AMD FX 8350 VS Intel Ivy Bridge K series for gaming - interesting perspective

[Pemalite]

BlueFalcon said:

MilkyWay@Home, Collatz Conjecture, etc. Those projects are going to net you a ton of BOINC points on AMD cards too.

BTW, if you are already willing to run your GPUs at full load, have you considered bitcoin mining? I've been mining with my 7970s and by the time 8970s launch, I should have enough  $ for a 'free' upgrade to those. I suppose it sounds like you genuinely want to help a noble cause :)

If I had the clock cycles to spare I probably would do some extra compute. :)
Hence why I want hardware several multiples faster than what I have! haha

Soleron said:

- Seamicro's tech is nothing to do with CPU silicon. It doesn't work for high performance servers. Calxeda's fabric does and they have shipping ARM server products; AMD does not.

- Woah. You just argued that AMD was fine in servers because ARM, but then you say ARM isn't suited for single-thread performance. So you must conclude that Intel cleans up on the low thread count servers, which is in fact most of the market (look at 2-socket vs 4-socket stats).

- One game AMD paid to have it included in is exactly my point. For a tech to have succeeded I want to see multiple vendors use it with no payment by the maker. Paying people to make stuff is the entire history of GPGPU up to now, see Nvidia and everything.

And btw no, that's not why it was a feature in DX11. It was in DX11 because IT WAS IN DX10, but Nvidia couldn't do it so MS pushed it out for them screwing over AMD.

- You're saying an extra $20 on RAM 1600 -> 1866 isn't worth a 10% graphics improvement? Because I'd sure pay for that.

- It's not DDR4 that will improve on-die graphics (look at the slides, DDR4 starts at the same performance and worse power consumption than DDR3). It's on-package memory that Intel will introduce in 2013 (Crystalwell) and that AMD isn't even close to releasing.

- QuickSync is awesome,  but it is anti-GPU compute. GPU compute says, why not use a big hot expensive vector processor to encode your videos? And QuickSync says, but if we add a tiny extra piece of dedicated silicon to the CPU it can beat the GPU's performance, do it in 1/10 the power, and have higher video quality. So isn't the implied future small dedicated SoC logic rather than GPU compute?

Programming for QS: "Encode my video"
Programming for GPUs: worse than the Cell

In regards to Seamicro and Arm, you are now putting words in my mouth and completely twisting what I say, so I'll leave the debate at that as it's pointless to carry it on, I suggest you go back and re-read what I said in context.

About Ram... Laptops, already come with Ram, So-Dimm DDR3 1866mhz is essentially twice as expensive than So-Dimm DDR1600mhz, and you don't get twice the performance. - Hence why DDR3 1600mhz is the best price/performance, argue all you wan't it's what the numbers and common sense says.

DDR4 is going to be a big improvement, take a look at the JDEC specs.
2133–4266 MT/s compared to DDR3's 800-2133 MT/s with DDR4 voltages sitting around 1.05–1.2 V.
So the cheapest DDR4 sticks will be on par with essentially the fastest and most expensive DDR3 sticks.
One of the best Ram kits you can buy is samsungs green memory and that will at-most top out at around 2600/2800 MT/s overclocked, still doesn't beat DDR4 especially once DDR4 matures and can clock higher than 4266 MT/s.

As for dedicated memory for IGP's AMD wen't down that route with the 790 and 890 chipsets where they packaged dedicated DDR3 ram for the IGP's, it was an adequate increase, but was hampered by the BOM increase so manufacturers stuck with cheap and slow memory.
It's another good increase for IGP's, but if they ever package the memory on die, it's wasted transisters that could otherwise be dedicated towards a beefier IGP or a better CPU.
DDR4 will for awhile put-off that need.

As for QuickSync, it's part of the GPU, it's just a dedicated pipeline that's part of the video decoder engine, hence why Sandy Bridge-E and Ivy Bridge-E doesn't get quicksync, because it doesn't have a GPU.
nVidia and AMD could do the same, but GPU's are increasing in speed at a relatively fast pace and each generation of new cards will automatically get a speed-up, best to spend those transisters on more shaders I suppose.
Then again, if AMD and nVidia saw a market they would probably include similar functionality.