Home GPU Comparison NVIDIA P102 100 vs AMD Radeon RX 480

NVIDIA P102 100 vs AMD Radeon RX 480

We compared two Desktop platform GPUs: 5GB VRAM P102 100 and 8GB VRAM Radeon RX 480 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.

Main Differences

NVIDIA P102 100 's Advantages
Released 1 years and 8 months late
Boost Clock has increased by 33% (1683MHz vs 1266MHz)
Larger VRAM bandwidth (440.3GB/s vs 256.0GB/s)
896 additional rendering cores
AMD Radeon RX 480 's Advantages
More VRAM (8GB vs 5GB)
Lower TDP (150W vs 250W)

Score

Benchmark

FP32 (float)
P102 100 +84%
10.77 TFLOPS
Radeon RX 480
5.834 TFLOPS
Blender
P102 100 +125%
844
Radeon RX 480
374
VS

Graphics Card

Feb 2018
Release Date
Jun 2016
Mining GPUs
Generation
Arctic Islands
Desktop
Type
Desktop
PCIe 3.0 x4
Bus Interface
PCIe 3.0 x16

Clock Speeds

1582 MHz
Base Clock
1120 MHz
1683 MHz
Boost Clock
1266 MHz
1376 MHz
Memory Clock
2000 MHz

Memory

5GB
Memory Size
8GB
GDDR5X
Memory Type
GDDR5
320bit
Memory Bus
256bit
440.3GB/s
Bandwidth
256.0GB/s

Render Config

25
SM Count
-
-
Compute Units
36
3200
Shading Units
2304
200
TMUs
144
80
ROPs
32
-
Tensor Cores
-
-
RT Cores
-
48 KB (per SM)
L1 Cache
16 KB (per CU)
0 MB
L2 Cache
2 MB

Theoretical Performance

134.6 GPixel/s
Pixel Rate
40.51 GPixel/s
336.6 GTexel/s
Texture Rate
182.3 GTexel/s
168.3 GFLOPS
FP16 (half)
5.834 TFLOPS
10.77 TFLOPS
FP32 (float)
5.834 TFLOPS
336.6 GFLOPS
FP64 (double)
364.6 GFLOPS

Graphics Processor

GP102
GPU Name
Ellesmere
GP102-100-A1
GPU Variant
Polaris 10 XT (215-0876184)
Pascal
Architecture
GCN 4.0
TSMC
Foundry
GlobalFoundries
16 nm
Process Size
14 nm
11.8 billion
Transistors
5.7 billion
471 mm²
Die Size
232 mm²

Board Design

250W
TDP
150W
600 W
Suggested PSU
450 W
No outputs
Outputs
1x HDMI 2.0b 3x DisplayPort 1.4a
2x 8-pin
Power Connectors
1x 6-pin

Graphics Features

12 (12_1)
DirectX
12 (12_0)
4.6
OpenGL
4.6
3.0
OpenCL
2.1
1.3
Vulkan
1.2
6.1
CUDA
-
6.4
Shader Model
6.4

Related GPU Comparisons

Related News

© 2024 - TopCPU.net   Contact Us Privacy Policy