Sign in with
Sign up | Sign in
Your question

AMD Bulldozer Simple Facts Please!!!!!

Last response: in CPUs
Share
September 17, 2010 7:47:06 AM

Hey guys, i was just going to upgrade my system to Phenom II X4 955 or 965 but then i heared about this new chipset bulldozer
that is suppose to come this year or next year, so i've been looking for simple key features about it but i couldnt, like the number of cores it will be availabe with, the size of the cache memory, will it support Hyper Threading like the Core i series,
will it be expensive, when will it be launched? Will it be supported by AM3 Socket?
if someone please have any info and have any advice would be great
Thank you for help!
a b à CPUs
September 17, 2010 10:07:55 AM

I recommend you upgrade to the latest Phenom II X6. It's not much more over the fastest Phenom II X4 and it will be the last upgrade for your motherboard I think.

Bulldozer is socket AM3+ so we can't plug them into an AM3 board but can plug in an AM3 CPU into an AM3 mobo.

Bulldozer has not been revealed to have HT, but it does have clusters of cores which share common parts of cores called modules. Each AMD module has 2 cores.

It will be launched 1st half of next year.

Feed me...
m
0
l
Related resources
September 17, 2010 10:21:58 AM

Been a AMD fanboy since getting my AMD 3000+ (upgraded since then), im hopeing these Cpu with be impressive, owe im not expecting performance difference like the old P4 v Athlon 64 days.

Also i hope it doesnt mean AMD will be bringing out £400+ Cpus again :( 
m
0
l
a b à CPUs
September 17, 2010 10:25:16 AM

I estimate that Bulldozer will achieve parity with Intel's Nehalem arch.

That's all.

I think Sandy Bridge will beat Bulldozer, but Bulldozer will be competitive and in roughly the same spot as Thuban, although I think AMD will breach the $300 barrier with Bulldozer.
m
0
l
September 17, 2010 10:29:19 AM

Well here's hopeing your right and that they'll OC like the 980x
m
0
l
a c 123 à CPUs
September 17, 2010 11:39:27 AM

I think a lot of people will be disappointed if Bulldozer is no better than Thuban; I know I will.
I'm thinking it will edge past Nehalem, get similarly beaten by Sandy Bridge, but cost a lot less, and perhaps, just perhaps, people will wake up and realize that a mid to high end prior generation (e.g. X4 or i5) is still all the CPU that 95% of people need (and 90% of those could probably use a X2 or C2D).
m
0
l
September 17, 2010 11:49:35 AM

300$!!!!!!!!!!!!!, so i think anyway if its released i wont be able to buy it!! :D ...i think i'll go for the phenom II?!
m
0
l
a c 126 à CPUs
September 17, 2010 5:27:18 PM

Quote:
I do not think SB will be faster clock for clock than BD.

Yes it does mean AMD will be selling $300+ cpu's again.


If the 12.5% performance increase is right then SB will be faster.

Then again we have to wait until BD is released. As far as we know its been deleayed.
m
0
l
a b à CPUs
September 17, 2010 5:58:38 PM

I'm hoping Bulldozer is faster.

I like the technology behind it. The one thing I still can't stomach is the lower quality chipsets one has to deal with when using an AMD platform.

They have improved considerably since the ATi acquisition but they still don't hold a candle to the all around great performance one gets with an Intel Chipset.

(HDD performance, RAID0,1,5 performance, USB performance and most I/O tasks are just generally better on an Intel High End platform).
m
0
l
September 18, 2010 5:17:48 AM

I think people are still kind of underestimating Bulldozer, for two reasons:
1. I don't think they understand how the cores on a bulldozer chip work, since i hear many people saying it may beat Sandy in multi threaded tasks but definitely not single threaded tasks. I don't think thats a fair assumption since in single threaded tasks, one bulldozer core has access to all resources in the module, and gets to use both 128 bit FMACS to equal Sandy Bridges 256 bit FPU. Also, if you have a program that uses 4 cores, and you have an 8 core (4 module) Bulldozer chip for example, instead of two modules being active using all cores, only one core in each of the four modules will be active, resulting in 4 beefy cores.

