Monday, March 16th 2020

Complete Hardware Specs Sheet of Xbox Series X Revealed

Microsoft just put out of the complete hardware specs-sheet of its next-generation Xbox Series X entertainment system. The list of hardware can go toe to toe with any modern gaming desktop, and even at its production scale, we're not sure if Microsoft can break-even at around $500, possibly counting on game and DLC sales to recover some of the costs and turn a profit. To begin with the semi-custom SoC at the heart of the beast, Microsoft partnered with AMD to deploy its current-generation "Zen 2" x86-64 CPU cores. Microsoft confirmed that the SoC will be built on the 7 nm "enhanced" process (very likely TSMC N7P). Its die-size is 360.45 mm².

The chip packs 8 "Zen 2" cores, with SMT enabling 16 logical processors, a humongous step up from the 8-core "Jaguar enhanced" CPU driving the Xbox One X. CPU clock speeds are somewhat vague. It points to 3.80 GHz nominal and 3.66 GHz with SMT enabled. Perhaps the console can toggle SMT somehow (possibly depending on whether a game requests it). There's no word on the CPU's cache sizes.
The graphics processor is another key component of the SoC given its lofty design goal of being able to game at 4K UHD with real-time ray-tracing. This GPU is based on AMD's upcoming RDNA2 graphics architecture, which is a step up from "Navi" (RDNA), in featuring real-time ray-tracing hardware optimized for DXR 1.1 and support for variable-rate shading (VRS). The GPU features 52 compute units (3,328 stream processors provided each CU has 64 stream processors in RDNA2). The GPU ticks at an engine clock speed of up to 1825 MHz, and has a peak compute throughput of 12 TFLOPs (not counting CPU). The display engine supports resolutions of up to 8K, even though the console's own performance targets at 4K at 60 frames per second, and up to 120 FPS. Variable refresh-rate is supported.

The memory subsystem is similar to what we reported earlier today - a 320-bit GDDR6 memory interface holding 16 GB of memory (mixed chip densities). It's becoming clear that Microsoft isn't implementing a hUMA common memory pool approach. 10 GB of the 16 GB runs at 560 GB/s bandwidth, while 6 GB of it runs at 336 GB/s. Storage is another area that's receiving big hardware uplifts: the Xbox Series X features a 1 TB NVMe SSD with 2400 MB/s peak sequential transfer rate, and an option for an additional 1 TB NVMe storage through an expansion module. External storage devices are supported, too, over 10 Gbps USB 3.2 gen 2. The console is confirmed to feature a Blu-ray drive that supports 4K UHD Blu-ray playback. All these hardware specs combine toward what Microsoft calls the "Xbox Velocity Architecture." Microsoft is also working toward improving the input latency of its game controllers.
Add your own comment

128 Comments on Complete Hardware Specs Sheet of Xbox Series X Revealed

#101
notb
Valantar
I have no doubt this will still be a good console, but that is a significant disadvantage for sure.
Well, maybe at least they'll keep a familiar, TV-table friendly form factor. There's always time to launch a locked mITX desktop.
Posted on Reply
#102
Rahnak
gamefoo21
I'm really not thrilled that both consoles have killed user replacement/upgrades on the flash, and that stuff wears out.
You can expand storage on both consoles. And it wears out? SSD durability easily outlast a console generation. Or two. Or three.
Posted on Reply
#103
Valantar
notb
Well, maybe at least they'll keep a familiar, TV-table friendly form factor. There's always time to launch a locked mITX desktop.
Sorry, a "locked mITX desktop"? As in a "build-your-own console"? I don't quite see what you're saying here, but if I'm right in that being what you meant, that is never, ever going to happen.
gamefoo21
I think they are banking on how well the PS4 Pro has done vs the One X.

