| | | | | | |

Core i7-10870H vs Ryzen 9 3900X


Description
The i7-10870H is based on Comet Lake architecture while the 3900X is based on Zen 2.

Using the multithread performance as a reference, the i7-10870H gets a score of 487 k points while the 3900X gets 756.3 k points.

Summarizing, the 3900X is 1.6 times faster than the i7-10870H. To get a proper comparison between both models, take a look to the data shown below.

Specs
CPUID
a0652
870f10
Core
Comet Lake-H
Matisse
Architecture
Base frecuency
2.2 GHz
3.8 GHz
Boost frecuency
5 GHz
4.6 GHz
Socket
FC-BGA 1440
AM4
Cores/Threads
8/16
12/24
TDP
45 W
105 W
Cache L1 (d+i)
8x32+8x32 kB
12x32+12x32 kB
Cache L2
8x256 kB
12x512 kB
Cache L3
16384 kB
4x16384 kB
Date
September 2020
July 2019
Mean monothread perf.
79.2k points
72.51k points
Mean multithread perf.
487.05k points
756.3k 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
i7-10870H
3900X
Test#1 (Integers)
4.77k
4.46k (x0.94)
Test#2 (FP)
19.81k
18.46k (x0.93)
Test#3 (Generic, ZIP)
6.29k
8.05k (x1.28)
Test#1 (Memory)
14.03k
23.71k (x1.69)
TOTAL
44.9k
54.68k (x1.22)

Multithread

i7-10870H

3900X
Test#1 (Integers)
31.21k
52.65k (x1.69)
Test#2 (FP)
151.01k
265.41k (x1.76)
Test#3 (Generic, ZIP)
50.13k
140.78k (x2.81)
Test#1 (Memory)
8.37k
46.91k (x5.61)
TOTAL
240.71k
505.76k (x2.1)

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
i7-10870H
3900X
Test#1 (Integers)
17.17k
17.35k (x1.01)
Test#2 (FP)
25.26k
25.87k (x1.02)
Test#3 (Generic, ZIP)
6.7k
8.72k (x1.3)
Test#1 (Memory)
13.81k
27.86k (x2.02)
TOTAL
62.95k
79.8k (x1.27)

Multithread

i7-10870H

3900X
Test#1 (Integers)
116.68k
201.57k (x1.73)
Test#2 (FP)
187.28k
284.41k (x1.52)
Test#3 (Generic, ZIP)
51.52k
145.16k (x2.82)
Test#1 (Memory)
8.39k
100.56k (x11.99)
TOTAL
363.87k
731.7k (x2.01)

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
i7-10870H
3900X
Test#1 (Integers)
16.14k
16.95k (x1.05)
Test#2 (FP)
24.74k
25.37k (x1.03)
Test#3 (Generic, ZIP)
5.98k
9.23k (x1.54)
Test#1 (Memory)
12.7k
24.83k (x1.96)
TOTAL
59.55k
76.38k (x1.28)

Multithread

i7-10870H

3900X
Test#1 (Integers)
117.03k
196.31k (x1.68)
Test#2 (FP)
199.88k
290.5k (x1.45)
Test#3 (Generic, ZIP)
50.64k
143.95k (x2.84)
Test#1 (Memory)
8.23k
64.92k (x7.89)
TOTAL
375.77k
695.69k (x1.85)

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
i7-10870H
3900X
Test#1 (Integers)
30.38k
16.73k (x0.55)
Test#2 (FP)
27.95k
24.74k (x0.89)
Test#3 (Generic, ZIP)
6.51k
8.82k (x1.35)
Test#1 (Memory)
14.37k
22.22k (x1.55)
TOTAL
79.2k
72.51k (x0.92)

Multithread

i7-10870H

3900X
Test#1 (Integers)
216.18k
248.24k (x1.15)
Test#2 (FP)
210.82k
309.66k (x1.47)
Test#3 (Generic, ZIP)
51.57k
140.01k (x2.71)
Test#1 (Memory)
8.47k
58.39k (x6.9)
TOTAL
487.05k
756.3k (x1.55)

Performance/W
i7-10870H
3900X
Test#1 (Integers)
4804 points/W
2364 points/W
Test#2 (FP)
4685 points/W
2949 points/W
Test#3 (Generic, ZIP)
1146 points/W
1333 points/W
Test#1 (Memory)
188 points/W
556 points/W
TOTAL
10823 points/W
7203 points/W

Performance/GHz
i7-10870H
3900X
Test#1 (Integers)
6075 points/GHz
3638 points/GHz
Test#2 (FP)
5589 points/GHz
5377 points/GHz
Test#3 (Generic, ZIP)
1302 points/GHz
1917 points/GHz
Test#1 (Memory)
2873 points/GHz
4831 points/GHz
TOTAL
15840 points/GHz
15763 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