2. This ones simple. Since the 1.25 bil settlement, AMD has said they will use all of intels available instruction sets (including AVX) in addition to new AMD instruction sets. This includes instructions for Fused Multiply- Add, which intel isnt implementing until Haswell.

As for sources, check the settlement info and any other source of Bulldozer info. I didnt use a specific source, this is all stuff i remember reading.
m
0
l
a b à CPUs
September 18, 2010 4:24:55 PM

Why don't we all wait until we see some reviews on BD? There is no point in speculating. At least with SB, we have a reliable review by AnandTech which says it's faster than Nehalem.
m
0
l
a c 123 à CPUs
September 18, 2010 6:08:06 PM

Good idea.
m
0
l
a b à CPUs
September 19, 2010 5:06:40 AM

Shadow703793 said:
Why don't we all wait until we see some reviews on BD? There is no point in speculating. At least with SB, we have a reliable review by AnandTech which says it's faster than Nehalem.

^What I normally say.
m
0
l
a c 126 à CPUs
September 19, 2010 6:29:56 AM

Shadow703793 said:
Why don't we all wait until we see some reviews on BD? There is no point in speculating. At least with SB, we have a reliable review by AnandTech which says it's faster than Nehalem.


Yep. And for BD all we have is AMD stating that 33% more cores = 50% better performance. If we take the 50-33 then it would mean about 17% in a per core performance improvement.

Of course thats all speculation. If we look at it right now, Deneb is about 20% away from Nehalem overall (more in some areas, less in others). That means that in order to beat SB which is currently 20% overall better than Nehalem. So that means in order to take back the totak performance crown BD would need to be 50% faster than Nehalem.

I am still going to hold off though. Until I get something solid from a thrid party source, BD is just a new idea waiting to be explored and SB is going to be the next best CPU.
m
0
l
a b à CPUs
September 19, 2010 6:49:35 AM

Quote:
I;m wondering why hasn't some moderator merge all those threads about AMD BD together, like how mousempnkey merged all those thread about HD6Ks, :D 


I hope not though, it'll get really confusing :) 

That's because I don't stop in here as much as I used to but it's an interesting thought. :whistle: 
m
0
l
September 19, 2010 12:36:39 PM

jimmysmitty said:
If the 12.5% performance increase is right then SB will be faster.

Then again we have to wait until BD is released. As far as we know its been deleayed.


The 12.5 number has been debunked plenty of times, it is not correct.
m
0
l
September 19, 2010 12:41:23 PM

jimmysmitty said:
Yep. And for BD all we have is AMD stating that 33% more cores = 50% better performance. If we take the 50-33 then it would mean about 17% in a per core performance improvement.

Of course thats all speculation. If we look at it right now, Deneb is about 20% away from Nehalem overall (more in some areas, less in others). That means that in order to beat SB which is currently 20% overall better than Nehalem. So that means in order to take back the totak performance crown BD would need to be 50% faster than Nehalem.

I am still going to hold off though. Until I get something solid from a thrid party source, BD is just a new idea waiting to be explored and SB is going to be the next best CPU.



The problem with all of that math is the "50% faster with 33% more cores" statement is about a fully utilized server processor in server workloads, 12 threads pegged vs. 16 cores pegged.

Imagine how long it takes you to get to work in rush hour traffic. Then think about that same road if there is light traffic or you are the only car on the road. Big difference.

I think people will be very happy and very surprised with the performance, but as pointed out above, it is best for everyone to wait until the actual results are out because all of the speculation is wrong. People just don't understand the architecture well enough to make an accurate assessment.
m
0
l
September 19, 2010 3:43:19 PM

jimmysmitty said:
Yep. And for BD all we have is AMD stating that 33% more cores = 50% better performance. If we take the 50-33 then it would mean about 17% in a per core performance improvement.


it has 50% better throughput. Thats different than performance. If you read the Bulldozer blog at AMD's website Fruehe keeps stressing that. Actually read the post "The Parallel Universe" if you decide to stop by there, it explains pretty well. Also read the comments since he answers more questions there.
m
0
l
a c 126 à CPUs
September 19, 2010 7:52:00 PM

yannifb said:
it has 50% better throughput. Thats different than performance. If you read the Bulldozer blog at AMD's website Fruehe keeps stressing that. Actually read the post "The Parallel Universe" if you decide to stop by there, it explains pretty well. Also read the comments since he answers more questions there.


