NVIDIA GeForce RTX 4090 vs AMD Radeon Instinct MI100

VS

NVIDIA GeForce RTX 4090

AMD Radeon Instinct MI100

We compared a Desktop platform GPU: 24GB VRAM GeForce RTX 4090 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 GeForce RTX 4090 's Advantages

Released 1 years and 10 months late

Boost Clock has increased by 68% (2520MHz vs 1502MHz)

8704 additional rendering cores

AMD Radeon Instinct MI100 's Advantages

More VRAM (32GB vs 24GB)

Larger VRAM bandwidth (1229GB/s vs 1.01TB/s)

Lower TDP (300W vs 450W)

Score

Benchmark

FP32 (float)

GeForce RTX 4090 +257%

82.58 TFLOPS

Radeon Instinct MI100

23.07 TFLOPS

GeForce RTX 4090

VS

Radeon Instinct MI100

Graphics Card

Sep 2022

Release Date

Nov 2020

GeForce 40

Generation

Radeon Instinct

Desktop

Type

Professional

PCIe 4.0 x16

Bus Interface

PCIe 4.0 x16

Clock Speeds

2235 MHz

Base Clock

1000 MHz

2520 MHz

Boost Clock

1502 MHz

1313 MHz

Memory Clock

1200 MHz

Memory

24GB

Memory Size

32GB

GDDR6X

Memory Type

HBM2

384bit

Memory Bus

4096bit

1.01TB/s

Bandwidth

1229GB/s

Render Config

-

Compute Units

120

128

SM Count

-

16384

Shading Units

7680

512

TMUs

480

176

ROPs

64

512

Tensor Cores

-

128

RT Cores

-

128 KB (per SM)

L1 Cache

16 KB (per CU)

72 MB

L2 Cache

8 MB

-

Theoretical Performance

443.5 GPixel/s

Pixel Rate

96.13 GPixel/s

1290 GTexel/s

Texture Rate

721.0 GTexel/s

82.58 TFLOPS

FP16 (half)

184.6 TFLOPS

82.58 TFLOPS

FP32 (float)

23.07 TFLOPS

1290 GFLOPS

FP64 (double)

11.54 TFLOPS

Board Design

450W

TDP

300W

850 W

Suggested PSU

700 W

1x HDMI 2.13x DisplayPort 1.4a

Outputs

No outputs

1x 16-pin

Power Connectors

2x 8-pin

Graphics Processor

AD102

GPU Name

Arcturus

AD102-300-A1

GPU Variant

Arcturus XL

Ada Lovelace

Architecture

CDNA 1.0

TSMC

Foundry

TSMC

5 nm

Process Size

7 nm

76.3 billion

Transistors

25.6 billion

609 mm²

Die Size

750 mm²

Graphics Features

12 Ultimate (12_2)

DirectX

N/A

4.6

OpenGL

N/A

3.0

OpenCL

2.1

1.3

Vulkan

N/A

8.9

CUDA

-

6.8

Shader Model

N/A

Related GPU Comparisons

1

NVIDIA GeForce RTX 4090 vs NVIDIA GeForce RTX 3060 8 GB GA104

2

NVIDIA GeForce RTX 4090 vs AMD Radeon R7 265X OEM

3

NVIDIA GeForce RTX 4090 vs AMD Radeon RX Vega 64

4

NVIDIA GeForce RTX 4090 vs NVIDIA GeForce GTX 660 Rev. 2

5

NVIDIA GeForce RTX 4090 vs NVIDIA GeForce GTX 465

6

NVIDIA GeForce RTX 4090 vs ATI FireMV 2250 PCIe x1

7

NVIDIA GeForce RTX 4090 vs NVIDIA GeForce GTX 760 X2

8

NVIDIA GeForce RTX 4090 vs NVIDIA GeForce GT 1010 DDR4

9

NVIDIA GeForce RTX 4090 vs NVIDIA GeForce GTX 950

10

NVIDIA GeForce RTX 4090 vs NVIDIA T1000

Related News

1

NVIDIA GB202 Chip Unveiled for the First Time, to be Used in RTX 5090 with 512-bit GDDR7 Memory

2

Strix Halo Integrated Graphics Score Appears on Passmark, Currently Slightly Below RTX 3060 12GB

3

AMD Unveils New RX 9070 XT Graphics Card Performance: Positioned Between RX 7900 GRE and RX 7900 XT

4

Double the Excitement! AMD FSR 4.0 to Launch Alongside RX 9070 XT Graphics Card

5

CPU-Z Minor Update: Support for Intel's Four New Products and New Memory

6

CXMT Reportedly Achieves 80% Yield in DDR5 Production

7

Intel Wildcat Lake Appears on Shipping List with FCBGA1516 Socket, Poised to Replace Alder Lake-N

8

The Commencement of ARM and Qualcomm Licensing Dispute Trial: Potential Major Impact on PC Market

9

NVIDIA Allegedly Equips RTX 5080 with 30Gbps Memory Speed, Other Models to Feature 28Gbps

10

Intel Reports High Return Rates for Devices Featuring Snapdragon X Series; Qualcomm Counters with 'Industry Standard' Claim