GPU Comparison

A

AMD

RADEON

AMD Radeon Pro W5500

CORE STATE Navi 14

VRAM 8 GB

CLOCK SPEED 1855 MHz

TDP 125 W

BUS WIDTH 128 bit

ARCHITECTURE RDNA 1.0

nm

PROCESS 7 nm

LAUNCH DATE 2020

VS

NVIDIA

GEFORCE

B200

CORE STATE GB100

VRAM 90 GB

CLOCK SPEED 1965 MHz

TDP 1000 W

BUS WIDTH 4096 bit

ARCHITECTURE Blackwell

nm

PROCESS 5 nm

LAUNCH DATE —

PERFORMANCE BENCHMARKS

geekbench_metal

54,302

N/A

geekbench_opencl

45,615

345,482

geekbench_vulkan

42,021

N/A

passmark_directx_10

47

N/A

passmark_directx_11

56

N/A

passmark_directx_12

39

N/A

passmark_directx_9

126

N/A

passmark_g2d

806

N/A

passmark_g3d

8,978

N/A

passmark_gpu_compute

4,804

N/A

DETAILED SPECIFICATIONS

SPECIFICATION

Pro W5500

B200

Core Specs

Shading Units

1,408

18,944 +1245.5%

Shaders

1,408

18,944 +1245.5%

TMUs

88

592 +572.7%

ROPs

32

24 -25.0%

Compute Units

22

—

SM Count

—

148

Clocks

Base Clock

1744 MHz

700 MHz

Boost Clock

1855 MHz

1965 MHz

Memory Clock

1750 MHz 14 Gbps effective

2000 MHz 8 Gbps effective

Memory

Memory Size

8 GB

90 GB

VRAM (MB)

8,192

92,160 +1025.0%

Memory Type

GDDR6

HBM3e

Memory Bus

128 bit

4096 bit

Bandwidth

224.0 GB/s

4.10 TB/s

Cache

L1 Cache

—

256 KB (per SM)

L2 Cache

2 MB

50 MB

Performance

Pixel Rate

59.36 GPixel/s

47.16 GPixel/s

Texture Rate

163.2 GTexel/s

1,163.3 GTexel/s

FP32 (TFLOPS)

5.224 TFLOPS

74.45 TFLOPS

FP64 (TFLOPS)

326.5 GFLOPS (1:16)

37.22 TFLOPS (1:2)

FP16 (TFLOPS)

10.45 TFLOPS (2:1)

1,191.2 TFLOPS (16:1)

AI/RT

Tensor Cores

—

592

Power

TDP

125 W

1000 W

TDP (W)

125

1,000 +700.0%

Suggested PSU

300 W

1400 W

Power Connectors

1x 6-pin

—

Architecture

Architecture

RDNA 1.0

Blackwell

GPU Name

Navi 14

GB100

Generation

Radeon Pro Navi (Navi Series)

Server Blackwell (Bxx)

Process Size

7 nm

5 nm

Transistors

6,400 million

104,000 million

Die Size

158 mm²

—

Foundry

TSMC

TSMC

Density

40.5M / mm²

—

API Support

DirectX

12 (12_1)

—

OpenGL

4.6

—

Vulkan

1.4

—

OpenCL

2.1

3.0

CUDA

—

10.0

Shader Model

6.8

—

Physical

Slot Width

Single-slot

SXM Module

Length

241 mm 9.5 inches

—

Height

111 mm 4.4 inches

—

Outputs

4x DisplayPort 1.4a

No outputs

Bus Interface

PCIe 4.0 x8

PCIe 5.0 x16

Other

Launch Price

399 USD

—

Production

End-of-life

Active

Predecessor

Radeon Pro Vega

Server Hopper

Successor

—

Server Rubin

View Radeon Pro W5500 Details View B200 Details