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 A40	AMD MI100	Cerebras WSE-3	Biren Technology BR100
Architecture	Ampere	CDNA	Wafer Scale Engine	Biren GPU
Form Factor	PCIe	PCIe	—	—
VRAM	48 GB	32 GB	44 GB	64 GB
Memory Bandwidth	696 GB/s	1,228 GB/s	—	—
TFLOPs (FP32)	37.4	23.1	—	—
TFLOPs (FP16)	150	184.6	—	1,000
TFLOPs	150	23.1	—	—
TFLOPs (FP8)	—	—	—	—
TDP	300 W	300 W	23000 W	550 W
Launch Date	Oct 2020	Nov 2020	Mar 2024	Aug 2022

Efficiency Metrics

Metric	A40	MI100	WSE-3	BR100
TFLOPs per Watt (FP32-eq)	0.25	0.08	—	—
Memory Bandwidth per GB	14.5 GB/s	38.4 GB/s	—	—

Performance Equivalence

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

To match 1x NVIDIA A40

AMD MI100

Compute (FP32-eq)

3.25x

Need 3.25x MI100

FP32 Compute

1.62x

Need 1.62x MI100

VRAM

1.50x

Need 1.50x MI100

Memory Bandwidth

0.57x

MI100 has 1.76x more

Cerebras WSE-3

VRAM

1.09x

Need 1.09x WSE-3

Biren Technology BR100

VRAM

0.75x

BR100 has 1.33x more

To match 1x AMD MI100

NVIDIA A40

Compute (FP32-eq)

0.31x

A40 is 3.25x faster

FP32 Compute

0.62x

A40 is 1.62x faster

VRAM

0.67x

A40 has 1.50x more

Memory Bandwidth

1.76x

Need 1.76x A40

Cerebras WSE-3

VRAM

0.73x

WSE-3 has 1.38x more

Biren Technology BR100

VRAM

0.50x

BR100 has 2.00x more

To match 1x Cerebras WSE-3

NVIDIA A40

VRAM

0.92x

A40 has 1.09x more

AMD MI100

VRAM

1.38x

Need 1.38x MI100

Biren Technology BR100

VRAM

0.69x

BR100 has 1.45x more

To match 1x Biren Technology BR100

NVIDIA A40

VRAM

1.33x

Need 1.33x A40

AMD MI100

VRAM

2.00x

Need 2.00x MI100

Cerebras WSE-3

VRAM

1.45x

Need 1.45x WSE-3

Pricing

Price Type	A40	MI100	WSE-3	BR100
CAPEX (Street Price)	—	—	—	—
OPEX (per hour)	—	—	—	—
Price per TFLOPs (FP32-eq)	—	—	—	—