It's decently slower and can't play 4K blurays.
While MS sadly stopped publishing sales numbers long before the XOX, it seems the sales deficit for it compared to the PS4 hasn't been even remotely as big as the OG XB1 vs. PS4 (they have hinted at near parity IIRC) - which is a significant achievement for a mid-generation spec bump with a 2-3:1 platform adoption deficit. This launch will be very interesting for sure - Sony obviously still has the mindshare advantage, but that might not be enough. Marketing and presentation (plus pricing, obviously) will be key going forward.
Posted on Reply
#104
notb
Valantar
Sorry, a "locked mITX desktop"? As in a "build-your-own console"? I don't quite see what you're saying here, but if I'm right in that being what you meant, that is never, ever going to happen.
As in Xbox Series X which is a custom SFF PC with locked OS.
So we should compare it to custom SFF PCs. And guess what: AsRock DeskMini GTX/RX is less than half the size. :)

Don't take me wrong. The Xbox looks very promising. If they called it "Surface Desktop" and shipped with Windows, this might have been the first time since Diablo2 that I preorder anything.
And I may still buy it for gaming when prices go down.
Posted on Reply
#105
Vayra86
I've got my popcorn out and I'm eagerly awaiting what the new content will look like. Specs are nice but content is where its at, but its not Microsoft's strong suit. Same goes for RT.

But hardware wise... this is fantastic and it will mean a serious boost is on its way for PC graphics too. A new mainstream norm is what they're obviously shooting for, and that norm has 4K in it. I'm not complaining. The baby steps are finally over, its about god damn time. After all on the PC resolution is just one of the many choices to spend resources on.

RDNA2 though. Shit. 2.23 Ghz on the PS5 and here we have a wide GPU doing 1.8. That is good and it will mean these things finally boost and clock proper, capable of doing a wide range. It will be very interesting what Nvidia is going to pull out of the hat now, and its clear they need make a big dent, even despite the Turing headstart. I mean, I'm still not really counting the ridiculous product called 2080ti as a viable thing, and considering that, they've got work to do. Very glad to see AMD return to proper high end, and not trailing a gen or two.

gamefoo21
I think they are banking on how well the PS4 Pro has done vs the One X.

It's decently slower and can't play 4K blurays.

If anything the Sony engineers are probably trying to overclock the memory. I'm also a little surprised that they aren't going for 3.6ghz on the 8cores instead they are giving it a 3.5ghz max boost... Not set, but 'variable'...

Water cooling your console for stable performance... :laugh:

The lack of memory bandwidth is going to hammer the PS5 at 4K. I suspect it'll be 1440p with 'image enhancements' console.

Then there's the storage system... It's going to drink power and it's going to be hot.

I'm really not thrilled that both consoles have killed user replacement/upgrades on the flash, and that stuff wears out.

The PS5 is definitely shaping up to be a cheaper console to build so it's likely going to undercut the Series X by $100 USD at least. IMHO
A lot of random thoughts... its all going to hammer and do this and that but you really don't know or can't say. And neither do we :)
The spec war however is just not interesting. When in doubt, watch the relevant South Park episode. What really matters is what the majority will do, and that focuses exclusively on the content that the majority can play.
Posted on Reply
#106
notb
Vayra86
It will be very interesting what Nvidia is going to pull out of the hat now, and its clear they need make a big dent, even despite the Turing headstart.
Well, obviously, a 7nm GPU, so the efficiency and performance crown will stay with them. AMD will go back to being the "value" option.

Also, these consoles will hopefully provoke an explosion of RTRT games - something Nvidia is already prepared for, while AMD and Intel merely mentioned working on.

So yeah... not much changes in the balance of power.
But we're likely looking at huge jump in game requirements for games ported from consoles - including a possibility of games that won't run (or won't be playable) without RTRT acceleration...

As for the Xbox - I'm really interested if the non-gaming features will be developed further. If yes, this could be an easy buy.
Posted on Reply
#107
gamefoo21
Vayra86
I've got my popcorn out and I'm eagerly awaiting what the new content will look like. Specs are nice but content is where its at, but its not Microsoft's strong suit. Same goes for RT.

But hardware wise... this is fantastic and it will mean a serious boost is on its way for PC graphics too. A new mainstream norm is what they're obviously shooting for, and that norm has 4K in it. I'm not complaining. The baby steps are finally over, its about god damn time. After all on the PC resolution is just one of the many choices to spend resources on.

