| | | | | | |

A6 9210 vs Xeon E5-2620 v4


Description
The 9210 is based on Excavator architecture while the E5-2620 v4 is based on Broadwell.

Using the multithread performance as a reference, the 9210 gets a score of 27.1 k points while the E5-2620 v4 gets 147.8 k points.

Summarizing, the E5-2620 v4 is 5.5 times faster than the 9210. To get a proper comparison between both models, take a look to the data shown below.

Specs
CPUID
670f00
406f1
Core
Stoney Ridge
Broadwell-EP
Architecture
Base frecuency
2.4 GHz
2.1 GHz
Boost frecuency
2.8 GHz
3 GHz
Socket
Socket FP4
Socket 2011-3
Cores/Threads
2/2
8/16
TDP
15 W
85 W
Cache L1 (d+i)
1x96+2x32 kB
8x32+8x32 kB
Cache L2
1024 kB
8x256 kB
Cache L3
0 kB
20480 kB
Date
June 2016
March 2016
Mean monothread perf.
20.78k points
29.39k points
Mean multithread perf.
27.13k points
237.83k points

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
9210
E5-2620 v4
Test#1 (Integers)
4.87k
8.22k (x1.69)
Test#2 (FP)
10.38k
12.06k (x1.16)
Test#3 (Generic, ZIP)
2.59k
4.01k (x1.55)
Test#1 (Memory)
2.38k
2.89k (x1.21)
TOTAL
20.22k
27.18k (x1.34)

Multithread

9210

E5-2620 v4
Test#1 (Integers)
7.41k
61.34k (x8.28)
Test#2 (FP)
11.87k
90.21k (x7.6)
Test#3 (Generic, ZIP)
3.35k
26.2k (x7.82)
Test#1 (Memory)
2.6k
4.62k (x1.78)
TOTAL
25.23k
182.37k (x7.23)

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
9210
E5-2620 v4
Test#1 (Integers)
4.71k
6.04k (x1.28)
Test#2 (FP)
11.03k
10.18k (x0.92)
Test#3 (Generic, ZIP)
2.59k
2.74k (x1.06)
Test#1 (Memory)
2.45k
2.41k (x0.98)
TOTAL
20.78k
21.37k (x1.03)

Multithread

9210

E5-2620 v4
Test#1 (Integers)
8.43k
47.51k (x5.64)
Test#2 (FP)
12.8k
75.12k (x5.87)
Test#3 (Generic, ZIP)
3.32k
19.72k (x5.94)
Test#1 (Memory)
2.59k
5.45k (x2.11)
TOTAL
27.13k
147.8k (x5.45)

Performance/W
9210
E5-2620 v4
Test#1 (Integers)
562 points/W
559 points/W
Test#2 (FP)
853 points/W
884 points/W
Test#3 (Generic, ZIP)
221 points/W
232 points/W
Test#1 (Memory)
172 points/W
64 points/W
TOTAL
1809 points/W
1739 points/W

Performance/GHz
9210
E5-2620 v4
Test#1 (Integers)
1683 points/GHz
2013 points/GHz
Test#2 (FP)
3938 points/GHz
3393 points/GHz
Test#3 (Generic, ZIP)
927 points/GHz
915 points/GHz
Test#1 (Memory)
873 points/GHz
802 points/GHz
TOTAL
7420 points/GHz
7123 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