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 A4000

CORE STATE GA104

VRAM 16 GB

CLOCK SPEED 1560 MHz

TDP 140 W

BUS WIDTH 256 bit

ARCHITECTURE Ampere

nm

PROCESS 8 nm

LAUNCH DATE 2021

PERFORMANCE BENCHMARKS

geekbench_opencl

317,994

105,739

3dmark_3dmark_steel_nomad_dx12

N/A

2,604

geekbench_vulkan

N/A

127,645

passmark_directx_10

N/A

126

passmark_directx_11

N/A

158

passmark_directx_12

N/A

72

passmark_directx_9

N/A

240

passmark_g2d

N/A

1,024

passmark_g3d

N/A

19,459

passmark_gpu_compute

N/A

9,760

DETAILED SPECIFICATIONS

SPECIFICATION

Instinct MI300X

RTX A4000

Core Specs

Shading Units

19,456

6,144 -68.4%

Shaders

19,456

6,144 -68.4%

TMUs

1,216

192 -84.2%

ROPs

0

96 +∞%

Compute Units

304

—

SM Count

—

48

Clocks

Base Clock

1000 MHz

735 MHz

Boost Clock

2100 MHz

1560 MHz

Memory Clock

1300 MHz 5.2 Gbps effective

1750 MHz 14 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

256 bit

Bandwidth

5.32 TB/s

448.0 GB/s

Cache

L1 Cache

16 KB (per CU)

128 KB (per SM)

L2 Cache

16 MB

4 MB

L3 Cache

256 MB

—

Performance

Pixel Rate

0 MPixel/s

149.8 GPixel/s

Texture Rate

2,553.6 GTexel/s

299.5 GTexel/s

FP32 (TFLOPS)

81.72 TFLOPS

19.17 TFLOPS

FP64 (TFLOPS)

40.86 TFLOPS (1:2)

299.5 GFLOPS (1:64)

FP16 (TFLOPS)

81.72 TFLOPS (1:1)

19.17 TFLOPS (1:1)

AI/RT

RT Cores

—

48

Tensor Cores

—

192

Matrix Cores

1,216

—

Power

TDP

750 W

140 W

TDP (W)

750

140 -81.3%

Suggested PSU

1150 W

300 W

Power Connectors

None

1x 6-pin

Architecture

Architecture

CDNA 3.0

Ampere

GPU Name

Aqua Vanjaram

GA104

Generation

Instinct (MIx)

Workstation Ampere (Ax000)

Process Size

5 nm

8 nm

Transistors

153,000 million

17,400 million

Die Size

1017 mm²

392 mm²

Foundry

TSMC

Samsung

Density

150.4M / mm²

44.4M / mm²

AMD MCM

MCM

2

—

API Support

DirectX

—

12 Ultimate (12_2)

OpenGL

—

4.6

Vulkan

—

1.4

OpenCL

3.0

3.0

CUDA

—

8.6

Shader Model

—

6.8

Physical

Slot Width

OAM Module

Single-slot

Length

—

241 mm 9.5 inches

Height

—

112 mm 4.4 inches

Outputs

No outputs

4x DisplayPort 1.4a

Bus Interface

PCIe 5.0 x16

PCIe 4.0 x16

Other

Production

—

End-of-life

Predecessor

Radeon Instinct

Quadro Turing

Successor

—

Workstation Ada

View Instinct MI300X Details View RTX A4000 Details