| | | | | | |

Xeon E5472 vs A9 9420


Description
The E5472 is based on Core architecture while the 9420 is based on Excavator.

Using the multithread performance as a reference, the E5472 gets a score of 48.6 k points while the 9420 gets 28.9 k points.

Summarizing, the E5472 is 1.7 times faster than the 9420. To get a proper comparison between both models, take a look to the data shown below.

Specs
CPUID
10676
670f00
Core
Harpertown
Stoney Ridge
Architecture
Base frecuency
3 GHz
3 GHz
Boost frecuency
3 GHz
3.6 GHz
Socket
LGA-771
Micro-BGA
Cores/Threads
4/4
2/2
TDP
80 W
15 W
Cache L1 (d+i)
4x32+4x32 kB
96+2x32 kB
Cache L2
2x6144 kB
1024 kB
Cache L3
kB
0 kB
Date
November 2007
April 2017
Mean monothread perf.
16.62k points
33.09k points
Mean multithread perf.
48.62k points
46.33k 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
E5472
9420
Test#1 (Integers)
2.29k
2.56k (x1.12)
Test#2 (FP)
5.85k
9.97k (x1.7)
Test#3 (Generic, ZIP)
2.44k
2.96k (x1.21)
Test#1 (Memory)
4.81k
2.12k (x0.44)
TOTAL
15.39k
17.61k (x1.14)

Multithread

E5472

9420
Test#1 (Integers)
9.06k
3.88k (x0.43)
Test#2 (FP)
23.09k
9.26k (x0.4)
Test#3 (Generic, ZIP)
9.7k
3.9k (x0.4)
Test#1 (Memory)
2.53k
1.74k (x0.69)
TOTAL
44.38k
18.79k (x0.42)

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
E5472
9420
Test#1 (Integers)
2.88k
8.41k (x2.92)
Test#2 (FP)
6.36k
11.48k (x1.81)
Test#3 (Generic, ZIP)
2.55k
3.29k (x1.29)
Test#1 (Memory)
4.83k
2.24k (x0.46)
TOTAL
16.62k
25.41k (x1.53)

Multithread

E5472

9420
Test#1 (Integers)
11.19k
11.25k (x1.01)
Test#2 (FP)
24.85k
13.69k (x0.55)
Test#3 (Generic, ZIP)
10.04k
2.09k (x0.21)
Test#1 (Memory)
2.54k
1.87k (x0.74)
TOTAL
48.62k
28.89k (x0.59)

Performance/W
E5472
9420
Test#1 (Integers)
140 points/W
750 points/W
Test#2 (FP)
311 points/W
912 points/W
Test#3 (Generic, ZIP)
125 points/W
139 points/W
Test#1 (Memory)
32 points/W
125 points/W
TOTAL
608 points/W
1926 points/W

Performance/GHz
E5472
9420
Test#1 (Integers)
961 points/GHz
2336 points/GHz
Test#2 (FP)
2119 points/GHz
3188 points/GHz
Test#3 (Generic, ZIP)
850 points/GHz
913 points/GHz
Test#1 (Memory)
1610 points/GHz
621 points/GHz
TOTAL
5539 points/GHz
7058 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