| | | | | | |

FX 8320 vs Xeon E5-2667 v3


Description
The 8320 is based on Piledriver architecture while the E5-2667 v3 is based on Haswell.

Using the multithread performance as a reference, the 8320 gets a score of 103.2 k points while the E5-2667 v3 gets 277.7 k points.

Summarizing, the E5-2667 v3 is 2.7 times faster than the 8320. To get a proper comparison between both models, take a look to the data shown below.

Specs
CPUID
600f20
306f2
Core
Vishera
Haswell-EP
Architecture
Base frecuency
3.5 GHz
3.2 GHz
Boost frecuency
4 GHz
3.6 GHz
Socket
Socket AM3+
LGA 2011-3
Cores/Threads
8/8
8/16
TDP
125 W
135 W
Cache L1 (d+i)
kB
8x32+8x32 kB
Cache L2
4x2048 kB
8x256 kB
Cache L3
8192 kB
20480 kB
Date
October 2012
September 2014
Mean monothread perf.
16.68k points
41.36k points
Mean multithread perf.
103.21k points
343.64k points

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
8320
E5-2667 v3
Test#1 (Integers)
5.35k
13.1k (x2.45)
Test#2 (FP)
5.14k
11.91k (x2.32)
Test#3 (Generic, ZIP)
2.15k
4.83k (x2.25)
Test#1 (Memory)
4.04k
3.83k (x0.95)
TOTAL
16.68k
33.68k (x2.02)

Multithread

8320

E5-2667 v3
Test#1 (Integers)
36.79k
105.42k (x2.87)
Test#2 (FP)
40.2k
109.99k (x2.74)
Test#3 (Generic, ZIP)
19.57k
44.56k (x2.28)
Test#1 (Memory)
6.66k
17.7k (x2.66)
TOTAL
103.21k
277.66k (x2.69)

Performance/W
8320
E5-2667 v3
Test#1 (Integers)
294 points/W
781 points/W
Test#2 (FP)
322 points/W
815 points/W
Test#3 (Generic, ZIP)
157 points/W
330 points/W
Test#1 (Memory)
53 points/W
131 points/W
TOTAL
826 points/W
2057 points/W

Performance/GHz
8320
E5-2667 v3
Test#1 (Integers)
1339 points/GHz
3638 points/GHz
Test#2 (FP)
1285 points/GHz
3309 points/GHz
Test#3 (Generic, ZIP)
537 points/GHz
1342 points/GHz
Test#1 (Memory)
1010 points/GHz
1065 points/GHz
TOTAL
4171 points/GHz
9354 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