AMD will launch AM4 platform in March 2016 says industry source

[mrmt]

It was similar than Pentium 4 fiasco. They have years in advantage on their experimental nodes, so they knew that they won't make it. However at difference of the current case, AMD was there. Now there is no competition near Intel.

So you and IntelUser2000 believe that Intel was prescient enough to know they would have production issues 4-5 years down the road, but that it wasn't proactive enough to make a course correction in the meantime? That would be extremely incompetent.

 

[AtenRa]

Feel free to provide the documentation.

because you have some flawed estimates about cost on both nodes. And its been ever so since AMD got a disadvantage. However with 14nm AMD products you tend to forget all those. Specially since they cant afford the designs to remove most of the penalties.

1: Provide proof R&D cost is not rising for every new process
2: Provide proof IC design cost is not rising for every new process
3: Provide proof that 14nm doesnt need more masks (double or triple pattern). Also 14nm have more process fabrication stages making Wafer cost more expensive than the node before.
4: Provide proof that 14nm yields today are better than 28nm

Then we can talk.

 

[AtenRa]

Even with A10, Core i3 + GT 730 GDDR5 would be faster.

Haven't tried this setup, got any links ??? because the GT730 with GDDR5 only has a 64bit memory controller.

 

[The Stilt]

I really hope AMD would be able to implement HBM for Raven Ridge, but I fear the technology is still too high-end to be used in a APU (market segment / price point) at the time RR is out. HBM or a extremely fast on-die frame buffer cache is mandatory in order to kick-(re)start the APU concept.

If AMD fails to solve the bandwidth issue, they will loose their only remaining edge over Intel. AMD has run out of time and unless the solution is introduced in Raven Ridge APU / SoCs the whole concept of AMD APUs will die along with this failure. After that the target markets for their APUs will be solely in developing countries.

In the other hand, if AMD is infact able to introduce HBM or a on-die frame buffer in Raven Ridge, the performance improvements for APUs will be simply tremendous. Even with the bandwidth available from a single HBM stack (128GB/s @ 500MHz) AMD could increase the GPU resources up to 2.5x (over current generation APUs).

However based on the history I´m not holding my breath for this to happen, at least not in Raven Ridge :'( Wouldn´t be too surprised if Raven Ridge would be restricted to DDR-2400 (DDR4) too D:

 

[mrmt]

If AMD fails to solve the bandwidth issue, they will loose their only remaining edge over Intel. AMD has run out of time and unless the solution is introduced in Raven Ridge APU / SoCs the whole concept of AMD APUs will die along with this failure. After that the target markets for their APUs will be solely in developing countries.

I think they already lost this battle. DDR4 will be enough for non-gaming applications for the foreseeable future and HBM still seems to have poor economics, too poor for the mainstream gaming market. A niche product with poor economics won't cut it.

I lost my faith in HBM by the time Lisa Su said that margins were poor on a $500 fury.

 

[cbn]

Even with A10, Core i3 + GT 730 GDDR5 would be faster.

Haven't tried this setup, got any links ??? because the GT730 with GDDR5 only has a 64bit memory controller.

The only review I ever found was one at tipidpc, but they took the info down.

I do own the card though. So if you want me to do some gaming benchmarks with my Athlon x 4 860K I would be happy to do so. Then we can compare to your A10-7850K.

P.S. The memory bus is only 64 bit, but the bandwidth @ 40 GB/s is still higher than an APU with dual channel DDR3/4 2400 (which has to share bandwidth with the CPU).

 

[BigDaveX]

If memory serves, the GPU in the Surface Book has a 64-bit memory bus, and it easily outperforms any Intel iGPU, to an extent where it'd almost certainly beat anything that an AMD APU has to offer. Though granted, that's a Maxwell-based chip instead of Kepler.

 

[Arachnotronic]

Lol at the people saying that Raven Ridge will use HBM. They're not even using it on the first Polaris card which I guarantee you has significantly greater cost & performance headroom.

 

[AtenRa]

The only review I ever found was one at tipidpc, but they took the info down.

I do own the card though. So if you want me to do some gaming benchmarks with my Athlon x 4 860K I would be happy to do so. Then we can compare to your A10-7850K.

