Originally Posted by computerparts
Originally Posted by Durquavian
I am quite happy for AMD and this new found momentum. However I don't think Intel is gonna take a huge hit on 4=/+ core CPUs. The diff in ghz will help and if HT does somehow make its way in it will help. But this is a great boon for AMD and a chance to get some compilers that actually even/reduce the bench deficit.
New found momentum could be a good way to describe it. Whether or not the hit will be huge remains to be seen. But if the current position of the i3's are any indication, then it's going to be pretty bad, 8 core could very well be the new quad core. And that's just the thing. I have been reading presentations and interviews from devs. I have not seen one mention of IPC or any indication that it will be a factor in performance anywhere. The only thing devs seem to be focusing on is getting as much jobs spread across as many cores as possible. Also throwing as much work as possible onto the gpu. There's even talks about the gpu handling physics, collision calculations, and other ops that have always been handled by the cpu. One thing is for certain, change is coming.
most of what you said is exactly what i have been pointing out but i had technical proof i will repost it.
#1 The Sony stuff about the APU / GPU will also be able to run computational and arbitrary code, allowing developers to run hundreds or thousands of parallelized tasks.
#2 The fact next gen game design and consoles will force more cores to be used because of the way the consoles are same as PC in most ways architecture wise.
#3 The way games will be designed will use AMD open64 compilers.
#4 The fact the consoles and PC are AMD X86 8core CPU and DX11+ APU/GPU in the ATI HD 7760-7850 range for Xbox one and PS4.
#5 The developers have been asking for this for years to unify the way programing and coding for consoles and PC are done.
#6 The developers have been given the ability to literally bypass the DirectX API and use other more efficient API's at theyre own choice and given literally direct access to the hardware at almost driver LVL.
The above stuff is important in the I5 quad without hyperhtreading because future is heavily multi threaded game wise and soon program wise next gen game design is being optimized around AMD / ATI and might go as far as not utilizing hyprthreading by Intel altogether who knows.
facts are next gen games will be different from ever before AMD / ATI will be optimized for and also will in general get a huge set of perks that Nvidia / Intel wont or even be capable of like for instance using the GPU to do alot of the tasks the CPU has done in past add to it actual good multi threaded coding / programing and then you get the dx11-dx11.1-dx11.2 advancements including multi threaded rendering http://forums.anandtech.com/showpost.php?p=31520674&postcount=28
old but relevant im sure things have progressed to bring the performance advantage even higher since this test was done in 2010-2011 so i am sure they can get more than double the performance / FPS as they got double in this test vs not using multi threaded rendering.
Which was done with a Intel quad-core CPU with HT and be aware that at that time multi threaded rendering could utilize or use upto 12 threads / cores on that game and only got to use 8 threads / cores yet still doubled the performance / FPS vs not using multi threaded rendering and to date only a handfull of games have used this yet future games will heavily use this.
I WANT TO ADD THIS FROM THE TEST At this point in time we appear to be GPU limited, but we may also be CPU limited. Firaxis says Civ V can scale to 12 threads; this would be a hex-core CPU with hyperthreading. Our testbed is only a quad-core CPU with HT, meaning we probably aren't maxing out Civ V on the CPU side. And even with HT, it's likely that 12 real cores would improve on performance relative to 6 cores + HT. Firaxis believes they're GPU limited, but it's hard to definitively tell which it is.
This is the true power of DX11. When properly implemented in both drivers and games, DX11's multi-threaded rendering capabilities are going to allow developers to push a lot more stuff out to the GPU without immediately bottlenecking the CPU.
Coincidentally, last month's interview with AMD's Richard Huddy at Bit-Tech also has a lot in common with this. AMD says DX11 multi-threaded rendering can double object/draw-call throughput, and they want to go well beyond that by bypassing the DX11 API.
which i want to point out is exactly what next gen game design brings to table being pushed hard by next gen consoles and AMD all in one CPU/APU's and so on.
also you got the AMD open64 compilers http://developer.amd.com/tools-and-sdks/cpu-development/x86-open64-compiler-suite/
being used in the design of the future games instead of the biased Intel compilers.
