| | | | | | |

Ryzen 5 3600 vs Ryzen 9 7950X


Description
The 3600 is based on Zen 2 architecture while the 7950X is based on Zen 4.

Using the multithread performance as a reference, the 3600 gets a score of 348.4 k points while the 7950X gets 1597.8 k points.

Summarizing, the 7950X is 4.6 times faster than the 3600. To get a proper comparison between both models, take a look to the data shown below.

Specs
CPUID
870f10
a60f12
Core
Matisse
Raphael
Architecture
Zen 2
Base frecuency
3.6 GHz
4.5 GHz
Boost frecuency
4.2 GHz
5.7 GHz
Socket
AM4
AM5
Cores/Threads
6/12
16/32
TDP
65 W
170 W
Cache L1 (d+i)
6x32+6x32 kB
16x32+16x32 kB
Cache L2
6x512 kB
16x1024 kB
Cache L3
32768 kB
131072 kB
Date
July 2019
September 2022
Mean monothread perf.
70.55k points
121.33k points
Mean multithread perf.
348.35k points
1597.79k points

Non-optimized benchmark
The benchmark in Mode 0 (FPU) measures cpu performance with non-optimized software. It uses the basic µinstructions from the i386 architecture with the i387 floating point unit. This mode is compatible with all CPUs so it's practical to compare very different CPUs
Monothread
3600
7950X
Test#1 (Integers)
4.2k
6.05k (x1.44)
Test#2 (FP)
17.36k
23.41k (x1.35)
Test#3 (Generic, ZIP)
7.5k
16.49k (x2.2)
Test#1 (Memory)
23.79k
34.35k (x1.44)
TOTAL
52.85k
80.3k (x1.52)

Multithread

3600

7950X
Test#1 (Integers)
22.11k
128.82k (x5.83)
Test#2 (FP)
108.04k
465.79k (x4.31)
Test#3 (Generic, ZIP)
56.81k
289.43k (x5.09)
Test#1 (Memory)
36.39k
75.23k (x2.07)
TOTAL
223.36k
959.27k (x4.29)

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
3600
7950X
Test#1 (Integers)
15.04k
26.86k (x1.79)
Test#2 (FP)
20.95k
30.05k (x1.43)
Test#3 (Generic, ZIP)
8.57k
16.15k (x1.89)
Test#1 (Memory)
21.71k
31.74k (x1.46)
TOTAL
66.27k
104.8k (x1.58)

Multithread

3600

7950X
Test#1 (Integers)
94.36k
430.6k (x4.56)
Test#2 (FP)
141.73k
545.91k (x3.85)
Test#3 (Generic, ZIP)
69.38k
289.57k (x4.17)
Test#1 (Memory)
32.72k
64.33k (x1.97)
TOTAL
338.19k
1330.41k (x3.93)

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
3600
7950X
Test#1 (Integers)
16.04k
40.61k (x2.53)
Test#2 (FP)
24.47k
31.82k (x1.3)
Test#3 (Generic, ZIP)
8.38k
16.63k (x1.98)
Test#1 (Memory)
21.66k
32.28k (x1.49)
TOTAL
70.55k
121.33k (x1.72)

Multithread

3600

7950X
Test#1 (Integers)
113.63k
683.17k (x6.01)
Test#2 (FP)
143.55k
563.45k (x3.93)
Test#3 (Generic, ZIP)
63.84k
286.77k (x4.49)
Test#1 (Memory)
27.34k
64.4k (x2.36)
TOTAL
348.35k
1597.79k (x4.59)

Performance/W
3600
7950X
Test#1 (Integers)
1748 points/W
4019 points/W
Test#2 (FP)
2208 points/W
3314 points/W
Test#3 (Generic, ZIP)
982 points/W
1687 points/W
Test#1 (Memory)
421 points/W
379 points/W
TOTAL
5359 points/W
9399 points/W

Performance/GHz
3600
7950X
Test#1 (Integers)
3819 points/GHz
7124 points/GHz
Test#2 (FP)
5825 points/GHz
5582 points/GHz
Test#3 (Generic, ZIP)
1995 points/GHz
2917 points/GHz
Test#1 (Memory)
5158 points/GHz
5663 points/GHz
TOTAL
16797 points/GHz
21286 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