Compare XPUs

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

Select XPUs to Compare

Clear all (5)Jump to results

Filter by Vendor

Showing 128 XPUs • 5 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	Graphcore Bow IPU	AMD MI300X	FuriosaAI RNGD (Renegade)	NVIDIA GeForce GT 730	NVIDIA A100 SXM
Architecture	Bow-2000	CDNA 3	Tensor Contraction Processor	Kepler	Ampere
Form Factor	—	OAM	PCIe	PCIe	SXM
VRAM	3.6 GB	192 GB	48 GB	2 GB	80 GB
Memory Bandwidth	—	5,300 GB/s	1,500 GB/s	28.5 GB/s	2,039 GB/s
TFLOPs (FP32)	—	163.4	—	0.693	19.5
TFLOPs (FP16)	1,000	1,307	—	—	312
TFLOPs	—	1,307	256	0.693	312
TFLOPs (FP8)	—	2,614	512	—	—
TDP	200 W	750 W	180 W	49 W	400 W
Launch Date	Mar 2022	Dec 2023	Jan 2024	Jun 2014	May 2020

Efficiency Metrics

Metric	Bow IPU	MI300X	RNGD (Renegade)	GeForce GT 730	A100 SXM
TFLOPs per Watt (FP32-eq)	—	0.87	0.71	0.01	0.39
Memory Bandwidth per GB	—	27.6 GB/s	31.3 GB/s	14.3 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 Graphcore Bow IPU

AMD MI300X

VRAM

0.02x

MI300X has 53.33x more

FuriosaAI RNGD (Renegade)

VRAM

0.07x

RNGD (Renegade) has 13.33x more

NVIDIA GeForce GT 730

VRAM

1.80x

Need 1.80x GeForce GT 730

NVIDIA A100 SXM

VRAM

0.04x

A100 SXM has 22.22x more

To match 1x AMD MI300X

Graphcore Bow IPU

VRAM

53.33x

Need 53.33x Bow IPU

FuriosaAI RNGD (Renegade)

Compute (FP32-eq)

5.11x

Need 5.11x RNGD (Renegade)

VRAM

4.00x

Need 4.00x RNGD (Renegade)

Memory Bandwidth

3.53x

Need 3.53x RNGD (Renegade)

NVIDIA GeForce GT 730

Compute (FP32-eq)

943.00x

Need 943.00x GeForce GT 730

FP32 Compute

235.79x

Need 235.79x GeForce GT 730

VRAM

96.00x

Need 96.00x GeForce GT 730

Memory Bandwidth

185.96x

Need 185.96x GeForce GT 730

NVIDIA A100 SXM

Compute (FP32-eq)

4.19x

Need 4.19x A100 SXM

FP32 Compute

8.38x

Need 8.38x A100 SXM

VRAM

2.40x

Need 2.40x A100 SXM

Memory Bandwidth

2.60x

Need 2.60x A100 SXM

To match 1x FuriosaAI RNGD (Renegade)

Graphcore Bow IPU

VRAM

13.33x

Need 13.33x Bow IPU

AMD MI300X

Compute (FP32-eq)

0.20x

MI300X is 5.11x faster

VRAM

0.25x

MI300X has 4.00x more

Memory Bandwidth

0.28x

MI300X has 3.53x more

NVIDIA GeForce GT 730

Compute (FP32-eq)

184.70x

Need 184.70x GeForce GT 730

VRAM

24.00x

Need 24.00x GeForce GT 730

Memory Bandwidth

52.63x

Need 52.63x GeForce GT 730

NVIDIA A100 SXM

Compute (FP32-eq)

0.82x

A100 SXM is 1.22x faster

VRAM

0.60x

A100 SXM has 1.67x more

Memory Bandwidth

0.74x

A100 SXM has 1.36x more

To match 1x NVIDIA GeForce GT 730

Graphcore Bow IPU

VRAM

0.56x

Bow IPU has 1.80x more

AMD MI300X

Compute (FP32-eq)

0.00x

MI300X is 943.00x faster

FP32 Compute

0.00x

MI300X is 235.79x faster

VRAM

0.01x

MI300X has 96.00x more

Memory Bandwidth

0.01x

MI300X has 185.96x more

FuriosaAI RNGD (Renegade)

Compute (FP32-eq)

0.01x

RNGD (Renegade) is 184.70x faster

VRAM

0.04x

RNGD (Renegade) has 24.00x more

Memory Bandwidth

0.02x

RNGD (Renegade) has 52.63x more

NVIDIA A100 SXM

Compute (FP32-eq)

0.00x

A100 SXM is 225.11x faster

FP32 Compute

0.04x

A100 SXM is 28.14x faster

VRAM

0.03x

A100 SXM has 40.00x more

Memory Bandwidth

0.01x

A100 SXM has 71.54x more

To match 1x NVIDIA A100 SXM

Graphcore Bow IPU

VRAM

22.22x

Need 22.22x Bow IPU

AMD MI300X

Compute (FP32-eq)

0.24x

MI300X is 4.19x faster

FP32 Compute

0.12x

MI300X is 8.38x faster

VRAM

0.42x

MI300X has 2.40x more

Memory Bandwidth

0.38x

MI300X has 2.60x more

FuriosaAI RNGD (Renegade)

Compute (FP32-eq)

1.22x

Need 1.22x RNGD (Renegade)

VRAM

1.67x

Need 1.67x RNGD (Renegade)

Memory Bandwidth

1.36x

Need 1.36x RNGD (Renegade)

NVIDIA GeForce GT 730

Compute (FP32-eq)

225.11x

Need 225.11x GeForce GT 730

FP32 Compute

28.14x

Need 28.14x GeForce GT 730

VRAM

40.00x

Need 40.00x GeForce GT 730

Memory Bandwidth

71.54x

Need 71.54x GeForce GT 730

Pricing

Price Type	Bow IPU	MI300X	RNGD (Renegade)	GeForce GT 730	A100 SXM
CAPEX (Street Price)	—	$35,000	—	—	$15,000
OPEX (per hour)	—	$10.40/hr	—	$0.04/hr	$4.05/hr
Price per TFLOPs (FP32-eq)	—	$54	—	—	$96