| | | | | | |

Core i9-13900K vs Ryzen 9 3900


Description
The i9-13900K is based on Raptor Lake architecture while the 3900 is based on Zen 2.

Using the multithread performance as a reference, the i9-13900K gets a score of 1763.1 k points while the 3900 gets 687.5 k points.

Summarizing, the i9-13900K is 2.6 times faster than the 3900. To get a proper comparison between both models, take a look to the data shown below.

Specs
CPUID
b0671
870f10
Core
Raptor Lake-S
Matisse
Architecture
Raptor Lake
Base frecuency
2.2 GHz
3.1 GHz
Boost frecuency
5.8 GHz
4.3 GHz
Socket
LGA 1700
AM4
Cores/Threads
24/32
12/24
TDP
125 W
65 W
Cache L1 (d+i)
8x32/16x64+8x48/16x32 kB
12x32+12x32 kB
Cache L2
8x2048+4x4096 kB
12x512 kB
Cache L3
36864 kB
4x16384 kB
Date
October 2022
September 2019
Mean monothread perf.
129.15k points
74.97k points
Mean multithread perf.
1763.08k 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
i9-13900K
3900
Test#1 (Integers)
9.77k
4.39k (x0.45)
Test#2 (FP)
24.52k
16.99k (x0.69)
Test#3 (Generic, ZIP)
17.17k
7.74k (x0.45)
Test#1 (Memory)
21.37k
24.57k (x1.15)
TOTAL
72.83k
53.69k (x0.74)

Multithread

i9-13900K

3900
Test#1 (Integers)
145.21k
48.45k (x0.33)
Test#2 (FP)
444.95k
230.81k (x0.52)
Test#3 (Generic, ZIP)
318.3k
122.82k (x0.39)
Test#1 (Memory)
27.2k
54.73k (x2.01)
TOTAL
935.66k
456.8k (x0.49)

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
i9-13900K
3900
Test#1 (Integers)
31.93k
16.59k (x0.52)
Test#2 (FP)
31.54k
24.55k (x0.78)
Test#3 (Generic, ZIP)
18.8k
8.55k (x0.45)
Test#1 (Memory)
20.82k
26.28k (x1.26)
TOTAL
103.09k
75.97k (x0.74)

Multithread

i9-13900K

3900
Test#1 (Integers)
522.07k
181.33k (x0.35)
Test#2 (FP)
584.17k
261.01k (x0.45)
Test#3 (Generic, ZIP)
344.38k
126.62k (x0.37)
Test#1 (Memory)
25.36k
66.64k (x2.63)
TOTAL
1475.97k
635.6k (x0.43)

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
i9-13900K
3900
Test#1 (Integers)
31.8k
16.16k (x0.51)
Test#2 (FP)
32.83k
23.75k (x0.72)
Test#3 (Generic, ZIP)
18.37k
9.32k (x0.51)
Test#1 (Memory)
21.13k
23.17k (x1.1)
TOTAL
104.13k
72.4k (x0.7)

Multithread

i9-13900K

3900
Test#1 (Integers)
532.97k
174.73k (x0.33)
Test#2 (FP)
596.78k
275.63k (x0.46)
Test#3 (Generic, ZIP)
342.96k
125.65k (x0.37)
Test#1 (Memory)
28.6k
44.17k (x1.54)
TOTAL
1501.31k
620.18k (x0.41)

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
i9-13900K
3900
Test#1 (Integers)
58.6k
16.85k (x0.29)
Test#2 (FP)
33.29k
26.03k (x0.78)
Test#3 (Generic, ZIP)
17.77k
9.54k (x0.54)
Test#1 (Memory)
19.49k
22.55k (x1.16)
TOTAL
129.15k
74.97k (x0.58)

Multithread

i9-13900K

3900
Test#1 (Integers)
804.04k
229.41k (x0.29)
Test#2 (FP)
613.45k
292.81k (x0.48)
Test#3 (Generic, ZIP)
311.08k
128.48k (x0.41)
Test#1 (Memory)
34.5k
36.8k (x1.07)
TOTAL
1763.08k
687.5k (x0.39)

Performance/W
i9-13900K
3900
Test#1 (Integers)
6432 points/W
3529 points/W
Test#2 (FP)
4908 points/W
4505 points/W
Test#3 (Generic, ZIP)
2489 points/W
1977 points/W
Test#1 (Memory)
276 points/W
566 points/W
TOTAL
14105 points/W
10577 points/W

Performance/GHz
i9-13900K
3900
Test#1 (Integers)
10104 points/GHz
3920 points/GHz
Test#2 (FP)
5739 points/GHz
6054 points/GHz
Test#3 (Generic, ZIP)
3064 points/GHz
2218 points/GHz
Test#1 (Memory)
3360 points/GHz
5243 points/GHz
TOTAL
22268 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