| | | | | | |

Ryzen 9 3900X vs Core i3-7100


Description
The 3900X is based on Zen 2 architecture while the i3-7100 is based on Kaby Lake.

Using the multithread performance as a reference, the 3900X gets a score of 756.3 k points while the i3-7100 gets 126.5 k points.

Summarizing, the 3900X is 6 times faster than the i3-7100. To get a proper comparison between both models, take a look to the data shown below.

Specs
CPUID
870f10
906e9
Core
Matisse
Kaby Lake-S
Architecture
Base frecuency
3.8 GHz
3.9 GHz
Boost frecuency
4.6 GHz
3.9 GHz
Socket
AM4
LGA 1151
Cores/Threads
12/24
2/4
TDP
105 W
51 W
Cache L1 (d+i)
12x32+12x32 kB
2x32+2x32 kB
Cache L2
12x512 kB
2x256 kB
Cache L3
4x16384 kB
3072 kB
Date
July 2019
January 2017
Mean monothread perf.
72.51k points
58.55k points
Mean multithread perf.
756.3k points
126.47k 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
3900X
i3-7100
Test#1 (Integers)
4.46k
4.01k (x0.9)
Test#2 (FP)
18.46k
16.38k (x0.89)
Test#3 (Generic, ZIP)
8.05k
5.31k (x0.66)
Test#1 (Memory)
23.71k
3.98k (x0.17)
TOTAL
54.68k
29.69k (x0.54)

Multithread

3900X

i3-7100
Test#1 (Integers)
52.65k
8.1k (x0.15)
Test#2 (FP)
265.41k
38.7k (x0.15)
Test#3 (Generic, ZIP)
140.78k
12.69k (x0.09)
Test#1 (Memory)
46.91k
3.76k (x0.08)
TOTAL
505.76k
63.24k (x0.13)

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
3900X
i3-7100
Test#1 (Integers)
17.35k
14.04k (x0.81)
Test#2 (FP)
25.87k
20.55k (x0.79)
Test#3 (Generic, ZIP)
8.72k
5.41k (x0.62)
Test#1 (Memory)
27.86k
3.99k (x0.14)
TOTAL
79.8k
43.99k (x0.55)

Multithread

3900X

i3-7100
Test#1 (Integers)
201.57k
30.09k (x0.15)
Test#2 (FP)
284.41k
47.84k (x0.17)
Test#3 (Generic, ZIP)
145.16k
13.13k (x0.09)
Test#1 (Memory)
100.56k
3.52k (x0.03)
TOTAL
731.7k
94.59k (x0.13)

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
3900X
i3-7100
Test#1 (Integers)
16.95k
14.41k (x0.85)
Test#2 (FP)
25.37k
22.38k (x0.88)
Test#3 (Generic, ZIP)
9.23k
5.45k (x0.59)
Test#1 (Memory)
24.83k
4.96k (x0.2)
TOTAL
76.38k
47.21k (x0.62)

Multithread

3900X

i3-7100
Test#1 (Integers)
196.31k
30.48k (x0.16)
Test#2 (FP)
290.5k
52.08k (x0.18)
Test#3 (Generic, ZIP)
143.95k
12.97k (x0.09)
Test#1 (Memory)
64.92k
4.56k (x0.07)
TOTAL
695.69k
100.1k (x0.14)

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
3900X
i3-7100
Test#1 (Integers)
16.73k
25.77k (x1.54)
Test#2 (FP)
24.74k
23.26k (x0.94)
Test#3 (Generic, ZIP)
8.82k
5.43k (x0.62)
Test#1 (Memory)
22.22k
4.09k (x0.18)
TOTAL
72.51k
58.55k (x0.81)

Multithread

3900X

i3-7100
Test#1 (Integers)
248.24k
54.98k (x0.22)
Test#2 (FP)
309.66k
54.73k (x0.18)
Test#3 (Generic, ZIP)
140.01k
13.12k (x0.09)
Test#1 (Memory)
58.39k
3.65k (x0.06)
TOTAL
756.3k
126.47k (x0.17)

Performance/W
3900X
i3-7100
Test#1 (Integers)
2364 points/W
1078 points/W
Test#2 (FP)
2949 points/W
1073 points/W
Test#3 (Generic, ZIP)
1333 points/W
257 points/W
Test#1 (Memory)
556 points/W
72 points/W
TOTAL
7203 points/W
2480 points/W

Performance/GHz
3900X
i3-7100
Test#1 (Integers)
3638 points/GHz
6607 points/GHz
Test#2 (FP)
5377 points/GHz
5964 points/GHz
Test#3 (Generic, ZIP)
1917 points/GHz
1393 points/GHz
Test#1 (Memory)
4831 points/GHz
1049 points/GHz
TOTAL
15763 points/GHz
15014 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