| | | | | | |

Ryzen 7 2700X vs Ryzen 9 3900X


Description
The 2700X is based on Zen+ architecture while the 3900X is based on Zen 2.

Using the multithread performance as a reference, the 2700X gets a score of 433.2 k points while the 3900X gets 756.3 k points.

Summarizing, the 3900X is 1.7 times faster than the 2700X. To get a proper comparison between both models, take a look to the data shown below.

Specs
CPUID
800f82
870f10
Core
Pinnacle Ridge
Matisse
Architecture
Base frecuency
3.7 GHz
3.8 GHz
Boost frecuency
4.3 GHz
4.6 GHz
Socket
AM4
AM4
Cores/Threads
8/16
12/24
TDP
105 W
105 W
Cache L1 (d+i)
8x64+8x32 kB
12x32+12x32 kB
Cache L2
8x512 kB
12x512 kB
Cache L3
16384 kB
4x16384 kB
Date
April 2018
July 2019
Mean monothread perf.
65.87k points
72.51k points
Mean multithread perf.
433.19k points
756.3k 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
2700X
3900X
Test#1 (Integers)
4.25k
4.46k (x1.05)
Test#2 (FP)
19.72k
18.46k (x0.94)
Test#3 (Generic, ZIP)
5.84k
8.05k (x1.38)
Test#1 (Memory)
21.36k
23.71k (x1.11)
TOTAL
51.17k
54.68k (x1.07)

Multithread

2700X

3900X
Test#1 (Integers)
35.04k
52.65k (x1.5)
Test#2 (FP)
181.42k
265.41k (x1.46)
Test#3 (Generic, ZIP)
64.86k
140.78k (x2.17)
Test#1 (Memory)
8.21k
46.91k (x5.72)
TOTAL
289.54k
505.76k (x1.75)

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
2700X
3900X
Test#1 (Integers)
15.22k
17.35k (x1.14)
Test#2 (FP)
24.12k
25.87k (x1.07)
Test#3 (Generic, ZIP)
5.87k
8.72k (x1.49)
Test#1 (Memory)
21k
27.86k (x1.33)
TOTAL
66.21k
79.8k (x1.21)

Multithread

2700X

3900X
Test#1 (Integers)
126.81k
201.57k (x1.59)
Test#2 (FP)
229.86k
284.41k (x1.24)
Test#3 (Generic, ZIP)
61.74k
145.16k (x2.35)
Test#1 (Memory)
9.77k
100.56k (x10.29)
TOTAL
428.19k
731.7k (x1.71)

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
2700X
3900X
Test#1 (Integers)
14.44k
16.95k (x1.17)
Test#2 (FP)
24.92k
25.37k (x1.02)
Test#3 (Generic, ZIP)
5.8k
9.23k (x1.59)
Test#1 (Memory)
19.07k
24.83k (x1.3)
TOTAL
64.24k
76.38k (x1.19)

Multithread

2700X

3900X
Test#1 (Integers)
122.01k
196.31k (x1.61)
Test#2 (FP)
220.34k
290.5k (x1.32)
Test#3 (Generic, ZIP)
59.89k
143.95k (x2.4)
Test#1 (Memory)
9.9k
64.92k (x6.56)
TOTAL
412.13k
695.69k (x1.69)

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
2700X
3900X
Test#1 (Integers)
15.61k
16.73k (x1.07)
Test#2 (FP)
26.08k
24.74k (x0.95)
Test#3 (Generic, ZIP)
5.84k
8.82k (x1.51)
Test#1 (Memory)
18.34k
22.22k (x1.21)
TOTAL
65.87k
72.51k (x1.1)

Multithread

2700X

3900X
Test#1 (Integers)
123.33k
248.24k (x2.01)
Test#2 (FP)
240.46k
309.66k (x1.29)
Test#3 (Generic, ZIP)
61.23k
140.01k (x2.29)
Test#1 (Memory)
8.17k
58.39k (x7.15)
TOTAL
433.19k
756.3k (x1.75)

Performance/W
2700X
3900X
Test#1 (Integers)
1175 points/W
2364 points/W
Test#2 (FP)
2290 points/W
2949 points/W
Test#3 (Generic, ZIP)
583 points/W
1333 points/W
Test#1 (Memory)
78 points/W
556 points/W
TOTAL
4126 points/W
7203 points/W

Performance/GHz
2700X
3900X
Test#1 (Integers)
3631 points/GHz
3638 points/GHz
Test#2 (FP)
6065 points/GHz
5377 points/GHz
Test#3 (Generic, ZIP)
1357 points/GHz
1917 points/GHz
Test#1 (Memory)
4266 points/GHz
4831 points/GHz
TOTAL
15319 points/GHz
15763 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