Ryzen 5 3600 vs Ryzen 9 3900
Description
Both models 3600 and 3900 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 3600 gets a score of 348.4 k points while the 3900 gets 687.5 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 3600 gets a score of 348.4 k points while the 3900 gets 687.5 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
3.6 GHz
3.1 GHz
Boost frecuency
4.2 GHz
4.3 GHz
Socket
AM4
AM4
Cores/Threads
6/12
12/24
TDP
65 W
65 W
Cache L1 (d+i)
6x32+6x32 kB
12x32+12x32 kB
Cache L2
6x512 kB
12x512 kB
Cache L3
32768 kB
4x16384 kB
Date
July 2019
September 2019
Mean monothread perf.
70.55k points
74.97k points
Mean multithread perf.
348.35k points
687.5k 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
3900
Test#1 (Integers)
4.2k
4.39k (x1.04)
Test#2 (FP)
17.36k
16.99k (x0.98)
Test#3 (Generic, ZIP)
7.5k
7.74k (x1.03)
Test#1 (Memory)
23.79k
24.57k (x1.03)
TOTAL
52.85k
53.69k (x1.02)
Multithread
3600
3900
Test#1 (Integers)
22.11k
48.45k (x2.19)
Test#2 (FP)
108.04k
230.81k (x2.14)
Test#3 (Generic, ZIP)
56.81k
122.82k (x2.16)
Test#1 (Memory)
36.39k
54.73k (x1.5)
TOTAL
223.36k
456.8k (x2.05)
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
3600
3900
Test#1 (Integers)
15.38k
16.59k (x1.08)
Test#2 (FP)
21.94k
24.55k (x1.12)
Test#3 (Generic, ZIP)
7.97k
8.55k (x1.07)
Test#1 (Memory)
24.76k
26.28k (x1.06)
TOTAL
70.05k
75.97k (x1.08)
Multithread
3600
3900
Test#1 (Integers)
96.91k
181.33k (x1.87)
Test#2 (FP)
135.12k
261.01k (x1.93)
Test#3 (Generic, ZIP)
70.39k
126.62k (x1.8)
Test#1 (Memory)
56.43k
66.64k (x1.18)
TOTAL
358.85k
635.6k (x1.77)
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
3900
Test#1 (Integers)
15.04k
16.16k (x1.07)
Test#2 (FP)
20.95k
23.75k (x1.13)
Test#3 (Generic, ZIP)
8.57k
9.32k (x1.09)
Test#1 (Memory)
21.71k
23.17k (x1.07)
TOTAL
66.27k
72.4k (x1.09)
Multithread
3600
3900
Test#1 (Integers)
94.36k
174.73k (x1.85)
Test#2 (FP)
141.73k
275.63k (x1.94)
Test#3 (Generic, ZIP)
69.38k
125.65k (x1.81)
Test#1 (Memory)
32.72k
44.17k (x1.35)
TOTAL
338.19k
620.18k (x1.83)
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
3900
Test#1 (Integers)
16.04k
16.85k (x1.05)
Test#2 (FP)
24.47k
26.03k (x1.06)
Test#3 (Generic, ZIP)
8.38k
9.54k (x1.14)
Test#1 (Memory)
21.66k
22.55k (x1.04)
TOTAL
70.55k
74.97k (x1.06)
Multithread
3600
3900
Test#1 (Integers)
113.63k
229.41k (x2.02)
Test#2 (FP)
143.55k
292.81k (x2.04)
Test#3 (Generic, ZIP)
63.84k
128.48k (x2.01)
Test#1 (Memory)
27.34k
36.8k (x1.35)
TOTAL
348.35k
687.5k (x1.97)
Performance/W
3600
3900
Test#1 (Integers)
1748 points/W
3529 points/W
Test#2 (FP)
2208 points/W
4505 points/W
Test#3 (Generic, ZIP)
982 points/W
1977 points/W
Test#1 (Memory)
421 points/W
566 points/W
TOTAL
5359 points/W
10577 points/W
Performance/GHz
3600
3900
Test#1 (Integers)
3819 points/GHz
3920 points/GHz
Test#2 (FP)
5825 points/GHz
6054 points/GHz
Test#3 (Generic, ZIP)
1995 points/GHz
2218 points/GHz
Test#1 (Memory)
5158 points/GHz
5243 points/GHz
TOTAL
16797 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.
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