and HSA | Foo_ | 2012/02/09 05:24 AM |