GeekRadar / The comparison desk

COMPARE.

GPU

AMD

AMD Zhongshan Subor Z+ GPU

Graphics processor

Video memory: 8 GB^*
Memory bus: 256 bit^*
Rated memory bandwidth: 153.60 GB/s^*

No matched benchmark results are available for this entry yet.

Processing & platform

Architecture: GCN 5.0^*
Process node: 14 nm^*
GPU cores: 1,536^*
Reported GPU frequency: 1,300 MHz^*
Reported chip die area: 397 mm²^*
Chip/package TDP: 100 W^*
Graphics processor: Fenghuang^*
Texture mapping units: 96^*
Raster output units: 32^*
Chip foundry: TSMC^*
Declared GPU TDP: 100 W^*
DirectX / feature level: 12 (12_1)^*
OpenGL: 4.6^*
OpenCL: 2.1^*
Vulkan: 1.2^*
Shader model: 6.0^*

Memory & storage

Memory options: 8^*
Video memory: 8 GB^*
Video memory type: GDDR5^*
Memory bus: 256 bit^*
Rated memory bandwidth: 153.60 GB/s^*

Power specifications

Thermal design power: 100 W^*

System configuration

Detailed specifications

Specifications 1 · 12 fields

Foundry: TSMC^*
Vendor: AMD^*
FP16 GFLOPS: 7,987^* GFLOPS
FP32 GFLOPS: 3,994^* GFLOPS
FP64 GFLOPS: 249.6^* GFLOPS
Product: AMD Zhongshan Subor Z+ GPU^*
Type: GPU^*
Release Date: 2018-08-03^*
Process Size (nm): 14^* nm
TDP (W): 100^* W
Die Size (mm^2): 397^* mm²
Freq (MHz): 1,300^* MHz

Specifications 2 · 20 fields

proc die size: 397^* mm²
cores: 1,536^*
memory clock: 1,200^*
ram: 8^*
name: AMD Zhongshan Subor Z+ GPU^*
ram type: GDDR5^*
bus width: 256^*
ram bandwidth: 153.6^* GB/s
fp16 performance: 7.987^*
fp32 performance: 3.994^*
fp64 performance: 0.2496^*
tdp: 100^* W
is retail board: No^*
gpi value: 3.39^*
vendor: amd^*
manufacturer: AMD^*
arch name: GCN 5.0^*
card release date: 2018-08-03^*
proc foundry: TSMC^*
proc process size: 14^* nm

Specifications 3 · 29 fields

DirectX / feature level

12 (12_1)^*

OpenCL

2.1^*

OpenGL

4.6^*

Shader model

6.0^*

Vulkan

1.2^*

Architecture

GCN 5.0^*

Memory bus

256^* bit

Reported shader processors

1,536^*

Reported theoretical FP16 peak

7.987^* TFLOPS

Scope and conditions

Arithmetic density: Not stated^*

Reported theoretical FP32 peak

3.994^* TFLOPS

Scope and conditions

Arithmetic density: Not stated^*

Reported theoretical FP64 peak

0.2496^* TFLOPS

Scope and conditions

Arithmetic density: Not stated^*

Reported display outputs

2x HDMI 2.0^*

Theoretical pixel fill rate

41.60 GPixel/s^*

Reported chip die area

397 mm²^*

Chip foundry

TSMC^*

Process node declaration

14 nm^*

Graphics processor

Fenghuang^*

Reported video memory

8^* GB

Rated memory bandwidth

153.6 GB/s^*

Video memory type

GDDR5^*

Raster output units

32^*

Reported shading units

1,536^*

2:4 tensor sparsity

No^*

Declared GPU TDP

100 W^*

Theoretical texture fill rate

124.8 GTexel/s^*

Texture mapping units

96^*

GPU cores

1,536^*

Video memory

8^* GB

Video memory type

GDDR5^*

* Provisional data