Xeon E5-1620 v2 vs E5-1660 v4
Description
The E5-1620 v2 is based on Ivy Bridge architecture while the E5-1660 v4 is based on Broadwell.
Using the multithread performance as a reference, the E5-1620 v2 gets a score of 144.6 k points while the E5-1660 v4 gets 320.5 k points.
Summarizing, the E5-1660 v4 is 2.2 times faster than the E5-1620 v2 . To get a proper comparison between both models, take a look to the data shown below.
Using the multithread performance as a reference, the E5-1620 v2 gets a score of 144.6 k points while the E5-1660 v4 gets 320.5 k points.
Summarizing, the E5-1660 v4 is 2.2 times faster than the E5-1620 v2 . To get a proper comparison between both models, take a look to the data shown below.
Specs
CPUID
306e4
406f1
Core
Ivy Bridge-EP
Broadwell-EP
Base frecuency
3.7 GHz
3.2 GHz
Boost frecuency
3.9 GHz
3.8 GHz
Socket
LGA 2011
Socket 2011-3
Cores/Threads
4 /8
8/16
TDP
130 W
140 W
Cache L1 (d+i)
4x32+x4x32 kB
8x32+8x32 kB
Cache L2
4x256 kB
8x256 kB
Cache L3
10240 kB
20480 kB
Date
September 2013
June 2016
Mean monothread perf.
34.37k points
37.6k points
Mean multithread perf.
144.57k points
320.49k points
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
E5-1620 v2
E5-1660 v4
Test#1 (Integers)
12.55k
12.41k (x0.99)
Test#2 (FP)
12.14k
17.23k (x1.42)
Test#3 (Generic, ZIP)
4.83k
4.89k (x1.01)
Test#1 (Memory)
4.85k
3.07k (x0.63)
TOTAL
34.37k
37.6k (x1.09)
Multithread
E5-1620 v2
E5-1660 v4
Test#1 (Integers)
51.93k
102.11k (x1.97)
Test#2 (FP)
56.7k
156.5k (x2.76)
Test#3 (Generic, ZIP)
23.81k
42.08k (x1.77)
Test#1 (Memory)
12.14k
19.8k (x1.63)
TOTAL
144.57k
320.49k (x2.22)
Performance/W
E5-1620 v2
E5-1660 v4
Test#1 (Integers)
399 points/W
729 points/W
Test#2 (FP)
436 points/W
1118 points/W
Test#3 (Generic, ZIP)
183 points/W
301 points/W
Test#1 (Memory)
93 points/W
141 points/W
TOTAL
1112 points/W
2289 points/W
Performance/GHz
E5-1620 v2
E5-1660 v4
Test#1 (Integers)
3217 points/GHz
3266 points/GHz
Test#2 (FP)
3113 points/GHz
4534 points/GHz
Test#3 (Generic, ZIP)
1238 points/GHz
1286 points/GHz
Test#1 (Memory)
1244 points/GHz
809 points/GHz
TOTAL
8812 points/GHz
9895 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.
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]
Test#2 (FP) [points vs time]
Test#3 (Generic, ZIP) [points vs time]
Test#1 (Memory) [points vs time]
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.
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]
Test#2 (FP) [points vs time]
Test#3 (Generic, ZIP) [points vs time]
Test#1 (Memory) [points vs time]
Hardlimit Benchmark Central - Ver. 3.11.4