You kinda missed this part:

Quote:
I am still going to hold off though. Until I get something solid from a thrid party source, BD is just a new idea waiting to be explored and SB is going to be the next best CPU.


I am not trusting anything. I can pull all the numbers to speculate. Thats what I did. I never said it was right or concrete. Thats why for the time being, until a third party has BD to test and show us what it can do Sandy Bridge is the next top end CPU performance wise since we have concrete info from Anand.

Same goes for you JF-AMD. I never trust anything straight from the company source. No offense but its hard to trust people who work for the company. Its like the reason why I got Windows 7. Not because Microsoft touted it to be great. but because I had a few friends at my job who had the Beta and said it was much better than Vista.
m
0
l
September 20, 2010 12:37:12 AM

jimmysmitty said:

Quote:
BD is just a new idea waiting to be explored and SB is going to be the next best CPU.




Sounds like you made up your mind already.

I recognize that some may not trust company sources, but think about this: Our long term credibility is far more valuable to us than a short term win.

If I tell you Bulldozer is going to be the best processor ever, and it isn't, then I am toast forever, you can't dig out of that hole. My reputation guides my paycheck. If I am reputable and respected, I can earn more in life. If I am a huckster who lies about product, then I earn less money down the road.

When we were getting ready to launch Magny Cours we said "50-60% greater performance." It was 80-120%. You won't find me hyping performance and you won't find me making performance comparisons against the competition. Nobody has both products in their hands. Anyone making a determination today about how the two will compare, will be wrong.
m
0
l
a c 126 à CPUs
September 20, 2010 1:27:42 AM

jf-amd said:
Sounds like you made up your mind already.

I recognize that some may not trust company sources, but think about this: Our long term credibility is far more valuable to us than a short term win.

If I tell you Bulldozer is going to be the best processor ever, and it isn't, then I am toast forever, you can't dig out of that hole. My reputation guides my paycheck. If I am reputable and respected, I can earn more in life. If I am a huckster who lies about product, then I earn less money down the road.

When we were getting ready to launch Magny Cours we said "50-60% greater performance." It was 80-120%. You won't find me hyping performance and you won't find me making performance comparisons against the competition. Nobody has both products in their hands. Anyone making a determination today about how the two will compare, will be wrong.


The last time we got was the over hyped 40% from Barcelona. That turned out to be worse than Kentsfield. Thats why I am not trusting anything yet. I am even not 100% on Anands review since it was done in controled areas and with unfinalized hardware.

I know you as a person may not, but you do not have any control over AMDs marketing department. They will spin what they need to to get sales..

Thats why I said I am waiting for BD results. I have seen sources claiming this or that and otehrs who say it will beat SB. None of it is 100% concrete. Right now I have concrete info showing SB as being better than Nehalem. So with what I have, SB is showing to be the best CPU someone can buy for performance in Q4 2010/Q1 2011. When we have BD results, if they are better than SB I will state that. Of course it would be nice to know WHEN we can expect BD since rumors float around on the web that it wont have to face SB, more that it will face Ivy Bridge instead.

And I have yet to make up my mind since I wont be building a new system until late 2011. More towards 22nm since I want a system with SATA 6.0, USB 3.0 and possibly light peak (I love fiber based tech).
m
0
l
a b à CPUs
September 20, 2010 12:47:16 PM

(You see, Jimmy and I won't see government handouts for quite some time)

Honestly, I'm excited about Fusion. If they can deliver 90% of an Athlon II's performance in a 18W package with decent graphics, I'm sure I'll drool over it.
m
0
l
a b à CPUs
September 20, 2010 12:54:01 PM

Hey JF ... glad to see you here.

