In 2018 AMD Zen should be Mature enough on both servers and WS, also Zen supports PCIe4.
Got a tip for us?
Let us know
Become a MacRumors Supporter for $50/year with no ads, ability to filter front page stories, and private forums.
MP 7,1 Waiting for Mac Pro 7,1 A1991 (no more)
- Thread starter Mago
- Start date
-
- Tags
- macpro 2016
- Sort by reaction score
In 2018 AMD Zen should be Mature enough on both servers and WS, also Zen supports PCIe4.
No Zen for me thanks. 2018 is still too far out anyway.
But Skylake-W looks sweet, by then the nMP will be awesome. PCIe4 will be great, let's see if Zen does indeed feature it at the time, and the lack of it in Intel's platform is a letdown, but 44 CPIe3 lanes on the CPU and another 24 on the PCH looks good for the nMP.
But Skylake-W looks sweet, by then the nMP will be awesome. PCIe4 will be great, let's see if Zen does indeed feature it at the time, and the lack of it in Intel's platform is a letdown, but 44 CPIe3 lanes on the CPU and another 24 on the PCH looks good for the nMP.
It seems Intel will be releasing Coffee Lake in 2018 after Kaby Lake in the 14nm process for the mainstream market, up to 6 cores.
At this time I believe Intel is really lost as to how to present their processor lineup.
At this time I believe Intel is really lost as to how to present their processor lineup.
Coffee Lake? That's a truly silly name. I guess 10nm is hard and they are thinking of just making bigger 14nm chips to get by?
Seems weird that high end laptop processors are being said to get the 6 cores, odd place to start. Is intel worried about the gaming-laptop market?
Seems weird that high end laptop processors are being said to get the 6 cores, odd place to start. Is intel worried about the gaming-laptop market?
Those will have beefier GPUs (GT3e) that's why they might go with an older but known and reliable process node.
Apple making a car is a difficult concept for me, but nonetheless they've hired hundreds of automotive people so I don't see what else they could be doing.
It's definitely not just iOS electronics in a car because they are hiring (for example) suspension, chassis, and battery experts. It really seems like they are going to make an electric car.
Well lets hope Jonny Ive doesn't design it. It will be very small.
Interesting to see that there are rumors about dark mode in iOS and in macOS Sierra. And people started hinting that it might be related with OLED displays. For iOS its obvious why - rumors about OLED displays in iOS devices. However...
That also might spawn speculation about OLED displays from Apple. The only monitor that I have heard lately about this technology in monitors is... Dell UP3017Q. 120 Hz, 30 inch 4K display with astounding image quality. For that you would need DP1.4. Currently the 5K display in 5K iMac, as far as I know, is also coming from Dell.
And then there is the memorable 8K iMac speculation still.
That also might spawn speculation about OLED displays from Apple. The only monitor that I have heard lately about this technology in monitors is... Dell UP3017Q. 120 Hz, 30 inch 4K display with astounding image quality. For that you would need DP1.4. Currently the 5K display in 5K iMac, as far as I know, is also coming from Dell.
And then there is the memorable 8K iMac speculation still.
I would love this in every OS. Tired of staring into a huge square flashlight all day.
But they'll have collected data on hundreds of thousands of cars entering and leaving the parking structures at the Space Ship campus, and determined that the average is that:
- A vehicle has 1.1983 passengers
- It has a cargo load of 1.1023 daypacks.
He'll bump the cargo area up to two daypacks, because that metric had a higher standard deviation.
Na, room for a second day pack will be a $3000 BTO.
http://semiaccurate.com/2016/07/25/amd-revamps-workstation-lines-adds-three-cards/
http://semiaccurate.com/2016/07/25/amd-puts-massive-ssds-gpus-calls-ssg/
So this is what apple demod at NaB - the FCP X update on presumably engineering Mac hardware with this.
"
AMD just changed the GPU game forever with their Radeon SSG technology. If you have been waiting for a GPU with massive flash storage on board, SemiAccurate has good news for you.
