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 72 XPUs • 4 selected

Alibaba

Hanguang 800

AMD

MI100

23.1 TFLOPs

AMD

MI210

181 TFLOPs

AMD

MI250X

383 TFLOPs

AMD

MI300A

980.6 TFLOPs

AMD

MI300X

1,307 TFLOPs

AMD

MI325X

1,400 TFLOPs

AMD

MI350X

2,100 TFLOPs

AMD

Radeon PRO W7900

122 TFLOPs

AMD

Radeon RX 7900 XT

104 TFLOPs

AMD

Radeon RX 7900 XTX

122 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

Etched

Sohu

10,000 TFLOPs

FuriosaAI

Warboy

Google

TPU v4

275 TFLOPs

Google

TPU v5e

197 TFLOPs

Google

TPU v5p

459 TFLOPs

Google

TPU v6e (Trillium)

918 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 A100 SXM	AMD MI250X	AMD MI210	Graphcore Bow IPU
Architecture	Ampere	CDNA 2	CDNA 2	Bow-2000
Form Factor	SXM	OAM	PCIe	—
VRAM	80 GB	128 GB	64 GB	3.6 GB
Memory Bandwidth	2,039 GB/s	3,277 GB/s	1,638 GB/s	—
TFLOPs (FP32)	19.5	47.9	45.3	—
TFLOPs (FP16)	312	383	181	1,000
TFLOPs	312	383	181	—
TFLOPs (FP8)	—	—	—	—
TDP	400 W	560 W	300 W	200 W
Launch Date	May 2020	Nov 2021	Jan 2022	Mar 2022

Efficiency Metrics

Metric	A100 SXM	MI250X	MI210	Bow IPU
TFLOPs per Watt (FP32-eq)	0.39	0.34	0.30	—
Memory Bandwidth per GB	25.5 GB/s	25.6 GB/s	25.6 GB/s	—

Performance Equivalence

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

To match 1x NVIDIA A100 SXM

AMD MI250X

Compute (FP32-eq)

0.81x

MI250X is 1.23x faster

FP32 Compute

0.41x

MI250X is 2.46x faster

VRAM

0.63x

MI250X has 1.60x more

Memory Bandwidth

0.62x

MI250X has 1.61x more

AMD MI210

Compute (FP32-eq)

1.72x

Need 1.72x MI210

FP32 Compute

0.43x

MI210 is 2.32x faster

VRAM

1.25x

Need 1.25x MI210

Memory Bandwidth

1.24x

Need 1.24x MI210

Graphcore Bow IPU

VRAM

22.22x

Need 22.22x Bow IPU

To match 1x AMD MI250X

NVIDIA A100 SXM

Compute (FP32-eq)

1.23x

Need 1.23x A100 SXM

FP32 Compute

2.46x

Need 2.46x A100 SXM

VRAM

1.60x

Need 1.60x A100 SXM

Memory Bandwidth

1.61x

Need 1.61x A100 SXM

AMD MI210

Compute (FP32-eq)

2.12x

Need 2.12x MI210

FP32 Compute

1.06x

Need 1.06x MI210

VRAM

2.00x

Need 2.00x MI210

Memory Bandwidth

2.00x

Need 2.00x MI210

Graphcore Bow IPU

VRAM

35.56x

Need 35.56x Bow IPU

To match 1x AMD MI210

NVIDIA A100 SXM

Compute (FP32-eq)

0.58x

A100 SXM is 1.72x faster

FP32 Compute

2.32x

Need 2.32x A100 SXM

VRAM

0.80x

A100 SXM has 1.25x more

Memory Bandwidth

0.80x

A100 SXM has 1.24x more

AMD MI250X

Compute (FP32-eq)

0.47x

MI250X is 2.12x faster

FP32 Compute

0.95x

MI250X is 1.06x faster

VRAM

0.50x

MI250X has 2.00x more

Memory Bandwidth

0.50x

MI250X has 2.00x more

Graphcore Bow IPU

VRAM

17.78x

Need 17.78x Bow IPU

To match 1x Graphcore Bow IPU

NVIDIA A100 SXM

VRAM

0.04x

A100 SXM has 22.22x more

AMD MI250X

VRAM

0.03x

MI250X has 35.56x more

AMD MI210

VRAM

0.06x

MI210 has 17.78x more

Pricing

Price Type	A100 SXM	MI250X	MI210	Bow IPU
CAPEX (Street Price)	$15,000	$12,000	$6,000	—
OPEX (per hour)	$4.05/hr	$2.00/hr	—	—
Price per TFLOPs (FP32-eq)	$96	$63	$66	—