Compare XPUs

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

Select XPUs to Compare

Clear all (7)Jump to results
Showing 128 XPUs • 7 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

Meta

MTIA v1

Microsoft

Maia 100

700 TFLOPs

Moore Threads

MTT S80

NVIDIA

A10

125 TFLOPs

NVIDIA

A100 SXM

312 TFLOPs

NVIDIA

A10G

125 TFLOPs

NVIDIA

A16

71.2 TFLOPs

NVIDIA

A30

165 TFLOPs

NVIDIA

A40

150 TFLOPs

NVIDIA

A800

312 TFLOPs

NVIDIA

B100

1,800 TFLOPs

NVIDIA

B200

2,250 TFLOPs

NVIDIA

GB200

2,500 TFLOPs

NVIDIA

GeForce GT 710

0.366 TFLOPs

NVIDIA

GeForce GT 730

0.693 TFLOPs

NVIDIA

GeForce GTX 1050 Ti

2.138 TFLOPs

NVIDIA

GeForce GTX 1060

4.375 TFLOPs

NVIDIA

GeForce GTX 1070

6.463 TFLOPs

NVIDIA

GeForce GTX 1070 Ti

8.186 TFLOPs

NVIDIA

GeForce GTX 1080

8.873 TFLOPs

NVIDIA

GeForce GTX 1080 Ti

11.34 TFLOPs

NVIDIA

GeForce GTX 1650

2.984 TFLOPs

NVIDIA

GeForce GTX 1660

5.027 TFLOPs

NVIDIA

GeForce GTX 1660 Super

5.027 TFLOPs

NVIDIA

GeForce RTX 2060

6.5 TFLOPs

NVIDIA

GeForce RTX 2060 Super

7.2 TFLOPs

NVIDIA

GeForce RTX 2070

7.5 TFLOPs

NVIDIA

GeForce RTX 2080

10.1 TFLOPs

NVIDIA

GeForce RTX 2080 Ti

13.4 TFLOPs

NVIDIA

GeForce RTX 3050

18.2 TFLOPs

NVIDIA

GeForce RTX 3060

25.4 TFLOPs

NVIDIA

GeForce RTX 3060 Ti

33.2 TFLOPs

NVIDIA

GeForce RTX 3070

40.5 TFLOPs

NVIDIA

GeForce RTX 3070 Ti

43.2 TFLOPs

NVIDIA

GeForce RTX 3080

59.2 TFLOPs

NVIDIA

GeForce RTX 3080 Ti

68.4 TFLOPs

NVIDIA

GeForce RTX 3090

71 TFLOPs

NVIDIA

GeForce RTX 3090 Ti

80 TFLOPs

NVIDIA

GeForce RTX 4060

30 TFLOPs

NVIDIA

GeForce RTX 4060 Ti

44 TFLOPs

NVIDIA

GeForce RTX 4060 Ti 16GB

44 TFLOPs

NVIDIA

GeForce RTX 4070

58.92 TFLOPs

NVIDIA

GeForce RTX 4070 Super

70 TFLOPs

NVIDIA

GeForce RTX 4070 Ti

80.16 TFLOPs

NVIDIA

GeForce RTX 4070 Ti Super

88 TFLOPs

NVIDIA

GeForce RTX 4080

97.76 TFLOPs

NVIDIA

GeForce RTX 4080 Super

104 TFLOPs

NVIDIA

GeForce RTX 4090

165.2 TFLOPs

NVIDIA

GeForce RTX 4090 D

165 TFLOPs

NVIDIA

GeForce RTX 5060

60 TFLOPs

NVIDIA

GeForce RTX 5060 Ti

88 TFLOPs

NVIDIA

GeForce RTX 5070

110 TFLOPs

NVIDIA

GeForce RTX 5070 Ti

133 TFLOPs

NVIDIA

GeForce RTX 5080

171 TFLOPs

NVIDIA

GeForce RTX 5090

318 TFLOPs

NVIDIA

GH200

989 TFLOPs

NVIDIA

H100 SXM

1,979 TFLOPs

NVIDIA

H200 SXM

1,979 TFLOPs

NVIDIA

K80

8.73 TFLOPs

NVIDIA

L4

121 TFLOPs

NVIDIA

L40

181.05 TFLOPs

NVIDIA

L40S

733 TFLOPs

NVIDIA

P100

9.3 TFLOPs

NVIDIA

P4

5.5 TFLOPs

NVIDIA

P40

12 TFLOPs

NVIDIA

Quadro K620

0.768 TFLOPs

NVIDIA

Quadro M4000

2.57 TFLOPs

NVIDIA

Quadro M60

4.825 TFLOPs

NVIDIA

Quadro P1000

1.894 TFLOPs

NVIDIA

Quadro P4000

5.304 TFLOPs

NVIDIA

Quadro P5000

8.873 TFLOPs

NVIDIA

Quadro P600

1.117 TFLOPs

NVIDIA

