| | | | | | |

Core i5-4690K vs i5-1035G4


Description
The i5-4690K is based on Haswell architecture while the i5-1035G4 is based on Ice Lake.

Using the multithread performance as a reference, the i5-4690K gets a score of 117.4 k points while the i5-1035G4 gets 143.9 k points.

Summarizing, the i5-1035G4 is 1.2 times faster than the i5-4690K . To get a proper comparison between both models, take a look to the data shown below.

Specs
CPUID
306c3
706e5
Core
Haswell
Ice Lake-U
Architecture
Base frecuency
3.5 GHz
1.1 GHz
Boost frecuency
3.9 GHz
3.7 GHz
Socket
LGA 1150
BGA 1526
Cores/Threads
4/4
4/8
TDP
88 W
15 W
Cache L1 (d+i)
4x32+4x32 kB
4x32+4x48 kB
Cache L2
4x256 kB
4x512 kB
Cache L3
6144 kB
6144 kB
Date
June 2014
August 2019
Mean monothread perf.
34.37k points
65.64k points
Mean multithread perf.
117.37k points
142.69k 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
i5-4690K
i5-1035G4
Test#1 (Integers)
4.39k
4.05k (x0.92)
Test#2 (FP)
10.93k
15.29k (x1.4)
Test#3 (Generic, ZIP)
4.82k
9.04k (x1.87)
Test#1 (Memory)
4.11k
10.54k (x2.57)
TOTAL
24.26k
38.92k (x1.6)

Multithread

i5-4690K

i5-1035G4
Test#1 (Integers)
8.67k
9.05k (x1.04)
Test#2 (FP)
21.42k
33.88k (x1.58)
Test#3 (Generic, ZIP)
9.52k
15.34k (x1.61)
Test#1 (Memory)
4.18k
6.74k (x1.61)
TOTAL
43.79k
65.01k (x1.48)

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
i5-4690K
i5-1035G4
Test#1 (Integers)
13.67k
7.07k (x0.52)
Test#2 (FP)
11.97k
10.55k (x0.88)
Test#3 (Generic, ZIP)
5.12k
5.27k (x1.03)
Test#1 (Memory)
4.4k
5.66k (x1.29)
TOTAL
35.17k
28.56k (x0.81)

Multithread

i5-4690K

i5-1035G4
Test#1 (Integers)
51.76k
25.28k (x0.49)
Test#2 (FP)
43.26k
37.48k (x0.87)
Test#3 (Generic, ZIP)
19.32k
17.77k (x0.92)
Test#1 (Memory)
2.69k
6.92k (x2.58)
TOTAL
117.03k
87.45k (x0.75)

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
i5-4690K
i5-1035G4
Test#1 (Integers)
13.71k
13.9k (x1.01)
Test#2 (FP)
12.53k
20.13k (x1.61)
Test#3 (Generic, ZIP)
4.98k
9.41k (x1.89)
Test#1 (Memory)
3.15k
10.59k (x3.36)
TOTAL
34.37k
54.03k (x1.57)

Multithread

i5-4690K

i5-1035G4
Test#1 (Integers)
50.91k
55.4k (x1.09)
Test#2 (FP)
45.46k
59.01k (x1.3)
Test#3 (Generic, ZIP)
18.55k
22.83k (x1.23)
Test#1 (Memory)
2.44k
6.7k (x2.74)
TOTAL
117.37k
143.94k (x1.23)

Performance/W
i5-4690K
i5-1035G4
Test#1 (Integers)
579 points/W
3694 points/W
Test#2 (FP)
517 points/W
3934 points/W
Test#3 (Generic, ZIP)
211 points/W
1522 points/W
Test#1 (Memory)
28 points/W
446 points/W
TOTAL
1334 points/W
9596 points/W

Performance/GHz
i5-4690K
i5-1035G4
Test#1 (Integers)
3515 points/GHz
3757 points/GHz
Test#2 (FP)
3213 points/GHz
5440 points/GHz
Test#3 (Generic, ZIP)
1277 points/GHz
2543 points/GHz
Test#1 (Memory)
807 points/GHz
2862 points/GHz
TOTAL
8812 points/GHz
14601 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