kc5tja wrote:
Change the image to what though? At 150KB per screen, you can only pack so many frame buffers into the video card's memory. Eventually, the CPU will need to load frames into the card, and it must do so at least at frame rate.
I get what your saying, but consider the latest generations of CPU's compared to GPUs.
Phenom 9950 has four 64-bit CPU cores at 2.6 GHz, A total of 758 million transistors. But only does 41.6 GFLOPS.
Where as AMD through their ATI division is making a Radeon HD 5970 with 2 256-bit cores, 4,308 million transistors, and a impressive 5440 GFLOPS of processing power.
With the large sizes (in the GBs) of DDR ram available to the graphics card. I was just envisioning building a dedicated GPU that will get the raw data from the CPU (such as a map of a area in a vedio game) and the CPU will only have to tell the GPU what is the X,Y,X and bearing of the person/characters to generate the map for example in a modern video game. Which is what many online games today do to limit the bandwidth requirements between the players.
kc5tja wrote:
Remember back in the mid-80s and early-90s when the MPC standard came out?
Depending on the specific year, I was either not alive yet, or too young to know what a computer is.
But I am looking it up as I am typing this.
Dimitri