It is hard to overstate what a sea change AMD’s SSG technology brings, putting large low latency storage on a GPU will bring about some amazing opportunities. More importantly things that simply could not be done on a GPU before are now not only possible but practical. For the professional space in movie rendering, previsualization, and massive, complex CAD models, persistent GPU storage really does change how things will be done.
On the technical front the idea is easy enough to explain, take a couple of M.2 PCIe3 4x NVMe SSDs and slap the onto a professional GPU. Connect them with eight PCIe lanes peeled off the main bus, and off you go. Not many more technical details were given out, nor were pictures of the card or board, but that should be enough to get us started.
In short you can now have terabytes of persistent low latency storage on your GPU, with persistent, low latency, and terabytes being the game changing parts so we will repeat them, several times. Terabytes of persistent low-latency storage on your GPU, really important. The hardware is just off the shelf M.2 SSDs so the low-level wear leveling will be handled by the hardware and users will see this first generation as just storage. If AMD doesn’t implement a flat memory model in very short order in the next generation or two, we will happily eat one. HINT.
So users now have a fairly coarse block addressable space on their professional GPUs, what’s the big deal? You don’t have to traverse the system PCie bus, the driver stack, CPU, back over the bus, and to storage to get data now so the impossible is now possible. Better yet the CPU overhead of sending data to the GPU is now gone as is the bus congestion brought on by streaming large textures from plentiful system memory to precious GPU memory. This is the roundabout technical way of saying that SemiAccuate thinks those 8x PCIe lanes peeled off for the SSDs are going to be more than made up for by the system traffic they free up. Faster, less energy, and lower latency.
But what about these benefits? The first demo AMD is said to be showing is a use case for movie editing and cleanup on the GPU. What is the issue here you may ask, this is old hat and has been done on the CPU for years. Some GPUs can even assist it without slowing things down in the process, so what does SSG add? How about 8K movie streaming and cleanup in realtime. At 96FPS. Sure you can do this with traditional methods but the best of them will run the same task at 17FPS.
AMD is happy to point out this is a 5.6x speedup or so for the cost of two consumer SSDs. Before SSG, possible but slow. After SSG, fast enough for most users. The impossible, realtime 8K cleanup, is now possible. Hugely complex and highly detailed CAD models that took the better part of an hour to load up and decompress will still take the better part of an hour to load up and decompress on an SSG GPU based system. Why bother? Because it takes the better part of an hour to load and decompress the first time, then it can stay resident on the GPU’s flash storage. The second time it should take seconds. If you look at the cost of a modern automotive or aerospace engineer’s time, SSG is a no-brainer, any CTO would be foolish not to deploy this tech ASAP, the ROI would be measured in weeks.
http://semiaccurate.com/2016/07/25/amd-puts-massive-ssds-gpus-calls-ssg/
So this is what apple demod at NaB - the FCP X update on presumably engineering Mac hardware with this.
"
It is hard to overstate what a sea change AMD’s SSG technology brings, putting large low latency storage on a GPU will bring about some amazing opportunities. More importantly things that simply could not be done on a GPU before are now not only possible but practical. For the professional space in movie rendering, previsualization, and massive, complex CAD models, persistent GPU storage really does change how things will be done.
On the technical front the idea is easy enough to explain, take a couple of M.2 PCIe3 4x NVMe SSDs and slap the onto a professional GPU. Connect them with eight PCIe lanes peeled off the main bus, and off you go. Not many more technical details were given out, nor were pictures of the card or board, but that should be enough to get us started.
In short you can now have terabytes of persistent low latency storage on your GPU, with persistent, low latency, and terabytes being the game changing parts so we will repeat them, several times. Terabytes of persistent low-latency storage on your GPU, really important. The hardware is just off the shelf M.2 SSDs so the low-level wear leveling will be handled by the hardware and users will see this first generation as just storage. If AMD doesn’t implement a flat memory model in very short order in the next generation or two, we will happily eat one. HINT.
