| | | | | | |

Xeon Silver 4110 vs Xeon E5-2680 v3


Description
The 4110 is based on Skylake architecture while the E5-2680 v3 is based on Haswell.

Using the multithread performance as a reference, the 4110 gets a score of 281.5 k points while the E5-2680 v3 gets 426.6 k points.

Summarizing, the E5-2680 v3 is 1.5 times faster than the 4110. To get a proper comparison between both models, take a look to the data shown below.

Specs
CPUID
50654
306f2
Core
Skylake-SP
Haswell-EP
Architecture
Base frecuency
2.1 GHz
2.5 GHz
Boost frecuency
3 GHz
3.3 GHz
Socket
LGA3647
LGA 2011-3
Cores/Threads
8/16
12/24
TDP
85 W
120 W
Cache L1 (d+i)
8x32+8x32 kB
12x32+12x32 kB
Cache L2
8x1024 kB
12x256 kB
Cache L3
11264 kB
30720 kB
Date
July 2017
September 2014
Mean monothread perf.
45.82k points
36.31k points
Mean multithread perf.
281.48k points
426.58k points

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
4110
E5-2680 v3
Test#1 (Integers)
18.78k
18.86k (x1)
Test#2 (FP)
16.25k
10.06k (x0.62)
Test#3 (Generic, ZIP)
3.99k
4.14k (x1.04)
Test#1 (Memory)
6.8k
3.24k (x0.48)
TOTAL
45.82k
36.31k (x0.79)

Multithread

4110

E5-2680 v3
Test#1 (Integers)
133.55k
218.93k (x1.64)
Test#2 (FP)
108.43k
139.75k (x1.29)
Test#3 (Generic, ZIP)
30.02k
55.47k (x1.85)
Test#1 (Memory)
9.48k
12.42k (x1.31)
TOTAL
281.48k
426.58k (x1.52)

Performance/W
4110
E5-2680 v3
Test#1 (Integers)
1571 points/W
1824 points/W
Test#2 (FP)
1276 points/W
1165 points/W
Test#3 (Generic, ZIP)
353 points/W
462 points/W
Test#1 (Memory)
112 points/W
103 points/W
TOTAL
3311 points/W
3555 points/W

Performance/GHz
4110
E5-2680 v3
Test#1 (Integers)
6259 points/GHz
5716 points/GHz
Test#2 (FP)
5417 points/GHz
3049 points/GHz
Test#3 (Generic, ZIP)
1330 points/GHz
1254 points/GHz
Test#1 (Memory)
2267 points/GHz
983 points/GHz
TOTAL
15273 points/GHz
11002 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