| | | | | | |

Xeon E5-2620 v4 vs Core i3-3217U


Description
The E5-2620 v4 is based on Broadwell architecture while the i3-3217U is based on Ivy Bridge.

Using the multithread performance as a reference, the E5-2620 v4 gets a score of 147.8 k points while the i3-3217U gets 35.8 k points.

Summarizing, the E5-2620 v4 is 4.1 times faster than the i3-3217U . To get a proper comparison between both models, take a look to the data shown below.

Specs
CPUID
406f1
306a9
Core
Broadwell-EP
Ivy Bridge
Architecture
Base frecuency
2.1 GHz
1.8 GHz
Boost frecuency
3 GHz
1.8 GHz
Socket
Socket 2011-3
BGA1023
Cores/Threads
8/16
2 /2
TDP
85 W
17 W
Cache L1 (d+i)
8x32+8x32 kB
2x32+2x32 kB
Cache L2
8x256 kB
2x256 kB
Cache L3
20480 kB
3072 kB
Date
March 2016
June 2012
Mean monothread perf.
29.39k points
16.09k points
Mean multithread perf.
237.83k points
35.81k 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
i3-3217U
Test#1 (Integers)
2.6k
1.79k (x0.69)
Test#2 (FP)
7.55k
5.02k (x0.66)
Test#3 (Generic, ZIP)
2.61k
2.21k (x0.85)
Test#1 (Memory)
2.03k
2.31k (x1.14)
TOTAL
14.79k
11.32k (x0.77)

Multithread

E5-2620 v4

i3-3217U
Test#1 (Integers)
17.41k
3.56k (x0.2)
Test#2 (FP)
75.46k
11.47k (x0.15)
Test#3 (Generic, ZIP)
26.25k
5.34k (x0.2)
Test#1 (Memory)
4.65k
2.54k (x0.55)
TOTAL
123.78k
22.91k (x0.19)

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
i3-3217U
Test#1 (Integers)
8.22k
5.37k (x0.65)
Test#2 (FP)
12.06k
5.25k (x0.44)
Test#3 (Generic, ZIP)
4.01k
2.2k (x0.55)
Test#1 (Memory)
2.89k
2.25k (x0.78)
TOTAL
27.18k
15.08k (x0.55)

Multithread

E5-2620 v4

i3-3217U
Test#1 (Integers)
61.34k
12.46k (x0.2)
Test#2 (FP)
90.21k
12.14k (x0.13)
Test#3 (Generic, ZIP)
26.2k
5.52k (x0.21)
Test#1 (Memory)
4.62k
2.64k (x0.57)
TOTAL
182.37k
32.75k (x0.18)

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
i3-3217U
Test#1 (Integers)
6.04k
5.83k (x0.97)
Test#2 (FP)
10.18k
5.79k (x0.57)
Test#3 (Generic, ZIP)
2.74k
2.22k (x0.81)
Test#1 (Memory)
2.41k
2.26k (x0.94)
TOTAL
21.37k
16.09k (x0.75)

Multithread

E5-2620 v4

i3-3217U
Test#1 (Integers)
47.51k
12.53k (x0.26)
Test#2 (FP)
75.12k
14.19k (x0.19)
Test#3 (Generic, ZIP)
19.72k
5.63k (x0.29)
Test#1 (Memory)
5.45k
3.46k (x0.63)
TOTAL
147.8k
35.81k (x0.24)

Performance/W
E5-2620 v4
i3-3217U
Test#1 (Integers)
559 points/W
737 points/W
Test#2 (FP)
884 points/W
835 points/W
Test#3 (Generic, ZIP)
232 points/W
331 points/W
Test#1 (Memory)
64 points/W
204 points/W
TOTAL
1739 points/W
2107 points/W

Performance/GHz
E5-2620 v4
i3-3217U
Test#1 (Integers)
2013 points/GHz
3238 points/GHz
Test#2 (FP)
3393 points/GHz
3217 points/GHz
Test#3 (Generic, ZIP)
915 points/GHz
1232 points/GHz
Test#1 (Memory)
802 points/GHz
1255 points/GHz
TOTAL
7123 points/GHz
8942 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