P.S. The memory bus is only 64 bit, but the bandwidth @ 40 GB/s is still higher than an APU with dual channel DDR3/4 2400 (which has to share bandwidth with the CPU).

Well i dont currently have the A10 but only the A8-7600, but i would really like to know how this GPU will do. we should talk in pm in a few days and try to make a new topic

 

[AtenRa]

Lol at the people saying that Raven Ridge will use HBM. They're not even using it on the first Polaris card which I guarantee you has significantly greater cost & performance headroom.

Im sure by H2 2017 HBM 2.0 will be more than fine for the high-End AMD APUs to go against Iris-Pro.
Apple could pay for those you know

 

[Arachnotronic]

Im sure by H2 2017 HBM 2.0 will be more than fine for the high-End AMD APUs to go against Iris-Pro.
Apple could pay for those you know

Keep promoting a potential AMD CPU win in a MacBook Pro until you're blue in the face but it's probably not going to happen.

 

[AtenRa]

Keep promoting a potential AMD CPU win in a MacBook Pro until you're blue in the face but it's probably not going to happen.

Same thing was said by an AMD GPU in the MAC pro. And dont forget Apple almost used an AMD APU(Llano), this time it will be different.

 

[Arachnotronic]

Same thing was said by an AMD GPU in the MAC pro. And dont forget Apple almost used an AMD APU(Llano), this time it will be different.

Lol, ok.

 

[Sweepr]

And dont forget Apple almost used an AMD APU(Llano), this time it will be different.

Based on? SA B$ doesn't count.

 

[AtenRa]

Lol, ok.

LoL all you want but Apple would be dump to pass off the opportunity to have a ZEN APU + Polaris dGPU in a Metal environment by late 2016 early 2017.

 

[erunion]

Lol at the people saying that Raven Ridge will use HBM. They're not even using it on the first Polaris card which I guarantee you has significantly greater cost & performance headroom.

it's interesting watching these rumors develop. first there was the suggestion that HBM could be used for APUs, then it definitely coming eventually, now it's going to be on Raven ridge? quite an escalation.

As far as I know HBM is a graphics only product and can not replace main system memory anyways.

 

[Arachnotronic]

LoL all you want but Apple would be dump to pass off the opportunity to have a ZEN APU + Polaris dGPU in a Metal environment by late 2016 early 2017.

Zen APU hasn't even taped out yet, so how can you possibly know if Zen APU will be any good?

Also, early 2016 MacBook Pro is almost certainly going to be SKL 4+4e, and I'd bet good money on an early 2017 MacBook Pro being a Kaby Lake design. By early 2018, Apple can choose between a Zen APU or Cannonlake.

 

[AtenRa]

Zen APU hasn't even taped out yet, so how can you possibly know if Zen APU will be any good?

Also, early 2016 MacBook Pro is almost certainly going to be SKL 4+4e, and I'd bet good money on an early 2017 MacBook Pro being a Kaby Lake design. By early 2018, Apple can choose between a Zen APU or Cannonlake.

Yea i mean when the APUs will start being manufactured, not when Mac Book Pro will be ready in retail.

Secondly, the performance of the AMD APU (Polaris iGPU) + Polaris dGPU with the Metal API, will make it far better than any Intel iGPU + dGPU.

 

[Arachnotronic]

Yea i mean when the APUs will start being manufactured, not when Mac Book Pro will be ready in retail.

Secondly, the performance of the AMD APU (Polaris iGPU) + Polaris dGPU with the Metal API, will make it far better than any Intel iGPU + dGPU.

Cool, can you share with us performance data of Kaby Lake GT4e as well as the highest configuration of Cannonlake? This is something that I am very interested in knowing and it would seem that you know all about it.

Much appreciated, thanks.

 

[ShintaiDK]

If Apple wanted gaming performance they would not go with AMD in the first place as dGPUs. They want (OpenCL) compute.

Assuming we avoid the epic hype train that is in full swing.

 

[AtenRa]

Cool, can you share with us performance data of Kaby Lake GT4e as well as the highest configuration of Cannonlake? This is something that I am very interested in knowing and it would seem that you know all about it.