AFG I think they will manage a 9W special from what I saw elswhere.

ENTP btw.

:) 
m
0
l
a b à CPUs
September 20, 2010 1:07:40 PM

I know that.

I just want something fast enough. I'm not going for that Atom-like rubbish :p 

I still have to run Photoshop!
m
0
l
September 20, 2010 1:15:23 PM

jimmysmitty said:
The last time we got was the over hyped 40% from Barcelona. That turned out to be worse than Kentsfield. Thats why I am not trusting anything yet. I am even not 100% on Anands review since it was done in controled areas and with unfinalized hardware.

I know you as a person may not, but you do not have any control over AMDs marketing department. They will spin what they need to to get sales..



2 things:

1. I am the director of product marketing, so I actually am in control of AMD's marketing when it comes to any claim about performance. I am the one that would decide what we say about performance. We are more conservative than you would think.

2. The 40% claim was from the head of the server division. It was in reference to STREAM memory throughput, not a client claim on client benchmarks. I think too many people interpreted that statement to be 40% better client performance on client benchmarks, it was never intended to be that.
m
0
l
a b à CPUs
September 20, 2010 1:19:09 PM


Edit: Don't bother, Reynod explained everything to me, it's cool bro.
m
0
l
a b à CPUs
September 20, 2010 1:32:06 PM

Well I can see a resurgence in Notebook sales and we all might finally have 4hrs of real battery use without having to resort to the sheer blasphemy of using a Netboot.

I played with one of those woefull EEPC things for a week and threw it away ... literally ... the Atoms are rubbish.

I gave it to a work mate who celebrated ... then played with it for a week and quietly filed it into a drawer ... next to the financial calculator with the printer, the old stamps, and sundry items of no real value or interest.

A historical anomaly ... must be an aweful lot of idiots out there ... now they are buying i-pads I guess ... what next month?

Seriously, I want something portable that won't grind to a halt when the graphics gets rough and that means something weighing like a boat anchor at present ... and connected to mains power.

Lets see what AMD's offers ... I can't see Intel matching the combined CPU / GPU power ... unless they buy NVidia.

I keep predicting that ... um ... and getting it wrong.
m
0
l
September 20, 2010 1:33:18 PM

jf-amd said:
2 things:

1. I am the director of product marketing, so I actually am in control of AMD's marketing when it comes to any claim about performance. I am the one that would decide what we say about performance. We are more conservative than you would think.

2. The 40% claim was from the head of the server division. It was in reference to STREAM memory throughput, not a client claim on client benchmarks. I think too many people interpreted that statement to be 40% better client performance on client benchmarks, it was never intended to be that.

Unfortunately, people distorted this, and ran with it.
I have 2 problems with this
1 Either these people who distorted this dont know that much to begin with, and this would have died a quick death
or
2 The people that distorted this did know it was a distortion, and had other motives to keep slinging it.

To me, its like what the media does, selectively editing the interview to make the one being interviewed as being lessor of a person , or more in line with the medias distorted position
m
0
l
a b à CPUs
September 20, 2010 1:43:44 PM

Reynod said:
Well I can see a resurgence in Notebook sales and we all might finally have 4hrs of real battery use without having to resort to the sheer blasphemy of using a Netboot.

I played with one of those woefull EEPC things for a week and threw it away ... literally ... the Atoms are rubbish.

I gave it to a work mate who celebrated ... then played with it for a week and quietly filed it into a drawer ... next to the financial calculator with the printer, the old stamps, and sundry items of no real value or interest.

A historical anomaly ... must be an aweful lot of idiots out there ... now they are buying i-pads I guess ... what next month?

Seriously, I want something portable that won't grind to a halt when the graphics gets rough and that means something weighing like a boat anchor at present ... and connected to mains power.

Lets see what AMD's offers ... I can't see Intel matching the combined CPU / GPU power ... unless they buy NVidia.

I keep predicting that ... um ... and getting it wrong.


I actually use a Macbook for about 4-6 hours battery (4 wi-fi, 6 energy saver). Had it since 2007. Nifty little piece of $2000 hardware I didn't pay for.

