| | | | | | |

Core i3-7100 vs i7-8650U


Description
Both models i3-7100 and i7-8650U are based on Kaby Lake architecture.

The first Kaby Lake CPU was released in August 2016. It uses a 14 nm process and was the first architecture in breaking the previous tick-tock model. Actually, it is not that different from the preceding Skylake: it has 64kB of L1 cache and 256kB L2 cache per core.

Using the multithread performance as a reference, the i3-7100 gets a score of 126.5 k points while the i7-8650U gets 173.5 k points.

Summarizing, the i7-8650U is 1.4 times faster than the i3-7100. To get a proper comparison between both models, take a look to the data shown below.

Specs
CPUID
906e9
806ea
Core
Kaby Lake-S
Kaby Lake-R
Architecture
Base frecuency
3.9 GHz
1.9 GHz
Boost frecuency
3.9 GHz
4.2 GHz
Socket
LGA 1151
BGA 1356
Cores/Threads
2/4
4/8
TDP
51 W
15 W
Cache L1 (d+i)
2x32+2x32 kB
4x32+4x32 kB
Cache L2
2x256 kB
4x256 kB
Cache L3
3072 kB
8192 kB
Date
January 2017
August 2017
Mean monothread perf.
58.55k points
55.86k points
Mean multithread perf.
126.47k points
173.49k 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
i3-7100
i7-8650U
Test#1 (Integers)
25.77k
21.61k (x0.84)
Test#2 (FP)
23.26k
19.69k (x0.85)
Test#3 (Generic, ZIP)
5.43k
4.61k (x0.85)
Test#1 (Memory)
4.09k
9.95k (x2.43)
TOTAL
58.55k
55.86k (x0.95)

Multithread

i3-7100

i7-8650U
Test#1 (Integers)
54.98k
78.38k (x1.43)
Test#2 (FP)
54.73k
72.02k (x1.32)
Test#3 (Generic, ZIP)
13.12k
16.95k (x1.29)
Test#1 (Memory)
3.65k
6.15k (x1.68)
TOTAL
126.47k
173.49k (x1.37)

Performance/W
i3-7100
i7-8650U
Test#1 (Integers)
1078 points/W
5225 points/W
Test#2 (FP)
1073 points/W
4802 points/W
Test#3 (Generic, ZIP)
257 points/W
1130 points/W
Test#1 (Memory)
72 points/W
410 points/W
TOTAL
2480 points/W
11566 points/W

Performance/GHz
i3-7100
i7-8650U
Test#1 (Integers)
6607 points/GHz
5146 points/GHz
Test#2 (FP)
5964 points/GHz
4689 points/GHz
Test#3 (Generic, ZIP)
1393 points/GHz
1097 points/GHz
Test#1 (Memory)
1049 points/GHz
2368 points/GHz
TOTAL
15014 points/GHz
13300 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