| | | | | | |

Core i9-11900KB vs Ryzen 9 3900


Description
The i9-11900KB is based on Tiger Lake architecture while the 3900 is based on Zen 2.

Using the multithread performance as a reference, the i9-11900KB gets a score of 537.2 k points while the 3900 gets 687.5 k points.

Summarizing, the 3900 is 1.3 times faster than the i9-11900KB. To get a proper comparison between both models, take a look to the data shown below.

Specs
CPUID
806d1
870f10
Core
Tiger Lake-H
Matisse
Architecture
Base frecuency
3.3 GHz
3.1 GHz
Boost frecuency
4.9 GHz
4.3 GHz
Socket
BGA 1787
AM4
Cores/Threads
8/16
12/24
TDP
65 W
65 W
Cache L1 (d+i)
8x32+8x48 kB
12x32+12x32 kB
Cache L2
8x1280 kB
12x512 kB
Cache L3
24576 kB
4x16384 kB
Date
July 2021
September 2019
Mean monothread perf.
63.79k points
74.97k points
Mean multithread perf.
537.18k points
687.5k points

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
i9-11900KB
3900
Test#1 (Integers)
24.09k
16.85k (x0.7)
Test#2 (FP)
19.54k
26.03k (x1.33)
Test#3 (Generic, ZIP)
8.48k
9.54k (x1.13)
Test#1 (Memory)
11.68k
22.55k (x1.93)
TOTAL
63.79k
74.97k (x1.18)

Multithread

i9-11900KB

3900
Test#1 (Integers)
220.79k
229.41k (x1.04)
Test#2 (FP)
225.98k
292.81k (x1.3)
Test#3 (Generic, ZIP)
79.1k
128.48k (x1.62)
Test#1 (Memory)
11.32k
36.8k (x3.25)
TOTAL
537.18k
687.5k (x1.28)

Performance/W
i9-11900KB
3900
Test#1 (Integers)
3397 points/W
3529 points/W
Test#2 (FP)
3477 points/W
4505 points/W
Test#3 (Generic, ZIP)
1217 points/W
1977 points/W
Test#1 (Memory)
174 points/W
566 points/W
TOTAL
8264 points/W
10577 points/W

Performance/GHz
i9-11900KB
3900
Test#1 (Integers)
4917 points/GHz
3920 points/GHz
Test#2 (FP)
3988 points/GHz
6054 points/GHz
Test#3 (Generic, ZIP)
1730 points/GHz
2218 points/GHz
Test#1 (Memory)
2384 points/GHz
5243 points/GHz
TOTAL
13018 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