| | | | | | |

Core i3-7100 vs Ryzen 9 3900


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

Using the multithread performance as a reference, the i3-7100 gets a score of 126.5 k points while the 3900 gets 687.5 k points.

Summarizing, the 3900 is 5.4 times faster than the i3-7100. To get a proper comparison between both models, take a look to the data shown below.

Specs
CPUID
906e9
870f10
Core
Kaby Lake-S
Matisse
Architecture
Base frecuency
3.9 GHz
3.1 GHz
Boost frecuency
3.9 GHz
4.3 GHz
Socket
LGA 1151
AM4
Cores/Threads
2/4
12/24
TDP
51 W
65 W
Cache L1 (d+i)
2x32+2x32 kB
12x32+12x32 kB
Cache L2
2x256 kB
12x512 kB
Cache L3
3072 kB
4x16384 kB
Date
January 2017
September 2019
Mean monothread perf.
58.55k points
74.97k points
Mean multithread perf.
126.47k 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
i3-7100
3900
Test#1 (Integers)
4.01k
4.39k (x1.09)
Test#2 (FP)
16.38k
16.99k (x1.04)
Test#3 (Generic, ZIP)
5.31k
7.74k (x1.46)
Test#1 (Memory)
3.98k
24.57k (x6.17)
TOTAL
29.69k
53.69k (x1.81)

Multithread

i3-7100

3900
Test#1 (Integers)
8.1k
48.45k (x5.98)
Test#2 (FP)
38.7k
230.81k (x5.96)
Test#3 (Generic, ZIP)
12.69k
122.82k (x9.68)
Test#1 (Memory)
3.76k
54.73k (x14.57)
TOTAL
63.24k
456.8k (x7.22)

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
i3-7100
3900
Test#1 (Integers)
14.04k
16.59k (x1.18)
Test#2 (FP)
20.55k
24.55k (x1.19)
Test#3 (Generic, ZIP)
5.41k
8.55k (x1.58)
Test#1 (Memory)
3.99k
26.28k (x6.58)
TOTAL
43.99k
75.97k (x1.73)

Multithread

i3-7100

3900
Test#1 (Integers)
30.09k
181.33k (x6.03)
Test#2 (FP)
47.84k
261.01k (x5.46)
Test#3 (Generic, ZIP)
13.13k
126.62k (x9.64)
Test#1 (Memory)
3.52k
66.64k (x18.94)
TOTAL
94.59k
635.6k (x6.72)

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
i3-7100
3900
Test#1 (Integers)
14.41k
16.16k (x1.12)
Test#2 (FP)
22.38k
23.75k (x1.06)
Test#3 (Generic, ZIP)
5.45k
9.32k (x1.71)
Test#1 (Memory)
4.96k
23.17k (x4.67)
TOTAL
47.21k
72.4k (x1.53)

Multithread

i3-7100

3900
Test#1 (Integers)
30.48k
174.73k (x5.73)
Test#2 (FP)
52.08k
275.63k (x5.29)
Test#3 (Generic, ZIP)
12.97k
125.65k (x9.69)
Test#1 (Memory)
4.56k
44.17k (x9.68)
TOTAL
100.1k
620.18k (x6.2)

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
i3-7100
3900
Test#1 (Integers)
25.77k
16.85k (x0.65)
Test#2 (FP)
23.26k
26.03k (x1.12)
Test#3 (Generic, ZIP)
5.43k
9.54k (x1.76)
Test#1 (Memory)
4.09k
22.55k (x5.51)
TOTAL
58.55k
74.97k (x1.28)

Multithread

i3-7100

3900
Test#1 (Integers)
54.98k
229.41k (x4.17)
Test#2 (FP)
54.73k
292.81k (x5.35)
Test#3 (Generic, ZIP)
13.12k
128.48k (x9.8)
Test#1 (Memory)
3.65k
36.8k (x10.09)
TOTAL
126.47k
687.5k (x5.44)

Performance/W
i3-7100
3900
Test#1 (Integers)
1078 points/W
3529 points/W
Test#2 (FP)
1073 points/W
4505 points/W
Test#3 (Generic, ZIP)
257 points/W
1977 points/W
Test#1 (Memory)
72 points/W
566 points/W
TOTAL
2480 points/W
10577 points/W

Performance/GHz
i3-7100
3900
Test#1 (Integers)
6607 points/GHz
3920 points/GHz
Test#2 (FP)
5964 points/GHz
6054 points/GHz
Test#3 (Generic, ZIP)
1393 points/GHz
2218 points/GHz
Test#1 (Memory)
1049 points/GHz
5243 points/GHz
TOTAL
15014 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.


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