14 DAY TRIAL // While an executive from Advanced Micro Device states that the company's ATI graphics unit is not on the "huge" chips building, as Nvidia, the rival responds that smaller may prove not to be better or more efficient. The war on the graphics cards market continues with new rounds, this time on the statements level, but the conflict is expected to last a few years more on the high-end graphics cards market segment.
Nvidia has already announced one of the largest graphics chips, the upcoming high-end GTX 280. The ultimate gaming enthusiasts expect this chip with high hopes. GTX 280 should provide great performance, but that will come through a large transistor count.
AMD, which has its plans of delivering extreme graphics technology with its upcoming X2, a continuation for the current 3870 X2 series, is determined to use a fundamentally different strategy.
"We took two chips and put it on one board (X2). By doing that we have a smaller chip that is much more power efficient," said Matt Skynner, vice president of marketing for the graphics products group at AMD. "We believe this is a much stronger strategy than going for a huge, monolithic chip that is very expensive and eats a lot of power and really can only be used for a small portion of the market," he said. "Scaling that large chip down into the performance segment doesn't make sense--because of the power and because of the size."
According to Skynner, AMD's strategy is to design GPUs for the mainstream market segment, then constantly moving the performance up by adding GPUs and not by making one "huge", extreme-performance chip. He also added that Nvidia's "strategy is to design for the highest performance at all cost. And we believe designing for the sweet spot and then leveraging for the extreme enthusiast market with multiple GPUs is the preferred approach."
AMD plans to apply this strategy to memory as well. According to the company, GDDR5 memory is another type of technology that helps cutting costs on delivering the same performance level. "You don't need a huge chip with a huge data path to get the bandwidth. You can utilize a technology like GDDR5 to get that bandwidth," Skynner said.
On the other hand, Nvidia, which favors very-fast, single-chip solutions, has another view on the development of big, very fast chips issue. Ujesh Desai, general manager for GeForce products at Nvidia, explains: "If you take two chips and put them together, you then have to add a bridge chip that allows the two chips to talk to each other... And you can't gang the memory together. So when you add it all up, you now have the power of two GPUs, the power of the bridge chip, and the power that all of that additional memory consumes. That's why it's too simplistic of an argument to say that two smaller chips is always more efficient."
"They don't have the money to invest in high-end GPUs anymore. At the high end, there is no prize for second place. If you're going to invest a half-billion dollars--which is what it takes to develop a new enthusiast-level GPU--you have to know you're going to win. You either do it to win, or you don't invest the money," Desai also said.
We should note that, while AMD's Radeon HD 3870 X2 uses two chips on a single board, Nvidia's GeForce 9800 GX2 has a dual-board design, with one 9800 chip on each board.