RDNA2 though. Shit. 2.23 Ghz on the PS5 and here we have a wide GPU doing 1.8. That is good and it will mean these things finally boost and clock proper, capable of doing a wide range. It will be very interesting what Nvidia is going to pull out of the hat now, and its clear they need make a big dent, even despite the Turing headstart. I mean, I'm still not really counting the ridiculous product called 2080ti as a viable thing, and considering that, they've got work to do. Very glad to see AMD return to proper high end, and not trailing a gen or two.



A lot of random thoughts... its all going to hammer and do this and that but you really don't know or can't say. And neither do we :)
The spec war however is just not interesting. When in doubt, watch the relevant South Park episode. What really matters is what the majority will do, and that focuses exclusively on the content that the majority can play.
That's true, but the PS4 Pro can't do real 4K.

The PS5 GPU is shaping up to be a lot like the 5700XT.

Memory bandwidth is very important at 4K60.

It'll be interesting either way to see what shakes out between these two.

Rahnak
You can expand storage on both consoles. And it wears out? SSD durability easily outlast a console generation. Or two. Or three.
NAND reliability drops like a rock if it's too hot. Not to mention type of NAND, there's also components related to the storage that can very easily die.

If the drive on the board dies, will Sony let the PS5 boot off the USB drive? MS might let you boot off the second drive but I really doubt it.

I guess I am just not a fan of an Apple approach to hardware. If the SSD fails, new MacBook for you! Or at least a motherboard.

Forgive me while I still have my Xbox, 360, PS2, SNES, etc... Sorry if I insult your sensibilities when I buy a console not to puke it's guts out in 5 to 7 years.

Consumerism is a shitty excuse to drive corporate profits.

I really hope right to repair sneaks past the big money trying to stop it.
Posted on Reply
#108
Rahnak
gamefoo21
NAND reliability drops like a rock if it's too hot. Not to mention type of NAND, there's also components related to the storage that can very easily die.

If the drive on the board dies, will Sony let the PS5 boot off the USB drive? MS might let you boot off the second drive but I really doubt it.

I guess I am just not a fan of an Apple approach to hardware. If the SSD fails, new MacBook for you! Or at least a motherboard.

Forgive me while I still have my Xbox, 360, PS2, SNES, etc... Sorry if I insult your sensibilities when I buy a console not to puke it's guts out in 5 to 7 years.

Consumerism is a shitty excuse to drive corporate profits.

I really hope right to repair sneaks past the big money trying to stop it.
If something dies on any of those consoles you mentioned, they're just as equally dead. Newer ones just have more points of failure, as it happens with any newer technology. I'm sure they've taken all your reliability concerns into account for you. Sony wants their consoles to last more than you do, I can guarantee you. And if they fail at it, it's a repeat of the 360, wouldn't be something new and Sony would pay the price for it.
Posted on Reply
#109
Super XP
gamefoo21
Seems people don't understand that AMD CPUs and GPUs drive both the Xbox One and PS4 already.
I thought of that too, maybe they really don't know that.

gamefoo21
That's true, but the PS4 Pro can't do real 4K.

The PS5 GPU is shaping up to be a lot like the 5700XT.
Speculation aside, the PS5 might end up being faster than the Xbox Series X, far more efficient and much faster over the 5700XT.
Posted on Reply
#110
Rahnak
Super XP
Speculation aside, the PS5 might end up being faster than the Xbox Series X, far more efficient and much faster over the 5700XT.
My guess (and I could be way off) is that XSX will have the advantage in pretty much all multi-platform games, because it does have more raw power and the upgrades seem more straightforward from current gen. That said, I do think the PS5's top exclusives, like GoW2 and Naughty Dog's next IP, will be better than anything on XSX because they just go the extra mile on getting that last drop of performance.
Posted on Reply
#111
Super XP
Rahnak
My guess (and I could be way off) is that XSX will have the advantage in pretty much all multi-platform games, because it does have more raw power and the upgrades seem more straightforward from current gen. That said, I do think the PS5's top exclusives, like GoW2 and Naughty Dog's next IP, will be better than anything on XSX because they just go the extra mile on getting that last drop of performance.
Well that makes sense. Microsoft plays up the performance advantage while Sony has the top exclusives to help drive unit sales. I'm not really into consoles myself, but realistically I am hoping both sell very well and share even market share, all for the sake of competition. Wishful thinking though lol
Posted on Reply
#112
mechtech
HwGeek
I hope MS wil let us use Win10 on it, so we could play or use it as a PC["Desktop Console" ].
I will buy it at first day if so.
lol if it ends up you can, I think PC sales would plummet.
Posted on Reply
#113
AnarchoPrimitiv
notb
Well, obviously, a 7nm GPU, so the efficiency and performance crown will stay with them. AMD will go back to being the "value" option.

