Monday, May 27th 2019

AMD Announces Radeon RX 5700 Based on Navi: RDNA, 7nm, PCIe Gen4, GDDR6

AMD at its 2019 Computex keynote today unveiled the Radeon RX 5000 family of graphics cards that leverage its new Navi graphics architecture and 7 nm silicon fabrication process. Navi isn't just an incremental upgrade over Vega with a handful new technologies, but the biggest overhaul to AMD's GPU SIMD design since Graphics CoreNext, circa 2011. Called RDNA or Radeon DNA, the new compute unit by AMD is a clean-slate SIMD design with a 1.25X IPC uplift over Vega, an overhauled on-chip cache hierarchy, and a more streamlined graphics pipeline.

In addition, the architecture is designed to increase performance-per-Watt by 50 percent over Vega. The first part to leverage Navi is the Radeon RX 5700. AMD ran a side-by-side demo of the RX 5700 versus the GeForce RTX 2070 at Strange Brigade, where NVIDIA's $500 card was beaten. "Strange Brigade" is one game where AMD fares generally well as it is heavily optimized for asynchonous compute. Navi also ticks two big technology check-boxes, PCI-Express gen 4.0, and GDDR6 memory. AMD has planned a July availability for the RX 5700, and did not disclose pricing.
Add your own comment

202 Comments on AMD Announces Radeon RX 5700 Based on Navi: RDNA, 7nm, PCIe Gen4, GDDR6

#176
Aquinus
Resident Wat-man
GoldenX said:
And still AMD drivers are the worst at OpenGL since... ATI. They never solved it.
It's gotten a lot better in the Linux ecosystem since they went the open source route with the majority of their driver code. It has done AMD a lot of good on the Linux front. I'm astonished at how much my Vega 64 just works and how it works fairly well to be honest.
Posted on Reply
#177
GoldenX
Aquinus said:

It's gotten a lot better in the Linux ecosystem since they went the open source route with the majority of their driver code. It has done AMD a lot of good on the Linux front. I'm astonished at how much my Vega 64 just works and how it works fairly well to be honest.
I would LOVE to have mesa's OpenGL driver on Windows.
Posted on Reply
#178
medi01
GoldenX said:

And still AMD drivers are the worst at OpenGL since... ATI. They never solved it.
Ties with AMD, plus, minuscule part of the market affected by it and scarcity of resources are at play, I think.

bug said:

But I'm not holding my breath.
Yes, just merely your eyes shut.
Not that I would expect less from someone who claimed cartels are OK, to justify nVidia.

Let me repeat it in big easy to read letters for you: ISA is there to stay, as 11 old CUDA, 7 years old GCN isn't going anywhere. As for microarchitecture, it is very apparently different even between Polaris and Vegas.
Posted on Reply
#179
FordGT90Concept
"I go fast!1!11!1!"
CUDA isn't an ISA, PTX is: https://docs.nvidia.com/cuda/parallel-thread-execution/

Equivalent GCN ISA docs: https://rocm-documentation.readthedocs.io/en/latest/GCN_ISA_Manuals/GCN-ISA-Manuals.html

There's not a whole lot different between Polaris and Vega other than the 16-bit instructions. It is unknown what Navi adds that Vega doesn't have. It might be less about ISA and more about optimization of the graphics pipeline.
Posted on Reply
#180
medi01
FordGT90Concept said:

There's not a whole lot different between Polaris and Vega other than the 16-bit instructions
Polaris is denser. Vega is an attempt to go with sparser, higher frequency design.
There are IPC differences even between Vega 64 and VII.

FordGT90Concept said:

CUDA isn't an ISA, PTX
Arguing about semantics. The very link you've posted is titled "CuDA toolkit"

FordGT90Concept said:

It is unknown what Navi adds that Vega doesn't have
In terms of instruction sense, what does Zen 2 add, what Zen doesn't have?

One coudl stick with the same ISA and yet have vastly different architectures on silicon level, what is there really to argue about?
Posted on Reply
#181
londiste
As I said in another thread to the same claim from you CUDA is not an ISA, it is an API.

PTX is not really an ISA either - it is middleware and a virtual machine is probably the best description for it. Nvidia does not have a static ISA as such over generations, they use PTX to expose the microarchitecure in a somewhat static way. AMD's GCN has been a fairly static thing regardless of the microarchitecture underneath.
Posted on Reply
#182
FordGT90Concept
"I go fast!1!11!1!"
medi01 said:

Polaris is denser. Vega is an attempt to go with sparser, higher frequency design.
There are IPC differences even between Vega 64 and VII.
Vega has more stages than Polaris, hence, higher frequencies.

medi01 said:
Arguing about semantics. The very link you've posted is titled "CuDA toolkit"
Everything GPGPU programming at NVIDIA is under "CUDA" branding. CUDA is not an ISA though.

medi01 said:
In terms of instruction sense, what does Zen 2 add, what Zen doesn't have?
Don't know yet because AMD hasn't given details about changes in Zen 2.

londiste said:
PTX is not really an ISA either - it is middleware and a virtual machine is probably the best description for it. Nvidia does not have a static ISA as such over generations, they use PTX to expose the microarchitecure in a somewhat static way. AMD's GCN has been a fairly static thing regardless of the microarchitecture underneath.
All ISAs have a measure of abstraction because of the necessity to preserve backwards compatibility of high level calls.
Posted on Reply
#183
bug
medi01 said:

Ties with AMD, plus, minuscule part of the market affected by it and scarcity of resources are at play, I think.


