| | | | | | |

Xeon E5-4640 vs Core i5-1035G4


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

Using the multithread performance as a reference, the E5-4640 gets a score of 610.2 k points while the i5-1035G4 gets 143.9 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
206d7
706e5
Core
Sandy Bridge-EP
Ice Lake-U
Architecture
Base frecuency
2.4 GHz
1.1 GHz
Boost frecuency
2.8 GHz
3.7 GHz
Socket
LGA 2011
BGA 1526
Cores/Threads
8 /16
4/8
TDP
95 W
15 W
Cache L1 (d+i)
8x32+8x32 kB
4x32+4x48 kB
Cache L2
8x256 kB
4x512 kB
Cache L3
20480 kB
6144 kB
Date
May 2012
August 2019
Mean monothread perf.
13.88k points
65.64k points
Mean multithread perf.
610.16k 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
E5-4640
i5-1035G4
Test#1 (Integers)
1.66k
4.05k (x2.43)
Test#2 (FP)
5.26k
15.29k (x2.91)
Test#3 (Generic, ZIP)
2.13k
9.04k (x4.25)
Test#1 (Memory)
2.53k
10.54k (x4.17)
TOTAL
11.58k
38.92k (x3.36)

Multithread

E5-4640

i5-1035G4
Test#1 (Integers)
77.64k
9.05k (x0.12)
Test#2 (FP)
212.2k
33.88k (x0.16)
Test#3 (Generic, ZIP)
113.11k
15.34k (x0.14)
Test#1 (Memory)
7.54k
6.74k (x0.89)
TOTAL
410.48k
65.01k (x0.16)

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
E5-4640
i5-1035G4
Test#1 (Integers)
6.19k
7.07k (x1.14)
Test#2 (FP)
5.89k
10.55k (x1.79)
Test#3 (Generic, ZIP)
2.11k
5.27k (x2.49)
Test#1 (Memory)
2.51k
5.66k (x2.26)
TOTAL
16.7k
28.56k (x1.71)

Multithread

E5-4640

i5-1035G4
Test#1 (Integers)
244.88k
25.28k (x0.1)
Test#2 (FP)
215.35k
37.48k (x0.17)
Test#3 (Generic, ZIP)
114.64k
17.77k (x0.16)
Test#1 (Memory)
6.76k
6.92k (x1.02)
TOTAL
581.63k
87.45k (x0.15)

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
E5-4640
i5-1035G4
Test#1 (Integers)
5.01k
13.9k (x2.77)
Test#2 (FP)
4.5k
20.13k (x4.47)
Test#3 (Generic, ZIP)
2.18k
9.41k (x4.32)
Test#1 (Memory)
2.19k
10.59k (x4.84)
TOTAL
13.88k
54.03k (x3.89)

Multithread

E5-4640

i5-1035G4
Test#1 (Integers)
251.29k
55.4k (x0.22)
Test#2 (FP)
236.61k
59.01k (x0.25)
Test#3 (Generic, ZIP)
114.89k
22.83k (x0.2)
Test#1 (Memory)
7.36k
6.7k (x0.91)
TOTAL
610.16k
143.94k (x0.24)

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

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