Quadro P6000

12.63 TFLOPs

NVIDIA

Quadro P620

1.386 TFLOPs

NVIDIA

Quadro RTX 6000

130.5 TFLOPs

NVIDIA

RTX 4000

57.6 TFLOPs

NVIDIA

RTX 4000 SFF Ada Generation

52 TFLOPs

NVIDIA

RTX 4500 Ada Generation

97 TFLOPs

NVIDIA

RTX 5000

89.2 TFLOPs

NVIDIA

RTX 5000 Ada Generation

130 TFLOPs

NVIDIA

RTX 5000 Blackwell

242 TFLOPs

NVIDIA

RTX 5880 Ada Generation

167 TFLOPs

NVIDIA

RTX 6000 Ada Generation

182.5 TFLOPs

NVIDIA

RTX 6000 Blackwell

362 TFLOPs

NVIDIA

RTX A2000

16 TFLOPs

NVIDIA

RTX A4000

38.7 TFLOPs

NVIDIA

RTX A4500

46.6 TFLOPs

NVIDIA

RTX A5000

54.2 TFLOPs

NVIDIA

RTX A6000

77.9 TFLOPs

NVIDIA

T1000

2.5 TFLOPs

NVIDIA

T4

65 TFLOPs

NVIDIA

T4G

65 TFLOPs

NVIDIA

V100S

16.4 TFLOPs

Rebellions

ATOM

SambaNova

SN40L

Tenstorrent

Grayskull

200 TFLOPs

Tenstorrent

Wormhole

364 TFLOPs

Maximum of 5 XPUs can be compared at once. Deselect one to add another.

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

SpecificationAMD MI100Alibaba Hanguang 800NVIDIA A16NVIDIA B100NVIDIA P40NVIDIA GeForce RTX 3090NVIDIA A100 SXM
ArchitectureCDNAXuanTieAmpereBlackwellPascalAmpereAmpere
Form FactorPCIe—PCIeSXMPCIePCIeSXM
VRAM32 GB16 GB64 GB192 GB24 GB24 GB80 GB
Memory Bandwidth1,228 GB/s—232 GB/s8,000 GB/s346 GB/s936 GB/s2,039 GB/s
TFLOPs (FP32)23.1—9.5451235.619.5
TFLOPs (FP16)184.6—————312
TFLOPs23.1—71.21,8001271312
TFLOPs (FP8)———————
TDP300 W150 W250 W700 W250 W350 W400 W
Launch DateNov 2020Sep 2019Apr 2021Mar 2024Sep 2016Sep 2020May 2020

Efficiency Metrics

MetricMI100Hanguang 800A16B100P40GeForce RTX 3090A100 SXM
TFLOPs per Watt (FP32-eq)0.08—0.141.290.050.100.39
Memory Bandwidth per GB38.4 GB/s—3.6 GB/s41.7 GB/s14.4 GB/s39.0 GB/s25.5 GB/s

Performance Equivalence

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

To match 1x AMD MI100

Alibaba Hanguang 800
VRAM
2.00x
Need 2.00x Hanguang 800
NVIDIA A16
Compute (FP32-eq)
0.65x
A16 is 1.54x faster
FP32 Compute
2.43x
Need 2.43x A16
VRAM
0.50x
A16 has 2.00x more
Memory Bandwidth
5.29x
Need 5.29x A16
NVIDIA B100
Compute (FP32-eq)
0.03x
B100 is 38.96x faster
FP32 Compute
0.51x
B100 is 1.95x faster
VRAM
0.17x
B100 has 6.00x more
Memory Bandwidth
0.15x
B100 has 6.51x more
NVIDIA P40
Compute (FP32-eq)
1.93x
Need 1.93x P40
FP32 Compute
1.93x
Need 1.93x P40
VRAM
1.33x
Need 1.33x P40
Memory Bandwidth
3.55x
Need 3.55x P40
NVIDIA GeForce RTX 3090
Compute (FP32-eq)
0.65x
GeForce RTX 3090 is 1.54x faster
FP32 Compute
0.65x
GeForce RTX 3090 is 1.54x faster
VRAM
1.33x
Need 1.33x GeForce RTX 3090
Memory Bandwidth
1.31x
Need 1.31x GeForce RTX 3090
NVIDIA A100 SXM
Compute (FP32-eq)
0.15x
A100 SXM is 6.75x faster
FP32 Compute
1.18x
Need 1.18x A100 SXM
VRAM
0.40x
A100 SXM has 2.50x more
Memory Bandwidth
0.60x
A100 SXM has 1.66x more

