| | | | | | |

Xeon E5472 vs Celeron G1610T


Description
The E5472 is based on Core architecture while the G1610T is based on Ivy Bridge.

Using the multithread performance as a reference, the E5472 gets a score of 48.6 k points while the G1610T gets 38.6 k points.

Summarizing, the E5472 is 1.3 times faster than the G1610T . To get a proper comparison between both models, take a look to the data shown below.

Specs
CPUID
10676
306a9
Core
Harpertown
Ivy Bridge
Architecture
Base frecuency
3 GHz
2.3 GHz
Socket
LGA-771
LGA 1155
Cores/Threads
4/4
2/2
TDP
80 W
35 W
Cache L1 (d+i)
4x32+4x32 kB
32+32 kB
Cache L2
2x6144 kB
256 kB
Cache L3
kB
2048 kB
Date
November 2007
December 2012
Mean monothread perf.
16.62k points
20.84k points
Mean multithread perf.
48.62k points
38.59k 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
G1610T
Test#1 (Integers)
2.29k
2.34k (x1.02)
Test#2 (FP)
5.85k
6.54k (x1.12)
Test#3 (Generic, ZIP)
2.44k
3k (x1.23)
Test#1 (Memory)
4.81k
2.74k (x0.57)
TOTAL
15.39k
14.62k (x0.95)

Multithread

E5472

G1610T
Test#1 (Integers)
9.06k
4.67k (x0.51)
Test#2 (FP)
23.09k
12.66k (x0.55)
Test#3 (Generic, ZIP)
9.7k
5.95k (x0.61)
Test#1 (Memory)
2.53k
2.53k (x1)
TOTAL
44.38k
25.8k (x0.58)

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
G1610T
Test#1 (Integers)
2.88k
7.87k (x2.73)
Test#2 (FP)
6.36k
7.14k (x1.12)
Test#3 (Generic, ZIP)
2.55k
3.04k (x1.19)
Test#1 (Memory)
4.83k
2.79k (x0.58)
TOTAL
16.62k
20.84k (x1.25)

Multithread

E5472

G1610T
Test#1 (Integers)
11.19k
15.12k (x1.35)
Test#2 (FP)
24.85k
14.05k (x0.57)
Test#3 (Generic, ZIP)
10.04k
5.94k (x0.59)
Test#1 (Memory)
2.54k
3.48k (x1.37)
TOTAL
48.62k
38.59k (x0.79)

Performance/W
E5472
G1610T
Test#1 (Integers)
140 points/W
432 points/W
Test#2 (FP)
311 points/W
401 points/W
Test#3 (Generic, ZIP)
125 points/W
170 points/W
Test#1 (Memory)
32 points/W
99 points/W
TOTAL
608 points/W
1103 points/W

Performance/GHz
E5472
G1610T
Test#1 (Integers)
961 points/GHz
3423 points/GHz
Test#2 (FP)
2119 points/GHz
3102 points/GHz
Test#3 (Generic, ZIP)
850 points/GHz
1323 points/GHz
Test#1 (Memory)
1610 points/GHz
1211 points/GHz
TOTAL
5539 points/GHz
9060 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