Also, these consoles will hopefully provoke an explosion of RTRT games - something Nvidia is already prepared for, while AMD and Intel merely mentioned working on.

So yeah... not much changes in the balance of power.
But we're likely looking at huge jump in game requirements for games ported from consoles - including a possibility of games that won't run (or won't be playable) without RTRT acceleration...

As for the Xbox - I'm really interested if the non-gaming features will be developed further. If yes, this could be an easy buy.
Your allegiance is obvious
Posted on Reply
#114
notb
AnarchoPrimitiv
Your allegiance is obvious
Liberal democrat?
Posted on Reply
#115
Valantar
notb
Well, obviously, a 7nm GPU, so the efficiency and performance crown will stay with them. AMD will go back to being the "value" option.

Also, these consoles will hopefully provoke an explosion of RTRT games - something Nvidia is already prepared for, while AMD and Intel merely mentioned working on.

So yeah... not much changes in the balance of power.
But we're likely looking at huge jump in game requirements for games ported from consoles - including a possibility of games that won't run (or won't be playable) without RTRT acceleration...

As for the Xbox - I'm really interested if the non-gaming features will be developed further. If yes, this could be an easy buy.
You're right that a 7nm Nvidia GPU is likely to have significant efficiency gains from their current 12nm ones. However AMD is nearly on par in efficiency (total, not architectural, and depending on how far the chip is pushed) with the current gen, and they're promising a significant increase with the upcoming cards despite no node change, something that's corroborated by the upcoming consoles (more than 250W power consumption for a console (even one as large as the XSX) is highly unlikely, and the CPU, SSD and so on consume at least some of that - let's say 50W, which would make that a crazy efficient 8c16t CPU - so the GPU must then be below 200W while delivering ~35% higher FLOPS than the 5700XT and RT). I still think Nvidia is likely to have the upper hand if their upcoming GPUs are on TSMC 7nm (there are rumors of consumer GPUs being Samsung 10nm or 8nm, which would be a smaller change from TSMC 12nm), but it won't be huge.

MS also showed the GoW 5 in-game benchmark in a build "updated" to run on XSX by a single engineer over two weeks (i.e. not optimized whatsoever) matching the performance of the same game with the same settings (PC Ultra IIRC) on a PC with a 2080. Which is a 215-225W GPU. The GoW 5 PC port is also generally regarded as being a very good port that performs very well and scales well with powerful PC hardware.

Beyond that, saying AMD "merely mentioned working on" RT - days after two consoles based on their hardware being announced with full RT support performant enough to run an early/unoptimized build of fully path traced Minecraft - is a serious stretch no matter if their PC GPUs have yet to be announced. While the details of AMD's implementation are scarce, we know it is bound to shader count and will thus scale up with bigger GPUs too.

I still expect Nvidia to have a small performance advantage with Ampere, but it doesn't look likely to be anything more than small, and given the proliferation of new features in the new consoles based on AMD hardware it's not all that likely that Nvidia will maintain an advantage in use/performance of new features simply due to the dominant implementation and development model being AMD-based (even if this ultimately falls back to open APIs like DXR).

As for non-gaming uses, I don't think that will happen. Consoles are not meant for general purpose use, and part of why MS lost the previous generation so badly was due to not focusing on gaming but too much on other features. They're obviously not making that mistake this time around.
Posted on Reply
#116
John Naylor
The Quim Reaper
10Gb of fast RAM, 6Gb of slow RAM...

