| | | | | | |

Core i9-7980XE vs Ryzen 9 3900


Description
The i9-7980XE is based on Skylake architecture while the 3900 is based on Zen 2.

Using the multithread performance as a reference, the i9-7980XE gets a score of 1223.8 k points while the 3900 gets 687.5 k points.

Summarizing, the i9-7980XE is 1.8 times faster than the 3900. To get a proper comparison between both models, take a look to the data shown below.

Specs
CPUID
50654
870f10
Core
Skylake-X
Matisse
Architecture
Base frecuency
2.6 GHz
3.1 GHz
Boost frecuency
4.4 GHz
4.3 GHz
Socket
LGA 2066
AM4
Cores/Threads
18/36
12/24
TDP
165 W
65 W
Cache L1 (d+i)
18x32+18x32 kB
12x32+12x32 kB
Cache L2
18x1024 kB
12x512 kB
Cache L3
25344 kB
4x16384 kB
Date
May 2017
September 2019
Mean monothread perf.
76.43k points
74.97k points
Mean multithread perf.
1223.79k 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
i9-7980XE
3900
Test#1 (Integers)
4.89k
4.39k (x0.9)
Test#2 (FP)
19.98k
16.99k (x0.85)
Test#3 (Generic, ZIP)
6.14k
7.74k (x1.26)
Test#1 (Memory)
9.81k
24.57k (x2.5)
TOTAL
40.82k
53.69k (x1.32)

Multithread

i9-7980XE

3900
Test#1 (Integers)
79.8k
48.45k (x0.61)
Test#2 (FP)
372.72k
230.81k (x0.62)
Test#3 (Generic, ZIP)
121.42k
122.82k (x1.01)
Test#1 (Memory)
26.48k
54.73k (x2.07)
TOTAL
600.43k
456.8k (x0.76)

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
i9-7980XE
3900
Test#1 (Integers)
31.16k
16.85k (x0.54)
Test#2 (FP)
28.13k
26.03k (x0.93)
Test#3 (Generic, ZIP)
6.65k
9.54k (x1.43)
Test#1 (Memory)
10.5k
22.55k (x2.15)
TOTAL
76.43k
74.97k (x0.98)

Multithread

i9-7980XE

3900
Test#1 (Integers)
560.19k
229.41k (x0.41)
Test#2 (FP)
516.97k
292.81k (x0.57)
Test#3 (Generic, ZIP)
123.94k
128.48k (x1.04)
Test#1 (Memory)
22.69k
36.8k (x1.62)
TOTAL
1223.79k
687.5k (x0.56)

Performance/W
i9-7980XE
3900
Test#1 (Integers)
3395 points/W
3529 points/W
Test#2 (FP)
3133 points/W
4505 points/W
Test#3 (Generic, ZIP)
751 points/W
1977 points/W
Test#1 (Memory)
137 points/W
566 points/W
TOTAL
7417 points/W
10577 points/W

Performance/GHz
i9-7980XE
3900
Test#1 (Integers)
7081 points/GHz
3920 points/GHz
Test#2 (FP)
6392 points/GHz
6054 points/GHz
Test#3 (Generic, ZIP)
1512 points/GHz
2218 points/GHz
Test#1 (Memory)
2386 points/GHz
5243 points/GHz
TOTAL
17371 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