Support NeoGAF

[SantaC]

If true, that is just a monster of a chip.

NVIDIA GH100 Hopper Flagship GPU To Measure About 1000mm2 Making It The Largest GPU Ever Made

NVIDIA Hopper GH100 GPU which will power the next-generation Data Centers has been rumored to feature a monster die size of around 1000mm2.

wccftech.com

However I am still confused. What is Nvidias next-gen gaming gpu, lovelace or hopper?

Edit: doh it was for datacenter and not gaming. Nevermind then. Nobody cares about datacenter

 

[ParaSeoul]

Nvidia's next gen mining GPU

 

[M1chl]

aka 10cm2 aka 3.3cm x 3.3cm​

For something which can be visualized, I know they write it like that, just to make it more impressive sounding.

 

[Kenpachii]

If true, that is just a monster of a chip.

NVIDIA GH100 Hopper Flagship GPU To Measure About 1000mm2 Making It The Largest GPU Ever Made

NVIDIA Hopper GH100 GPU which will power the next-generation Data Centers has been rumored to feature a monster die size of around 1000mm2.

wccftech.com

However I am still confused. What is Nvidias next-gen gaming gpu, lovelace or hopper?

Edit: doh it was for datacenter and not gaming. Nevermind then. Nobody cares about datacenter

Always wondered how loveace would be in any shape or way compete with next RDNA solution. The next RDNA card will be a monster and honestly they need hopper more then anything for that.

 

[Bo_Hazem]

Who cares if you can't buy it anyway? My next PC would be prebuilt at best.

 

[MadAnon]

They will look great in those mining farms.

 

[tusharngf]

NVIDIA Hopper GH100 'Preliminary Specs':​

NVIDIA Tesla Graphics Card	Tesla K40 (PCI-Express)	Tesla M40 (PCI-Express)	Tesla P100 (PCI-Express)	Tesla P100 (SXM2)	Tesla V100 (SXM2)	NVIDIA A100 (SXM4)	NVIDIA H100 (SMX4?)
GPU	GK110 (Kepler)	GM200 (Maxwell)	GP100 (Pascal)	GP100 (Pascal)	GV100 (Volta)	GA100 (Ampere)	GH100 (Hopper)
Process Node	28nm	28nm	16nm	16nm	12nm	7nm	5nm
Transistors	7.1 Billion	8 Billion	15.3 Billion	15.3 Billion	21.1 Billion	54.2 Billion	TBD
GPU Die Size	551 mm2	601 mm2	610 mm2	610 mm2	815mm2	826mm2	~1000mm2?
SMs	15	24	56	56	80	108	134 (Per Module)
TPCs	15	24	28	28	40	54	TBD
FP32 CUDA Cores Per SM	192	128	64	64	64	64	64?
FP64 CUDA Cores / SM	64	4	32	32	32	32	32?
FP32 CUDA Cores	2880	3072	3584	3584	5120	6912	8576 (Per Module) 17152 (Complete)
FP64 CUDA Cores	960	96	1792	1792	2560	3456	4288 (Per Module)? 8576 (Complete)?
Tensor Cores	N/A	N/A	N/A	N/A	640	432	TBD
Texture Units	240	192	224	224	320	432	TBD
Boost Clock	875 MHz	1114 MHz	1329MHz	1480 MHz	1530 MHz	1410 MHz	~1400 MHz
TOPs (DNN/AI)	N/A	N/A	N/A	N/A	125 TOPs	1248 TOPs 2496 TOPs with Sparsity	TBD
FP16 Compute	N/A	N/A	18.7 TFLOPs	21.2 TFLOPs	30.4 TFLOPs	312 TFLOPs 624 TFLOPs with Sparsity	779 TFLOPs (Per Module)? 1558 TFLOPs with Sparsity (Per Module)?
FP32 Compute	5.04 TFLOPs	6.8 TFLOPs	10.0 TFLOPs	10.6 TFLOPs	15.7 TFLOPs	19.4 TFLOPs 156 TFLOPs With Sparsity	24.2 TFLOPs (Per Module)? 193.6 TFLOPs With Sparsity?
FP64 Compute	1.68 TFLOPs	0.2 TFLOPs	4.7 TFLOPs	5.30 TFLOPs	7.80 TFLOPs	19.5 TFLOPs (9.7 TFLOPs standard)	24.2 TFLOPs (Per Module)? (12.1 TFLOPs standard)?
Memory Interface	384-bit GDDR5	384-bit GDDR5	4096-bit HBM2	4096-bit HBM2	4096-bit HBM2	6144-bit HBM2e	6144-bit HBM2e
Memory Size	12 GB GDDR5 @ 288 GB/s	24 GB GDDR5 @ 288 GB/s	16 GB HBM2 @ 732 GB/s 12 GB HBM2 @ 549 GB/s	16 GB HBM2 @ 732 GB/s	16 GB HBM2 @ 900 GB/s	Up To 40 GB HBM2 @ 1.6 TB/s Up To 80 GB HBM2 @ 1.6 TB/s	Up To 100 GB HBM2e @ 3.5 Gbps
L2 Cache Size	1536 KB	3072 KB	4096 KB	4096 KB	6144 KB	40960 KB	81920 KB
TDP	235W	250W	250W	300W	300W	400W	~450-500W