| | | | | | |

Core i7-6820HQ vs Xeon E5-2620 v4


Description
The i7-6820HQ is based on Skylake architecture while the E5-2620 v4 is based on Broadwell.

Using the multithread performance as a reference, the i7-6820HQ gets a score of 205.9 k points while the E5-2620 v4 gets 237.8 k points.

Summarizing, the E5-2620 v4 is 1.2 times faster than the i7-6820HQ. To get a proper comparison between both models, take a look to the data shown below.

Specs
CPUID
506e3
406f1
Core
Skylake-H
Broadwell-EP
Architecture
Base frecuency
2.7 GHz
2.1 GHz
Boost frecuency
3.6 GHz
3 GHz
Socket
BGA1440
Socket 2011-3
Cores/Threads
4/8
8/16
TDP
45 W
85 W
Cache L1 (d+i)
4x32+4x32 kB
8x32+8x32 kB
Cache L2
4x256 kB
8x256 kB
Cache L3
8192 kB
20480 kB
Date
October 2015
March 2016
Mean monothread perf.
50.1k points
29.39k points
Mean multithread perf.
205.89k points
237.83k 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
i7-6820HQ
E5-2620 v4
Test#1 (Integers)
3.18k
2.6k (x0.82)
Test#2 (FP)
13.02k
7.55k (x0.58)
Test#3 (Generic, ZIP)
4.17k
2.61k (x0.63)
Test#1 (Memory)
6.93k
2.03k (x0.29)
TOTAL
27.3k
14.79k (x0.54)

Multithread

i7-6820HQ

E5-2620 v4
Test#1 (Integers)
13.26k
17.41k (x1.31)
Test#2 (FP)
62.23k
75.46k (x1.21)
Test#3 (Generic, ZIP)
20.34k
26.25k (x1.29)
Test#1 (Memory)
5.46k
4.65k (x0.85)
TOTAL
101.29k
123.78k (x1.22)

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
i7-6820HQ
E5-2620 v4
Test#1 (Integers)
11.54k
8.22k (x0.71)
Test#2 (FP)
16.69k
12.06k (x0.72)
Test#3 (Generic, ZIP)
4.51k
4.01k (x0.89)
Test#1 (Memory)
7.27k
2.89k (x0.4)
TOTAL
40.01k
27.18k (x0.68)

Multithread

i7-6820HQ

E5-2620 v4
Test#1 (Integers)
48.5k
61.34k (x1.26)
Test#2 (FP)
77.02k
90.21k (x1.17)
Test#3 (Generic, ZIP)
21.3k
26.2k (x1.23)
Test#1 (Memory)
5.24k
4.62k (x0.88)
TOTAL
152.06k
182.37k (x1.2)

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
i7-6820HQ
E5-2620 v4
Test#1 (Integers)
11.78k
6.04k (x0.51)
Test#2 (FP)
18.06k
10.18k (x0.56)
Test#3 (Generic, ZIP)
4.48k
2.74k (x0.61)
Test#1 (Memory)
7.12k
2.41k (x0.34)
TOTAL
41.44k
21.37k (x0.52)

Multithread

i7-6820HQ

E5-2620 v4
Test#1 (Integers)
49.46k
47.51k (x0.96)
Test#2 (FP)
84.8k
75.12k (x0.89)
Test#3 (Generic, ZIP)
20.7k
19.72k (x0.95)
Test#1 (Memory)
4.77k
5.45k (x1.14)
TOTAL
159.73k
147.8k (x0.93)

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
i7-6820HQ
E5-2620 v4
Test#1 (Integers)
20.99k
12.16k (x0.58)
Test#2 (FP)
18.63k
11.82k (x0.63)
Test#3 (Generic, ZIP)
4.33k
3.02k (x0.7)
Test#1 (Memory)
6.15k
2.4k (x0.39)
TOTAL
50.1k
29.39k (x0.59)

Multithread

i7-6820HQ

E5-2620 v4
Test#1 (Integers)
91.8k
103.77k (x1.13)
Test#2 (FP)
87.24k
102.28k (x1.17)
Test#3 (Generic, ZIP)
20.55k
26.13k (x1.27)
Test#1 (Memory)
6.3k
5.65k (x0.9)
TOTAL
205.89k
237.83k (x1.16)

Performance/W
i7-6820HQ
E5-2620 v4
Test#1 (Integers)
2040 points/W
1221 points/W
Test#2 (FP)
1939 points/W
1203 points/W
Test#3 (Generic, ZIP)
457 points/W
307 points/W
Test#1 (Memory)
140 points/W
66 points/W
TOTAL
4575 points/W
2798 points/W

Performance/GHz
i7-6820HQ
E5-2620 v4
Test#1 (Integers)
5831 points/GHz
4054 points/GHz
Test#2 (FP)
5174 points/GHz
3939 points/GHz
Test#3 (Generic, ZIP)
1204 points/GHz
1005 points/GHz
Test#1 (Memory)
1708 points/GHz
799 points/GHz
TOTAL
13917 points/GHz
9798 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