Much appreciated, thanks.

Do you have any illusions that Intel Kabylake GT4e iGPU will even come close to Polaris in Compute performance with the Highly AMD GCN optimized Metal API as an added bonus ???
Not only that but the thought of almost doubling the Compute performance by using a dGPU Polaris in CrossFire mode without many of the drawbacks of DX-11, will only make the combination of the ZEN APU + Polaris dGPU a product Apple would kill to have.

 

[Arachnotronic]

Do you have any illusions that Intel Kabylake GT4e iGPU will even come close to Polaris in Compute performance with the Highly AMD GCN optimized Metal API as an added bonus ???
Not only that but the thought of almost doubling the Compute performance by using a dGPU Polaris in CrossFire mode without many of the drawbacks of DX-11, will only make the combination of the ZEN APU + Polaris dGPU a product Apple would kill to have.

Do you have any illusions that Zen will even come close to Kabylake or Cannonlake in CPU perf?

Can't have it both ways. Can't assume that AMD will magically close the CPU gap while Intel will not close the GPU gap (actually Broadwell GT3 rips AMD's best iGPUs apart and SKL GT4e will increase Intel's lead).

 

[ShintaiDK]

AMD track record is that the next APU flops more than what it replaces. Carrizo APU for laptops have been a complete flop.

Yet somehow all this changes every single time with the next APU.

 

[AtenRa]

actually Broadwell GT3 rips AMD's best iGPUs apart and SKL GT4e will increase Intel's lead

Have you seen any Compute performance Benchmarks of the new Iris pro 6200 in any of the reviews ???

I havent, and it seams OpenCL drivers are excellent as always on the Intel iGPUs.

Current official Windows 10 64bit driver (non Beta)
https://downloadcenter.intel.com/download/25484/Intel-Graphics-Driver-for-Windows-7-8-1-10-15-40-
Driver Version: 15.40.10.64.4300 & 15.40.10.32.4300
DATE: October 16, 2015

KNOWN ISSUES:

• - Forced Application Scaling feature is not enabled in Windows 10
• - Green line may be observed when Denoise is enabled on 6th Generation Intel® Core™ Processors
• - Game may exit if quality settings are set to high on Hitman Absolution* on 4th/5th Generation Intel Core Processors
• - Luxmark* 3.x may not run to completion
• - Two active taskbars may appear when DisplayPort monitor attached to the system is unplugged while in extended desktop display configuration
• - Graphics corruption may be observed in Battlefield Hardline*, Kishonti*, Crysis Warhead* and GRID Autosport* games
• - Graphics corruption may be observed on Risen 3: Titan Lords* on 6th Generation Intel® Core™ Processors
• - Lost Planet 2* may show black background on game menu on 6th Generation Intel® Core™ Processors
• - System may hang in Grand Theft Auto V*, Star Trek Online* and Runescape* games
• - Display flickering may be observed while adjusting brightness on the main menu of the Rage* game
• - Cyberlink Power Director 13* application may crash after loading projects when Shared Virtual Memory is enabled on 5th/6th Generation Intel Core Processors
• - Black screen may occur in DOTA 2, Diablo 3 games and with some 4K DisplayPort displays.
• - System may hang while playing game with active Miracast session
• - Cyberlink Power Director 13 application may crash after loading projects when Shared Virtual Memory is enabled
• - NetFlix* may show corruption playing in Edge browser, or fail to play in Miracast session

And then you believe Apple will not jump in to the opportunity to use ZEN with Polaris.

 

[mrmt]

it's interesting watching these rumors develop. first there was the suggestion that HBM could be used for APUs, then it definitely coming eventually, now it's going to be on Raven ridge? quite an escalation.

As far as I know HBM is a graphics only product and can not replace main system memory anyways.

This. Basically this means making the APU more complex, because the HBM will work as a frame buffer and you would still use DDR memory as a main memory for the system otherwise costs will skyrocket.

Given that AMD is still reeling from putting HBM on very high end SKUs, I will be quite surprised if they are able to put HBM on cheap mainstream SKUs. Zen might improve their cost structure a bit but I doubt squander this cost improvement with HBM won't help them.