Yes, just merely your eyes shut.
Not that I would expect less from someone who claimed cartels are OK, to justify nVidia.

Let me repeat it in big easy to read letters for you: ISA is there to stay, as 11 old CUDA, 7 years old GCN isn't going anywhere. As for microarchitecture, it is very apparently different even between Polaris and Vegas.
Can you write that using bigger fonts? Cause that will make you even more right :D
Posted on Reply
#184
GoldenX
The amount of people calling marketing names ISAs is too big.
Posted on Reply
#185
medi01
FordGT90Concept said:

Everything GPGPU programming at NVIDIA is under "CUDA" branding. CUDA is not an ISA though.
How old is <insert "more correct" name than CUDA>?
Posted on Reply
#186
FordGT90Concept
"I go fast!1!11!1!"
medi01 said:

How old is <insert "more correct" name than CUDA>?
https://docs.nvidia.com/cuda/parallel-thread-execution/index.html#release-notes
PTX 1.0 = CUDA 1.0 = sm_{10,11}
https://www.techpowerup.com/forums/threads/nvidia-graphics-ip.244158/
G80 is the first GPU to use DirectX 10 (Shader Model 1.0)/CUDA 1.0 = GeForce 8800 series = first launched November 8, 2006 with 8800 GTX and GTS

PTX ISA is 12 years, 6 months, 27 days old.
Posted on Reply
#187
medi01
FordGT90Concept said:

PTX ISA is 12 years, 6 months, 27 days old.
Thanks.
And, cough.
Posted on Reply
#188
FordGT90Concept
"I go fast!1!11!1!"
As pointed out, I think NVIDIA and AMD treat their ISAs differently. AMD names ISAs by literally the instructions it supports where NVIDIA never discloses the machine ISA and instead runs everything through a virtual machine that accepts PTX. AMD uses their drivers to smooth over compatibility problems between ISAs not unlike NVIDIA does with PTX. I think one of the reasons why the open source community has problems with NVIDIA is because they never disclose the actual machine code the GPUs support; they only provide documentation on PTX which requires a good driver (which open source developers can't create) in order to function as designed. Open source is at NVIDIA's mercy and they don't really care outside of AI/compute products.

AMD makes most of their ISAs available here:
https://developer.amd.com/resources/developer-guides-manuals/
Posted on Reply
#189
bug
FordGT90Concept said:

As pointed out, I think NVIDIA and AMD treat their ISAs differently. AMD names ISAs by literally the instructions it supports where NVIDIA never discloses the machine ISA and instead runs everything through a virtual machine that accepts PTX.
And we have successfully deviated from AMD mixing GCN+Navi and pure Navi under the same GPU family to "what is an ISA". GJ medi.
Posted on Reply
#190
FordGT90Concept
"I go fast!1!11!1!"
All we know from driver is that it's a new compute unit (GFX10). Until AMD gives more information, we don't know how significant the changes are. GCN has a fairly rigid architectural layout which Vega, despite being called "Next-Generation Compute Unit," still stuck to that layout (page 9). RDNA may be divorced from GCN but it also may not be.
Posted on Reply
#191
bug
FordGT90Concept said:

All we know from driver is that it's a new compute unit (GFX10). Until AMD gives more information, we don't know how significant the changes are. GCN has a fairly rigid architectural layout which Vega, despite being called "Next-Generation Compute Unit," it still stuck to that layout. RDNA may be divorced from GCN but it also may not be.
You're right of course. The mixing of architectures is nothing but a rumor at this point.
Posted on Reply
#192
londiste
FordGT90Concept said:
All ISAs have a measure of abstraction because of the necessity to preserve backwards compatibility of high level calls.
The lines between what is an ISA and API are more and more difficult to draw, there is a lot of grey area here. ISA is architecture, the big picture, what the building blocks of a chip (GPU in this case) are designed for, instructions and whatnot. Underneath it is microarchitecture that implements the ISA/architecture and while the problems it solves are defined by ISA, implementation may differ completely. On the other side of things ISA is used to implement APIs.

