| | | | | | |

Core i7-1165G7 vs Xeon E5-2670 v3


Description
The i7-1165G7 is based on Tiger Lake architecture while the E5-2670 v3 is based on Haswell.

Using the multithread performance as a reference, the i7-1165G7 gets a score of 210.4 k points while the E5-2670 v3 gets 452.9 k points.

Summarizing, the E5-2670 v3 is 2.2 times faster than the i7-1165G7. To get a proper comparison between both models, take a look to the data shown below.

Specs
CPUID
806c1
306f2
Core
Tiger Lake-UP3
Haswell-EP
Architecture
Base frecuency
2.8 GHz
2.3 GHz
Boost frecuency
4.7 GHz
3.1 GHz
Socket
BGA 1449
LGA 2011-3
Cores/Threads
4/8
12/24
TDP
28 W
120 W
Cache L1 (d+i)
4x32+4x48 kB
12x32+12x32 kB
Cache L2
4x1280 kB
12x256 kB
Cache L3
12288 kB
30720 kB
Date
September 2020
September 2014
Mean monothread perf.
62.1k points
36.41k points
Mean multithread perf.
210.4k points
452.9k 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
i7-1165G7
E5-2670 v3
Test#1 (Integers)
4.26k
3.52k (x0.83)
Test#2 (FP)
19.54k
8.68k (x0.44)
Test#3 (Generic, ZIP)
10.95k
2.83k (x0.26)
Test#1 (Memory)
11.08k
3.13k (x0.28)
TOTAL
45.84k
18.17k (x0.4)

Multithread

i7-1165G7

E5-2670 v3
Test#1 (Integers)
15.69k
32.7k (x2.08)
Test#2 (FP)
68.3k
105.18k (x1.54)
Test#3 (Generic, ZIP)
33.66k
35.18k (x1.05)
Test#1 (Memory)
12.16k
9.54k (x0.78)
TOTAL
129.81k
182.59k (x1.41)

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
i7-1165G7
E5-2670 v3
Test#1 (Integers)
14.48k
11.08k (x0.76)
Test#2 (FP)
24.18k
9.57k (x0.4)
Test#3 (Generic, ZIP)
11.95k
3.18k (x0.27)
Test#1 (Memory)
11.01k
3.28k (x0.3)
TOTAL
61.62k
27.11k (x0.44)

Multithread

i7-1165G7

E5-2670 v3
Test#1 (Integers)
50.98k
139.07k (x2.73)
Test#2 (FP)
80.7k
133.47k (x1.65)
Test#3 (Generic, ZIP)
36.61k
46.6k (x1.27)
Test#1 (Memory)
12.02k
6.65k (x0.55)
TOTAL
180.32k
325.78k (x1.81)

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
i7-1165G7
E5-2670 v3
Test#1 (Integers)
16.27k
11.18k (x0.69)
Test#2 (FP)
25.74k
10.06k (x0.39)
Test#3 (Generic, ZIP)
11.5k
3.21k (x0.28)
Test#1 (Memory)
10.82k
3.12k (x0.29)
TOTAL
64.32k
27.57k (x0.43)

Multithread

i7-1165G7

E5-2670 v3
Test#1 (Integers)
54k
140.98k (x2.61)
Test#2 (FP)
88.76k
145.37k (x1.64)
Test#3 (Generic, ZIP)
35.23k
45.62k (x1.29)
Test#1 (Memory)
12.14k
6.75k (x0.56)
TOTAL
190.12k
338.73k (x1.78)

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
i7-1165G7
E5-2670 v3
Test#1 (Integers)
22.97k
18.62k (x0.81)
Test#2 (FP)
21.61k
10.49k (x0.49)
Test#3 (Generic, ZIP)
8.99k
4.04k (x0.45)
Test#1 (Memory)
8.52k
3.26k (x0.38)
TOTAL
62.1k
36.41k (x0.59)

Multithread

i7-1165G7

E5-2670 v3
Test#1 (Integers)
82.75k
236.25k (x2.86)
Test#2 (FP)
86.58k
151.05k (x1.74)
Test#3 (Generic, ZIP)
29.34k
58.9k (x2.01)
Test#1 (Memory)
11.72k
6.7k (x0.57)
TOTAL
210.4k
452.9k (x2.15)

Performance/W
i7-1165G7
E5-2670 v3
Test#1 (Integers)
2955 points/W
1969 points/W
Test#2 (FP)
3092 points/W
1259 points/W
Test#3 (Generic, ZIP)
1048 points/W
491 points/W
Test#1 (Memory)
419 points/W
56 points/W
TOTAL
7514 points/W
3774 points/W

Performance/GHz
i7-1165G7
E5-2670 v3
Test#1 (Integers)
4887 points/GHz
6006 points/GHz
Test#2 (FP)
4599 points/GHz
3385 points/GHz
Test#3 (Generic, ZIP)
1912 points/GHz
1303 points/GHz
Test#1 (Memory)
1813 points/GHz
1052 points/GHz
TOTAL
13212 points/GHz
11745 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