| | | | | | |

Engineering Sample 506E8 vs Core i3-8130U


Description
Both models 506E8 and i3-8130U are based on Kaby Lake architecture.

The first Kaby Lake CPU was released in August 2016. It uses a 14 nm process and was the first architecture in breaking the previous tick-tock model. Actually, it is not that different from the preceding Skylake: it has 64kB of L1 cache and 256kB L2 cache per core.

Using the multithread performance as a reference, the 506E8 gets a score of 211.6 k points while the i3-8130U gets 88.3 k points.

Summarizing, the 506E8 is 2.4 times faster than the i3-8130U. To get a proper comparison between both models, take a look to the data shown below.

Specs
CPUID
506e8
806ea
Core
Kaby Lake
Kaby Lake-R
Architecture
Base frecuency
2.4 GHz
2.2 GHz
Boost frecuency
3.7 GHz
3.4 GHz
Socket
LGA 1151
BGA 1356
Cores/Threads
4/8
2/4
TDP
- W
15 W
Cache L1 (d+i)
4x32+4x32 kB
2x32+2x32 kB
Cache L2
4x256 kB
2x256 kB
Cache L3
8192 kB
4096 kB
Date
June 2016
February 2018
Mean monothread perf.
56.39k points
47.35k points
Mean multithread perf.
211.6k points
88.35k points

AVX2 optimized benchmark
The benchmark in mode III (AVX2), like AVX1, is optimized to used 256 bits registers beside the second version of the Advanced Vector Extensions (AVX). The first AVX2 compatible CPU was released in 2013.
Monothread
506E8
i3-8130U
Test#1 (Integers)
23.91k
21.09k (x0.88)
Test#2 (FP)
21.03k
19.41k (x0.92)
Test#3 (Generic, ZIP)
5.05k
4.05k (x0.8)
Test#1 (Memory)
6.4k
2.8k (x0.44)
TOTAL
56.39k
47.35k (x0.84)

Multithread

506E8

i3-8130U
Test#1 (Integers)
95.3k
38.23k (x0.4)
Test#2 (FP)
91.94k
38.89k (x0.42)
Test#3 (Generic, ZIP)
22.06k
8.75k (x0.4)
Test#1 (Memory)
2.3k
2.47k (x1.07)
TOTAL
211.6k
88.35k (x0.42)

Performance/W
506E8
i3-8130U
Test#1 (Integers)