| | | | | | |

Ryzen 9 3900 vs Ryzen 7 1700X


Description
The 3900 is based on Zen 2 architecture while the 1700X is based on Zen.

Using the multithread performance as a reference, the 3900 gets a score of 687.5 k points while the 1700X gets 372.7 k points.

Summarizing, the 3900 is 1.8 times faster than the 1700X. To get a proper comparison between both models, take a look to the data shown below.

Specs
CPUID
870f10
800f11
Core
Matisse
Summit Ridge
Architecture
Base frecuency
3.1 GHz
3.4 GHz
Boost frecuency
4.3 GHz
3.8 GHz
Socket
AM4
AM4
Cores/Threads
12/24
8/16
TDP
65 W
95 W
Cache L1 (d+i)
12x32+12x32 kB
8x64+8x32 kB
Cache L2
12x512 kB
8x512 kB
Cache L3
4x16384 kB
2x8192 kB
Date
September 2019
March 2017
Mean monothread perf.
74.97k points
56.76k points
Mean multithread perf.
687.5k points
372.73k points

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
3900
1700X
Test#1 (Integers)
16.16k
12.5k (x0.77)
Test#2 (FP)
23.75k
22.92k (x0.96)
Test#3 (Generic, ZIP)
9.32k
5.45k (x0.58)
Test#1 (Memory)
23.17k
14.72k (x0.64)
TOTAL
72.4k
55.59k (x0.77)

Multithread

3900

1700X
Test#1 (Integers)
174.73k
92.51k (x0.53)
Test#2 (FP)
275.63k
144.76k (x0.53)
Test#3 (Generic, ZIP)
125.65k
54.43k (x0.43)
Test#1 (Memory)
44.17k
22.08k (x0.5)
TOTAL
620.18k
313.78k (x0.51)

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
1700X
Test#1 (Integers)
16.85k
13.72k (x0.81)
Test#2 (FP)
26.03k
22.48k (x0.86)
Test#3 (Generic, ZIP)
9.54k
5.12k (x0.54)
Test#1 (Memory)
22.55k
15.44k (x0.68)
TOTAL
74.97k
56.76k (x0.76)

Multithread

3900

1700X
Test#1 (Integers)
229.41k
110.92k (x0.48)
Test#2 (FP)
292.81k
200.56k (x0.68)
Test#3 (Generic, ZIP)
128.48k
54.24k (x0.42)
Test#1 (Memory)
36.8k
7.01k (x0.19)
TOTAL
687.5k
372.73k (x0.54)

Performance/W
3900
1700X
Test#1 (Integers)
3529 points/W
1168 points/W
Test#2 (FP)
4505 points/W
2111 points/W
Test#3 (Generic, ZIP)
1977 points/W
571 points/W
Test#1 (Memory)
566 points/W
74 points/W
TOTAL
10577 points/W
3923 points/W

Performance/GHz
3900
1700X
Test#1 (Integers)
3920 points/GHz
3611 points/GHz
Test#2 (FP)
6054 points/GHz
5916 points/GHz
Test#3 (Generic, ZIP)
2218 points/GHz
1348 points/GHz
Test#1 (Memory)
5243 points/GHz
4063 points/GHz
TOTAL
17435 points/GHz
14938 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