The Nvidia 970 designers are smiling.
They never stopped... that single card oust sold all 26 AMD cards combined for it's generation by a factor > 2.

We see this "is gonna" discussion with every new CPU release and ever new GPU release ... and when you go back to read the "is gonna" predictions, they never quite live up to the early billing. Save the enthusiasm for post release testing.
Posted on Reply
#117
agentnathan009
ppn
560GBs 10GB gpu optimal memory, only problem is the cpu will eat alot of that 10GB-5,5=4,5GB, 560-336=224, so the GPU is left with 4,5GB at 224GBs.

How about NO, and gives us HBM2E 32GB 1TBs, 5nm maxed to 420mm2 GPU only, and separate 60mm2 8 core ZEN3 with separate DDR5 24GB, or forget about it.
They let just any fanboy in here don't they... Clearly you have no clue how much all of that premium would cost... Furthermore, if you used your brain, you would have grasped the elusive concept that consoles, Playstation included, don't use full PC Operating Systems and so they don't have all the other tasks, etc. running in the background and therefore don't need as much memory to function as well as a PC. The Series X has 16GB of memory, and possibly subdivided so GPU gets dedicated and CPU gets dedicated amount to play with. 8-10GB is more than enough for GPU with Ray tracing for a console. 6GB is enough for the rest of the system for everything else that it processes such as audio, AI characters, physics, etc.
Posted on Reply
#118
Valantar
ppn
560GBs 10GB gpu optimal memory, only problem is the cpu will eat alot of that 10GB-5,5=4,5GB, 560-336=224, so the GPU is left with 4,5GB at 224GBs.

How about NO, and gives us HBM2E 32GB 1TBs, 5nm maxed to 420mm2 GPU only, and separate 60mm2 8 core ZEN3 with separate DDR5 24GB, or forget about it.
Did you miss the part where they explained that the CPU has memory separate from the 10GB GPU pool? 16GB total, 2,5GB reserved for OS etc., 10GB prioritizing the GPU, with the rest for the CPU's gaming needs. While the CPU and GPU might share some RAM, the GPU will be the main consumer of memory in high resolution gaming, so the GPU being bandwidth starved. Most game data not related to graphics is rather space efficient, after all.
Posted on Reply
#119
rvalencia
Valantar
Yes? None of that is a general GPU shader workload (even if they all can be performed (much slower) on shader cores). Just like a video decode block can decode video as fast as (or even faster than) a high-end CPU doesn't mean that power is translatable back to general CPU tasks - quite the opposite. All you're saying is "RT hardware can perform RT workloads", which ... well, one would certainly hope so. Saying the XSX has 25TF of compute power is flat out false. Saying it has the equivalent of 25 TF of compute power if RT workloads is counted as if they were done on shader cores is true. Those two statements are very clearly not the same.
RT cores have assimilated certain workloads that were done on shaders e.g. Volta's DXR.

RT core is a specialized compute unit optimized for certain workload types and "shaders" are specialized compute units optimized for raster graphics workloads.
RDNA 2 and Turing effectively returns to DX9 style non-unified shader compute units.

gamefoo21
The specs are out and they show differences in design and the likely impact of performance.

The PS5 is likely going to be slower, but it's going to have the faster NVME drive, but it'll be more energy efficient.

That's ironically not exactly true but not wrong about AMD and it's history. The One X GPU was definitely bigger and badder than anything Polaris but smaller than Vega. Even the new GPU is definitely bigger and badder than Navi but what's interesting is that it's not just a tuned up Vega 44 like last time, it's very likely RDNA 2, which is smaller than Arcturus, which will likely get pulled into the consumer market like Vega 10 and 20. Soo...

Back on topic...

PS5 GPU: 36CUs, up to 2.26Ghz, up to 10.28TFLOPS, 256bit gddr6 memory

XsX GPU: 52CUs, 1.82Ghz, 12TFLOPS, 320bit gddr6 memory

That's quite a bit of variablity for a single manufacturer.
In 2013, AMD used to provide multiple SKU levels up to high-end GPU for the PC market while providing GPUs for MS and Sony. Server bias Bulldozer era financial problems and focus on TFLOPS bias server GPUs without scaling raster hardware have caused brain drain on AMD's RTG. Reminder for RTG, GPUs are not DSPs.

