| | | | | | |

Celeron J3455 vs Xeon E5645


Description
The J3455 is based on Goldmont architecture while the E5645 is based on Westmere.

Using the multithread performance as a reference, the J3455 gets a score of 47.3 k points while the E5645 gets 77 k points.

Summarizing, the E5645 is 1.6 times faster than the J3455. To get a proper comparison between both models, take a look to the data shown below.

Specs
CPUID
506c9
206c2
Core
Apollo Lake
Westmere-EP
Architecture
Base frecuency
1.5 GHz
2.4 GHz
Boost frecuency
2.3 GHz
2.8 GHz
Socket
BGA1296
LGA 1366
Cores/Threads
4/4
6 /6
TDP
10 W
80 W
Cache L1 (d+i)
4x32+4x24 kB
64 kB
Cache L2
2x1024 kB
256 kB
Cache L3
0 kB
12288 kB
Date
August 2016
March 2010
Mean monothread perf.
12.98k points
15.64k points
Mean multithread perf.
47.34k points
76.96k 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
J3455
E5645
Test#1 (Integers)
6.02k
6.47k (x1.07)
Test#2 (FP)
3.49k
4.4k (x1.26)
Test#3 (Generic, ZIP)
2.01k
2.43k (x1.21)
Test#1 (Memory)
1.47k
2.33k (x1.59)
TOTAL
12.98k
15.64k (x1.2)

Multithread

J3455

E5645
Test#1 (Integers)
23.7k
34.43k (x1.45)
Test#2 (FP)
13.75k
24.23k (x1.76)
Test#3 (Generic, ZIP)
7.8k
14.48k (x1.86)
Test#1 (Memory)
2.09k
3.81k (x1.83)
TOTAL
47.34k
76.96k (x1.63)

Performance/W
J3455
E5645
Test#1 (Integers)
2370 points/W
430 points/W
Test#2 (FP)
1375 points/W
303 points/W
Test#3 (Generic, ZIP)
780 points/W
181 points/W
Test#1 (Memory)
209 points/W
48 points/W
TOTAL
4734 points/W
962 points/W

Performance/GHz
J3455
E5645
Test#1 (Integers)
2619 points/GHz
2311 points/GHz
Test#2 (FP)
1517 points/GHz
1573 points/GHz
Test#3 (Generic, ZIP)
872 points/GHz
867 points/GHz
Test#1 (Memory)
637 points/GHz
833 points/GHz
TOTAL
5645 points/GHz
5584 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