| | | | | | |

Xeon E5-2620 v4 vs Core i7-4790K


Description
The E5-2620 v4 is based on Broadwell architecture while the i7-4790K is based on Haswell.

Using the multithread performance as a reference, the E5-2620 v4 gets a score of 237.8 k points while the i7-4790K gets 215.5 k points.

Summarizing, the E5-2620 v4 is 1.1 times faster than the i7-4790K . To get a proper comparison between both models, take a look to the data shown below.

Specs
CPUID
406f1
306c3
Core
Broadwell-EP
Haswell
Architecture
Base frecuency
2.1 GHz
4 GHz
Boost frecuency
3 GHz
4.4 GHz
Socket
Socket 2011-3
LGA 1150
Cores/Threads
8/16
4/8
TDP
85 W
88 W
Cache L1 (d+i)
8x32+8x32 kB
32+32 kB
Cache L2
8x256 kB
256 kB
Cache L3
20480 kB
8192 kB
Date
March 2016
May 2014
Mean monothread perf.
29.39k points
52.47k points
Mean multithread perf.
237.83k points
215.47k 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
E5-2620 v4
i7-4790K
Test#1 (Integers)
2.6k
5.06k (x1.95)
Test#2 (FP)
7.55k
12.63k (x1.67)
Test#3 (Generic, ZIP)
2.61k
5.81k (x2.23)
Test#1 (Memory)
2.03k
4.96k (x2.45)
TOTAL
14.79k
28.47k (x1.92)

Multithread

E5-2620 v4

i7-4790K
Test#1 (Integers)
17.41k
18.28k (x1.05)
Test#2 (FP)
75.46k
64.07k (x0.85)
Test#3 (Generic, ZIP)
26.25k
27.52k (x1.05)
Test#1 (Memory)
4.65k
7.97k (x1.71)
TOTAL
123.78k
117.84k (x0.95)

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
E5-2620 v4
i7-4790K
Test#1 (Integers)
8.22k
15.6k (x1.9)
Test#2 (FP)
12.06k
13.92k (x1.15)
Test#3 (Generic, ZIP)
4.01k
6.12k (x1.53)
Test#1 (Memory)
2.89k
5k (x1.73)
TOTAL
27.18k
40.65k (x1.5)

Multithread

E5-2620 v4

i7-4790K
Test#1 (Integers)
61.34k
65.48k (x1.07)
Test#2 (FP)
90.21k
63.29k (x0.7)
Test#3 (Generic, ZIP)
26.2k
27.93k (x1.07)
Test#1 (Memory)
4.62k
7.84k (x1.7)
TOTAL
182.37k
164.54k (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
E5-2620 v4
i7-4790K
Test#1 (Integers)
6.04k
15.8k (x2.62)
Test#2 (FP)
10.18k
14.35k (x1.41)
Test#3 (Generic, ZIP)
2.74k
5.97k (x2.18)
Test#1 (Memory)
2.41k
5.17k (x2.15)
TOTAL
21.37k
41.29k (x1.93)

Multithread

E5-2620 v4

i7-4790K
Test#1 (Integers)
47.51k
62.79k (x1.32)
Test#2 (FP)
75.12k
66.48k (x0.89)
Test#3 (Generic, ZIP)
19.72k
26.35k (x1.34)
Test#1 (Memory)
5.45k
8.74k (x1.6)
TOTAL
147.8k
164.36k (x1.11)

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
E5-2620 v4
i7-4790K
Test#1 (Integers)
12.16k
26.16k (x2.15)
Test#2 (FP)
11.82k
14.78k (x1.25)
Test#3 (Generic, ZIP)
3.02k
6.01k (x1.99)
Test#1 (Memory)
2.4k
5.52k (x2.3)
TOTAL
29.39k
52.47k (x1.79)

Multithread

E5-2620 v4

i7-4790K
Test#1 (Integers)
103.77k
107.76k (x1.04)
Test#2 (FP)
102.28k
70.84k (x0.69)
Test#3 (Generic, ZIP)
26.13k
27.99k (x1.07)
Test#1 (Memory)
5.65k
8.87k (x1.57)
TOTAL
237.83k
215.47k (x0.91)

Performance/W
E5-2620 v4
i7-4790K
Test#1 (Integers)
1221 points/W
1225 points/W
Test#2 (FP)
1203 points/W
805 points/W
Test#3 (Generic, ZIP)
307 points/W
318 points/W
Test#1 (Memory)
66 points/W
101 points/W
TOTAL
2798 points/W
2448 points/W

Performance/GHz
E5-2620 v4
i7-4790K
Test#1 (Integers)
4054 points/GHz
5946 points/GHz
Test#2 (FP)
3939 points/GHz
3359 points/GHz
Test#3 (Generic, ZIP)
1005 points/GHz
1366 points/GHz
Test#1 (Memory)
799 points/GHz
1254 points/GHz
TOTAL
9798 points/GHz
11925 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