LinkBack URL
About LinkBacksRead more.The ‘performance’ line of CPUs will stick with 32nm Piledriver cores.
Read more.The ‘performance’ line of CPUs will stick with 32nm Piledriver cores.
Well that just about wraps it up for top end prices. With no real competition Intel will innovate little and keep the prices high.
Of course I'm perfect you just need to lower your expectations.
Quite disappointed but I think on the desktop side, AMDs strategy is to optimise game engines to better use more cores and to offload as much to the graphics card as possible. (Which is why I think the console wins were important). Then offer value to compete favorably on the price points.
Would have still liked to see a new FX generation though.
Does this also mean no further development in the higher end 2p server space?, would be a shame to see them fall even further behind there, pricing on there boxes makes then very attractive for Virtual environments.
Salazaar : <Touching wood as I write this...>
I wonder if they're moving to an Intel like roadmap of releasing their APUs first, then the server parts a gen later - we've only just seen the server versions of IVB, after the desktop Haswell release. It's unfortunate for us, but it does make sense - they build the server parts from proven cores on a mature process, especially important when you're dealing with larger die sizes if you want reasonable yields. Launching a large die with a brand new, ground-up uarch on a cutting edge process didn't go exactly go smoothly for AMD with BD. Intel's tick-tock methodology makes a good amount of sense for that reason, taking on one challenge at a time.
I think a new FX core will have to come eventually, as they'll need to refresh the server range before too long, but I also think they don't want to develop new chips on an aging platform. They're obviously positioning FM2+ as the 1P successor to AM3 in entry-level servers, which presumably means they have no real interesting in increasing the shelf-life of AM3+, so no interesting in releasing new FX CPUs or AM3+ Opterons.
I suspect they will release new FX CPUs when they decide on how to unify the APU and CPU platforms, which I've theorised previously might be when they decide to adopt DDR4. The fact that the server chips use HT for interCPU communication means they'll have to do a fairly significant silicon redesign to fulfill the multi-socket server chips (including MCMs for high core count) and bring all the current northbridge logic onto the CPU die. Makes me wonder if the server side of the business might be a major target for the semi-custom team...
AMD is going to use Freedom Fabric as their successor to HT, and it would not surprise me if Excavator is a massive redesign of the platform.
Just think for a little about what we actually see there:
1. 2013 change to 2014 (new year) is in the middle of the roadmap.
2. Richland starts at the beginning of the road map.
3. Richland had its release on June 2013 (04.06.2013)
Now add '2' to '3' and multiply by '1' = The roadmap reaches just the first half of 2014.
We may see more in Q3 and Q4 2014.
They *must* be doing *something* about the higher end line-up for desktops as well as servers, a 32nm CPU is not going to be tenable in the mid to high end much longer, manufacturing costs and power demands vs Intel's shrinking dies will make it extremely hard to compete on any front.
My guess is the roadmap doesn't show anything there because they aren't ready for an announcement and don't want the rumour mill spinning too hard and focus shifted away from CPUs coming out now or very soon - i.e. its just marketing spin.
I think they'll do AM4 with new FX chips mid-2014, when DDR4 is established. Or, they may do a FM3 focus at the same time, as DDR4 will have HUGE benefits to APUs. Maybe the now-legendary octo-core APU will finally see the light of day then, too...
I bet they're hoping that with being in next gen game engines in particular (which I imagine is where the bulk of their 'performance' sales are now) will get better threaded, so you can scale by adding cores, and I'd imagine amd's per core unit cost is much less than intels. They appear to have given up in the pure performance/clock basis a while ago and are now firmly positioned in the budget end of the market.
Depending how mantle takes off they may try to push APUs as high end solutions. I can see a 6/8 core APU with a half decent GCN core attached, crossfired with a discrete GPU and essentially use the built in one to do the physics simulations etc.
TBF, performance/clock has been an utterly meaningless metric for as long as I can remember. If chip A, running at 1GHz, scores 100 points while drawing 100W, but chip B runs at 5GHz to score 100 points at 100W, who cares, besides fanboys grasping at straws? The BD uarch was designed from the start to clock highly, with smaller but more highly pipelined cores vs K10.
Moving away from desktop CPUs, the Cotex A5 gives higher performance/clock than even an A9 in some scenarios.
http://www.itproportal.com/2012/03/0...ising-results/
But it isn't clocked as high as the A9. Even if it was pushed to A9 clock speeds, performance doesn't necessarily scale linearly with clock speed, and neither does performance/watt.
Going to agree with that first sentence 100% - what do AMD want folks to partner with their nice, shiny new R290? Surely, they're not expecting folks to run out to get an i7?Originally Posted by kingpotnoodle
I was kind of hoping for something like an 8520 and 8550 to replace the current 8320 and 8350s. Given the rumours I've seen were saying that the successors were going to be slightly improved, the numbering scheme made sense.
"Freedom Fabric" - isn't that what Captain America's uniform is made of?
(sorry, couldn't resist, end-of-day silliness reigns).
Career status: still enjoying my new career in DevOps, but it's keeping me busy...
Freedom Fabric just gets you lots of single socket machines in a dense array, some workloads don't want that.
The people running Oracle/Exchange/anything written in Java still want lots of cores and dimm sockets in a single machine image.
As for people thinking Mantle makes this an irrelevance, my C compiler will never benefit from Mantle, not all workloads are game related. Am happy with the 8350 for now, but would have been nice to know there would be an upgrade at some point in the next couple of years.
I was having this discussion elsewhere, if you look at core numbers from Intel chips dual cores were introduced in 2005, quad cores in 2007, and that's where we are today even though the server space moved to 6 cores in 2008, 8 in 2010 and 12 in 2013. That 2007 date roughly co-incides with a couple of multi-core gaming consoles being launched so I suspect that innovation is already dead, if Intel wanted they were perfectly capable of producing 8 core CPUs say for £250, but nope, no consumer demand so they keep prices high in the high end. This might change now that the next generation is here though, who wants to bet there'll be a move to 8 core chips (though this'll push AMD even harder).
People still think that a faster cpu is better than a slower dual-core...or appear to at least
Old puter - still good enuff till I save some pennies!
There are currently 1 users browsing this thread. (0 members and 1 guests)
Posting Permissions
Reply With Quote
