| | | | | | |

Core i3-1115G4 vs i3-4170


Description
The i3-1115G4 is based on Tiger Lake architecture while the i3-4170 is based on Haswell.

Using the multithread performance as a reference, the i3-1115G4 gets a score of 138 k points while the i3-4170 gets 92.7 k points.

Summarizing, the i3-1115G4 is 1.5 times faster than the i3-4170. To get a proper comparison between both models, take a look to the data shown below.

Specs
CPUID
806c1
306c3
Core
Tiger Lake UP3
Haswell
Architecture
Base frecuency
3 GHz
3.7 GHz
Boost frecuency
4.1 GHz
3.7 GHz
Socket
BGA1449
LGA1150
Cores/Threads
2/4
2/4
TDP
28 W
54 W
Cache L1 (d+i)
2x32+2x48 kB
2x32+2x32 kB
Cache L2
2x1280 kB
2x256 kB
Cache L3
6144 kB
3072 kB
Date
September 2020
March 2015
Mean monothread perf.
62.19k points
44.24k points
Mean multithread perf.
137.96k points
92.71k 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
i3-1115G4
i3-4170
Test#1 (Integers)
3.75k
4.24k (x1.13)
Test#2 (FP)
17.22k
10.58k (x0.61)
Test#3 (Generic, ZIP)
9.79k
4.87k (x0.5)
Test#1 (Memory)
8.21k
4.2k (x0.51)
TOTAL
38.97k
23.88k (x0.61)

Multithread

i3-1115G4

i3-4170
Test#1 (Integers)
9.19k
7.7k (x0.84)
Test#2 (FP)
35.47k
27.14k (x0.77)
Test#3 (Generic, ZIP)
19.14k
11.48k (x0.6)
Test#1 (Memory)
5.82k
2.68k (x0.46)
TOTAL
69.62k
49k (x0.7)

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
i3-1115G4
i3-4170
Test#1 (Integers)
12.9k
13.1k (x1.02)
Test#2 (FP)
21.4k
11.68k (x0.55)
Test#3 (Generic, ZIP)
10.73k
5.07k (x0.47)
Test#1 (Memory)
8.16k
4.19k (x0.51)
TOTAL
53.19k
34.04k (x0.64)

Multithread

i3-1115G4

i3-4170
Test#1 (Integers)
30.31k
25.81k (x0.85)
Test#2 (FP)
45.13k
25k (x0.55)
Test#3 (Generic, ZIP)
20.17k
11.96k (x0.59)
Test#1 (Memory)
5.77k
3.87k (x0.67)
TOTAL
101.38k
66.65k (x0.66)

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
i3-1115G4
i3-4170
Test#1 (Integers)
14.65k
13.24k (x0.9)
Test#2 (FP)
21.57k
12.37k (x0.57)
Test#3 (Generic, ZIP)
9.93k
5.11k (x0.51)
Test#1 (Memory)
8.02k
4.17k (x0.52)
TOTAL
54.18k
34.89k (x0.64)

Multithread

i3-1115G4

i3-4170
Test#1 (Integers)
32.14k
28.15k (x0.88)
Test#2 (FP)
43.54k
29.95k (x0.69)
Test#3 (Generic, ZIP)
19.58k
11.84k (x0.6)
Test#1 (Memory)
5.61k
2.73k (x0.49)
TOTAL
100.87k
72.68k (x0.72)

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
i3-1115G4
i3-4170
Test#1 (Integers)
24.25k
22.17k (x0.91)
Test#2 (FP)
21.63k
12.58k (x0.58)
Test#3 (Generic, ZIP)
9.09k
5.09k (x0.56)
Test#1 (Memory)
7.23k
4.4k (x0.61)
TOTAL
62.19k
44.24k (x0.71)

Multithread

i3-1115G4

i3-4170
Test#1 (Integers)
56.9k
47k (x0.83)
Test#2 (FP)
55.68k
31.06k (x0.56)
Test#3 (Generic, ZIP)
19.29k
11.96k (x0.62)
Test#1 (Memory)
6.09k
2.68k (x0.44)
TOTAL
137.96k
92.71k (x0.67)

Performance/W
i3-1115G4
i3-4170
Test#1 (Integers)
2032 points/W
870 points/W
Test#2 (FP)
1989 points/W
575 points/W
Test#3 (Generic, ZIP)
689 points/W
222 points/W
Test#1 (Memory)
217 points/W
50 points/W
TOTAL
4927 points/W
1717 points/W

Performance/GHz
i3-1115G4
i3-4170
Test#1 (Integers)
5914 points/GHz
5991 points/GHz
Test#2 (FP)
5275 points/GHz
3401 points/GHz
Test#3 (Generic, ZIP)
2216 points/GHz
1375 points/GHz
Test#1 (Memory)
1764 points/GHz
1189 points/GHz
TOTAL
15169 points/GHz
11956 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