| | | | | | |

Ryzen 9 3900 vs Core i5-12400


Description
The 3900 is based on Zen 2 architecture while the i5-12400 is based on Alder Lake.

Using the multithread performance as a reference, the 3900 gets a score of 687.5 k points while the i5-12400 gets 544.6 k points.

Summarizing, the 3900 is 1.3 times faster than the i5-12400. To get a proper comparison between both models, take a look to the data shown below.

Specs
CPUID
870f10
90672
Core
Matisse
Arder Lake-S
Architecture
Base frecuency
3.1 GHz
2.5 GHz
Boost frecuency
4.3 GHz
4.4 GHz
Socket
AM4
LGA 1700
Cores/Threads
12/24
6/12
TDP
65 W
65 W
Cache L1 (d+i)
12x32+12x32 kB
6x32+6x48 kB
Cache L2
12x512 kB
6x1280 kB
Cache L3
4x16384 kB
18432 kB
Date
September 2019
January 2022
Mean monothread perf.
74.97k points
102.51k points
Mean multithread perf.
687.5k points
544.64k 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
i5-12400
Test#1 (Integers)
4.39k
7.51k (x1.71)
Test#2 (FP)
16.99k
18.66k (x1.1)
Test#3 (Generic, ZIP)
7.74k
13.32k (x1.72)
Test#1 (Memory)
24.57k
14.8k (x0.6)
TOTAL
53.69k
54.29k (x1.01)

Multithread

3900

i5-12400
Test#1 (Integers)
48.45k
35.52k (x0.73)
Test#2 (FP)
230.81k
138.43k (x0.6)
Test#3 (Generic, ZIP)
122.82k
85.55k (x0.7)
Test#1 (Memory)
54.73k
21.72k (x0.4)
TOTAL
456.8k
281.22k (x0.62)

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
i5-12400
Test#1 (Integers)
16.59k
24.24k (x1.46)
Test#2 (FP)
24.55k
23.92k (x0.97)
Test#3 (Generic, ZIP)
8.55k
14.43k (x1.69)
Test#1 (Memory)
26.28k
14.84k (x0.56)
TOTAL
75.97k
77.43k (x1.02)

Multithread

3900

i5-12400
Test#1 (Integers)
181.33k
124.33k (x0.69)
Test#2 (FP)
261.01k
168.8k (x0.65)
Test#3 (Generic, ZIP)
126.62k
100k (x0.79)
Test#1 (Memory)
66.64k
21.2k (x0.32)
TOTAL
635.6k
414.33k (x0.65)

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
i5-12400
Test#1 (Integers)
16.16k
23.84k (x1.48)
Test#2 (FP)
23.75k
25.09k (x1.06)
Test#3 (Generic, ZIP)
9.32k
14.1k (x1.51)
Test#1 (Memory)
23.17k
14.48k (x0.62)
TOTAL
72.4k
77.51k (x1.07)

Multithread

3900

i5-12400
Test#1 (Integers)
174.73k
123.98k (x0.71)
Test#2 (FP)
275.63k
176.89k (x0.64)
Test#3 (Generic, ZIP)
125.65k
97.42k (x0.78)
Test#1 (Memory)
44.17k
20.78k (x0.47)
TOTAL
620.18k
419.07k (x0.68)

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
i5-12400
Test#1 (Integers)
16.85k
48.08k (x2.85)
Test#2 (FP)
26.03k
25.6k (x0.98)
Test#3 (Generic, ZIP)
9.54k
14.02k (x1.47)
Test#1 (Memory)
22.55k
14.81k (x0.66)
TOTAL
74.97k
102.51k (x1.37)

Multithread

3900

i5-12400
Test#1 (Integers)
229.41k
230.14k (x1)
Test#2 (FP)
292.81k
198.07k (x0.68)
Test#3 (Generic, ZIP)
128.48k
94.78k (x0.74)
Test#1 (Memory)
36.8k
21.64k (x0.59)
TOTAL
687.5k
544.64k (x0.79)

Performance/W
3900
i5-12400
Test#1 (Integers)
3529 points/W
3541 points/W
Test#2 (FP)
4505 points/W
3047 points/W
Test#3 (Generic, ZIP)
1977 points/W
1458 points/W
Test#1 (Memory)
566 points/W
333 points/W
TOTAL
10577 points/W
8379 points/W

Performance/GHz
3900
i5-12400
Test#1 (Integers)
3920 points/GHz
10927 points/GHz
Test#2 (FP)
6054 points/GHz
5819 points/GHz
Test#3 (Generic, ZIP)
2218 points/GHz
3186 points/GHz
Test#1 (Memory)
5243 points/GHz
3365 points/GHz
TOTAL
17435 points/GHz
23298 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