Thursday, December 15th 2011

AMD Starts Shipping 28 nm GPUs for Revenue

AMD CEO Rory Read, speaking at the IT Supply Chain conference organized by Raymond James this Tuesday, said that his company had begun shipping 28 nm GPUs for revenue (meaning, in volumes big enough to fetch revenue). With it, AMD fulfilled its promise to be the first to the market with GPUs built on the 28 nm silicon fab process. AMD's foundry partner for these chips is TSMC. "We are ramping 28nm [products] with TSMC in Taiwan and shipping the products here and now. We are very excited about the products," said Read.

At the upcoming CES event, AMD will formally unveil a range of products that will use its 28 nm GPUs. CES will give AMD a good opportunity to bag design wins with large volume manufacturers of notebooks and PCs. What this means for the enthusiast community is that whenever AMD does launch its Radeon HD 7900 series, it won't be a "paper-launch".
Source: X-bit Labs
Add your own comment

28 Comments on AMD Starts Shipping 28 nm GPUs for Revenue

#26
btarunr
Editor & Senior Moderator
Yellow&Nerdy?Hopefully this won't flop like Bulldozer. At least they have fired their PR, so there won't be BS marketing. Let's hope for good availability at launch.
Yup. In their press briefing, I believe they spelled out the exact transistor count to the last digit (the entire 10-digit number), and it's not an abstract-looking/rounded-off 'x' followed by a number of zeroes.
Posted on Reply
#27
pantherx12
ZubasaThe VILW5 arch really did suck, look at the 2900XT. ;)
That is why they slaped a crap load of shaders on the HD4800s.
Aye like AMD have admitted them selfs a lot of games would not activated all of the vliv5 design.

Typically only 3 of 5 were active.
Posted on Reply
#28
Benetanegia
pantherx12Aye like AMD have admitted them selfs a lot of games would not activated all of the vliv5 design.

Typically only 3 of 5 were active.
Actually, according to some tests from people at Beyond3D and Gamedev.net, it was actually close to 4 and that's what makes the most sense to be honest. Pixel operations are in RGBA, 4 shaders use. Vertex operations are made using vec4 too. VLIW5 was not completely used, although Ati's idea was to have one 4d + one 1d ops being made, it just didn't happen as often as they thought. In any case going to VLIW4 should have really fixed most of that.

For games VLIW didn't suck at all. It was not as efficient, but was far from sucking. GPGPU that's another story. I don't expect much more gaming performance from abandoning VLIW. 5-10% tops.
Posted on Reply
Add your own comment
Jan 10th, 2025 09:18 EST change timezone

New Forum Posts

Popular Reviews

Controversial News Posts