So users now have a fairly coarse block addressable space on their professional GPUs, what’s the big deal? You don’t have to traverse the system PCie bus, the driver stack, CPU, back over the bus, and to storage to get data now so the impossible is now possible. Better yet the CPU overhead of sending data to the GPU is now gone as is the bus congestion brought on by streaming large textures from plentiful system memory to precious GPU memory. This is the roundabout technical way of saying that SemiAccuate thinks those 8x PCIe lanes peeled off for the SSDs are going to be more than made up for by the system traffic they free up. Faster, less energy, and lower latency.
But what about these benefits? The first demo AMD is said to be showing is a use case for movie editing and cleanup on the GPU. What is the issue here you may ask, this is old hat and has been done on the CPU for years. Some GPUs can even assist it without slowing things down in the process, so what does SSG add? How about 8K movie streaming and cleanup in realtime. At 96FPS. Sure you can do this with traditional methods but the best of them will run the same task at 17FPS.
AMD is happy to point out this is a 5.6x speedup or so for the cost of two consumer SSDs. Before SSG, possible but slow. After SSG, fast enough for most users. The impossible, realtime 8K cleanup, is now possible. Hugely complex and highly detailed CAD models that took the better part of an hour to load up and decompress will still take the better part of an hour to load up and decompress on an SSG GPU based system. Why bother? Because it takes the better part of an hour to load and decompress the first time, then it can stay resident on the GPU’s flash storage. The second time it should take seconds. If you look at the cost of a modern automotive or aerospace engineer’s time, SSG is a no-brainer, any CTO would be foolish not to deploy this tech ASAP, the ROI would be measured in weeks.
I guess you missed the memo. They have been using codenames based on stuff in Oregon (mostly) for quite some time now.
really? you wouldn't be interested in seeing a car designed by Ive?
why not? i don't get it.
According to AMD roadmaps, Navi is the architecture which will have next gen memory. Interesting.http://semiaccurate.com/2016/07/25/amd-revamps-workstation-lines-adds-three-cards/
http://semiaccurate.com/2016/07/25/amd-puts-massive-ssds-gpus-calls-ssg/
So this is what apple demod at NaB - the FCP X update on presumably engineering Mac hardware with this.
"
AMD just changed the GPU game forever with their Radeon SSG technology. If you have been waiting for a GPU with massive flash storage on board, SemiAccurate has good news for you.
It is hard to overstate what a sea change AMD’s SSG technology brings, putting large low latency storage on a GPU will bring about some amazing opportunities. More importantly things that simply could not be done on a GPU before are now not only possible but practical. For the professional space in movie rendering, previsualization, and massive, complex CAD models, persistent GPU storage really does change how things will be done.
On the technical front the idea is easy enough to explain, take a couple of M.2 PCIe3 4x NVMe SSDs and slap the onto a professional GPU. Connect them with eight PCIe lanes peeled off the main bus, and off you go. Not many more technical details were given out, nor were pictures of the card or board, but that should be enough to get us started.
In short you can now have terabytes of persistent low latency storage on your GPU, with persistent, low latency, and terabytes being the game changing parts so we will repeat them, several times. Terabytes of persistent low-latency storage on your GPU, really important. The hardware is just off the shelf M.2 SSDs so the low-level wear leveling will be handled by the hardware and users will see this first generation as just storage. If AMD doesn’t implement a flat memory model in very short order in the next generation or two, we will happily eat one. HINT.
So users now have a fairly coarse block addressable space on their professional GPUs, what’s the big deal? You don’t have to traverse the system PCie bus, the driver stack, CPU, back over the bus, and to storage to get data now so the impossible is now possible. Better yet the CPU overhead of sending data to the GPU is now gone as is the bus congestion brought on by streaming large textures from plentiful system memory to precious GPU memory. This is the roundabout technical way of saying that SemiAccuate thinks those 8x PCIe lanes peeled off for the SSDs are going to be more than made up for by the system traffic they free up. Faster, less energy, and lower latency.
