| | | | | | |

Ryzen 9 3950X vs 5950X


Description
The 3950X is based on Zen 2 architecture while the 5950X is based on Zen 3.

Using the multithread performance as a reference, the 3950X gets a score of 959.8 k points while the 5950X gets 1081 k points.

Summarizing, the 5950X is 1.1 times faster than the 3950X. To get a proper comparison between both models, take a look to the data shown below.

Specs
CPUID
870f10
a20f10
Core
Matisse
Vermeer
Architecture
Base frecuency
3.5 GHz
3.4 GHz
Boost frecuency
4.7 GHz
4.9 GHz
Socket
AM4
AM4
Cores/Threads
16/32
16/32
TDP
105 W
105 W
Cache L1 (d+i)
16x32+16x32 kB
16x32+16x32 kB
Cache L2
16x512 kB
16x512 kB
Cache L3
4x16384 kB
2x32768 kB
Date
November 2019
November 2020
Mean monothread perf.
72.95k points
87.3k points
Mean multithread perf.
959.77k points
1080.96k 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
3950X
5950X
Test#1 (Integers)
16.49k
22.91k (x1.39)
Test#2 (FP)
26.16k
26.24k (x1)
Test#3 (Generic, ZIP)
7.9k
11.87k (x1.5)
Test#1 (Memory)
22.4k
26.28k (x1.17)
TOTAL
72.95k
87.3k (x1.2)

Multithread

3950X

5950X
Test#1 (Integers)
334.49k
359.17k (x1.07)
Test#2 (FP)
423.74k
479.04k (x1.13)
Test#3 (Generic, ZIP)
187.85k
214.59k (x1.14)
Test#1 (Memory)
13.69k
28.16k (x2.06)
TOTAL
959.77k
1080.96k (x1.13)

Performance/W
3950X
5950X
Test#1 (Integers)
3186 points/W
3421 points/W
Test#2 (FP)
4036 points/W
4562 points/W
Test#3 (Generic, ZIP)
1789 points/W
2044 points/W
Test#1 (Memory)
130 points/W
268 points/W
TOTAL
9141 points/W
10295 points/W

Performance/GHz
3950X
5950X
Test#1 (Integers)
3509 points/GHz
4676 points/GHz
Test#2 (FP)
5566 points/GHz
5355 points/GHz
Test#3 (Generic, ZIP)
1681 points/GHz
2423 points/GHz
Test#1 (Memory)
4765 points/GHz
5363 points/GHz
TOTAL
15522 points/GHz
17817 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