Ryzen 9 3900 vs Ryzen 5 3600
Description
Both models 3900 and 3600 are based on Zen 2 architecture.
Zen 2 is fabricated on the 7nm process from TSMC and it’s the third generation of Zen CPUs. It comes with 64kB of L1 cache and 512kB of L2 cache per core. Zen 2 CPUs are divided into 3 categories: Matisse (desktop), Rome (Server) and Castle Peak (high-end desktop).
Using the multithread performance as a reference, the 3900 gets a score of 687.5 k points while the 3600 gets 348.4 k points.
Summarizing, the 3900 is 2 times faster than the 3600. To get a proper comparison between both models, take a look to the data shown below.
Zen 2 is fabricated on the 7nm process from TSMC and it’s the third generation of Zen CPUs. It comes with 64kB of L1 cache and 512kB of L2 cache per core. Zen 2 CPUs are divided into 3 categories: Matisse (desktop), Rome (Server) and Castle Peak (high-end desktop).
Using the multithread performance as a reference, the 3900 gets a score of 687.5 k points while the 3600 gets 348.4 k points.
Summarizing, the 3900 is 2 times faster than the 3600. To get a proper comparison between both models, take a look to the data shown below.
Specs
CPUID
870f10
870f10
Core
Matisse
Matisse
Base frecuency
3.1 GHz
3.6 GHz
Boost frecuency
4.3 GHz
4.2 GHz
Socket
AM4
AM4
Cores/Threads
12/24
6/12
TDP
65 W
65 W
Cache L1 (d+i)
12x32+12x32 kB
6x32+6x32 kB
Cache L2
12x512 kB
6x512 kB
Cache L3
4x16384 kB
32768 kB
Date
September 2019
July 2019
Mean monothread perf.
74.97k points
70.55k points
Mean multithread perf.
687.5k points
348.35k 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
3900
3600
Test#1 (Integers)
4.39k
4.2k (x0.96)
Test#2 (FP)
16.99k
17.36k (x1.02)
Test#3 (Generic, ZIP)
7.74k
7.5k (x0.97)
Test#1 (Memory)
24.57k
23.79k (x0.97)
TOTAL
53.69k
52.85k (x0.98)
Multithread
3900
3600
Test#1 (Integers)
48.45k
22.11k (x0.46)
Test#2 (FP)
230.81k
108.04k (x0.47)
Test#3 (Generic, ZIP)
122.82k
56.81k (x0.46)
Test#1 (Memory)
54.73k
36.39k (x0.67)
TOTAL
456.8k
223.36k (x0.49)
SSE3 optimized benchmark
The benchmark in mode I (SSE) is optimized for the use of SIMD instructions with 128 bits register and the SSE set up to version 3. Nearly every modern CPU has support for this mode.
Monothread
3900
3600
Test#1 (Integers)
16.59k
15.38k (x0.93)
Test#2 (FP)
24.55k
21.94k (x0.89)
Test#3 (Generic, ZIP)
8.55k
7.97k (x0.93)
Test#1 (Memory)
26.28k
24.76k (x0.94)
TOTAL
75.97k
70.05k (x0.92)
Multithread
3900
3600
Test#1 (Integers)
181.33k
96.91k (x0.53)
Test#2 (FP)
261.01k
135.12k (x0.52)
Test#3 (Generic, ZIP)
126.62k
70.39k (x0.56)
Test#1 (Memory)
66.64k
56.43k (x0.85)
TOTAL
635.6k
358.85k (x0.56)
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
3900
3600
Test#1 (Integers)
16.16k
15.04k (x0.93)
Test#2 (FP)
23.75k
20.95k (x0.88)
Test#3 (Generic, ZIP)
9.32k
8.57k (x0.92)
Test#1 (Memory)
23.17k
21.71k (x0.94)
TOTAL
72.4k
66.27k (x0.92)
Multithread
3900
3600
Test#1 (Integers)
174.73k
94.36k (x0.54)
Test#2 (FP)
275.63k
141.73k (x0.51)
Test#3 (Generic, ZIP)
125.65k
69.38k (x0.55)
Test#1 (Memory)
44.17k
32.72k (x0.74)
TOTAL
620.18k
338.19k (x0.55)
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
3900
3600
Test#1 (Integers)
16.85k
16.04k (x0.95)
Test#2 (FP)
26.03k
24.47k (x0.94)
Test#3 (Generic, ZIP)
9.54k
8.38k (x0.88)
Test#1 (Memory)
22.55k
21.66k (x0.96)
TOTAL
74.97k
70.55k (x0.94)
Multithread
3900
3600
Test#1 (Integers)
229.41k
113.63k (x0.5)
Test#2 (FP)
292.81k
143.55k (x0.49)
Test#3 (Generic, ZIP)
128.48k
63.84k (x0.5)
Test#1 (Memory)
36.8k
27.34k (x0.74)
TOTAL
687.5k
348.35k (x0.51)
Performance/W
3900
3600
Test#1 (Integers)
3529 points/W
1748 points/W
Test#2 (FP)
4505 points/W
2208 points/W
Test#3 (Generic, ZIP)
1977 points/W
982 points/W
Test#1 (Memory)
566 points/W
421 points/W
TOTAL
10577 points/W
5359 points/W
Performance/GHz
3900
3600
Test#1 (Integers)
3920 points/GHz
3819 points/GHz
Test#2 (FP)
6054 points/GHz
5825 points/GHz
Test#3 (Generic, ZIP)
2218 points/GHz
1995 points/GHz
Test#1 (Memory)
5243 points/GHz
5158 points/GHz
TOTAL
17435 points/GHz
16797 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.
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]
Test#2 (FP) [points vs time]
Test#3 (Generic, ZIP) [points vs time]
Test#1 (Memory) [points vs time]
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.
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]
Test#2 (FP) [points vs time]
Test#3 (Generic, ZIP) [points vs time]
Test#1 (Memory) [points vs time]
Hardlimit Benchmark Central - Ver. 3.11.4