But what about these benefits? The first demo AMD is said to be showing is a use case for movie editing and cleanup on the GPU. What is the issue here you may ask, this is old hat and has been done on the CPU for years. Some GPUs can even assist it without slowing things down in the process, so what does SSG add? How about 8K movie streaming and cleanup in realtime. At 96FPS. Sure you can do this with traditional methods but the best of them will run the same task at 17FPS.
AMD is happy to point out this is a 5.6x speedup or so for the cost of two consumer SSDs. Before SSG, possible but slow. After SSG, fast enough for most users. The impossible, realtime 8K cleanup, is now possible. Hugely complex and highly detailed CAD models that took the better part of an hour to load up and decompress will still take the better part of an hour to load up and decompress on an SSG GPU based system. Why bother? Because it takes the better part of an hour to load and decompress the first time, then it can stay resident on the GPU’s flash storage. The second time it should take seconds. If you look at the cost of a modern automotive or aerospace engineer’s time, SSG is a no-brainer, any CTO would be foolish not to deploy this tech ASAP, the ROI would be measured in weeks.
Vega is the one with completely Out-of-Order capabilities, with complete independence from CPU scheduling, so it is more like System-on-chip type of hardware. AMD is slowly evolving its architecture.
Edit: After thinking a bit on this, computers like current Mac Pro design will benefit from this technology a lot. You just need to add coherent fabric to the computer, and connect the GPUs with it.
Edit 2:
Holy hell!
Hehe, and the fact that flagship Quadro was revealed by Nvidia just two days before is saying much
.One more link from SA: http://semiaccurate.com/2016/07/25/amd-unveils-loom-prorender-software/
Specially, I love this part:
Last edited:
As pcper says http://www.pcper.com/news/Graphics-...essional-GPU-Paired-Low-Latency-Flash-Storage
This might not be a full move towards HSA but it's an interesting step - having full TB sized models via the SSD attached to the GPU will be interesting.
AMD and Nvidia have different strengths - AMD doesn't that's all of the VR stuff Nvidia does (allowing different viewpoints for example). But stuff like this seems a nice counter.
AMD have indicated there will be something after Crossfire but not gone jntobit. Maybe we'll see it come through for post Polaris.
Anyway - looks like something with waiting a month or two for.
This might not be a full move towards HSA but it's an interesting step - having full TB sized models via the SSD attached to the GPU will be interesting.
AMD and Nvidia have different strengths - AMD doesn't that's all of the VR stuff Nvidia does (allowing different viewpoints for example). But stuff like this seems a nice counter.
AMD have indicated there will be something after Crossfire but not gone jntobit. Maybe we'll see it come through for post Polaris.
Anyway - looks like something with waiting a month or two for.
It appears that this is designed for GPU clusters, with single machine. Remember? Single CPU, multiple GPUs stacked together with coherent fabric, working on HPC tasks.
About Crossfire: coherent fabrics for consumers and professional use. It is the best way to get highest possible scaling, with next ten APIs, and HSA.
Nothing like assuming things about my life to bolster your ignorance.
The new "Pro" gpu from AMD seem aligned with Mac Pro naming :
WX7100 => D710 ¦ DX700 ¦ DX710
WX5100 => D510 ¦ DX500 ¦ DX510
WX4100 => D310 ¦ D410 ¦ D400 ¦ DX400 ¦ DX410
BTW are just rebadged Polaris 10XT, 10pro and 11xt. Or Radeon RX480/470/460..
@koyot @ManuelGomez
WX7100 => D710 ¦ DX700 ¦ DX710
WX5100 => D510 ¦ DX500 ¦ DX510
WX4100 => D310 ¦ D410 ¦ D400 ¦ DX400 ¦ DX410
BTW are just rebadged Polaris 10XT, 10pro and 11xt. Or Radeon RX480/470/460..
@koyot @ManuelGomez