I also want to add to it the fact ATI will be capable of tackling the extra tasks far better than Nvidia https://en.bitcoin.it/wiki/Mining_hardware_comparison
bitcoin mining is relevant because it is almost doing same thing compare a CPU to an ATI GPU ATI dominates even against top of line enthusiast Intel overclocked to the moon on LN2 and ATI wipes the floor with Intel and Nvidia also at this task so make an educated assumption of what next gen games / game design brings to table for AMD / ATI.
A GPU has a lot of cores (hundreds). Each core is basically able to compute one 32-bit arithmetic operation per clock cycle -- as a pipeline. Indeed, GPU's work well with extreme parallelism: when there are many identical work units to perform, actually many more than actual cores ("identical" meaning "same instructions", but not "same data").
GPU's achieve great performance by using heavy parallelism, with hundreds (if not thousands) of cores. This is made possible by pipelining (each individual operation takes many cycles to run, but successive operations can be launched like trucks on a highway) and sharing instruction decoding (since many cores will run the same instructions at the same time).
THIS IS FROM ONE OF MY PREVIOUS POSTS FROM SONY
The system is also set up to run graphics and computational code synchronously, without suspending one to run the other. Norden says that Sony has worked to carefully balance the two processors to provide maximum graphics power of 1.843 teraFLOPS at an 800Mhz clock speed while still leaving enough room for computational tasks. The GPU will also be able to run arbitrary code, allowing developers to run hundreds or thousands of parallelized tasks.
Sony is building its CPU ( x86 same as PC AMD 8core ) on what it's calling an extended DirectX 11.1+ feature set ( ATI HD 7850 equivalent directX11 APU ), including extra debugging support that is not available on PC platforms ( presently ) . This system will also give developers more direct access to the shader pipeline than they had on the PS3 or through DirectX itself. "This is access you're not used to getting on the PC, and as a result you can do a lot more cool things and have a lot more access to the power of the system," Norden said. A low-level API will also let coders talk directly with the hardware in a way that's "much lower-level than DirectX and OpenGL," but still not quite at the driver level.
Xbox one is also nearly exact specs and such all AMD / ATI and 8core also.
This is relevant becasue again they are trying to make the game design a one time coding thing in otherwards they only make the game once and it works for all systems aka simplify / unify the game design and make it more fluid so you can bet alot of these tweaks / optimizations will flow over into the PC's using ATI / AMD 8cores and any processors with 4+ cores not including the synthetic hyperthreaded ones Intel uses so i see this as a very strategic tactical move by AMD / ATI that has been in the works for years.
Basically the AMD FX 8350 is slowwer than the I5 at single threaded tasks but future is multi threaded where the FX shines not single threaded the above information confirms this add to it a powerfull ATI GPU will make up for where the AMD FX CPU or any AMD CPU lacks performance per core basically to sum it up AMD's performance in future games when paired with a powerfull ATI GPU / APU will be alot better than previously.
I am sure there is an optimization between AMD / ATI given they are same company so i can only quess the two will perform better together than Intel / ATI or Intel / Nvidia would in future with these perks.
I have not even gotten into the HSA thing yet either http://developer.amd.com/resources/heterogeneous-computing/what-is-heterogeneous-system-architecture-hsa/
which will also bring huge perks / benefits to AMD / ATI also Intel and Nvidia are not involved with HSA.
Norden says that Sony has worked to carefully balance the two processors to provide maximum graphics power of 1.843 teraFLOPS at an 800Mhz clock speed while still leaving enough room for computational tasks. The GPU will also be able to run arbitrary code, allowing developers to run hundreds or thousands of parallelized tasks
Norden said. A low-level API will also let coders talk directly with the hardware in a way that's "much lower-level than DirectX and OpenGL," but still not quite at the driver level.
i would also like to point out most of these advancements / tweaks will move over into the PC side of game development because otherwise they are essentially designing 2 different games for almost identical hardware which i see as a waste of money if the coding will literally work on both flawlessly why would they change it and microsoft wont jump the developers #$% because they already told them it is on them to design them and gave the developers free range to do so in otherwards they gave game developers the OK to use other API's and such for game design for PC and console.
to sum it up 4+cores with ATI GPU / APU will have the best performance in future games is what it boils down to the CPU doesnt need to be AMD or Intel as long as it is 4+ cores will be just fine in otherwards AMD FX 6000-8000 or Intel I7 and future 4+ core CPU's will be optimal for future games.Edited by rickcooperjr - 7/27/13 at 7:35pm