| | | | | | |

Ryzen 9 3900 vs Core i9-10900K


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

Using the multithread performance as a reference, the 3900 gets a score of 687.5 k points while the i9-10900K gets 685.6 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
870f10
a0655
Core
Matisse
Comet Lake-S
Architecture
Base frecuency
3.1 GHz
3.7 GHz
Boost frecuency
4.3 GHz
5.2 GHz
Socket
AM4
LGA 1200
Cores/Threads
12/24
10/20
TDP
65 W
125 W
Cache L1 (d+i)
12x32+12x32 kB
10x32+10x32 kB
Cache L2
12x512 kB
10x256 kB
Cache L3
4x16384 kB
20480 kB
Date
September 2019
April 2020
Mean monothread perf.
74.97k points
80.41k points
Mean multithread perf.
687.5k points
685.65k 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
3900
i9-10900K
Test#1 (Integers)
16.59k
19.5k (x1.18)
Test#2 (FP)
24.55k
28.01k (x1.14)
Test#3 (Generic, ZIP)
8.55k
7.45k (x0.87)
Test#1 (Memory)
26.28k
15.82k (x0.6)
TOTAL
75.97k
70.79k (x0.93)

Multithread

3900

i9-10900K
Test#1 (Integers)
181.33k
194.49k (x1.07)
Test#2 (FP)
261.01k
312.59k (x1.2)
Test#3 (Generic, ZIP)
126.62k
89.14k (x0.7)
Test#1 (Memory)
66.64k
12.58k (x0.19)
TOTAL
635.6k
608.81k (x0.96)

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
i9-10900K
Test#1 (Integers)
16.85k
32.67k (x1.94)
Test#2 (FP)
26.03k
28.49k (x1.09)
Test#3 (Generic, ZIP)
9.54k
6.53k (x0.69)
Test#1 (Memory)
22.55k
12.72k (x0.56)
TOTAL
74.97k
80.41k (x1.07)

Multithread

3900

i9-10900K
Test#1 (Integers)
229.41k
307.39k (x1.34)
Test#2 (FP)
292.81k
298.47k (x1.02)
Test#3 (Generic, ZIP)
128.48k
72.94k (x0.57)
Test#1 (Memory)
36.8k
6.85k (x0.19)
TOTAL
687.5k
685.65k (x1)

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

Performance/GHz
3900
i9-10900K
Test#1 (Integers)
3920 points/GHz
6282 points/GHz
Test#2 (FP)
6054 points/GHz
5479 points/GHz
Test#3 (Generic, ZIP)
2218 points/GHz
1257 points/GHz
Test#1 (Memory)
5243 points/GHz
2445 points/GHz
TOTAL
17435 points/GHz
15463 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