| | | | | | |

Core i7-12700H vs Ryzen 9 3900


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

Using the multithread performance as a reference, the i7-12700H gets a score of 643.3 k points while the 3900 gets 687.5 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
906a3
870f10
Core
Alder Lake-H
Matisse
Architecture
Base frecuency
4.7 GHz
3.1 GHz
Boost frecuency
4.7 GHz
4.3 GHz
Socket
BGA 1744
AM4
Cores/Threads
14/20
12/24
TDP
115 W
65 W
Cache L1 (d+i)
6x32/8x64+6x48/8x32 kB
12x32+12x32 kB
Cache L2
6x1280+6x2048 kB
12x512 kB
Cache L3
24576 kB
4x16384 kB
Date
January 2022
September 2019
Mean monothread perf.
93.12k points
74.97k points
Mean multithread perf.
643.29k 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
i7-12700H
3900
Test#1 (Integers)
7.95k
4.39k (x0.55)
Test#2 (FP)
19.74k
16.99k (x0.86)
Test#3 (Generic, ZIP)
13.29k
7.74k (x0.58)
Test#1 (Memory)
14.97k
24.57k (x1.64)
TOTAL
55.95k
53.69k (x0.96)

Multithread

i7-12700H

3900
Test#1 (Integers)
53.64k
48.45k (x0.9)
Test#2 (FP)
171.15k
230.81k (x1.35)
Test#3 (Generic, ZIP)
94.92k
122.82k (x1.29)
Test#1 (Memory)
9.24k
54.73k (x5.92)
TOTAL
328.95k
456.8k (x1.39)

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
i7-12700H
3900
Test#1 (Integers)
24.26k
16.59k (x0.68)
Test#2 (FP)
24.03k
24.55k (x1.02)
Test#3 (Generic, ZIP)
14.75k
8.55k (x0.58)
Test#1 (Memory)
12.08k
26.28k (x2.18)
TOTAL
75.12k
75.97k (x1.01)

Multithread

i7-12700H

3900
Test#1 (Integers)
199.99k
181.33k (x0.91)
Test#2 (FP)
218.01k
261.01k (x1.2)
Test#3 (Generic, ZIP)
102.62k
126.62k (x1.23)
Test#1 (Memory)
9.42k
66.64k (x7.07)
TOTAL
530.04k
635.6k (x1.2)

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
i7-12700H
3900
Test#1 (Integers)
25.81k
16.16k (x0.63)
Test#2 (FP)
26.18k
23.75k (x0.91)
Test#3 (Generic, ZIP)
14.71k
9.32k (x0.63)
Test#1 (Memory)
13.88k
23.17k (x1.67)
TOTAL
80.58k
72.4k (x0.9)

Multithread

i7-12700H

3900
Test#1 (Integers)
203.61k
174.73k (x0.86)
Test#2 (FP)
249.64k
275.63k (x1.1)
Test#3 (Generic, ZIP)
101.32k
125.65k (x1.24)
Test#1 (Memory)
9.55k
44.17k (x4.62)
TOTAL
564.12k
620.18k (x1.1)

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
i7-12700H
3900
Test#1 (Integers)
41.64k
16.85k (x0.4)
Test#2 (FP)
25.48k
26.03k (x1.02)
Test#3 (Generic, ZIP)
13.2k
9.54k (x0.72)
Test#1 (Memory)
12.8k
22.55k (x1.76)
TOTAL
93.12k
74.97k (x0.81)

Multithread

i7-12700H

3900
Test#1 (Integers)
276.56k
229.41k (x0.83)
Test#2 (FP)
251.6k
292.81k (x1.16)
Test#3 (Generic, ZIP)
104.55k
128.48k (x1.23)
Test#1 (Memory)
10.58k
36.8k (x3.48)
TOTAL
643.29k
687.5k (x1.07)

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

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