Netbooks are rubbish. Anything in general with a 10" or smaller screen is rubbish.

You might want to take a look at the new CULVs Reynod. Ain't much, but it's the closest thing to your sliced cheese... (you won't buy a Mac will you?)
m
0
l
a b à CPUs
September 20, 2010 1:51:44 PM

JF I agree AMD has been pretty conservative with regards to recent releases.

I think the fact that we know so little about what your about to release in terms of fusion anyway (other than the Zacate vs i5 video, and the recent slides) is probably driving higher expectation.

One thing that really interests me is in regards to the wasted silicon when you disable ondie (well ondice) graphics ... for instance i3 and i5.

I'd like to think AMD's ondie GPU / APU will have the flexibility to retain APU functionality ... when discrete graphics are installed.

Simply disabling a heap of silicon which could otherwise be put to good use ... seems just odd.


Edit: AFG We have a Macbook ... for Garage Band !!! That's all it gets used for ... sad eh? lol
m
0
l
a b à CPUs
September 20, 2010 1:54:59 PM

What will be a dealbreaker will definitely be a good OpenGL driver.

Atoms doing Photoshop aren't that bad if they use CS4+ with a good OpenGL GPU.
m
0
l
a b à CPUs
September 20, 2010 1:57:52 PM

I get 3hrs out of my A100 Toshy 1.4M ... that's still better than than a Netbook.

Sorry bout the offtopic ...

/slaps self
m
0
l
a b à CPUs
September 20, 2010 2:28:22 PM

Netbooks tend to have slightly more battery life, but believe me, there's no way I'm ever going to use one for school, it's so slow for Adobe CS4.

/hugs Reynod
m
0
l
September 20, 2010 3:20:18 PM

Can't speak to a zacate since I am on the server side. However, today's products allow for hybrid graphics, would hope that continues.
m
0
l
a b à CPUs
September 20, 2010 3:30:07 PM

jf-amd said:
2 things:

1. I am the director of product marketing, so I actually am in control of AMD's marketing when it comes to any claim about performance. I am the one that would decide what we say about performance. We are more conservative than you would think.

2. The 40% claim was from the head of the server division. It was in reference to STREAM memory throughput, not a client claim on client benchmarks. I think too many people interpreted that statement to be 40% better client performance on client benchmarks, it was never intended to be that.



I recall the 40% claim. It was an outright claim. It was not specified that AMD were referencing STREAM memory throughput. It is like an advertising claim written on an ad... except those on an add require an asterix and small print writing.

AMD is by no means the only company guilty of this (or product type).
http://news.cnet.com/AMD-Go-to-Barcelona-over-Clovertow...

Quote:
After years breathing AMD's dust, Intel beat its rival to the punch by releasing its quad-core Xeon 5300 "Clovertown" processor for servers in November. But AMD's "Barcelona" quad-core chip, due to arrive midway through 2007, will be a significant notch faster than the Clovertown chips expected to be on the market at that time, said Randy Allen, AMD's corporate vice president for server and workstation products.

"We expect across a wide variety of workloads for Barcelona to outperform Clovertown by 40 percent," Allen said.


Read more: http://news.cnet.com/AMD-Go-to-Barcelona-over-Clovertow...



I'm still waiting for Wireless Products that can achieve anything near their "theoretical" throughput. 54Mbps... BS! 108Mbps? BS! And don't get me started on Wireless N. Hell you could be right near or a tad further then near (as recommended) and still never hit anything close to those numbers.
m
0
l
a b à CPUs
September 20, 2010 3:40:48 PM

jf-amd said:
2 things:

1. I am the director of product marketing, so I actually am in control of AMD's marketing when it comes to any claim about performance. I am the one that would decide what we say about performance. We are more conservative than you would think.

2. The 40% claim was from the head of the server division. It was in reference to STREAM memory throughput, not a client claim on client benchmarks. I think too many people interpreted that statement to be 40% better client performance on client benchmarks, it was never intended to be that.


