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

RTX 2000 Ada Generation

CORE STATE AD107

VRAM 16 GB

CLOCK SPEED 2130 MHz

TDP 70 W

BUS WIDTH 128 bit

ARCHITECTURE Ada Lovelace

nm

PROCESS 5 nm

LAUNCH DATE 2024

PERFORMANCE BENCHMARKS

geekbench_opencl

317,994

78,074

3dmark_3dmark_steel_nomad_dx12

N/A

1,767

geekbench_vulkan

N/A

83,360

passmark_directx_10

N/A

82

passmark_directx_11

N/A

138

passmark_directx_12

N/A

71

passmark_directx_9

N/A

216

passmark_g2d

N/A

1,072

passmark_g3d

N/A

16,927

passmark_gpu_compute

N/A

7,834

DETAILED SPECIFICATIONS

SPECIFICATION

Instinct MI300X

RTX 2000 Ada Generation

Core Specs

Shading Units

19,456

2,816 -85.5%

Shaders

19,456

2,816 -85.5%

TMUs

1,216

88 -92.8%

ROPs

0

48 +∞%

Compute Units

304

—

SM Count

—

22

Clocks

Base Clock

1000 MHz

1620 MHz

Boost Clock

2100 MHz

2130 MHz

Memory Clock

1300 MHz 5.2 Gbps effective

2000 MHz 16 Gbps effective

Memory

Memory Size

192 GB

16 GB

VRAM (MB)

196,608

16,384 -91.7%

Memory Type

HBM3

GDDR6

Memory Bus

8192 bit

128 bit

Bandwidth

5.32 TB/s

256.0 GB/s

Cache

L1 Cache

16 KB (per CU)

128 KB (per SM)

L2 Cache

16 MB

12 MB

L3 Cache

256 MB

—

Performance

Pixel Rate

0 MPixel/s

102.2 GPixel/s

Texture Rate

2,553.6 GTexel/s

187.4 GTexel/s

FP32 (TFLOPS)

81.72 TFLOPS

12.00 TFLOPS

FP64 (TFLOPS)

40.86 TFLOPS (1:2)

187.4 GFLOPS (1:64)

FP16 (TFLOPS)

81.72 TFLOPS (1:1)

12.00 TFLOPS (1:1)

AI/RT

RT Cores

—

22

Tensor Cores

—

88

Matrix Cores

1,216

—

Power

TDP

750 W

70 W

TDP (W)

750

70 -90.7%

Suggested PSU

1150 W

250 W

Power Connectors

None

None

Architecture

Architecture

CDNA 3.0

Ada Lovelace

GPU Name

Aqua Vanjaram

AD107

Generation

Instinct (MIx)

Workstation Ada (x000A)

Process Size

5 nm

5 nm

Transistors

153,000 million

18,900 million

Die Size

1017 mm²

159 mm²

Foundry

TSMC

TSMC

Density

150.4M / mm²

118.9M / 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

—

6.9

Physical

Slot Width

OAM Module

Dual-slot

Length

—

168 mm 6.6 inches

Height

—

69 mm 2.7 inches

Outputs

No outputs

4x mini-DisplayPort 1.4a

Bus Interface

PCIe 5.0 x16

PCIe 4.0 x8

Other

Launch Price

—

649 USD

Production

—

Active

Predecessor

Radeon Instinct

Workstation Ampere

Successor

—

Blackwell PRO W

View Instinct MI300X Details View RTX 2000 Ada Generation Details