Again, there are grey areas all around it but at a high level:
- From what we know AMD's GCN is a fairly by-the-book ISA on GCN cards. Not completely so but generally this is the case.
- Nvidia has been deliberately unclear about what their actual hardware ISA looks like for every generation. It is exposed almost exclusively via PTX that is effectively the ISA for Nvidia cards but not what the hardware itself does as PTX is a VM layer above hardware. I am sure there are drawbacks to this approach, more complex software/driver development being the obvious one.
Posted on Reply
#193
bug
londiste said:

The lines between what is an ISA and API are more and more difficult to draw, there is a lot of grey area here.
Quite the opposite, actually: https://en.wikipedia.org/wiki/Instruction_set_architecture
An instruction set architecture (ISA) is an abstract model of a computer. It is also referred to as architecture or computer architecture. A realization of an ISA is called an implementation.
In the GPU world, you can't do radical change of the silicon (implementation) while keeping the same instruction set. You can't use the hardware judiciously if you do that.
That hold mostly true for CPUs as well. x86 has been done to death and beyond, but ever since the inclusion of the FPU onto the CPU, CPUs have advanced not by revolutionizing the x86 implementation*, but by implementing complementary instruction sets: x87, MMX, SSE, AVX in their various incarnations.

*doesn't mean the x86 implementation hasn't been refined in the meantime, just that it wasn't the only advancement vector anymore
Posted on Reply
#194
medi01
FordGT90Concept said:

As pointed out, I think NVIDIA and AMD treat their ISAs differently. AMD names ISAs by literally the instructions it supports where NVIDIA never discloses the machine ISA and instead runs everything through a virtual machine that accepts PTX. AMD uses their drivers to smooth over compatibility problems between ISAs not unlike NVIDIA does with PTX. I think one of the reasons why the open source community has problems with NVIDIA is because they never disclose the actual machine code the GPUs support; they only provide documentation on PTX which requires a good driver (which open source developers can't create) in order to function as designed. Open source is at NVIDIA's mercy and they don't really care outside of AI/compute products.
Don't even CPUs have, cough, "micro code"?
Posted on Reply
#195
FordGT90Concept
"I go fast!1!11!1!"
Yup, instructions are decoded into ALU/FPU/SIMD operation codes which are executed. The vast majority of them are not directly accessible nor would you want to because they would be like throwing wrenches in the processor.
Posted on Reply
#196
londiste
That is the definition of architecture vs microarchitecture. Architecture (and ISA) is x86 while microarchitecture (implementation) varies.
Posted on Reply
#197
medi01
What are the reasons to believe AMD executes GCN instructions directly, instead of decoding them into micro-arch specific "opcodes", like nVidia, Intel and, hold on, AMD itself with AMD CPUs?

And if they don't, how on earth does one know what micro-arch is used by AMD?
Posted on Reply
#198
londiste
medi01 said:
What are the reasons to believe AMD executes GCN instructions directly, instead of decoding them into micro-arch specific "opcodes", like nVidia, Intel and, hold on, AMD itself with AMD CPUs?
And if they don't, how on earth does one know what micro-arch is used by AMD?
AMD is being rather stingy on architectural details, even more so than Nvidia. The consensus is though that ISA used on AMD GPUs is GCN (or variation of it) being called directly enough in the hardware.

Both architecture/microarchitecture and ISA/implementation are hardware things. Above that are varying layers of APIs, usually in software, sometimes in firmware. The reason this whole thing was brought up was your claim that CUDA is Nvidia's ISA which is patently incorrect. CUDA is an API (and a specialized one at that), PTX is still an API but a lower level one and while Nvidia is not being too clear about it PTX seems to be brought to life to hide ISA changes between GPU generations. Nvidia has never been forthcoming about what the ISA for their GPUs really is.
Posted on Reply
#199
medi01
londiste said:

AMD is being rather stingy on architectural details, even more so than Nvidia.
londiste said:

The consensus is though that ISA used on AMD GPUs is GCN
The jump from micro-arch to ISA in a comment to a post literally citing AMD rep clarifying that those are 2 different things is mind boggling.

londiste said:

PTX is still an API
[MEDIA=giphy]UvwI1X7XkbXq0[/MEDIA]
Posted on Reply
#200
londiste
medi01 said:
The jump from micro-arch to ISA in a comment to a post literally citing AMD rep clarifying that those are 2 different things is mind boggling.
What are you talking about?

GCN is architecture, ISA. Microarchitecture is its implementation.

Well, you can call PTX an ISA if you want. Nvidia halfway does. It is worth noting though that PTX is a virtual machine with a defined ISA (read: software). How this is mapped into actual GPU hardware is not well known (and Nvidia does not say). There is enough evidence to say the ISA underneath PTX is different between GPU generations. Nvidia drivers contain a compiler that compiles PTX code into binary code.
Posted on Reply
Add your own comment