| | | | | | |

Ryzen 9 3900 vs Core i7-12700H


Description
The 3900 is based on Zen 2 architecture while the i7-12700H is based on Alder Lake.

Using the multithread performance as a reference, the 3900 gets a score of 687.5 k points while the i7-12700H gets 643.3 k points.

Summarizing, the 3900 is 1.1 times faster than the i7-12700H. To get a proper comparison between both models, take a look to the data shown below.

Specs
CPUID
870f10
906a3
Core
Matisse
Alder Lake-H
Architecture
Base frecuency
3.1 GHz
4.7 GHz
Boost frecuency
4.3 GHz
4.7 GHz
Socket
AM4
BGA 1744
Cores/Threads
12/24
14/20
TDP
65 W
115 W
Cache L1 (d+i)
12x32+12x32 kB
6x32/8x64+6x48/8x32 kB
Cache L2
12x512 kB
6x1280+6x2048 kB
Cache L3
4x16384 kB
24576 kB
Date
September 2019
January 2022
Mean monothread perf.
74.97k points
93.12k points
Mean multithread perf.
687.5k points
643.29k 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
i7-12700H
Test#1 (Integers)
4.39k
7.95k (x1.81)
Test#2 (FP)
16.99k
19.74k (x1.16)
Test#3 (Generic, ZIP)
7.74k
13.29k (x1.72)
Test#1 (Memory)
24.57k
14.97k (x0.61)
TOTAL
53.69k
55.95k (x1.04)

Multithread

3900

i7-12700H
Test#1 (Integers)
48.45k
53.64k (x1.11)
Test#2 (FP)
230.81k
171.15k (x0.74)
Test#3 (Generic, ZIP)
122.82k
94.92k (x0.77)
Test#1 (Memory)
54.73k
9.24k (x0.17)
TOTAL
456.8k
328.95k (x0.72)

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
i7-12700H
Test#1 (Integers)
16.59k
24.26k (x1.46)
Test#2 (FP)
24.55k
24.03k (x0.98)
Test#3 (Generic, ZIP)
8.55k
14.75k (x1.73)
Test#1 (Memory)
26.28k
12.08k (x0.46)
TOTAL
75.97k
75.12k (x0.99)

Multithread

3900

i7-12700H
Test#1 (Integers)
181.33k
199.99k (x1.1)
Test#2 (FP)
261.01k
218.01k (x0.84)
Test#3 (Generic, ZIP)
126.62k
102.62k (x0.81)
Test#1 (Memory)
66.64k
9.42k (x0.14)
TOTAL
635.6k
530.04k (x0.83)

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
i7-12700H
Test#1 (Integers)
16.16k
25.81k (x1.6)
Test#2 (FP)
23.75k
26.18k (x1.1)
Test#3 (Generic, ZIP)
9.32k
14.71k (x1.58)
Test#1 (Memory)
23.17k
13.88k (x0.6)
TOTAL
72.4k
80.58k (x1.11)

Multithread

3900

i7-12700H
Test#1 (Integers)
174.73k
203.61k (x1.17)
Test#2 (FP)
275.63k
249.64k (x0.91)
Test#3 (Generic, ZIP)
125.65k
101.32k (x0.81)
Test#1 (Memory)
44.17k
9.55k (x0.22)
TOTAL
620.18k
564.12k (x0.91)

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
i7-12700H
Test#1 (Integers)
16.85k
41.64k (x2.47)
Test#2 (FP)
26.03k
25.48k (x0.98)
Test#3 (Generic, ZIP)
9.54k
13.2k (x1.38)
Test#1 (Memory)
22.55k
12.8k (x0.57)
TOTAL
74.97k
93.12k (x1.24)

Multithread

3900

i7-12700H
Test#1 (Integers)
229.41k
276.56k (x1.21)
Test#2 (FP)
292.81k
251.6k (x0.86)
Test#3 (Generic, ZIP)
128.48k
104.55k (x0.81)
Test#1 (Memory)
36.8k
10.58k (x0.29)
TOTAL
687.5k
643.29k (x0.94)

Performance/W
3900
i7-12700H
Test#1 (Integers)
3529 points/W
2405 points/W
Test#2 (FP)
4505 points/W
2188 points/W
Test#3 (Generic, ZIP)
1977 points/W
909 points/W
Test#1 (Memory)
566 points/W
92 points/W
TOTAL
10577 points/W
5594 points/W

Performance/GHz
3900
i7-12700H
Test#1 (Integers)
3920 points/GHz
8859 points/GHz
Test#2 (FP)
6054 points/GHz
5422 points/GHz
Test#3 (Generic, ZIP)
2218 points/GHz
2808 points/GHz
Test#1 (Memory)
5243 points/GHz
2724 points/GHz
TOTAL
17435 points/GHz
19813 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