NVIDIA H100 PCIe vs AMD Radeon Instinct MI100

VS

NVIDIA H100 PCIe AMD Radeon Instinct MI100

AI GPU We compared a GPU: 80GB VRAM H100 PCIe and a Professional market GPU: 32GB VRAM Radeon Instinct MI100 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.

Main Differences

NVIDIA H100 PCIe 's Advantages

Released 1 years and 4 months late

Boost Clock has increased by 17% (1755MHz vs 1502MHz)

More VRAM (80GB vs 32GB)

Larger VRAM bandwidth (2039GB/s vs 1229GB/s)

6912 additional rendering cores

AMD Radeon Instinct MI100 's Advantages

Lower TDP (300W vs 350W)

Score

Benchmark

FP32 (float)

H100 PCIe +122%

51.22 TFLOPS

Radeon Instinct MI100

23.07 TFLOPS

H100 PCIe

VS

Radeon Instinct MI100

Graphics Card

Mar 2022

Release Date

Nov 2020

Tesla Hopper

Generation

Radeon Instinct

AI GPU

Type

Professional

PCIe 5.0 x16

Bus Interface

PCIe 4.0 x16

Clock Speeds

1095 MHz

Base Clock

1000 MHz

1755 MHz

Boost Clock

1502 MHz

1593 MHz

Memory Clock

1200 MHz

Memory

80GB

Memory Size

32GB

HBM2e

Memory Type

HBM2

5120bit

Memory Bus

4096bit

2039GB/s

Bandwidth

1229GB/s

Render Config

114

SM Count

-

Compute Units

120

14592

Shading Units

7680

456

TMUs

480

24

ROPs

64

456

Tensor Cores

-

RT Cores

-

256 KB (per SM)

L1 Cache

16 KB (per CU)

50 MB

L2 Cache

8 MB

Theoretical Performance

42.12 GPixel/s

Pixel Rate

96.13 GPixel/s

800.3 GTexel/s

Texture Rate

721.0 GTexel/s

204.9 TFLOPS

FP16 (half)

184.6 TFLOPS

51.22 TFLOPS

FP32 (float)

23.07 TFLOPS

25.61 TFLOPS

FP64 (double)

11.54 TFLOPS

Graphics Processor

GH100

GPU Name

Arcturus

-

GPU Variant

Arcturus XL

Hopper

Architecture

CDNA 1.0

TSMC

Foundry

TSMC

4 nm

Process Size

7 nm

80 billion

Transistors

25.6 billion

814 mm²

Die Size

750 mm²

Board Design

350W

TDP

300W

750 W

Suggested PSU

700 W

No outputs

Outputs

No outputs

1x 16-pin

Power Connectors

2x 8-pin

Graphics Features

N/A

DirectX

N/A

OpenGL

N/A

3.0

OpenCL

2.1

N/A

Vulkan

N/A

9.0

CUDA

-

N/A

Shader Model

N/A

Related GPU Comparisons

1

NVIDIA H100 PCIe vs NVIDIA A100 PCIe

2

NVIDIA H100 PCIe vs NVIDIA RTX A6000

3

NVIDIA L40 vs NVIDIA H100 PCIe

4

NVIDIA H100 PCIe vs NVIDIA L4

5

AMD Radeon Instinct MI300 vs NVIDIA H100 PCIe

6

NVIDIA Tesla P100 PCIe 16 GB vs NVIDIA H100 PCIe

7

AMD Radeon Instinct MI60 vs AMD Radeon Instinct MI100

8

NVIDIA H100 PCIe vs NVIDIA A800 PCIe 80 GB

9

NVIDIA H100 PCIe vs NVIDIA H100 PCIe 80 GB

10

NVIDIA H100 PCIe vs NVIDIA H100 PCIe 96 GB