| | | | | | |

Xeon E5-2680 v4 vs Ryzen 9 3900


Description
The E5-2680 v4 is based on Broadwell architecture while the 3900 is based on Zen 2.

Using the multithread performance as a reference, the E5-2680 v4 gets a score of 1162.6 k points while the 3900 gets 687.5 k points.

Summarizing, the E5-2680 v4 is 1.7 times faster than the 3900. To get a proper comparison between both models, take a look to the data shown below.

Specs
CPUID
406f1
870f10
Core
Broadwell-EP
Matisse
Architecture
Base frecuency
2.4 GHz
3.1 GHz
Boost frecuency
3.3 GHz
4.3 GHz
Socket
LGA 2011-3
AM4
Cores/Threads
14/28
12/24
TDP
120 W
65 W
Cache L1 (d+i)
14x32+14x32 kB
12x32+12x32 kB
Cache L2
14x256 kB
12x512 kB
Cache L3
35840 kB
4x16384 kB
Date
March 2016
September 2019
Mean monothread perf.
41.35k points
74.97k points
Mean multithread perf.
1162.63k points
687.5k 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
E5-2680 v4
3900
Test#1 (Integers)
17.8k
16.85k (x0.95)
Test#2 (FP)
16.51k
26.03k (x1.58)
Test#3 (Generic, ZIP)
4.47k
9.54k (x2.13)
Test#1 (Memory)
2.56k
22.55k (x8.8)
TOTAL
41.35k
74.97k (x1.81)

Multithread

E5-2680 v4

3900
Test#1 (Integers)
494.82k
229.41k (x0.46)
Test#2 (FP)
514.13k
292.81k (x0.57)
Test#3 (Generic, ZIP)
132.87k
128.48k (x0.97)
Test#1 (Memory)
20.8k
36.8k (x1.77)
TOTAL
1162.63k
687.5k (x0.59)

Performance/W
E5-2680 v4
3900
Test#1 (Integers)
4124 points/W
3529 points/W
Test#2 (FP)
4284 points/W
4505 points/W
Test#3 (Generic, ZIP)
1107 points/W
1977 points/W
Test#1 (Memory)
173 points/W
566 points/W
TOTAL
9689 points/W
10577 points/W

Performance/GHz
E5-2680 v4
3900
Test#1 (Integers)
5393 points/GHz
3920 points/GHz
Test#2 (FP)
5004 points/GHz
6054 points/GHz
Test#3 (Generic, ZIP)
1355 points/GHz
2218 points/GHz
Test#1 (Memory)
777 points/GHz
5243 points/GHz
TOTAL
12529 points/GHz
17435 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