GPU Comparison

A

AMD

RADEON

AMD Radeon Instinct MI300

CORE STATE Aqua Vanjaram

VRAM 128 GB

CLOCK SPEED 1700 MHz

TDP 600 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

3dmark_3dmark_steel_nomad_dx12

N/A

9,223

geekbench_opencl

N/A

317,684

geekbench_vulkan

N/A

270,615

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 MI300

RTX 4090

Core Specs

Shading Units

14,080

16,384 +16.4%

Shaders

14,080

16,384 +16.4%

TMUs

880

512 -41.8%

ROPs

0

176 +∞%

Compute Units

220

—

SM Count

—

128

Clocks

Base Clock

1000 MHz

2235 MHz

Boost Clock

1700 MHz

2520 MHz

Memory Clock

1600 MHz 6.4 Gbps effective

1313 MHz 21 Gbps effective

Memory

Memory Size

128 GB

24 GB

VRAM (MB)

131,072

24,576 -81.3%

Memory Type

HBM3

GDDR6X

Memory Bus

8192 bit

384 bit

Bandwidth

6.55 TB/s

1.01 TB/s

Cache

L1 Cache

16 KB (per CU)

128 KB (per SM)

L2 Cache

16 MB

72 MB

Performance

Pixel Rate

0 MPixel/s

443.5 GPixel/s

Texture Rate

1,496.0 GTexel/s

1,290.2 GTexel/s

FP32 (TFLOPS)

47.87 TFLOPS

82.58 TFLOPS

FP64 (TFLOPS)

47.87 TFLOPS (1:1)

1,290.2 GFLOPS (1:64)

FP16 (TFLOPS)

383.0 TFLOPS (8:1)

82.58 TFLOPS (1:1)

AI/RT

RT Cores

—

128

Tensor Cores

—

512

Matrix Cores

880

—

Power

TDP

600 W

450 W

TDP (W)

600

450 -25.0%

Suggested PSU

1000 W

850 W

Power Connectors

2x 8-pin

1x 16-pin

Architecture

Architecture

CDNA 3.0

Ada Lovelace

GPU Name

Aqua Vanjaram

AD102

Generation

Radeon 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

—

Triple-slot

Length

267 mm 10.5 inches

304 mm 12 inches

Height

111 mm 4.4 inches

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

FirePro Data Center

GeForce 30

Successor

—

GeForce 50

View Radeon Instinct MI300 Details View GeForce RTX 4090 Details