A PS4 equivalent rig for $500.00?

[torok]

Pemalite said:

Your entire first part of the argument is that the CPU is powerfull because the GPU can assist in processing.
Well here is a news flash. - The PC can do it too, in-fact it's been doing it longer than the consoles, but that doesn't actually make the CPU powerfull, that just means the CPU is weak and is getting assistance from another processor.
In the PC space they do it to conserve energy.

And another fact is, Ram is a temporary fast form of storage, it DOES NOT do any form of processing, you could have 1024GB/s of memory bandwidth, but if you don't have the compute resources to make any use of it... Then it would be utterly and completely pointless.
Besides the PS4's memory bandwidth has to be split between the CPU, GPU and what-ever other processors the PS4 uses, that 176GB/s number? It's going to be much lower than that for actuall games.
You basically took the number Sony advertised and ran with it, claiming it as the holy grail, the reality is far different that that I'm afraid.
The same thing occured with the Playstation 3 and the pretty horrible performing Cell.

As for PCI-E's bandwidth, especially PCI-E 3.0 16x isn't a problem, not even really for compute, there is a reason why there is GDDR5 Memory next to the GPU so that the PCI-E interface isn't hammered hard and constantly, but that's simple logic.
Besides, the GDDR5 Ram in my PC is faster than the PS4's, the PC will also move to GDDR6 and/or maybe XDR2 Ram soon, possibly within the next GPU release cycle.
You also have 512bit memory configurations in the PC rather than the mid-range 256bit bus the PS4 employs.

As for the memory wall, that has to be the funniest thing I have read all day.
So what you're saying is that you would see no difference in performance moving from a Core i3 (Which is essentially how fast an 8 core Jaguar would be.) to a Core i7 6-core, 12 threaded processor if you used the same Ram.
I have the ability to disable my cores and hyper threads, wan't me to disable them more to represent a Dual-Core? I can assure you the performance gains are real and stupidly massive by having all functional units enabled.

I also have a Phenom 2 x6 1090T 6 core processor in another PC and the motherboard supports DDR2 and DDR3 Ram, the CPU also has a DDR2 and DDR3 memory controller, wan't to know what I discovered a few years back? There was ZERO and I mean ZERO differences in performance between DDR2 800mhz Ram and DDR3 1866mhz Ram in gaming on the PC.

CPU's have Caches to keep data that's required for processing near the compute engines, which is both stupidly fast and low latency.
The CPU also utilises various types of predictors so that it can predict the data it is going to require ahead of time, this prevents a resource stall where if the CPU doesn't have the data it needs in the Cache it has to travel all the way down to system memory and regardless of how fast or low latency the system memory is, it will NEVER make up for the bandwidth and latency differences between the L4/L3/L2 and L1 caches.
Simple fact of the matter is, Jaguar's predictors are relatively simple, it's going to be doing allot of slow trips down to the GDDR5 Ram, possibly wasting millions/billions of cycles.

This may also hurt your pride for the Playstation 4 a bit, but... Without the PC and the PC's technology that PC's gamers have essentially "Funded" the research and development for... You wouldn't have the Playstation 4 at all, not how it is today.
You would more than likely ended up with an ARM based solution that a mobile phone uses instead.

First, I did not said anywhere that RAM does any kind on calculation. Second, I don't seem to understand the PCI-E bandwidht problem and the massive performace hit that coping data from CPU to GPU creates. When you work with, let's say, CUDA, sometimes you forget about doing some work that would be 200x faster on the GPU just because the amount of time to pass and get back the date would take longer than doing it slowly on the CPU. The thing here is balanced performance, splitting worload between the two. An unified memory architecture will allow PS4 do physics calculations that won't be on PC versions simply because it can jut get the data and calculate on GPU without data passing costs. You have data, it's on CPUs memory space (DDR3), then you must pass it to the GPU memory space (GDDR5). Now try it using PCI-E and see if it looks fast for anything. I can already garantee you, if the data is small, it doesn't matter if the GPU does the operation 300x faster, you will have to use the CPU. The biggest prove of this problems is looking at what NVidia is doing with their GPU tech for clusters. Their biggest problems is that a node, when splitting work in a CUDA program had to: load data on CPU, send to GPU. Get it back on CPU and then send via ethernet/infiniband to all the other nodes that would do the same. Now, they have the hability to access the network interface directly form the GPU, so a GPU can actually send data to other without passing it to the CPU. 

Second, the "memory wall". If you don't believe, reasearch on Google or ask a HPC specialist. This is the single reason that supercomputing migrated form the traditional supercomputer PRAM model for the distributed model we see on clusters. And is one of the primary reasons for Cloud Computing. More machines, more memory bandwidth. On old supercomputers (current ones are actually clusters) you increaser the core count and tried your best to find a better memory technology, but that race was lost long ago. Cache is there to help, not to solve. It all depends if the ammount of data you need will fit on it or not. If it won't, you will have to refill it anyway. Having more cores only makes it worse. And cores only help if the code you are running is optimized to use them. A lot of games are 32-bit executables, just to show how they aren't that worried about optimization now (3GB RAM limit for the executable).

Now, on PS4, you know what you have under the hood. The developer knows exactly. You can even predict and interfere in the way things will be on cache to gain performance. You will have games using heavy parallel processing in 8-cores plus offloading some physics to GPU (SPH it's a good example). And believe me, heavy parallel processing is something they aren't doing on PC games yet. And the GPU part it's even worse, it's much more harder to write code that runs calculation well on any GPU than on a specific one, simply because the compilers suck (I mean CUDA tools and OpenCL tools). For the CPU part, you have amazing compilers (partially thanks to Intel works on the 70s and 80s with matematicians). And besides that, it is currently a mess. NVidia and AMD can't create a common GPU API/Framework for doing calculations and we have to watch OpenCL AMD GPUs and CUDA NVidia GPUs (they work with OpenCL too, but NVidia only creates tools for CUDA and they are far better. Current dev tools for AMD GPUs simply suck terribly bad compared to CUDA). And that will make one hell of a difference.