| | | | | | |

Core i5-3320M vs i3-8100


Description
The i5-3320M is based on Ivy Bridge architecture while the i3-8100 is based on Coffee Lake.

Using the multithread performance as a reference, the i5-3320M gets a score of 58.8 k points while the i3-8100 gets 157.6 k points.

Summarizing, the i3-8100 is 2.7 times faster than the i5-3320M . To get a proper comparison between both models, take a look to the data shown below.

Specs
CPUID
306a9
906eb
Core
Ivy Bridge
Coffee Lake-S
Architecture
Base frecuency
2.6 GHz
3.6 GHz
Boost frecuency
3.3 GHz
3.6 GHz
Socket
BGA1023
LGA 1151
Cores/Threads
2/4
4/4
TDP
35 W
65 W
Cache L1 (d+i)
2x32+2x32 kB
4x32+4x32 kB
Cache L2
2x256 kB
4x256 kB
Cache L3
3072 kB
6144 kB
Date
June 2012
October 2017
Mean monothread perf.
29.22k points
59.18k points
Mean multithread perf.
58.81k points
200.4k 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
i5-3320M
i3-8100
Test#1 (Integers)
3.21k
3.72k (x1.16)
Test#2 (FP)
9.05k
15.33k (x1.69)
Test#3 (Generic, ZIP)
3.94k
4.71k (x1.19)
Test#1 (Memory)
3.93k
6.76k (x1.72)
TOTAL
20.13k
30.52k (x1.52)

Multithread

i5-3320M

i3-8100
Test#1 (Integers)
6.08k
14.48k (x2.38)
Test#2 (FP)
19.02k
59.59k (x3.13)
Test#3 (Generic, ZIP)
8.85k
18.07k (x2.04)
Test#1 (Memory)
3.98k
4.3k (x1.08)
TOTAL
37.93k
96.43k (x2.54)

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
i5-3320M
i3-8100
Test#1 (Integers)
10.89k
13.51k (x1.24)
Test#2 (FP)
9.77k
19.38k (x1.98)
Test#3 (Generic, ZIP)
3.98k
5.06k (x1.27)
Test#1 (Memory)
3.77k
7.87k (x2.09)
TOTAL
28.4k
45.81k (x1.61)

Multithread

i5-3320M

i3-8100
Test#1 (Integers)
20.23k
52.88k (x2.61)
Test#2 (FP)
20.83k
75.92k (x3.64)
Test#3 (Generic, ZIP)
9.49k
19.52k (x2.06)
Test#1 (Memory)
4.04k
4.53k (x1.12)
TOTAL
54.6k
152.86k (x2.8)

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
i5-3320M
i3-8100
Test#1 (Integers)
10.64k
13.52k (x1.27)
Test#2 (FP)
10.53k
20.57k (x1.95)
Test#3 (Generic, ZIP)
4.07k
4.96k (x1.22)
Test#1 (Memory)
3.97k
7.91k (x1.99)
TOTAL
29.22k
46.96k (x1.61)

Multithread

i5-3320M

i3-8100
Test#1 (Integers)
21.27k
53.4k (x2.51)
Test#2 (FP)
23.93k
80.87k (x3.38)
Test#3 (Generic, ZIP)
9.48k
19.03k (x2.01)
Test#1 (Memory)
4.12k
4.29k (x1.04)
TOTAL
58.81k
157.59k (x2.68)

Performance/W
i5-3320M
i3-8100
Test#1 (Integers)
608 points/W
822 points/W
Test#2 (FP)
684 points/W
1244 points/W
Test#3 (Generic, ZIP)
271 points/W
293 points/W
Test#1 (Memory)
118 points/W
66 points/W
TOTAL
1680 points/W
2425 points/W

Performance/GHz
i5-3320M
i3-8100
Test#1 (Integers)
3225 points/GHz
3757 points/GHz
Test#2 (FP)
3191 points/GHz
5714 points/GHz
Test#3 (Generic, ZIP)
1234 points/GHz
1377 points/GHz
Test#1 (Memory)
1203 points/GHz
2196 points/GHz
TOTAL
8853 points/GHz
13044 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