| | | | | | |

Mobile 3020e vs A6 9220e


Description
The 3020e is based on Zen architecture while the 9220e is based on Excavator.

Using the multithread performance as a reference, the 3020e gets a score of 52.4 k points while the 9220e gets 29.4 k points.

Summarizing, the 3020e is 1.8 times faster than the 9220e. To get a proper comparison between both models, take a look to the data shown below.

Specs
CPUID
820f01
670f00
Core
Dali
Stoney Ridge
Architecture
Base frecuency
1.2 GHz
1.6 GHz
Boost frecuency
2.6 GHz
2.4 GHz
Socket
BGA 1140
BGA-FT4
Cores/Threads
2/2
2/2
TDP
6 W
6 W
Cache L1 (d+i)
2x64+2x32 kB
96+2x32 kB
Cache L2
2x512 kB
1024 kB
Cache L3
4096 kB
0 kB
Date
January 2020
June 2017
Mean monothread perf.
29.34k points
22.34k points
Mean multithread perf.
52.42k points
29.39k 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
3020e
9220e
Test#1 (Integers)
9.28k
7.84k (x0.84)
Test#2 (FP)
14.56k
10.54k (x0.72)
Test#3 (Generic, ZIP)
3.44k
2.27k (x0.66)
Test#1 (Memory)
2.06k
1.7k (x0.83)
TOTAL
29.34k
22.34k (x0.76)

Multithread

3020e

9220e
Test#1 (Integers)
15.75k
11.42k (x0.72)
Test#2 (FP)
28.63k
12.58k (x0.44)
Test#3 (Generic, ZIP)
5.87k
3.62k (x0.62)
Test#1 (Memory)
2.17k
1.77k (x0.82)
TOTAL
52.42k
29.39k (x0.56)

Performance/W
3020e
9220e
Test#1 (Integers)
2625 points/W
1903 points/W
Test#2 (FP)
4771 points/W
2097 points/W
Test#3 (Generic, ZIP)
979 points/W
603 points/W
Test#1 (Memory)
361 points/W
296 points/W
TOTAL
8737 points/W
4898 points/W

Performance/GHz
3020e
9220e
Test#1 (Integers)
3570 points/GHz
3265 points/GHz
Test#2 (FP)
5602 points/GHz
4390 points/GHz
Test#3 (Generic, ZIP)
1323 points/GHz
944 points/GHz
Test#1 (Memory)
792 points/GHz
709 points/GHz
TOTAL
11287 points/GHz
9309 points/GHz

Monothread performance graph
Monothread performance graphics gives the performance vs time. They are useful to measure the time it takes to the CPU to reach the maximum performance.

Usually, CPU's performance will be steady during these tests but if it has a slow frequency strategy, the first samples will show a lower score.


Test#1 (Integers) [points vs time]

grafica bm.hardlimit.com


Test#2 (FP) [points vs time]

grafica bm.hardlimit.com


Test#3 (Generic, ZIP) [points vs time]

grafica bm.hardlimit.com


Test#1 (Memory) [points vs time]

grafica bm.hardlimit.com

Multithread performance graph
Multithread graphs measure the performance against a heavy load during certain time.

If CPU's TDP doesn't limit the frequency and the machine is properly cooled, performance should remain steady vs time. Otherwise, the performance score will oscillate or decrease over time.


Test#1 (Integers) [points vs time]

grafica bm.hardlimit.com


Test#2 (FP) [points vs time]

grafica bm.hardlimit.com


Test#3 (Generic, ZIP) [points vs time]

grafica bm.hardlimit.com


Test#1 (Memory) [points vs time]

grafica bm.hardlimit.com

Hardlimit Benchmark Central - Ver. 3.11.4