GPU Comparison

A

AMD

RADEON

AMD Instinct MI300X

CORE STATE Aqua Vanjaram

VRAM 192 GB

CLOCK SPEED 2100 MHz

TDP 750 W

BUS WIDTH 8192 bit

ARCHITECTURE CDNA 3.0

nm

PROCESS 5 nm

LAUNCH DATE 2023

VS

NVIDIA

GEFORCE

GeForce RTX 4090

CORE STATE AD102

VRAM 24 GB

CLOCK SPEED 2520 MHz

TDP 450 W

BUS WIDTH 384 bit

ARCHITECTURE Ada Lovelace

nm

PROCESS 5 nm

LAUNCH DATE 2022

PERFORMANCE BENCHMARKS

geekbench_opencl

317,994

255,416

3dmark_3dmark_steel_nomad_dx12

N/A

9,223

geekbench_vulkan

N/A

271,631

passmark_directx_10

N/A

224

passmark_directx_11

N/A

326

passmark_directx_12

N/A

150

passmark_directx_9

N/A

397

passmark_g2d

N/A

1,299

passmark_g3d

N/A

38,194

passmark_gpu_compute

N/A

26,613

DETAILED SPECIFICATIONS

SPECIFICATION

Instinct MI300X

RTX 4090

Core Specs

Shading Units

19,456

16,384 -15.8%

Shaders

19,456

16,384 -15.8%

TMUs

1,216

512 -57.9%

ROPs

0

176 +∞%

Compute Units

304

—

SM Count

—

128

Clocks

Base Clock

1000 MHz

2235 MHz

Boost Clock

2100 MHz

2520 MHz

Memory Clock

1300 MHz 5.2 Gbps effective

1313 MHz 21 Gbps effective

Memory

Memory Size

192 GB

24 GB

VRAM (MB)

196,608

24,576 -87.5%

Memory Type

HBM3

GDDR6X

Memory Bus

8192 bit

384 bit

Bandwidth

5.32 TB/s

1.01 TB/s

Cache

L1 Cache

16 KB (per CU)

128 KB (per SM)

L2 Cache

16 MB

72 MB

L3 Cache

256 MB

—

Performance

Pixel Rate

0 MPixel/s

443.5 GPixel/s

Texture Rate

2,553.6 GTexel/s

1,290.2 GTexel/s

FP32 (TFLOPS)

81.72 TFLOPS

82.58 TFLOPS

FP64 (TFLOPS)

40.86 TFLOPS (1:2)

1,290.2 GFLOPS (1:64)

FP16 (TFLOPS)

81.72 TFLOPS (1:1)

82.58 TFLOPS (1:1)

AI/RT

RT Cores

—

128

Tensor Cores

—

512

Matrix Cores

1,216

—

Power

TDP

750 W

450 W

TDP (W)

750

450 -40.0%

Suggested PSU

1150 W

850 W

Power Connectors

None

1x 16-pin

Architecture

Architecture

CDNA 3.0

Ada Lovelace

GPU Name

Aqua Vanjaram

AD102

Generation

Instinct (MIx)

GeForce 40

Process Size

5 nm

5 nm

Transistors

153,000 million

76,300 million

Die Size

1017 mm²

609 mm²

Foundry

TSMC

TSMC

Density

150.4M / mm²

125.3M / mm²

AMD MCM

MCM

2

—

API Support

DirectX

—

12 Ultimate (12_2)

OpenGL

—

4.6

Vulkan

—

1.4

OpenCL

3.0

3.0

CUDA

—

8.9

Shader Model

—

6.8

Physical

Slot Width

OAM Module

Triple-slot

Length

—

304 mm 12 inches

Height

—

137 mm 5.4 inches

Outputs

No outputs

1x HDMI 2.13x DisplayPort 1.4a

Bus Interface

PCIe 5.0 x16

PCIe 4.0 x16

Other

Launch Price

—

1,599 USD

Production

—

End-of-life

Predecessor

Radeon Instinct

GeForce 30

Successor

—

GeForce 50

View Instinct MI300X Details View GeForce RTX 4090 Details