| | | | | | |

Ryzen 9 5950X vs 3900


Description
The 5950X is based on Zen 3 architecture while the 3900 is based on Zen 2.

Using the multithread performance as a reference, the 5950X gets a score of 1081 k points while the 3900 gets 687.5 k points.

Summarizing, the 5950X is 1.6 times faster than the 3900. To get a proper comparison between both models, take a look to the data shown below.

Specs
CPUID
a20f10
870f10
Core
Vermeer
Matisse
Architecture
Base frecuency
3.4 GHz
3.1 GHz
Boost frecuency
4.9 GHz
4.3 GHz
Socket
AM4
AM4
Cores/Threads
16/32
12/24
TDP
105 W
65 W
Cache L1 (d+i)
16x32+16x32 kB
12x32+12x32 kB
Cache L2
16x512 kB
12x512 kB
Cache L3
2x32768 kB
4x16384 kB
Date
November 2020
September 2019
Mean monothread perf.
87.3k points
74.97k points
Mean multithread perf.
1080.96k 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
5950X
3900
Test#1 (Integers)
22.91k
16.85k (x0.74)
Test#2 (FP)
26.24k
26.03k (x0.99)
Test#3 (Generic, ZIP)
11.87k
9.54k (x0.8)
Test#1 (Memory)
26.28k
22.55k (x0.86)
TOTAL
87.3k
74.97k (x0.86)

Multithread

5950X

3900
Test#1 (Integers)
359.17k
229.41k (x0.64)
Test#2 (FP)
479.04k
292.81k (x0.61)
Test#3 (Generic, ZIP)
214.59k
128.48k (x0.6)
Test#1 (Memory)
28.16k
36.8k (x1.31)
TOTAL
1080.96k
687.5k (x0.64)

Performance/W
5950X
3900
Test#1 (Integers)
3421 points/W
3529 points/W
Test#2 (FP)
4562 points/W
4505 points/W
Test#3 (Generic, ZIP)
2044 points/W
1977 points/W
Test#1 (Memory)
268 points/W
566 points/W
TOTAL
10295 points/W
10577 points/W

Performance/GHz
5950X
3900
Test#1 (Integers)
4676 points/GHz
3920 points/GHz
Test#2 (FP)
5355 points/GHz
6054 points/GHz
Test#3 (Generic, ZIP)
2423 points/GHz
2218 points/GHz
Test#1 (Memory)
5363 points/GHz
5243 points/GHz
TOTAL
17817 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