Compare XPUs

Select up to 5 XPUs to compare side-by-side

Select XPUs to Compare

Clear all (4)Jump to results

Filter by Vendor

Showing 128 XPUs • 4 selected

Alibaba

Hanguang 800

AMD

MI100

23.1 TFLOPs

AMD

MI210

181 TFLOPs

AMD

MI250X

383 TFLOPs

AMD

MI300X

1,307 TFLOPs

AMD

MI325X

1,400 TFLOPs

AMD

MI350X

2,100 TFLOPs

AMD

MI355X

5,300 TFLOPs

AMD

Radeon Pro V520

23.04 TFLOPs

AWS

Inferentia2

190 TFLOPs

AWS

Trainium

190 TFLOPs

AWS

Trainium2

680 TFLOPs

Baidu

Kunlun II

Biren Technology

BR100

Cambricon

MLU370

256 TFLOPs

Cerebras

WSE-3

Enflame Technology

CloudBlazer T20

FuriosaAI

RNGD (Renegade)

256 TFLOPs

FuriosaAI

Warboy

Google

TPU v4

275 TFLOPs

Google

TPU v5e

197 TFLOPs

Google

TPU v5p

459 TFLOPs

Graphcore

Bow IPU

Graphcore

IPU-M2000

Groq

LPU Inference Engine

Huawei

Ascend 910B

Iluvatar CoreX

BI-V150

300 TFLOPs

Intel

Data Center GPU Max 1100

177 TFLOPs

Intel

Data Center GPU Max 1550

419 TFLOPs

Intel Habana

Gaudi 2

432 TFLOPs

Intel Habana

Gaudi 3

1,835 TFLOPs

Multi-Metric Comparison

Relative performance across 5 key metrics (normalized to 100 = best in comparison)

Compute Performance (BF16)

Memory Capacity

Power Consumption

Power Efficiency

Specifications

Specification	NVIDIA RTX A2000	NVIDIA V100S	NVIDIA GH200	NVIDIA A100 SXM
Architecture	Ampere	Volta	Hopper	Ampere
Form Factor	PCIe	PCIe	SXM	SXM
VRAM	12 GB	32 GB	96 GB	80 GB
Memory Bandwidth	288 GB/s	1,134 GB/s	4,000 GB/s	2,039 GB/s
TFLOPs (FP32)	8	16.4	67	19.5
TFLOPs (FP16)	—	—	—	312
TFLOPs	16	16.4	989	312
TFLOPs (FP8)	—	—	—	—
TDP	70 W	250 W	1000 W	400 W
Launch Date	Oct 2021	Nov 2019	May 2023	May 2020

Efficiency Metrics

Metric	RTX A2000	V100S	GH200	A100 SXM
TFLOPs per Watt (FP32-eq)	0.11	0.07	0.49	0.39
Memory Bandwidth per GB	24.0 GB/s	35.4 GB/s	41.7 GB/s	25.5 GB/s

Performance Equivalence

How many units of each GPU are needed to match the performance of the others?

To match 1x NVIDIA RTX A2000

NVIDIA V100S

Compute (FP32-eq)

0.49x

V100S is 2.05x faster

FP32 Compute

0.49x

V100S is 2.05x faster

VRAM

0.38x

V100S has 2.67x more

Memory Bandwidth

0.25x

V100S has 3.94x more

NVIDIA GH200

Compute (FP32-eq)

0.02x

GH200 is 61.81x faster

FP32 Compute

0.12x

GH200 is 8.38x faster

VRAM

0.13x

GH200 has 8.00x more

Memory Bandwidth

0.07x

GH200 has 13.89x more

NVIDIA A100 SXM

Compute (FP32-eq)

0.05x

A100 SXM is 19.50x faster

FP32 Compute

0.41x

A100 SXM is 2.44x faster

VRAM

0.15x

A100 SXM has 6.67x more

Memory Bandwidth

0.14x

A100 SXM has 7.08x more

To match 1x NVIDIA V100S

NVIDIA RTX A2000

Compute (FP32-eq)

2.05x

Need 2.05x RTX A2000

FP32 Compute

2.05x

Need 2.05x RTX A2000

VRAM

2.67x

Need 2.67x RTX A2000

Memory Bandwidth

3.94x

Need 3.94x RTX A2000

NVIDIA GH200

Compute (FP32-eq)

0.03x

GH200 is 30.15x faster

FP32 Compute

0.24x

GH200 is 4.09x faster

VRAM

0.33x

GH200 has 3.00x more

Memory Bandwidth

0.28x

GH200 has 3.53x more

NVIDIA A100 SXM

Compute (FP32-eq)

0.11x

A100 SXM is 9.51x faster

FP32 Compute

0.84x

A100 SXM is 1.19x faster

VRAM

0.40x

A100 SXM has 2.50x more

Memory Bandwidth

0.56x

A100 SXM has 1.80x more

To match 1x NVIDIA GH200

NVIDIA RTX A2000

Compute (FP32-eq)

61.81x

Need 61.81x RTX A2000

FP32 Compute

8.38x

Need 8.38x RTX A2000

VRAM

8.00x

Need 8.00x RTX A2000

Memory Bandwidth

13.89x

Need 13.89x RTX A2000

NVIDIA V100S

Compute (FP32-eq)

30.15x

Need 30.15x V100S

FP32 Compute

4.09x

Need 4.09x V100S

VRAM

3.00x

Need 3.00x V100S

Memory Bandwidth

3.53x

Need 3.53x V100S

NVIDIA A100 SXM

Compute (FP32-eq)

3.17x

Need 3.17x A100 SXM

FP32 Compute

3.44x

Need 3.44x A100 SXM

VRAM

1.20x

Need 1.20x A100 SXM

Memory Bandwidth

1.96x

Need 1.96x A100 SXM

To match 1x NVIDIA A100 SXM

NVIDIA RTX A2000

Compute (FP32-eq)

19.50x

Need 19.50x RTX A2000

FP32 Compute

2.44x

Need 2.44x RTX A2000

VRAM

6.67x

Need 6.67x RTX A2000

Memory Bandwidth

7.08x

Need 7.08x RTX A2000

NVIDIA V100S

Compute (FP32-eq)

9.51x

Need 9.51x V100S

FP32 Compute

1.19x

Need 1.19x V100S

VRAM

2.50x

Need 2.50x V100S

Memory Bandwidth

1.80x

Need 1.80x V100S

NVIDIA GH200

Compute (FP32-eq)

0.32x

GH200 is 3.17x faster

FP32 Compute

0.29x

GH200 is 3.44x faster

VRAM

0.83x

GH200 has 1.20x more

Memory Bandwidth

0.51x

GH200 has 1.96x more

Pricing

Price Type	RTX A2000	V100S	GH200	A100 SXM
CAPEX (Street Price)	—	—	—	$15,000
OPEX (per hour)	$0.04/hr	$0.88/hr	$1.49/hr	$4.05/hr
Price per TFLOPs (FP32-eq)	—	—	—	$96