Compare XPUs

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

Select XPUs to Compare

Clear all (3)Jump to results

Filter by Vendor

Showing 72 XPUs • 3 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 A10	Intel Data Center GPU Max 1100	Etched Sohu
Architecture	Ampere	Ponte Vecchio	Transformer ASIC
Form Factor	PCIe	OAM	PCIe
VRAM	24 GB	48 GB	144 GB
Memory Bandwidth	600 GB/s	1,229 GB/s	4,800 GB/s
TFLOPs (FP32)	31.2	22	10,000
TFLOPs (FP16)	125	177	—
TFLOPs	125	177	10,000
TFLOPs (FP8)	—	—	—
TDP	150 W	300 W	700 W
Launch Date	Apr 2021	Jan 2023	Jun 2024

Efficiency Metrics

Metric	A10	Data Center GPU Max 1100	Sohu
TFLOPs per Watt (FP32-eq)	0.42	0.29	14.29
Memory Bandwidth per GB	25.0 GB/s	25.6 GB/s	33.3 GB/s

Performance Equivalence

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

To match 1x NVIDIA A10

Intel Data Center GPU Max 1100

Compute (FP32-eq)

0.71x

Data Center GPU Max 1100 is 1.42x faster

FP32 Compute

1.42x

Need 1.42x Data Center GPU Max 1100

VRAM

0.50x

Data Center GPU Max 1100 has 2.00x more

Memory Bandwidth

0.49x

Data Center GPU Max 1100 has 2.05x more

Etched Sohu

Compute (FP32-eq)

0.01x

Sohu is 160.00x faster

FP32 Compute

0.00x

Sohu is 320.51x faster

VRAM

0.17x

Sohu has 6.00x more

Memory Bandwidth

0.13x

Sohu has 8.00x more

To match 1x Intel Data Center GPU Max 1100

NVIDIA A10

Compute (FP32-eq)

1.42x

Need 1.42x A10

FP32 Compute

0.71x

A10 is 1.42x faster

VRAM

2.00x

Need 2.00x A10

Memory Bandwidth

2.05x

Need 2.05x A10

Etched Sohu

Compute (FP32-eq)

0.01x

Sohu is 112.99x faster

FP32 Compute

0.00x

Sohu is 454.55x faster

VRAM

0.33x

Sohu has 3.00x more

Memory Bandwidth

0.26x

Sohu has 3.91x more

To match 1x Etched Sohu

NVIDIA A10

Compute (FP32-eq)

160.00x

Need 160.00x A10

FP32 Compute

320.51x

Need 320.51x A10

VRAM

6.00x

Need 6.00x A10

Memory Bandwidth

8.00x

Need 8.00x A10

Intel Data Center GPU Max 1100

Compute (FP32-eq)

112.99x

Need 112.99x Data Center GPU Max 1100

FP32 Compute

454.55x

Need 454.55x Data Center GPU Max 1100

VRAM

3.00x

Need 3.00x Data Center GPU Max 1100

Memory Bandwidth

3.91x

Need 3.91x Data Center GPU Max 1100

Pricing

Price Type	A10	Data Center GPU Max 1100	Sohu
CAPEX (Street Price)	—	$5,000	—
OPEX (per hour)	—	—	—
Price per TFLOPs (FP32-eq)	—	$56	—