| | | | | | |

Core i5-10500H vs Ryzen 9 3900


Description
The i5-10500H is based on Comet Lake architecture while the 3900 is based on Zen 2.

Using the multithread performance as a reference, the i5-10500H gets a score of 379 k points while the 3900 gets 687.5 k points.

Summarizing, the 3900 is 1.8 times faster than the i5-10500H. To get a proper comparison between both models, take a look to the data shown below.

Specs
CPUID
a0652
870f10
Core
Comet Lake-S
Matisse
Architecture
Base frecuency
3.1 GHz
3.1 GHz
Boost frecuency
4.5 GHz
4.3 GHz
Socket
LGA 1200
AM4
Cores/Threads
6/12
12/24
TDP
65 W
65 W
Cache L1 (d+i)
6x32+6x32 kB
12x32+12x32 kB
Cache L2
6x256 kB
12x512 kB
Cache L3
12288 kB
4x16384 kB
Date
April 2020
September 2019
Mean monothread perf.
72.1k points
74.97k points
Mean multithread perf.
378.99k 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
i5-10500H
3900
Test#1 (Integers)
4.98k
4.39k (x0.88)
Test#2 (FP)
17.92k
16.99k (x0.95)
Test#3 (Generic, ZIP)
5.81k
7.74k (x1.33)
Test#1 (Memory)
12.55k
24.57k (x1.96)
TOTAL
41.26k
53.69k (x1.3)

Multithread

i5-10500H

3900
Test#1 (Integers)
29.53k
48.45k (x1.64)
Test#2 (FP)
118.16k
230.81k (x1.95)
Test#3 (Generic, ZIP)
38.43k
122.82k (x3.2)
Test#1 (Memory)
5.29k
54.73k (x10.35)
TOTAL
191.41k
456.8k (x2.39)

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
i5-10500H
3900
Test#1 (Integers)
15.89k
16.59k (x1.04)
Test#2 (FP)
22.74k
24.55k (x1.08)
Test#3 (Generic, ZIP)
6.09k
8.55k (x1.4)
Test#1 (Memory)
12.49k
26.28k (x2.1)
TOTAL
57.21k
75.97k (x1.33)

Multithread

i5-10500H

3900
Test#1 (Integers)
96.8k
181.33k (x1.87)
Test#2 (FP)
149.1k
261.01k (x1.75)
Test#3 (Generic, ZIP)
39.68k
126.62k (x3.19)
Test#1 (Memory)
5.28k
66.64k (x12.63)
TOTAL
290.85k
635.6k (x2.19)

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
i5-10500H
3900
Test#1 (Integers)
15.86k
16.16k (x1.02)
Test#2 (FP)
24.07k
23.75k (x0.99)
Test#3 (Generic, ZIP)
5.94k
9.32k (x1.57)
Test#1 (Memory)
11.82k
23.17k (x1.96)
TOTAL
57.69k
72.4k (x1.26)

Multithread

i5-10500H

3900
Test#1 (Integers)
97.37k
174.73k (x1.79)
Test#2 (FP)
154.42k
275.63k (x1.78)
Test#3 (Generic, ZIP)
38.76k
125.65k (x3.24)
Test#1 (Memory)
5.4k
44.17k (x8.18)
TOTAL
295.96k
620.18k (x2.1)

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
i5-10500H
3900
Test#1 (Integers)
27.93k
16.85k (x0.6)
Test#2 (FP)
25.41k
26.03k (x1.02)
Test#3 (Generic, ZIP)
5.91k
9.54k (x1.61)
Test#1 (Memory)
12.85k
22.55k (x1.75)
TOTAL
72.1k
74.97k (x1.04)

Multithread

i5-10500H

3900
Test#1 (Integers)
176.41k
229.41k (x1.3)
Test#2 (FP)
158.8k
292.81k (x1.84)
Test#3 (Generic, ZIP)
38.53k
128.48k (x3.33)
Test#1 (Memory)
5.25k
36.8k (x7)
TOTAL
378.99k
687.5k (x1.81)

Performance/W
i5-10500H
3900
Test#1 (Integers)
2714 points/W
3529 points/W
Test#2 (FP)
2443 points/W
4505 points/W
Test#3 (Generic, ZIP)
593 points/W
1977 points/W
Test#1 (Memory)
81 points/W
566 points/W
TOTAL
5831 points/W
10577 points/W

Performance/GHz
i5-10500H
3900
Test#1 (Integers)
6207 points/GHz
3920 points/GHz
Test#2 (FP)
5647 points/GHz
6054 points/GHz
Test#3 (Generic, ZIP)
1313 points/GHz
2218 points/GHz
Test#1 (Memory)
2856 points/GHz
5243 points/GHz
TOTAL
16023 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