Why PCs still have separate memory for CPU and GPU...

[Kinthalis]

I thought the PS3 had separate memory buses fro it’s CPU and GPU?

Rendering/transcoding video is one of the things GPU’s can do a LOT faster, and common home software has been including GPU accelerated transcoding/rendering.

[Blakeyrat]

@Harmonix

Could GPGPU work on … say excel?

I would buy a monster video card just for speeding up Excel if microsoft did that.

(I regularly push the limits of what should be done in excel)

Possibly, but they’d have to rewrite Excel’s core and probably ditch VBA to make it work, and Microsoft won’t do that until they have literally no other choice. VBA doesn’t even properly support multi-threading on current machines, there’s no chance they could implement CUDA-like calculations without ditching it.

[urban1a]

Is there now some overlap between CPU and GPU processors? The new ASUS Nexus 7 tablet uses a Nvidia Tegra 3 quad-core processor, but also comes with a 12 (16?)-core graphics processor. Nvidia is mostly known as a Graphics Processor company.

Bob

[Cerowyn]

@Qwertol

What I don’t understand why they are not making something similar with high performance systems (only using fast memory chips like GDDR5 or something like that, yeah that would be expensive, but gamers usually don’t care that much).

Most high-end cards do use DDR5 memory. A Radeon HD 7970, for instance, uses 3 GB of DDR5 memory, with 264 GB/s throughput. Even the bottom of the mid-range HD 7750 uses DDR5 memory.

[Whack-a-Mole]

@Gagundathar

I use Bryce 7 in my work.
It takes a LOT of time to render a scene since I am only using an E2200 CPU.
In fact, if I do an intensive render, I have to release one of the cores just so I can surf the web while I wait the 15-45 minutes that a high res picture takes to be complete.

I can’t imagine why a GPU wouldn’t be an order of magnitude better in terms of speed.

GPUs are heaps better at such tasks IF (note the big “if”) the software can make use of it.

My company does a lot of video work and I just built a PC for them which uses an Nvidia card to work with the Adobe suite. Some things, like encoding, are all CPU based but other things (and I really do not know what) absolutely take advantage of the Nvidia CUDA cores. Or so I am told. The guy who does this work say the PC I built him blows the doors off the Mac he used to use.

Here is a good analogy of the difference between a CPU and a GPU (CPU = an executive and a GPU = a laborer):

One way to visualize it is a CPU works like a small group of very smart people who can quickly do any task given to them. A GPU is a large group of relatively dumb people who aren’t individually very fast or smart, but who can be trained to do repetitive tasks, and collectively can be more productive just due to the sheer number of people.

It’s not that a CPU is fat, spoiled, or lazy. Both CPUs and GPUs are creations made from billions of microscopic transistors crammed on a small piece of silicon. On silicon chips, size is expensive. The structures that make CPUs good at what they do take up lots of space. When those structures are omitted, that leaves plenty of room for many “dumb” ALU’s, which individually are very small.

The ALUs of a GPU are partitioned into groups, and each group of ALUs shares management, so members of the group cannot be made to work on separate tasks. They can either all work on nearly identical variations of one single task, in perfect sync with one another, or nothing at all. Trying different hashes repeatedly - the process behind Bitcoin mining - is a very repetitive task suitable for a GPU, with each attempt varying only by the changing of one number (called a “nonce”) in the data being hashed.

The ATI Radeon 5970 is a popular video card for Bitcoin mining and, to date, offers the best known performance of any video card for this purpose.

This particular card has 3,200 “Stream Processors”, which can be thought of as 3,200 very dumb execution units that can be trained to all do the same repetitive task, just so long as they don’t have to make any decisions that interrupts their flow. Those execution units are contained in blocks. The 5970 uses a VLIW-5 architecture, which means the 3,200 Stream Processors are actually 640 “Cores,” Each able to process 5 instruction per clock cycle. Nvidia would call these cores “Cuda Cores”, but as mentioned in this article, they are not VLIW, meaning they cannot do as much work per cycle. This is why comparing graphics cards by core count alone is not an accurate method of determining performance, and this is also why nVidia lags so far behind ATI in SHA-256 hashing.

Since ALU’s are what do all the work of Bitcoin mining, the number of available ALU’s has a direct effect on the hash output. Compare that to a 4-core CPU that can switch tasks on a dime, but has ALU’s in some small multiple of four, if not just four ALU’s alone. Trying a single SHA256 hash in the context of Bitcoin mining requires around 1,000 simple mathematical steps that must be performed entirely by ALU’s.

That, in a nutshell, is why GPU’s can mine Bitcoins so much faster than CPU’s. Bitcoin mining requires no decision making - it is repetitive mathematical work for a computer. The only decision making that must be made in Bitcoin mining is, “do I have a valid block” or “do I not”. That’s an excellent workload to run on a GPU.

SOURCE: Why a GPU mines faster than a CPU - Bitcoin Wiki

[RaftPeople]

@urban1a

Is there now some overlap between CPU and GPU processors? The new ASUS Nexus 7 tablet uses a Nvidia Tegra 3 quad-core processor, but also comes with a 12 (16?)-core graphics processor. Nvidia is mostly known as a Graphics Processor company.

Bob

You aren’t seeing an overlap as much as placing different components on a single chip (SoC). CPU cores and GPU cores get placed on the same chip but they each still retain their style of processing (and therefore specialty).

NVIDIA licensed an ARM CPU core (almost all phones and other electronic devices other than PC’s use ARM processors), stuck a few of those on a chip and then stuck a few of their own GPU cores on the chip. It’s the same thing all the players are doing (Apple, Samsung, etc.).

[Kinthalis]

Yep AMD already has a line (or two?) or APU’s which are exactly that a general computing CPU + specialized GPU cores.

I have one (the AMD A8) running on my home theater PC. For one low price, and the TDP/size requirements of a standard CPU I get a little chip that does everything pretty well, from processing HD video, recording live TV, to playing games at a nice pace at 720p.

Pretty cool stuff.