To match 1x Alibaba Hanguang 800

AMD MI100
VRAM
0.50x
MI100 has 2.00x more
NVIDIA A16
VRAM
0.25x
A16 has 4.00x more
NVIDIA B100
VRAM
0.08x
B100 has 12.00x more
NVIDIA P40
VRAM
0.67x
P40 has 1.50x more
NVIDIA GeForce RTX 3090
VRAM
0.67x
GeForce RTX 3090 has 1.50x more
NVIDIA A100 SXM
VRAM
0.20x
A100 SXM has 5.00x more

To match 1x NVIDIA A16

AMD MI100
Compute (FP32-eq)
1.54x
Need 1.54x MI100
FP32 Compute
0.41x
MI100 is 2.43x faster
VRAM
2.00x
Need 2.00x MI100
Memory Bandwidth
0.19x
MI100 has 5.29x more
Alibaba Hanguang 800
VRAM
4.00x
Need 4.00x Hanguang 800
NVIDIA B100
Compute (FP32-eq)
0.04x
B100 is 25.28x faster
FP32 Compute
0.21x
B100 is 4.74x faster
VRAM
0.33x
B100 has 3.00x more
Memory Bandwidth
0.03x
B100 has 34.48x more
NVIDIA P40
Compute (FP32-eq)
2.97x
Need 2.97x P40
FP32 Compute
0.79x
P40 is 1.26x faster
VRAM
2.67x
Need 2.67x P40
Memory Bandwidth
0.67x
P40 has 1.49x more
NVIDIA GeForce RTX 3090
Compute (FP32-eq)
1.00x
Need 1.00x GeForce RTX 3090
FP32 Compute
0.27x
GeForce RTX 3090 is 3.75x faster
VRAM
2.67x
Need 2.67x GeForce RTX 3090
Memory Bandwidth
0.25x
GeForce RTX 3090 has 4.03x more
NVIDIA A100 SXM
Compute (FP32-eq)
0.23x
A100 SXM is 4.38x faster
FP32 Compute
0.49x
A100 SXM is 2.05x faster
VRAM
0.80x
A100 SXM has 1.25x more
Memory Bandwidth
0.11x
A100 SXM has 8.79x more

To match 1x NVIDIA B100

AMD MI100
Compute (FP32-eq)
38.96x
Need 38.96x MI100
FP32 Compute
1.95x
Need 1.95x MI100
VRAM
6.00x
Need 6.00x MI100
Memory Bandwidth
6.51x
Need 6.51x MI100
Alibaba Hanguang 800
VRAM
12.00x
Need 12.00x Hanguang 800
NVIDIA A16
Compute (FP32-eq)
25.28x
Need 25.28x A16
FP32 Compute
4.74x
Need 4.74x A16
VRAM
3.00x
Need 3.00x A16
Memory Bandwidth
34.48x
Need 34.48x A16
NVIDIA P40
Compute (FP32-eq)
75.00x
Need 75.00x P40
FP32 Compute
3.75x
Need 3.75x P40
VRAM
8.00x
Need 8.00x P40
Memory Bandwidth
23.12x
Need 23.12x P40
NVIDIA GeForce RTX 3090
Compute (FP32-eq)
25.35x
Need 25.35x GeForce RTX 3090
FP32 Compute
1.26x
Need 1.26x GeForce RTX 3090
VRAM
8.00x
Need 8.00x GeForce RTX 3090
Memory Bandwidth
8.55x
Need 8.55x GeForce RTX 3090
NVIDIA A100 SXM
Compute (FP32-eq)
5.77x
Need 5.77x A100 SXM
FP32 Compute
2.31x
Need 2.31x A100 SXM
VRAM
2.40x
Need 2.40x A100 SXM
Memory Bandwidth
3.92x
Need 3.92x A100 SXM

