| | | | | | |

Xeon E5-2620 v4 vs FX 8120


Description
The E5-2620 v4 is based on Broadwell architecture while the 8120 is based on Bulldozer.

Using the multithread performance as a reference, the E5-2620 v4 gets a score of 147.8 k points while the 8120 gets 70.8 k points.

Summarizing, the E5-2620 v4 is 2.1 times faster than the 8120. To get a proper comparison between both models, take a look to the data shown below.

Specs
CPUID
406f1
600f12
Core
Broadwell-EP
Zambezi
Architecture
Base frecuency
2.1 GHz
3.1 GHz
Boost frecuency
3 GHz
4 GHz
Socket
Socket 2011-3
Socket AM3+
Cores/Threads
8/16
8/8
TDP
85 W
125 W
Cache L1 (d+i)
8x32+8x32 kB
4x64+8x16 kB
Cache L2
8x256 kB
4x2048 kB
Cache L3
20480 kB
8192 kB
Date
March 2016
October 2011
Mean monothread perf.
29.39k points
23.5k points
Mean multithread perf.
237.83k points
70.78k 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
E5-2620 v4
8120
Test#1 (Integers)
6.04k
9.31k (x1.54)
Test#2 (FP)
10.18k
6.85k (x0.67)
Test#3 (Generic, ZIP)
2.74k
2.77k (x1.01)
Test#1 (Memory)
2.41k
4.58k (x1.9)
TOTAL
21.37k
23.5k (x1.1)

Multithread

E5-2620 v4

8120
Test#1 (Integers)
47.51k
25.84k (x0.54)
Test#2 (FP)
75.12k
28.49k (x0.38)
Test#3 (Generic, ZIP)
19.72k
13.84k (x0.7)
Test#1 (Memory)
5.45k
2.61k (x0.48)
TOTAL
147.8k
70.78k (x0.48)

Performance/W
E5-2620 v4
8120
Test#1 (Integers)
559 points/W
207 points/W
Test#2 (FP)
884 points/W
228 points/W
Test#3 (Generic, ZIP)
232 points/W
111 points/W
Test#1 (Memory)
64 points/W
21 points/W
TOTAL
1739 points/W
566 points/W

Performance/GHz
E5-2620 v4
8120
Test#1 (Integers)
2013 points/GHz
2327 points/GHz
Test#2 (FP)
3393 points/GHz
1712 points/GHz
Test#3 (Generic, ZIP)
915 points/GHz
693 points/GHz
Test#1 (Memory)
802 points/GHz
1144 points/GHz
TOTAL
7123 points/GHz
5876 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