Monday, June 15th 2020
AMD "Navi 12" Silicon Powering the Radeon Pro 5600M Rendered
Out of the blue, AMD announced its Radeon Pro 5600M mobile discrete graphics solution exclusive for Apple's 16-inch MacBook Pro. It turns out that the Pro 5600M is based on an all new ASIC by AMD, codenamed "Navi 12." This is a multi-chip module, much like "Vega 20," featuring a 7 nm GPU die and two 16 Gbit (4 GB) HBM2 memory stacks sitting on an interposer. While the actual specs of the GPU die on the "Navi 14" aren't known, on the Pro 5600M, it is configured with 40 RDNA compute units amounting to 2,560 stream processors, 160 TMUs, and possibly 64 ROPs.
The engine clock of the Pro 5600M is set at up to 1035 MHz. The HBM2 memory is clocked at 1.54 Gbps, which at the 2048-bit bus width, translates to 394 GB/s of memory bandwidth. There are two big takeaways from this expensive-looking ASIC design: a significantly smaller PCB footprint compared to a "Navi 10" ASIC with its eight GDDR6 memory chips; and a significantly lower power envelope. AMD rates the typical power at just 50 W. In the render below, the new ASIC is shown next to a "Navi 14" ASIC that power RX/Pro 5500-series SKUs.
The engine clock of the Pro 5600M is set at up to 1035 MHz. The HBM2 memory is clocked at 1.54 Gbps, which at the 2048-bit bus width, translates to 394 GB/s of memory bandwidth. There are two big takeaways from this expensive-looking ASIC design: a significantly smaller PCB footprint compared to a "Navi 10" ASIC with its eight GDDR6 memory chips; and a significantly lower power envelope. AMD rates the typical power at just 50 W. In the render below, the new ASIC is shown next to a "Navi 14" ASIC that power RX/Pro 5500-series SKUs.
42 Comments on AMD "Navi 12" Silicon Powering the Radeon Pro 5600M Rendered
And yes, TDP mostly equals power consumption.
I didn't say anything about this specific apple GPU, I just said AMD has no efficiency advantage.
And if 2060 is consuming less power than why the ASUS one has more power consumption??
You are straight up wrong.
As gamersnexus described it, it's a made up number used to beat down forum users over which processor has the lower TDP when in reality it isn't isn't supposed to represent power consumption, let alone being accurate at what it is supposed to indicate (thermal power dissipation).
Laptop 15W TDP ranges from 10W to about 45W depending on vendor and configuration.
GPU TDP is actually more closely constrained by AMD and Nvidia, simply because their entire product is a single board and as such they have far more control over the power delivery than AMD or Intel do with CPUs that rely on third-party motherboard manufacturers to handle.
In addition, it is very difficult to have an apple to apple comparison of performance between laptops. This is because the specs, cooling solution and the BIOS configurations differs widely. Even if we can get one with more or less exact specs, the cooling solution and laptop configurations will largely determine the performance of the laptop. Unlike on a desktop where you can afford huge cooling solution, the cooling solutions in laptops are really bare minimal. So if one is to cut cost and scrimp on the cooling solution, this may result in a hotter and/or slower performance. In terms of the laptop configuration, it depends on how aggressive the laptop maker wants to be by allowing a longer boost, higher power, higher temps, etc. All these are preset in the BIOS which we have no/ limited access to in laptops.
CPU situation is different.
The GPU in question here is the Navi 12-based Radeon Pro 5600M (with HBM2).
The GPU in your video is the Navi 10-based Radeon RX 5600M (with GDDR6).
Yes, this naming is confusing in its similarity, but they are differen product lines (RX is mainstream consumer/gaming, Pro is productivity/workstation), so the similar naming just indicates similar performance/product stack positioning.
If this was used by anyone other than Apple I would expect a higher clocked version named RX 5700M or some such. Yes. Considering that AMD just sent out a press release saying this in clear text, yes, that is exactly what is happening.
I have to say, I would love for them to make this into a premium SFF desktop GPU ... push it to 75W, stick it on a 2-slot HHHL card, wow, it would knock the socks off anything else available in that form factor. The price would obviously be high, but there are quite a few SFF enthusiasts out there willing to pay that premium.
Agree with you on the premium SFF GPU. I intentionally paid extra for a 5700XT and other than a brief excercise in seeing what it was capable of, have never run it at speeds that would even beat a stock 5700. My daily-driver undervolt barely spins the fans beyond their minimum rpm and in benchmarks I'm giving up about 15% of the stock performance.
Yes, it's not great performance/$, but I'm happy to pay the premium for performance/Watt because although I don't care about electricity costs, I do care about it being damn-near silent.
I'm just imagining a ... let's call it RX 5700 Nano - why not? It would sure be a worthy successor to the near-legendary R9 Nano - at 75W, two slot HHHL form factor, probably ~1300MHz or possibly a bit more (given that this does 1035 at 50W). That would absolutely destroy the current highest performance HHHL GPU, the GTX 1650. They could even make it a harvested die with a couple of CUs cut off, letting Apple run off with the best chips. It could still deliver ~1660 Ti performance unless the frequency scaling falls off a cliff at low clocks (considering how low the MBP version is clocked, there should be plenty of headroom without getting notably inefficient). It might not be the highest volume product ever - not by any means given the premium pricing something like this would demand - but it would be the darling of the SFF crowd for years to come.