| | | | | | |

Core i5-6400 vs Xeon E5-2670 v3


Description
The i5-6400 is based on Skylake architecture while the E5-2670 v3 is based on Haswell.

Using the multithread performance as a reference, the i5-6400 gets a score of 174.1 k points while the E5-2670 v3 gets 452.9 k points.

Summarizing, the E5-2670 v3 is 2.6 times faster than the i5-6400 . To get a proper comparison between both models, take a look to the data shown below.

Specs
CPUID
506e3
306f2
Core
Skylake-S
Haswell-EP
Architecture
Base frecuency
2.7 GHz
2.3 GHz
Boost frecuency
3.3 GHz
3.1 GHz
Socket
LGA 1151
LGA 2011-3
Cores/Threads
4/4
12/24
TDP
65 W
120 W
Cache L1 (d+i)
4x32+4x32 kB
12x32+12x32 kB
Cache L2
4x256 kB
12x256 kB
Cache L3
6144 kB
30720 kB
Date
September 2015
September 2014
Mean monothread perf.
48.05k points
36.41k points
Mean multithread perf.
174.05k points
452.9k 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
i5-6400
E5-2670 v3
Test#1 (Integers)
3.2k
3.52k (x1.1)
Test#2 (FP)
12.81k
8.68k (x0.68)
Test#3 (Generic, ZIP)
4.18k
2.83k (x0.68)
Test#1 (Memory)
4.3k
3.13k (x0.73)
TOTAL
24.49k
18.17k (x0.74)

Multithread

i5-6400

E5-2670 v3
Test#1 (Integers)
11.45k
32.7k (x2.86)
Test#2 (FP)
46.67k
105.18k (x2.25)
Test#3 (Generic, ZIP)
14.69k
35.18k (x2.39)
Test#1 (Memory)
5.92k
9.54k (x1.61)
TOTAL
78.73k
182.59k (x2.32)

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
i5-6400
E5-2670 v3
Test#1 (Integers)
11.56k
11.08k (x0.96)
Test#2 (FP)
16.53k
9.57k (x0.58)
Test#3 (Generic, ZIP)
4.3k
3.18k (x0.74)
Test#1 (Memory)
3.97k
3.28k (x0.83)
TOTAL
36.36k
27.11k (x0.75)

Multithread

i5-6400

E5-2670 v3
Test#1 (Integers)
43.01k
139.07k (x3.23)
Test#2 (FP)
64.46k
133.47k (x2.07)
Test#3 (Generic, ZIP)
16.14k
46.6k (x2.89)
Test#1 (Memory)
5.91k
6.65k (x1.13)
TOTAL
129.51k
325.78k (x2.52)

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
i5-6400
E5-2670 v3
Test#1 (Integers)
11.82k
11.18k (x0.95)
Test#2 (FP)
18.36k
10.06k (x0.55)
Test#3 (Generic, ZIP)
4.43k
3.21k (x0.72)
Test#1 (Memory)
4.95k
3.12k (x0.63)
TOTAL
39.56k
27.57k (x0.7)

Multithread

i5-6400

E5-2670 v3
Test#1 (Integers)
46.04k
140.98k (x3.06)
Test#2 (FP)
69.47k
145.37k (x2.09)
Test#3 (Generic, ZIP)
16.33k
45.62k (x2.79)
Test#1 (Memory)
7.74k
6.75k (x0.87)
TOTAL
139.58k
338.73k (x2.43)

AVX2 optimized benchmark
The benchmark in mode III (AVX2), like AVX1, is optimized to used 256 bits registers beside the second version of the Advanced Vector Extensions (AVX). The first AVX2 compatible CPU was released in 2013.
Monothread
i5-6400
E5-2670 v3
Test#1 (Integers)
21.1k
18.62k (x0.88)
Test#2 (FP)
18.28k
10.49k (x0.57)
Test#3 (Generic, ZIP)
4.22k
4.04k (x0.96)
Test#1 (Memory)
4.45k
3.26k (x0.73)
TOTAL
48.05k
36.41k (x0.76)

Multithread

i5-6400

E5-2670 v3
Test#1 (Integers)
80.03k
236.25k (x2.95)
Test#2 (FP)
71.1k
151.05k (x2.12)
Test#3 (Generic, ZIP)
16.19k
58.9k (x3.64)
Test#1 (Memory)
6.73k
6.7k (x1)
TOTAL
174.05k
452.9k (x2.6)

Performance/W
i5-6400
E5-2670 v3
Test#1 (Integers)
1231 points/W
1969 points/W
Test#2 (FP)
1094 points/W
1259 points/W
Test#3 (Generic, ZIP)
249 points/W
491 points/W
Test#1 (Memory)
104 points/W
56 points/W
TOTAL
2678 points/W
3774 points/W

Performance/GHz
i5-6400
E5-2670 v3
Test#1 (Integers)
6394 points/GHz
6006 points/GHz
Test#2 (FP)
5539 points/GHz
3385 points/GHz
Test#3 (Generic, ZIP)
1279 points/GHz
1303 points/GHz
Test#1 (Memory)
1348 points/GHz
1052 points/GHz
TOTAL
14560 points/GHz
11745 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