| | | | | | |

Xeon E5-4640 vs E5-2680 v2


Description
The E5-4640 is based on Sandy Bridge architecture while the E5-2680 v2 is based on Ivy Bridge.

Using the multithread performance as a reference, the E5-4640 gets a score of 610.2 k points while the E5-2680 v2 gets 551.1 k points.

Summarizing, the E5-4640 is 1.1 times faster than the E5-2680 v2 . To get a proper comparison between both models, take a look to the data shown below.

Specs
CPUID
206d7
306e4
Core
Sandy Bridge-EP
Ivy Bridge-EP
Architecture
Base frecuency
2.4 GHz
2.8 GHz
Boost frecuency
2.8 GHz
3.6 GHz
Socket
LGA 2011
LGA 2011
Cores/Threads
8 /16
10 /20
TDP
95 W
115 W
Cache L1 (d+i)
8x32+8x32 kB
10x32+10x32 kB
Cache L2
8x256 kB
10x256 kB
Cache L3
20480 kB
25600 kB
Date
May 2012
September 2013
Mean monothread perf.
13.88k points
28.23k points
Mean multithread perf.
610.16k points
551.1k 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
E5-2680 v2
Test#1 (Integers)
6.19k
11.96k (x1.93)
Test#2 (FP)
5.89k
10.73k (x1.82)
Test#3 (Generic, ZIP)
2.11k
4.59k (x2.17)
Test#1 (Memory)
2.51k
4.31k (x1.72)
TOTAL
16.7k
31.6k (x1.89)

Multithread

E5-4640

E5-2680 v2
Test#1 (Integers)
244.88k
218.24k (x0.89)
Test#2 (FP)
215.35k
206.92k (x0.96)
Test#3 (Generic, ZIP)
114.64k
100.37k (x0.88)
Test#1 (Memory)
6.76k
11.45k (x1.69)
TOTAL
581.63k
536.99k (x0.92)

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
E5-4640
E5-2680 v2
Test#1 (Integers)
5.01k
10.55k (x2.11)
Test#2 (FP)
4.5k
10.02k (x2.23)
Test#3 (Generic, ZIP)
2.18k
3.99k (x1.84)
Test#1 (Memory)
2.19k
3.66k (x1.67)
TOTAL
13.88k
28.23k (x2.03)

Multithread

E5-4640

E5-2680 v2
Test#1 (Integers)
251.29k
215.04k (x0.86)
Test#2 (FP)
236.61k
230.43k (x0.97)
Test#3 (Generic, ZIP)
114.89k
96.87k (x0.84)
Test#1 (Memory)
7.36k
8.76k (x1.19)
TOTAL
610.16k
551.1k (x0.9)

Performance/W
E5-4640
E5-2680 v2
Test#1 (Integers)
2645 points/W
1870 points/W
Test#2 (FP)
2491 points/W
2004 points/W
Test#3 (Generic, ZIP)
1209 points/W
842 points/W
Test#1 (Memory)
78 points/W
76 points/W
TOTAL
6423 points/W
4792 points/W

Performance/GHz
E5-4640
E5-2680 v2
Test#1 (Integers)
1790 points/GHz
2931 points/GHz
Test#2 (FP)
1609 points/GHz
2784 points/GHz
Test#3 (Generic, ZIP)
777 points/GHz
1109 points/GHz
Test#1 (Memory)
782 points/GHz
1017 points/GHz
TOTAL
4957 points/GHz
7841 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