| | | | | | |

Core i7-10870H vs Xeon E5-2670 v3


Description
The i7-10870H is based on Comet Lake architecture while the E5-2670 v3 is based on Haswell.

Using the multithread performance as a reference, the i7-10870H gets a score of 487 k points while the E5-2670 v3 gets 452.9 k points.

Summarizing, the i7-10870H is 1.1 times faster than the E5-2670 v3. To get a proper comparison between both models, take a look to the data shown below.

Specs
CPUID
a0652
306f2
Core
Comet Lake-H
Haswell-EP
Architecture
Base frecuency
2.2 GHz
2.3 GHz
Boost frecuency
5 GHz
3.1 GHz
Socket
FC-BGA 1440
LGA 2011-3
Cores/Threads
8/16
12/24
TDP
45 W
120 W
Cache L1 (d+i)
8x32+8x32 kB
12x32+12x32 kB
Cache L2
8x256 kB
12x256 kB
Cache L3
16384 kB
30720 kB
Date
September 2020
September 2014
Mean monothread perf.
79.2k points
36.41k points
Mean multithread perf.
487.05k 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
i7-10870H
E5-2670 v3
Test#1 (Integers)
4.77k
3.52k (x0.74)
Test#2 (FP)
19.81k
8.68k (x0.44)
Test#3 (Generic, ZIP)
6.29k
2.83k (x0.45)
Test#1 (Memory)
14.03k
3.13k (x0.22)
TOTAL
44.9k
18.17k (x0.4)

Multithread

i7-10870H

E5-2670 v3
Test#1 (Integers)
31.21k
32.7k (x1.05)
Test#2 (FP)
151.01k
105.18k (x0.7)
Test#3 (Generic, ZIP)
50.13k
35.18k (x0.7)
Test#1 (Memory)
8.37k
9.54k (x1.14)
TOTAL
240.71k
182.59k (x0.76)

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
i7-10870H
E5-2670 v3
Test#1 (Integers)
17.17k
11.08k (x0.64)
Test#2 (FP)
25.26k
9.57k (x0.38)
Test#3 (Generic, ZIP)
6.7k
3.18k (x0.47)
Test#1 (Memory)
13.81k
3.28k (x0.24)
TOTAL
62.95k
27.11k (x0.43)

Multithread

i7-10870H

E5-2670 v3
Test#1 (Integers)
116.68k
139.07k (x1.19)
Test#2 (FP)
187.28k
133.47k (x0.71)
Test#3 (Generic, ZIP)
51.52k
46.6k (x0.9)
Test#1 (Memory)
8.39k
6.65k (x0.79)
TOTAL
363.87k
325.78k (x0.9)

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
i7-10870H
E5-2670 v3
Test#1 (Integers)
16.14k
11.18k (x0.69)
Test#2 (FP)
24.74k
10.06k (x0.41)
Test#3 (Generic, ZIP)
5.98k
3.21k (x0.54)
Test#1 (Memory)
12.7k
3.12k (x0.25)
TOTAL
59.55k
27.57k (x0.46)

Multithread

i7-10870H

E5-2670 v3
Test#1 (Integers)
117.03k
140.98k (x1.2)
Test#2 (FP)
199.88k
145.37k (x0.73)
Test#3 (Generic, ZIP)
50.64k
45.62k (x0.9)
Test#1 (Memory)
8.23k
6.75k (x0.82)
TOTAL
375.77k
338.73k (x0.9)

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
i7-10870H
E5-2670 v3
Test#1 (Integers)
30.38k
18.62k (x0.61)
Test#2 (FP)
27.95k
10.49k (x0.38)
Test#3 (Generic, ZIP)
6.51k
4.04k (x0.62)
Test#1 (Memory)
14.37k
3.26k (x0.23)
TOTAL
79.2k
36.41k (x0.46)

Multithread

i7-10870H

E5-2670 v3
Test#1 (Integers)
216.18k
236.25k (x1.09)
Test#2 (FP)
210.82k
151.05k (x0.72)
Test#3 (Generic, ZIP)
51.57k
58.9k (x1.14)
Test#1 (Memory)
8.47k
6.7k (x0.79)
TOTAL
487.05k
452.9k (x0.93)

Performance/W
i7-10870H
E5-2670 v3
Test#1 (Integers)
4804 points/W
1969 points/W
Test#2 (FP)
4685 points/W
1259 points/W
Test#3 (Generic, ZIP)
1146 points/W
491 points/W
Test#1 (Memory)
188 points/W
56 points/W
TOTAL
10823 points/W
3774 points/W

Performance/GHz
i7-10870H
E5-2670 v3
Test#1 (Integers)
6075 points/GHz
6006 points/GHz
Test#2 (FP)
5589 points/GHz
3385 points/GHz
Test#3 (Generic, ZIP)
1302 points/GHz
1303 points/GHz
Test#1 (Memory)
2873 points/GHz
1052 points/GHz
TOTAL
15840 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