Super XP
I thought of that too, maybe they really don't know that.

Speculation aside, the PS5 might end up being faster than the Xbox Series X, far more efficient and much faster over the 5700XT.
RDNA 2 36 CU at 2230 Mhz vs RDNA 2 52 CU at 1825Mhz is like comparing RTX 2070 with 36 CU equivalent at 2230 Mhz OC (10.28 TFLOPS) with 448 GB/s BW against MSI RTX 2080 Super Gaming X Trio with 12.15 TFLOPS with 496 GB/s BW.

RTX 2070 at 2230 Mhz wouldn't beat MSI RTX 2080 Super Gaming X Trio.

RDNA 2 is not GCN i.e. RDNA (aka NAVI) is designed with scalability. Read AMD's road map.

Posted on Reply
#120
Valantar
rvalencia
RT cores have assimilated certain workloads that were done on shaders e.g. Volta's DXR.

RT core is a specialized compute unit optimized for certain workload types and "shaders" are specialized compute units optimized for raster graphics workloads.
RDNA 2 and Turing effectively returns to DX9 style non-unified shader compute units.
Again: yes, and? None of this means that an RT core (or AMD's equivalent, which seems to be rather different from Nvidia's and more integrated into the regular CU) can perform regular FP32 operations, which would be a requirement for saying the GPU has 25TFlops. So, saying that is wrong. Period. Again: it has the equivalent of 25TFlops if RT operations are counted as if they were executed on a non-RT GPU. If you aren't doing that specific thing, it has 12TFlops.

As for saying GPU shaders are specialized compute units ... well, sure, they're specialized for FP32 (and formerly FP64, lately also FP16 and INT8/INT4) units, but FP32 operations are a quite general class of computation with uses far beyond graphics. RT operations are definitely more specialized than this. As such it's entirely accurate to call one a form of general purpose compute and one specialized hardware.
Posted on Reply
#121
rvalencia
Valantar
Again: yes, and? None of this means that an RT core (or AMD's equivalent, which seems to be rather different from Nvidia's and more integrated into the regular CU) can perform regular FP32 operations, which would be a requirement for saying the GPU has 25TFlops. So, saying that is wrong. Period. Again: it has the equivalent of 25TFlops if RT operations are counted as if they were executed on a non-RT GPU. If you aren't doing that specific thing, it has 12TFlops.

As for saying GPU shaders are specialized compute units ... well, sure, they're specialized for FP32 (and formerly FP64, lately also FP16 and INT8/INT4) units, but FP32 operations are a quite general class of computation with uses far beyond graphics. RT operations are definitely more specialized than this. As such it's entirely accurate to call one a form of general purpose compute and one specialized hardware.
FYI, NVIDIA's' RT unit is inside SM unit level which is equivalent to AMD's CU.

RT core is less specialized when compared to T&L/TFU (texture filter unit) /ROPS hardware since RT can accelerate non-graphics workloads such as audio and physics logic collision. BVH search tree and collision hardware have a wider application when compared to T&L hardware.

Modern ROPS has re-order layers via ROV (Rasterizer Order Views) feature instead of wasting compute shader resource.
Posted on Reply
#122
Super XP
rvalencia
RT cores have assimilated certain workloads that were done on shaders e.g. Volta's DXR.

RT core is a specialized compute unit optimized for certain workload types and "shaders" are specialized compute units optimized for raster graphics workloads.
RDNA 2 and Turing effectively returns to DX9 style non-unified shader compute units.


In 2013, AMD used to provide multiple SKU levels up to high-end GPU for the PC market while providing GPUs for MS and Sony. Server bias Bulldozer era financial problems and focus on TFLOPS bias server GPUs without scaling raster hardware have caused brain drain on AMD's RTG. Reminder for RTG, GPUs are not DSPs.


