| | | | | | |

Core i3-10105 vs i3-9100


Description
The i3-10105 is based on Comet Lake architecture while the i3-9100 is based on Coffee Lake.

Using the multithread performance as a reference, the i3-10105 gets a score of 253.9 k points while the i3-9100 gets 229.2 k points.

Summarizing, the i3-10105 is 1.1 times faster than the i3-9100. To get a proper comparison between both models, take a look to the data shown below.

Specs
CPUID
a0653
906eb
Core
Comet Lake-S
Coffee Lake-S
Architecture
Base frecuency
3.7 GHz
3.6 GHz
Boost frecuency
4.4 GHz
4.2 GHz
Socket
LGA 1200
LGA 1151
Cores/Threads
4/8
4/4
TDP
65 W
65 W
Cache L1 (d+i)
4x32+4x32 kB
4x32+4x32 kB
Cache L2
4x256 kB
4x256 kB
Cache L3
6144 kB
6144 kB
Date
March 2021
April 2019
Mean monothread perf.
68.92k points
66.74k points
Mean multithread perf.
253.93k points
229.2k 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
i3-10105
i3-9100
Test#1 (Integers)
4.5k
4.3k (x0.95)
Test#2 (FP)
18.39k
17.79k (x0.97)
Test#3 (Generic, ZIP)
5.78k
5.58k (x0.96)
Test#1 (Memory)
8.3k
8.86k (x1.07)
TOTAL
36.97k
36.53k (x0.99)

Multithread

i3-10105

i3-9100
Test#1 (Integers)
16.13k
15.99k (x0.99)
Test#2 (FP)
75.62k
66.31k (x0.88)
Test#3 (Generic, ZIP)
27.88k
20.75k (x0.74)
Test#1 (Memory)
3.57k
4.44k (x1.24)
TOTAL
123.2k
107.49k (x0.87)

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
i3-10105
i3-9100
Test#1 (Integers)
16.19k
15.53k (x0.96)
Test#2 (FP)
23.07k
22.21k (x0.96)
Test#3 (Generic, ZIP)
6.04k
5.79k (x0.96)
Test#1 (Memory)
8.46k
8.31k (x0.98)
TOTAL
53.77k
51.84k (x0.96)

Multithread

i3-10105

i3-9100
Test#1 (Integers)
57.59k
58.56k (x1.02)
Test#2 (FP)
100.63k
86.17k (x0.86)
Test#3 (Generic, ZIP)
28.59k
22.4k (x0.78)
Test#1 (Memory)
3.56k
4.55k (x1.28)
TOTAL
190.38k
171.69k (x0.9)

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
i3-10105
i3-9100
Test#1 (Integers)
16.11k
14.81k (x0.92)
Test#2 (FP)
24.12k
22.15k (x0.92)
Test#3 (Generic, ZIP)
5.71k
5.42k (x0.95)
Test#1 (Memory)
7.89k
4.8k (x0.61)
TOTAL
53.83k
47.17k (x0.88)

Multithread

i3-10105

i3-9100
Test#1 (Integers)
58.25k
52.08k (x0.89)
Test#2 (FP)
105.73k
87.45k (x0.83)
Test#3 (Generic, ZIP)
27.8k
20.98k (x0.75)
Test#1 (Memory)
3.51k
4.24k (x1.21)
TOTAL
195.29k
164.75k (x0.84)

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
i3-10105
i3-9100
Test#1 (Integers)
28.9k
28.03k (x0.97)
Test#2 (FP)
25.85k
24.5k (x0.95)
Test#3 (Generic, ZIP)
5.88k
5.73k (x0.98)
Test#1 (Memory)
8.29k
8.48k (x1.02)
TOTAL
68.92k
66.74k (x0.97)

Multithread

i3-10105

i3-9100
Test#1 (Integers)
111.69k
107.5k (x0.96)
Test#2 (FP)
110.23k
95.11k (x0.86)
Test#3 (Generic, ZIP)
28.45k
22.02k (x0.77)
Test#1 (Memory)
3.56k
4.57k (x1.29)
TOTAL
253.93k
229.2k (x0.9)

Performance/W
i3-10105
i3-9100
Test#1 (Integers)
1718 points/W
1654 points/W
Test#2 (FP)
1696 points/W
1463 points/W
Test#3 (Generic, ZIP)
438 points/W
339 points/W
Test#1 (Memory)
55 points/W
70 points/W
TOTAL
3907 points/W
3526 points/W

Performance/GHz
i3-10105
i3-9100
Test#1 (Integers)
6568 points/GHz
6675 points/GHz
Test#2 (FP)
5876 points/GHz
5833 points/GHz
Test#3 (Generic, ZIP)
1337 points/GHz
1365 points/GHz
Test#1 (Memory)
1883 points/GHz
2018 points/GHz
TOTAL
15664 points/GHz
15891 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