By using this site, you agree to our Privacy Policy and our Terms of Use. Close

Forums - Nintendo Discussion - Rumor: Nintendo Switch Dev Kit Specs

Random_Matt on 20 October 2016

Some random guy on a forum, i'll wait for DF.



Around the Network
teigaga on 20 October 2016
Soundwave said:
540p on a TV is unacceptable, the dock better be able to bump that to 720p at least. 540p is OK for portable play.

I presume this isn't referring to Native NX games but imaging straight PS4 ports. 



HoloDust on 20 October 2016

Those are, more or less, nVidia Shield TV specs - 256/16/16 config (shaders/TMUs/ROPs) running at 1GHz (so 512GFLOPS for FLOPS folks).

For comparison, benched with GFXBench, GPU similar to PS4's is outperforming Shield TV by 3-4x.

Shield TV is consuming 20W in gaming and it's built on 20nm node.



Sh1nn on 20 October 2016
Random_Matt said:
Some random guy on a forum, i'll wait for DF.

 

NWPlayer123 is a well known homebrew and exploit creator for NIntendo consoles. She's legit.

And Zlatan is a game developer.



numberwang on 20 October 2016

So WiiU Zelda is the definitive version?



Around the Network
Jizz_Beard_thePirate on 20 October 2016
WC4Life said:
Captain_Yuri said:
Yea I saw this but I will wait for DF because it says "Maxwell" which isn't really what I would call "same architecture as the world’s top-performing GeForce gaming graphics cards" since that is Pascal atm

Early dev-kits aren't the same spec than the console, the dev-kit only needs the same performance target. After some time the dev-kits will get revisions to final spec. These dev-kit specs could however be bogus but not simply because it says Maxwell.

Thats true



                  

PC Specs: CPU: 7800X3D || GPU: Strix 4090 || RAM: 32GB DDR5 6000 || Main SSD: WD 2TB SN850

Sh1nn on 20 October 2016

From Sebbi,he works at RedLynx (Trials series)

56 CUDA cores = 512 flop/cycle (multiply-adds, fp32). At 1 GHz this is 0.5 TFLOP/s. Main memory is 4 GB and bandwidth is 25.6 GB/s.

Xbox One GPU is 3x wider. 768 SIMD lanes = 1536 flop/cycle (multiply-adds, fp32). At 853 MHz this is 1.3 TFLOP/s. Main memory is 8 GB and bandwidth is 68 GB/s. Plus ESRAM of course.

Xbox One raw performance and bandwidth are both roughly 2.5x. Even if we assume that Nvidia's GPU is more efficient, we are looking at roughly 2x difference.

This comparison completely ignores the fast ESRAM memory on Xbox One. It will further increase Xbox One's bandwidth advantage. And Xbox One's main memory BW is already pretty low compared to 176 GB/s of PS4. Double rate 16 bit math will of course help the Nvidia GPU a bit, but this only increases ALU performance (in limited cases) and only helps in cases where you are not texture samping bound (2:1 ALU to TEX rate makes you easily TEX bound) or memory bandwidth bound (25.6 GB/s means that you often are BW bound).

If these specs are true, this console is not fast enough to run Xbox One 900p ports at reduced 720p resolution. Quality also needs to be slightly scaled down. But these are rumoured specs, hopefully the real specs are a bit higher. I would like to see a new Pascal based GPU.

https://forum.beyond3d.com/threads/nintendo-switch-hw-api-discussion.59709/page-3#post-1948968



Platina on 20 October 2016

I'll wait for actual details first..



NintenDomination [May 2015 - July 2017]
 

  - Official  VGChartz Tutorial Thread - 

NintenDomination [2015/05/19 - 2017/07/02]
 
          

 

 

Here lies the hidden threads. 

 | |

Nintendo Metascore | Official NintenDomination | VGC Tutorial Thread

| Best and Worst of Miiverse | Manga Discussion Thead |
[3DS] Winter Playtimes [Wii U]

SubiyaCryolite on 20 October 2016
Sh1nn said:
From Sebbi,he works at RedLynx (Trials series)

56 CUDA cores = 512 flop/cycle (multiply-adds, fp32). At 1 GHz this is 0.5 TFLOP/s. Main memory is 4 GB and bandwidth is 25.6 GB/s.

Xbox One GPU is 3x wider. 768 SIMD lanes = 1536 flop/cycle (multiply-adds, fp32). At 853 MHz this is 1.3 TFLOP/s. Main memory is 8 GB and bandwidth is 68 GB/s. Plus ESRAM of course.

Xbox One raw performance and bandwidth are both roughly 2.5x. Even if we assume that Nvidia's GPU is more efficient, we are looking at roughly 2x difference.

This comparison completely ignores the fast ESRAM memory on Xbox One. It will further increase Xbox One's bandwidth advantage. And Xbox One's main memory BW is already pretty low compared to 176 GB/s of PS4. Double rate 16 bit math will of course help the Nvidia GPU a bit, but this only increases ALU performance (in limited cases) and only helps in cases where you are not texture samping bound (2:1 ALU to TEX rate makes you easily TEX bound) or memory bandwidth bound (25.6 GB/s means that you often are BW bound).

If these specs are true, this console is not fast enough to run Xbox One 900p ports at reduced 720p resolution. Quality also needs to be slightly scaled down. But these are rumoured specs, hopefully the real specs are a bit higher. I would like to see a new Pascal based GPU.

https://forum.beyond3d.com/threads/nintendo-switch-hw-api-discussion.59709/page-3#post-1948968

This seems like an accurate assessment. Even with advances in technology I find it impossible for such a small formfactor (dock included) to match the XBox.



I predict that the Wii U will sell a total of 18 million units in its lifetime. 

The NX will be a 900p machine

Bofferbrauer on 20 October 2016
Sh1nn said:
From Sebbi,he works at RedLynx (Trials series)

56 CUDA cores = 512 flop/cycle (multiply-adds, fp32). At 1 GHz this is 0.5 TFLOP/s. Main memory is 4 GB and bandwidth is 25.6 GB/s.

Xbox One GPU is 3x wider. 768 SIMD lanes = 1536 flop/cycle (multiply-adds, fp32). At 853 MHz this is 1.3 TFLOP/s. Main memory is 8 GB and bandwidth is 68 GB/s. Plus ESRAM of course.

Xbox One raw performance and bandwidth are both roughly 2.5x. Even if we assume that Nvidia's GPU is more efficient, we are looking at roughly 2x difference.

This comparison completely ignores the fast ESRAM memory on Xbox One. It will further increase Xbox One's bandwidth advantage. And Xbox One's main memory BW is already pretty low compared to 176 GB/s of PS4. Double rate 16 bit math will of course help the Nvidia GPU a bit, but this only increases ALU performance (in limited cases) and only helps in cases where you are not texture samping bound (2:1 ALU to TEX rate makes you easily TEX bound) or memory bandwidth bound (25.6 GB/s means that you often are BW bound).

If these specs are true, this console is not fast enough to run Xbox One 900p ports at reduced 720p resolution. Quality also needs to be slightly scaled down. But these are rumoured specs, hopefully the real specs are a bit higher. I would like to see a new Pascal based GPU.

https://forum.beyond3d.com/threads/nintendo-switch-hw-api-discussion.59709/page-3#post-1948968

Wouldn't be the first time that early devkits are weaker or pretty different in hardware specs of the final console, simply due to the fact that the final hardware is not done in time for the first games to be developed at