| | | | | | |

Core i5-1035G4 vs Xeon E5-4640


Description
The i5-1035G4 is based on Ice Lake architecture while the E5-4640 is based on Sandy Bridge.

Using the multithread performance as a reference, the i5-1035G4 gets a score of 143.9 k points while the E5-4640 gets 610.2 k points.

Summarizing, the E5-4640 is 4.2 times faster than the i5-1035G4. To get a proper comparison between both models, take a look to the data shown below.

Specs
CPUID
706e5
206d7
Core
Ice Lake-U
Sandy Bridge-EP
Architecture
Base frecuency
1.1 GHz
2.4 GHz
Boost frecuency
3.7 GHz
2.8 GHz
Socket
BGA 1526
LGA 2011
Cores/Threads
4/8
8 /16
TDP
15 W
95 W
Cache L1 (d+i)
4x32+4x48 kB
8x32+8x32 kB
Cache L2
4x512 kB
8x256 kB
Cache L3
6144 kB
20480 kB
Date
August 2019
May 2012
Mean monothread perf.
65.64k points
13.88k points
Mean multithread perf.
142.69k points
610.16k 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
i5-1035G4
E5-4640
Test#1 (Integers)
4.05k
1.66k (x0.41)
Test#2 (FP)
15.29k
5.26k (x0.34)
Test#3 (Generic, ZIP)
9.04k
2.13k (x0.24)
Test#1 (Memory)
10.54k
2.53k (x0.24)
TOTAL
38.92k
11.58k (x0.3)

Multithread

i5-1035G4

E5-4640
Test#1 (Integers)
9.05k
77.64k (x8.58)
Test#2 (FP)
33.88k
212.2k (x6.26)
Test#3 (Generic, ZIP)
15.34k
113.11k (x7.37)
Test#1 (Memory)
6.74k
7.54k (x1.12)
TOTAL
65.01k
410.48k (x6.31)

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
i5-1035G4
E5-4640
Test#1 (Integers)
7.07k
6.19k (x0.88)
Test#2 (FP)
10.55k
5.89k (x0.56)
Test#3 (Generic, ZIP)
5.27k
2.11k (x0.4)
Test#1 (Memory)
5.66k
2.51k (x0.44)
TOTAL
28.56k
16.7k (x0.58)

Multithread

i5-1035G4

E5-4640
Test#1 (Integers)
25.28k
244.88k (x9.69)
Test#2 (FP)
37.48k
215.35k (x5.75)
Test#3 (Generic, ZIP)
17.77k
114.64k (x6.45)
Test#1 (Memory)
6.92k
6.76k (x0.98)
TOTAL
87.45k
581.63k (x6.65)

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
i5-1035G4
E5-4640
Test#1 (Integers)
13.9k
5.01k (x0.36)
Test#2 (FP)
20.13k
4.5k (x0.22)
Test#3 (Generic, ZIP)
9.41k
2.18k (x0.23)
Test#1 (Memory)
10.59k
2.19k (x0.21)
TOTAL
54.03k
13.88k (x0.26)

Multithread

i5-1035G4

E5-4640
Test#1 (Integers)
55.4k
251.29k (x4.54)
Test#2 (FP)
59.01k
236.61k (x4.01)
Test#3 (Generic, ZIP)
22.83k
114.89k (x5.03)
Test#1 (Memory)
6.7k
7.36k (x1.1)
TOTAL
143.94k
610.16k (x4.24)

Performance/W
i5-1035G4
E5-4640
Test#1 (Integers)
3694 points/W
2645 points/W
Test#2 (FP)
3934 points/W
2491 points/W
Test#3 (Generic, ZIP)
1522 points/W
1209 points/W
Test#1 (Memory)
446 points/W
78 points/W
TOTAL
9596 points/W
6423 points/W

Performance/GHz
i5-1035G4
E5-4640
Test#1 (Integers)
3757 points/GHz
1790 points/GHz
Test#2 (FP)
5440 points/GHz
1609 points/GHz
Test#3 (Generic, ZIP)
2543 points/GHz
777 points/GHz
Test#1 (Memory)
2862 points/GHz
782 points/GHz
TOTAL
14601 points/GHz
4957 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