| | | | | | |

Core i9-10900K vs Ryzen 9 3900


Description
The i9-10900K is based on Comet Lake architecture while the 3900 is based on Zen 2.

Using the multithread performance as a reference, the i9-10900K gets a score of 685.6 k points while the 3900 gets 687.5 k points.

Summarizing, the 3900 is 1 times faster than the i9-10900K. To get a proper comparison between both models, take a look to the data shown below.

Specs
CPUID
a0655
870f10
Core
Comet Lake-S
Matisse
Architecture
Base frecuency
3.7 GHz
3.1 GHz
Boost frecuency
5.2 GHz
4.3 GHz
Socket
LGA 1200
AM4
Cores/Threads
10/20
12/24
TDP
125 W
65 W
Cache L1 (d+i)
10x32+10x32 kB
12x32+12x32 kB
Cache L2
10x256 kB
12x512 kB
Cache L3
20480 kB
4x16384 kB
Date
April 2020
September 2019
Mean monothread perf.
80.41k points
74.97k points
Mean multithread perf.
685.65k points
687.5k points

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
i9-10900K
3900
Test#1 (Integers)
19.5k
16.59k (x0.85)
Test#2 (FP)
28.01k
24.55k (x0.88)
Test#3 (Generic, ZIP)
7.45k
8.55k (x1.15)
Test#1 (Memory)
15.82k
26.28k (x1.66)
TOTAL
70.79k
75.97k (x1.07)

Multithread

i9-10900K

3900
Test#1 (Integers)
194.49k
181.33k (x0.93)
Test#2 (FP)
312.59k
261.01k (x0.83)
Test#3 (Generic, ZIP)
89.14k
126.62k (x1.42)
Test#1 (Memory)
12.58k
66.64k (x5.3)
TOTAL
608.81k
635.6k (x1.04)

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
i9-10900K
3900
Test#1 (Integers)
32.67k
16.85k (x0.52)
Test#2 (FP)
28.49k
26.03k (x0.91)
Test#3 (Generic, ZIP)
6.53k
9.54k (x1.46)
Test#1 (Memory)
12.72k
22.55k (x1.77)
TOTAL
80.41k
74.97k (x0.93)

Multithread

i9-10900K

3900
Test#1 (Integers)
307.39k
229.41k (x0.75)
Test#2 (FP)
298.47k
292.81k (x0.98)
Test#3 (Generic, ZIP)
72.94k
128.48k (x1.76)
Test#1 (Memory)
6.85k
36.8k (x5.37)
TOTAL
685.65k
687.5k (x1)

Performance/W
i9-10900K
3900
Test#1 (Integers)
2459 points/W
3529 points/W
Test#2 (FP)
2388 points/W
4505 points/W
Test#3 (Generic, ZIP)
583 points/W
1977 points/W
Test#1 (Memory)
55 points/W
566 points/W
TOTAL
5485 points/W
10577 points/W

Performance/GHz
i9-10900K
3900
Test#1 (Integers)
6282 points/GHz
3920 points/GHz
Test#2 (FP)
5479 points/GHz
6054 points/GHz
Test#3 (Generic, ZIP)
1257 points/GHz
2218 points/GHz
Test#1 (Memory)
2445 points/GHz
5243 points/GHz
TOTAL
15463 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