cdrkf
Judicious
etayorius :
blackkstar :
@juan, GCN will never be as efficient in traditional GPGPU as a chip from Nvidia. Nvidia's goals are to remove as much GPGPU as possible to reduce transistor count while not crippling specific GPGPU tasks (like those required for PhysX). If they cripple something and it's more efficient to add transistors for specific tasks (NVENC), they will go that route.
AMD's GPU goals are to create a strong monster for HSA. Their efficiency will come from the large performance gains of HSA over GPGPU. But until we see HSA come to fruition, AMD will lag behind.
I do not think AMD has any reason to chase after low power like in mobile ARM. That is a race to the bottom market and it does AMD no good to be there. They want to be in markets where HSA can do well and AMD can offer a solution that no one else can. An efficient and small GPU is not special and it becomes another competitor to ARM GPUs and smaller Nvidia GPUs. But as far as competing with Nvidia on efficiency, AMD is going to have to compete with someone who feels it's fine to just cut functionality out of a product to raise efficiency when AMD is not in the position to do that thanks to HSA.
But being a GPGPU monster for HSA is going to cost transistors and it's going to put AMD behind Nvidia and company in efficiency in traditional tasks. I think that Nvidia knows this and it's why it's pushing efficiency so hard in marketing material (like reviews screaming GTX 750 Ti is fantastic for PPW).
AMD's value and efficiency here won't show up until we get software that can exploit their hardware. And knowing how things have been in the past, it's not a guaranteed thing.
AMD's GPU goals are to create a strong monster for HSA. Their efficiency will come from the large performance gains of HSA over GPGPU. But until we see HSA come to fruition, AMD will lag behind.
I do not think AMD has any reason to chase after low power like in mobile ARM. That is a race to the bottom market and it does AMD no good to be there. They want to be in markets where HSA can do well and AMD can offer a solution that no one else can. An efficient and small GPU is not special and it becomes another competitor to ARM GPUs and smaller Nvidia GPUs. But as far as competing with Nvidia on efficiency, AMD is going to have to compete with someone who feels it's fine to just cut functionality out of a product to raise efficiency when AMD is not in the position to do that thanks to HSA.
But being a GPGPU monster for HSA is going to cost transistors and it's going to put AMD behind Nvidia and company in efficiency in traditional tasks. I think that Nvidia knows this and it's why it's pushing efficiency so hard in marketing material (like reviews screaming GTX 750 Ti is fantastic for PPW).
AMD's value and efficiency here won't show up until we get software that can exploit their hardware. And knowing how things have been in the past, it's not a guaranteed thing.
AMD slogan should be:
Lagging today for creating the Tech of tomorrow, who will be obsolete then.
It`s basically the same strategy they used with Bulldozer. HSA seems awesome but if they can`t make use of the tech NOW, they are basically screwed.
Damn it AMD, Damn it... just give me a 4-6 Core Phenom based CPU with 15% increased IPC and 20% increased speed, and i would haste to the local PC Hardware Store.
AMD have actually been pretty forward looking with their designs and haven't been playing it safe...
Phenom was the *first* monolithic quad core on the market. TLB bug + low clock rate + lack of transistors for cache killed it's performance related to Core 2 Quad (2 dual cores in 1 package, a poor solution imo Intel got lucky that Phenom I had problems imo). Phenom II fixed these issues and was a superb chip competative at release with the higher end C2Q chips. Intel then release the first i7 which essentially mixed their stronger core (C2) with all of the enhancements AMD released with Phenom I (monolithic quad core, HT type interface rather than FSB, 3rd level cache etc) and bolted on HT that they had back when they screwed up so badly with P4.
AMD then release bulldozer (2 years late) which unfortunately pitched it against Sandy (gen 2 i7) when it *should* have gone against the previous gen. Bullozer was also a brave design, and was / is reasonably competative againts 1st gen i7 but not against Sandy which had major uarch improvements. Piledriver (which should have been out in time to compete against Sandy) had to contend with Ivy instead...
On the APU side, Intel still don't have anything close to the level of integration that AMD has with HSA- the main issue at the moment is there is no software to take full advantage of the capability however it's imporated for AMD to get something into the wild or there never will be.
Ok, they're behind but you need to give AMD some credit. I mean if you go back to the late 90s, AMD not only kept pace with Intel, they outran them repeatedly with the first Athlon, Athlon Thunderbird (first 1ghz+ cpu), Athlon XP (competative with P4), Athlon 64 (Destroyed P4) and Athlon 64 x2 (first dual core), and they did this with a fraction of the budget Intel had (which is what lead Intel to play dirty as AMD had an equal or better product for nearly a decade).