GPU Comparison

A

AMD

RADEON

AMD Radeon Instinct MI200

CORE STATE Aldebaran

VRAM 64 GB

CLOCK SPEED 1700 MHz

TDP 300 W

BUS WIDTH 4096 bit

ARCHITECTURE CDNA 2.0

nm

PROCESS 6 nm

LAUNCH DATE —

VS

NVIDIA

GEFORCE

GeForce RTX 4070 SUPER

CORE STATE AD104

VRAM 12 GB

CLOCK SPEED 2475 MHz

TDP 220 W

BUS WIDTH 192 bit

ARCHITECTURE Ada Lovelace

nm

PROCESS 5 nm

LAUNCH DATE 2024

PERFORMANCE BENCHMARKS

3dmark_3dmark_steel_nomad_dx12

N/A

4,627

geekbench_opencl

N/A

192,684

geekbench_vulkan

N/A

179,271

passmark_directx_10

N/A

167

passmark_directx_11

N/A

273

passmark_directx_12

N/A

110

passmark_directx_9

N/A

344

passmark_g2d

N/A

1,184

passmark_g3d

N/A

29,995

passmark_gpu_compute

N/A

17,108

DETAILED SPECIFICATIONS

SPECIFICATION

Instinct MI200

RTX 4070 SUPER

Core Specs

Shading Units

6,656

7,168 +7.7%

Shaders

6,656

7,168 +7.7%

TMUs

416

224 -46.2%

ROPs

0

80 +∞%

Compute Units

104

—

SM Count

—

56

Clocks

Base Clock

1000 MHz

1980 MHz

Boost Clock

1700 MHz

2475 MHz

Memory Clock

1600 MHz 3.2 Gbps effective

1313 MHz 21 Gbps effective

Memory

Memory Size

64 GB

12 GB

VRAM (MB)

65,536

12,288 -81.3%

Memory Type

HBM2e

GDDR6X

Memory Bus

4096 bit

192 bit

Bandwidth

1.64 TB/s

504.2 GB/s

Cache

L1 Cache

16 KB (per CU)

128 KB (per SM)

L2 Cache

16 MB

48 MB

Performance

Pixel Rate

0 MPixel/s

198.0 GPixel/s

Texture Rate

707.2 GTexel/s

554.4 GTexel/s

FP32 (TFLOPS)

22.63 TFLOPS

35.48 TFLOPS

FP64 (TFLOPS)

22.63 TFLOPS (1:1)

554.4 GFLOPS (1:64)

FP16 (TFLOPS)

181.0 TFLOPS (8:1)

35.48 TFLOPS (1:1)

AI/RT

RT Cores

—

56

Tensor Cores

—

224

Power

TDP

300 W

220 W

TDP (W)

300

220 -26.7%

Suggested PSU

700 W

550 W

Power Connectors

1x 8-pin

1x 16-pin

Architecture

Architecture

CDNA 2.0

Ada Lovelace

GPU Name

Aldebaran

AD104

Generation

Radeon Instinct (MIx)

GeForce 40

Process Size

6 nm

5 nm

Transistors

58,200 million

35,800 million

Die Size

724 mm²

294 mm²

Foundry

TSMC

TSMC

Density

80.4M / mm²

121.8M / mm²

AMD MCM

MCM

1

—

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

Dual-slot

Length

—

267 mm 10.5 inches

Height

—

112 mm 4.4 inches

Outputs

No outputs

1x HDMI 2.13x DisplayPort 1.4a

Bus Interface

PCIe 4.0 x16

PCIe 4.0 x16

Other

Launch Price

—

599 USD

Production

End-of-life

End-of-life

Predecessor

FirePro Data Center

GeForce 30

Successor

—

GeForce 50

View Radeon Instinct MI200 Details View GeForce RTX 4070 SUPER Details