NVIDIA could reach 8K cores with next-generation architecture

Published: 3rd Mar 2020, 21:00 | Comments

newz

A huge monolithic GPU or a multi-chip design?

NVIDIA Graphics Device with 124 Compute Units spotted

Just a few days ago we discussed a leak from Geekbench where two graphics devices equipped with 118 and 104 Compute Units were spotted, only to learn that there is even a 124-CU device in the very same database.

Obviously, at this point, we believe that the full specs of the upcoming big core could feature even 128 CUs (8192 CUDA cores) in full form, however, such silicon might never be available for the market with full specs due to manufacturing yields.

The same thing happened with GV100 (Volta) for Tesla V100 and Quadro GV100. The GV100 GPU was only available with 80 Volta Streaming Multiprocessors enabled, despite featuring 84 in total (source).

That said, it is possible that the leaked 124 CU (SM) device is the next-gen Tesla (it would lack just as many SMs as Tesla Volta). We do not know for sure if the next-gen architecture for Tesla is codenamed Ampere, Hopper or something else. However, NVIDIA CEO will host an opening keynote at GTC 2020 (which shifted to an online event) where he might provide an update on these GPUs, next-gen architecture and future roadmaps.

The leaked device was reported with a relatively low GPU clock of 1.11 GHz, which further suggests Tesla or Quadro rather than GeForce device. It is also important to note that we do not know how many CUDA cores are in each Streaming Multiprocessor, as this number has changed in the past. See the chart below for details.

NVIDIA TESLA (Speculation)
SKUCUs / SMsCUDA CoresMemory
Next-Gen Device #1
 
124
 
7936
 
32GB HBM2e
Next-Gen Device #2
 
118
 
7552
 
24GB HBM2e
Next-Gen Device #3
 
108
 
6912
 
48GB HBM2e
Tesla V100 (Volta)
 
80
 
5120
 
32GB HBM2
Tesla P100 (Pascal)
 
56
 
3584
 
16GB HBM2
Tesla M40 (Maxwell)
 
24
 
3072
 
12GB GDDR5
Tesla K40 (Kepler)
 
15
 
2880
 
12GB GDDR5
Next-Gen: Ampere?, Maxwell  SM * 128 = CUDA,  Kepler SM*192 = CUDA, Volta & Pascal SM*64 = CUDA

Source: Geekbench via _rogame & W_At_Ar_U, Tom’s Hardware


by WhyCry

Previous Post
AMD Radeon RX 590 GME spotted in China
Next Post
AMD EPYC Zen4 "Genoa" and next-generation Radeon Instinct GPUs to power El Captain Supercomputer





Back to Top ↑