RDNA 2 36 CU at 2230 Mhz vs RDNA 2 52 CU at 1825Mhz is like comparing RTX 2070 with 36 CU equivalent at 2230 Mhz OC (10.28 TFLOPS) with 448 GB/s BW against MSI RTX 2080 Super Gaming X Trio with 12.15 TFLOPS with 496 GB/s BW.

RTX 2070 at 2230 Mhz wouldn't beat MSI RTX 2080 Super Gaming X Trio.

RDNA 2 is not GCN i.e. RDNA (aka NAVI) is designed with scalability. Read AMD's road map.


Already have read AMD info on all there products. RDNA2 is a new uArch.

Both Console chips are highly customized. Customized RDNA2 and ZEN2 with everything else.
Posted on Reply
#123
Valantar
rvalencia
FYI, NVIDIA's' RT unit is inside SM unit level which is equivalent to AMD's CU.

RT core is less specialized when compared to T&L/TFU (texture filter unit) /ROPS hardware since RT can accelerate non-graphics workloads such as audio and physics logic collision. BVH search tree and collision hardware have a wider application when compared to T&L hardware.

Modern ROPS has re-order layers via ROV (Rasterizer Order Views) feature instead of wasting compute shader resource.
...still can't do general FP32 compute. Please stop splitting hairs over this. That RT performance can be translated into an equivalent of FP32 performance if RT is done purely in shaders does not mean this conversion can be reversed and RT performance can be added to the total TFlops.
Posted on Reply
#124
Valantar
rvalencia

Meanwhile at NVIDIA camp... with Turing. NVIDIA PR just road-killed your argument.

You're an AMD fanboy. eat it.
Lolwut? Here I am arguing against blindly adding together various converted numbers into a meaningless total that won't be comparable to anything, and which overstates the general compute performance of a part, and that makes me an AMD fanboy? Put more simply, you say it has 25TF, I say no, it has 12TF but can be seen as having the equivalent of 25TF if calculated a specific way, and that makes me an AMD fanboy? Seriously? Saying it has 25TF is far more positive for AMD, ffs. Which is what I am saying is a stupid thing to do.

Conversions like this is like saying an F1 car is 10 times the car a Honda Civic is because its 10 times faster, which ignores that the Civic can do a lot more than go fast - it can seat several people, take you grocery shopping, etc. FP32 is general purpose compute. RT cores do not do general purpose compute. Nor do tensor cores or any other specialized hardware. If Nvidia is copying a particularly stupid and easily misunderstood marketing point from AMD, that does not in any way make it less stupid or easily misunderstood.

Also, reported. Thanks for keeping the discussion civil, dude.
Posted on Reply
#125
rvalencia
Valantar
Lolwut? Here I am arguing against blindly adding together various converted numbers into a meaningless total that won't be comparable to anything, and which overstates the general compute performance of a part, and that makes me an AMD fanboy? Put more simply, you say it has 25TF, I say no, it has 12TF but can be seen as having the equivalent of 25TF if calculated a specific way, and that makes me an AMD fanboy? Seriously? Saying it has 25TF is far more positive for AMD, ffs. Which is what I am saying is a stupid thing to do.

Conversions like this is like saying an F1 car is 10 times the car a Honda Civic is because its 10 times faster, which ignores that the Civic can do a lot more than go fast - it can seat several people, take you grocery shopping, etc. FP32 is general purpose compute. RT cores do not do general purpose compute. Nor do tensor cores or any other specialized hardware. If Nvidia is copying a particularly stupid and easily misunderstood marketing point from AMD, that does not in any way make it less stupid or easily misunderstood.

Also, reported. Thanks for keeping the discussion civil, dude.
You can't handle the truth when you censor a debate when you can't win.


Meanwhile, NVIDIA PR throws in RT cores' TFLOPS into marketing.

Expect AMD PR to weaponize RT cores TFLOPS when "Big Navi" arrives.

Why debate about FP32 general-purpose shader compute (not generalize like SSE) when future game titles have significant RT workloads?
Current shaders accelerate Z-buffer accelerated structures while RT cores accelerate BVH accelerated structures.
Posted on Reply
Add your own comment