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	AMD MI100	Meta MTIA v1	NVIDIA H100 PCIe	Baidu Kunlun II
Architecture	CDNA	Meta Training & Inference Accelerator	Hopper	Kunlun Core
Form Factor	PCIe	—	PCIe	—
VRAM	32 GB	128 GB	80 GB	32 GB
Memory Bandwidth	1,228 GB/s	—	2,000 GB/s	—
TFLOPs (FP32)	23.1	—	51	—
TFLOPs (FP16)	184.6	—	1,513	256
TFLOPs	23.1	—	1,513	—
TFLOPs (FP8)	—	—	—	—
TDP	300 W	400 W	350 W	200 W
Launch Date	Nov 2020	May 2023	Sep 2022	Aug 2021

Efficiency Metrics

Metric	MI100	MTIA v1	H100 PCIe	Kunlun II
TFLOPs per Watt (FP32-eq)	0.08	—	2.16	—
Memory Bandwidth per GB	38.4 GB/s	—	25.0 GB/s	—

Performance Equivalence

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

To match 1x AMD MI100

Meta MTIA v1

VRAM

0.25x

MTIA v1 has 4.00x more

NVIDIA H100 PCIe

Compute (FP32-eq)

0.03x

H100 PCIe is 32.75x faster

FP32 Compute

0.45x

H100 PCIe is 2.21x faster

VRAM

0.40x

H100 PCIe has 2.50x more

Memory Bandwidth

0.61x

H100 PCIe has 1.63x more

Baidu Kunlun II

VRAM

1.00x

Kunlun II has 1.00x more

To match 1x Meta MTIA v1

AMD MI100

VRAM

4.00x

Need 4.00x MI100

NVIDIA H100 PCIe

VRAM

1.60x

Need 1.60x H100 PCIe

Baidu Kunlun II

VRAM

4.00x

Need 4.00x Kunlun II

To match 1x NVIDIA H100 PCIe

AMD MI100

Compute (FP32-eq)

32.75x

Need 32.75x MI100

FP32 Compute

2.21x

Need 2.21x MI100

VRAM

2.50x

Need 2.50x MI100

Memory Bandwidth

1.63x

Need 1.63x MI100

Meta MTIA v1

VRAM

0.63x

MTIA v1 has 1.60x more

Baidu Kunlun II

VRAM

2.50x

Need 2.50x Kunlun II

To match 1x Baidu Kunlun II

AMD MI100

VRAM

1.00x

MI100 has 1.00x more

Meta MTIA v1

VRAM

0.25x

MTIA v1 has 4.00x more

NVIDIA H100 PCIe

VRAM

0.40x

H100 PCIe has 2.50x more

Pricing

Price Type	MI100	MTIA v1	H100 PCIe	Kunlun II
CAPEX (Street Price)	—	—	—	—
OPEX (per hour)	—	—	—	—
Price per TFLOPs (FP32-eq)	—	—	—	—