JAYDEEJOHN said:
Unfortunately, people distorted this, and ran with it.
I have 2 problems with this
1 Either these people who distorted this dont know that much to begin with, and this would have died a quick death
or
2 The people that distorted this did know it was a distortion, and had other motives to keep slinging it.

To me, its like what the media does, selectively editing the interview to make the one being interviewed as being lessor of a person , or more in line with the medias distorted position



**********

Firstly, I've seen JF's posts here and elsewhere (Anand, etc), and invariably he's been clear, measured, and factual. Not that many/most of our members here would necessarily care for my input: But for whatever it's worth this is one of the people I pay attention to when he chooses to speak.

The most website denizens and PC fans could possibly complain about is he's limited as to what he (has been able to.. has chosen to.. has the final data to justify) say(ing); that he sticks strictly to facts and doesn't indulge in the conjecture that fuels so many threads; and that he's far FAR FAR too professional to affirm/deny/participate in random individual's assertations/statements/flames as to the nature of whatever B*%$%F*%&$#ing that The Evil Empire will receive... blah blah blah


And Jay: You're preaching to the chior here, brutha. Strikes to the heart of most of my rants here <laugh>
m
0
l
a b à CPUs
September 20, 2010 3:41:02 PM

jf-amd said:
Can't speak to a zacate since I am on the server side. However, today's products allow for hybrid graphics, would hope that continues.

+1 for the hybrid graphics. Since you DO work for the Server division, would you like to tell if workstation boards/chip sets will support such a feature? I think a lot of the folks that run workstation GPUs would like this....

edit: mobile workstations; not desktop/2P workstations.

Also, will Bulldozer allow one to completely turn off the 2nd (or more) CPU in a 2P (or more) set up along with turning off un-needed cores of CPU1/0.
m
0
l
September 20, 2010 5:27:11 PM

Workstations fall under client, not server. There used to be Opteron-based servers but for now, the vast majority of the market is driven by single socket and graphics, so I don't really participate.

There will be different ways of potentially addressing the cores in a module. Much of this depends on software support, so I really can't comment right now; some of it is out of our hands.
m
0
l
September 20, 2010 6:15:12 PM

I wonder how good M$ will be on all this?
m
0
l
September 20, 2010 6:36:56 PM

since we are obviously working with them, they should be fine.
m
0
l
a b à CPUs
September 20, 2010 9:23:37 PM

jf-amd said:
Workstations fall under client, not server. There used to be Opteron-based servers but for now, the vast majority of the market is driven by single socket and graphics, so I don't really participate.

So let me get this straight, AMD considers some of the 2P stuff as workstations? Wouldn't all 2P stuff technically be under "server" as they use the server chipsets,etc? Exactly what does AMD consider to be "server" and "workstation"?

Btw, when I was referring to "workstation" I was referring to a 2P set up with a workstation GPU. Sorry for any confusion.
Quote:


There will be different ways of potentially addressing the cores in a module. Much of this depends on software support, so I really can't comment right now; some of it is out of our hands.

Make sense. Hopefully, the Linux community will be able to implement things like this.... I'm pretty damn sure Microsoft will do it.
m
0
l
September 20, 2010 9:40:59 PM

One more question for JF-AMD
Just want to know about this image that i found that shows that AMD Bulldozer might be supported by AM3 Sockets

and please guys dont ignore my last question about the cpu reg?!
m
0
l
September 20, 2010 9:49:26 PM

Kaspro, its completely off topic, if you want make a thread regarding this
m
0
l
September 20, 2010 9:59:35 PM

Shadow703793 said:
So let me get this straight, AMD considers some of the 2P stuff as workstations? Wouldn't all 2P stuff technically be under "server" as they use the server chipsets,etc? Exactly what does AMD consider to be "server" and "workstation"?

Btw, when I was referring to "workstation" I was referring to a 2P set up with a workstation GPU. Sorry for any confusion.
Quote:


There will be different ways of potentially addressing the cores in a module. Much of this depends on software support, so I really can't comment right now; some of it is out of our hands.