To match 1x NVIDIA P40

AMD MI100
Compute (FP32-eq)
0.52x
MI100 is 1.93x faster
FP32 Compute
0.52x
MI100 is 1.93x faster
VRAM
0.75x
MI100 has 1.33x more
Memory Bandwidth
0.28x
MI100 has 3.55x more
Alibaba Hanguang 800
VRAM
1.50x
Need 1.50x Hanguang 800
NVIDIA A16
Compute (FP32-eq)
0.34x
A16 is 2.97x faster
FP32 Compute
1.26x
Need 1.26x A16
VRAM
0.38x
A16 has 2.67x more
Memory Bandwidth
1.49x
Need 1.49x A16
NVIDIA B100
Compute (FP32-eq)
0.01x
B100 is 75.00x faster
FP32 Compute
0.27x
B100 is 3.75x faster
VRAM
0.13x
B100 has 8.00x more
Memory Bandwidth
0.04x
B100 has 23.12x more
NVIDIA GeForce RTX 3090
Compute (FP32-eq)
0.34x
GeForce RTX 3090 is 2.96x faster
FP32 Compute
0.34x
GeForce RTX 3090 is 2.97x faster
VRAM
1.00x
GeForce RTX 3090 has 1.00x more
Memory Bandwidth
0.37x
GeForce RTX 3090 has 2.71x more
NVIDIA A100 SXM
Compute (FP32-eq)
0.08x
A100 SXM is 13.00x faster
FP32 Compute
0.62x
A100 SXM is 1.63x faster
VRAM
0.30x
A100 SXM has 3.33x more
Memory Bandwidth
0.17x
A100 SXM has 5.89x more

To match 1x NVIDIA GeForce RTX 3090

AMD MI100
Compute (FP32-eq)
1.54x
Need 1.54x MI100
FP32 Compute
1.54x
Need 1.54x MI100
VRAM
0.75x
MI100 has 1.33x more
Memory Bandwidth
0.76x
MI100 has 1.31x more
Alibaba Hanguang 800
VRAM
1.50x
Need 1.50x Hanguang 800
NVIDIA A16
Compute (FP32-eq)
1.00x
A16 is 1.00x faster
FP32 Compute
3.75x
Need 3.75x A16
VRAM
0.38x
A16 has 2.67x more
Memory Bandwidth
4.03x
Need 4.03x A16
NVIDIA B100
Compute (FP32-eq)
0.04x
B100 is 25.35x faster
FP32 Compute
0.79x
B100 is 1.26x faster
VRAM
0.13x
B100 has 8.00x more
Memory Bandwidth
0.12x
B100 has 8.55x more
NVIDIA P40
Compute (FP32-eq)
2.96x
Need 2.96x P40
FP32 Compute
2.97x
Need 2.97x P40
VRAM
1.00x
P40 has 1.00x more
Memory Bandwidth
2.71x
Need 2.71x P40
NVIDIA A100 SXM
Compute (FP32-eq)
0.23x
A100 SXM is 4.39x faster
FP32 Compute
1.83x
Need 1.83x A100 SXM
VRAM
0.30x
A100 SXM has 3.33x more
Memory Bandwidth
0.46x
A100 SXM has 2.18x more

To match 1x NVIDIA A100 SXM

AMD MI100
Compute (FP32-eq)
6.75x
Need 6.75x MI100
FP32 Compute
0.84x
MI100 is 1.18x faster
VRAM
2.50x
Need 2.50x MI100
Memory Bandwidth
1.66x
Need 1.66x MI100
Alibaba Hanguang 800
VRAM
5.00x
Need 5.00x Hanguang 800
NVIDIA A16
Compute (FP32-eq)
4.38x
Need 4.38x A16
FP32 Compute
2.05x
Need 2.05x A16
VRAM
1.25x
Need 1.25x A16
Memory Bandwidth
8.79x
Need 8.79x A16
NVIDIA B100
Compute (FP32-eq)
0.17x
B100 is 5.77x faster
FP32 Compute
0.43x
B100 is 2.31x faster
VRAM
0.42x
B100 has 2.40x more
Memory Bandwidth
0.25x
B100 has 3.92x more
NVIDIA P40
Compute (FP32-eq)
13.00x
Need 13.00x P40
FP32 Compute
1.63x
Need 1.63x P40
VRAM
3.33x
Need 3.33x P40
Memory Bandwidth
5.89x
Need 5.89x P40
NVIDIA GeForce RTX 3090
Compute (FP32-eq)
4.39x
Need 4.39x GeForce RTX 3090
FP32 Compute
0.55x
GeForce RTX 3090 is 1.83x faster
VRAM
3.33x
Need 3.33x GeForce RTX 3090
Memory Bandwidth
2.18x
Need 2.18x GeForce RTX 3090

Pricing

Price TypeMI100Hanguang 800A16B100P40GeForce RTX 3090A100 SXM
CAPEX (Street Price)——————$15,000
OPEX (per hour)——$0.47/hr—$2.07/hr$0.11/hr$4.05/hr
Price per TFLOPs (FP32-eq)——————$96