| | | | | | |

Ryzen 5 3500U vs Xeon E5-2620


Description
The 3500U is based on Zen+ architecture while the E5-2620 is based on Sandy Bridge.

Using the multithread performance as a reference, the 3500U gets a score of 146.6 k points while the E5-2620 gets 224.7 k points.

Summarizing, the E5-2620 is 1.5 times faster than the 3500U. To get a proper comparison between both models, take a look to the data shown below.

Specs
CPUID
810f81
206d7
Core
Picasso
Sandy Bridge-EP
Architecture
Base frecuency
2.1 GHz
2 GHz
Boost frecuency
3.7 GHz
2.5 GHz
Socket
BGA-FP5
LGA 2011
Cores/Threads
4/8
6/12
TDP
15 W
95 W
Cache L1 (d+i)
4x64+6x32 kB
6x32+6x32 kB
Cache L2
4x512 kB
6x256 kB
Cache L3
4096 kB
15360 kB
Date
January 2019
March 2012
Mean monothread perf.
36.64k points
18.8k points
Mean multithread perf.
140.97k points
224.7k points

AVX optimized benchmark
The benchmark in mode II (AVX) is optimized to used 256 bits registers beside the first version of the Advanced Vector Extensions (AVX). The first AVX compatible CPU was released in 2011.
Monothread
3500U
E5-2620
Test#1 (Integers)
11.1k
6.95k (x0.63)
Test#2 (FP)
18.97k
6.24k (x0.33)
Test#3 (Generic, ZIP)
3.9k
3.05k (x0.78)
Test#1 (Memory)
3.39k
2.56k (x0.76)
TOTAL
37.37k
18.8k (x0.5)

Multithread

3500U

E5-2620
Test#1 (Integers)
45.74k
90.01k (x1.97)
Test#2 (FP)
75.47k
82.43k (x1.09)
Test#3 (Generic, ZIP)
21.89k
42.59k (x1.95)
Test#1 (Memory)
3.49k
9.66k (x2.76)
TOTAL
146.6k
224.7k (x1.53)

Performance/W
3500U
E5-2620
Test#1 (Integers)
3049 points/W
948 points/W
Test#2 (FP)
5032 points/W
868 points/W
Test#3 (Generic, ZIP)
1459 points/W
448 points/W
Test#1 (Memory)
233 points/W
102 points/W
TOTAL
9773 points/W
2365 points/W

Performance/GHz
3500U
E5-2620
Test#1 (Integers)
3001 points/GHz
2780 points/GHz
Test#2 (FP)
5128 points/GHz
2494 points/GHz
Test#3 (Generic, ZIP)
1053 points/GHz
1220 points/GHz
Test#1 (Memory)
916 points/GHz
1024 points/GHz
TOTAL
10099 points/GHz
7519 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