Make sense. Hopefully, the Linux community will be able to implement things like this.... I'm pretty damn sure Microsoft will do it.


Actually we are aligned around product, so I am aligned around Opteron, embedded and STREAM processors. There is a different team that looks at the workstation business, but that is a team primarily driven by a VP in the graphics business. The reality of the situation is that 95% of the workstation purchasing is driven by a.) the graphics solutions and b.) the ISV certification for the app. The processor is a distant third.

The only part of the workstation business that I used to touch is the 2P workstations, and that is a very small part of the overall workstation market, so I have little influence there.

Don't take my statements about workstation to mean that AMD is not interested in that market. We are, it is just not part of my world.
m
0
l
September 20, 2010 10:01:38 PM

kaspro said:
One more question for JF-AMD
Just want to know about this image that i found that shows that AMD Bulldozer might be supported by AM3 Sockets
http://images.anandtech.com/reviews/cpu/amd/FAD2009/desktoproadmap.jpg
and please guys dont ignore my last question about the cpu reg?!


A. I don't work in client.

B. That question has been answered on many forums already. Bulldozer will not be supported in AM3.
m
0
l
September 20, 2010 10:53:56 PM

Will there be more demos of Fusion and or Bulldozer any time soon? I dont really know of all of the electronic showcase events so if there's still some more this year i'd appreciate knowing the major ones in which demos might be present.
m
0
l
a b à CPUs
September 21, 2010 12:04:11 AM

One more question to JF-AMD:
In regards to Stream, I find that there are not many plug-ins/software that use OpenCL/Stream,etc currently on the AMD side. On the other hand, there are quite a notable collection of CUDA enabled plugins/software available with tangible benifits. For example, CS5 Mercury playback engine. Another example is n-Tracer,iray,etc for 3DSMax. Is AMD doing much to promote OpenCL,etc? I see nVida promoting Tesla/CUDA however, I don't see AMD doing anything like this currently. We (a friend and I, do note I didn't write the code; it's a CFD sim if you wanted to know) have found that CUDA is significantly easier to use than OpenCL/CirectCompute due to the lack of documentation,etc for OpenCL, AMD may want to look in to improving this.

Quote:
The reality of the situation is that 95% of the workstation purchasing is driven by a.) the graphics solutions and b.) the ISV certification for the app. The processor is a distant third.

What about the HPC crowd? Surely they would be driven by the CPU and the related systems (esp. CPU >> RAM subsystem)?
m
0
l
September 21, 2010 1:38:55 AM

Shadow703793 said:
One more question to JF-AMD:
In regards to Stream, I find that there are not many plug-ins/software that use OpenCL/Stream,etc currently on the AMD side. On the other hand, there are quite a notable collection of CUDA enabled plugins/software available with tangible benifits. For example, CS5 Mercury playback engine. Another example is n-Tracer,iray,etc for 3DSMax. Is AMD doing much to promote OpenCL,etc? I see nVida promoting Tesla/CUDA however, I don't see AMD doing anything like this currently. We (a friend and I, do note I didn't write the code; it's a CFD sim if you wanted to know) have found that CUDA is significantly easier to use than OpenCL/CirectCompute due to the lack of documentation,etc for OpenCL, AMD may want to look in to improving this.

Quote:
The reality of the situation is that 95% of the workstation purchasing is driven by a.) the graphics solutions and b.) the ISV certification for the app. The processor is a distant third.

What about the HPC crowd? Surely they would be driven by the CPU and the related systems (esp. CPU >> RAM subsystem)?


Yes, we are doing a lot with OpenCL and you will continue to see more. OpenCL is an open environment, Cuda is a closed environment. Closed environments allow you time to market advantages at times, but they do not guarantee long-term cross-platform compatibility. I have talked to a lot of programmers that believe Cuda is ahead, but also see cuda as a threat because they are potentially held hostage to a single company. So the benefit (today) might not outweigh the risks (tomorrow).

As for HPC, yes, they are very much processor-driven and I spend a lot of time with them. Clusters are very much an "at this point and time" type of purchase.
m
0
l
!