| | | | | | |

Xeon E5-4640 vs Celeron J3455


Description
The E5-4640 is based on Sandy Bridge architecture while the J3455 is based on Goldmont.

Using the multithread performance as a reference, the E5-4640 gets a score of 581.6 k points while the J3455 gets 47.3 k points.

Summarizing, the E5-4640 is 12.3 times faster than the J3455. To get a proper comparison between both models, take a look to the data shown below.

Specs
CPUID
206d7
506c9
Core
Sandy Bridge-EP
Apollo Lake
Architecture
Base frecuency
2.4 GHz
1.5 GHz
Boost frecuency
2.8 GHz
2.3 GHz
Socket
LGA 2011
BGA1296
Cores/Threads
8 /16
4/4
TDP
95 W
10 W
Cache L1 (d+i)
8x32+8x32 kB
4x32+4x24 kB
Cache L2
8x256 kB
2x1024 kB
Cache L3
20480 kB
0 kB
Date
May 2012
August 2016
Mean monothread perf.
13.88k points
12.98k points
Mean multithread perf.
610.16k points
47.34k 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
E5-4640
J3455
Test#1 (Integers)
6.19k
6.02k (x0.97)
Test#2 (FP)
5.89k
3.49k (x0.59)
Test#3 (Generic, ZIP)
2.11k
2.01k (x0.95)
Test#1 (Memory)
2.51k
1.47k (x0.58)
TOTAL
16.7k
12.98k (x0.78)

Multithread

E5-4640

J3455
Test#1 (Integers)
244.88k
23.7k (x0.1)
Test#2 (FP)
215.35k
13.75k (x0.06)
Test#3 (Generic, ZIP)
114.64k
7.8k (x0.07)
Test#1 (Memory)
6.76k
2.09k (x0.31)
TOTAL
581.63k
47.34k (x0.08)

Performance/W
E5-4640
J3455
Test#1 (Integers)
2578 points/W
2370 points/W
Test#2 (FP)
2267 points/W
1375 points/W
Test#3 (Generic, ZIP)
1207 points/W
780 points/W
Test#1 (Memory)
71 points/W
209 points/W
TOTAL
6122 points/W
4734 points/W

Performance/GHz
E5-4640
J3455
Test#1 (Integers)
2210 points/GHz
2619 points/GHz
Test#2 (FP)
2105 points/GHz
1517 points/GHz
Test#3 (Generic, ZIP)
755 points/GHz
872 points/GHz
Test#1 (Memory)
895 points/GHz
637 points/GHz
TOTAL
5966 points/GHz
5645 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