| | | | | | |

Xeon E5-4640 vs Core i9-10980XE


Description
The E5-4640 is based on Sandy Bridge architecture while the i9-10980XE is based on Cascade Lake.

Using the multithread performance as a reference, the E5-4640 gets a score of 610.2 k points while the i9-10980XE gets 929.8 k points.

Summarizing, the i9-10980XE is 1.5 times faster than the E5-4640 . To get a proper comparison between both models, take a look to the data shown below.

Specs
CPUID
206d7
50657
Core
Sandy Bridge-EP
Cascade Lake-X
Architecture
Base frecuency
2.4 GHz
3 GHz
Boost frecuency
2.8 GHz
4.8 GHz
Socket
LGA 2011
LGA 2066
Cores/Threads
8 /16
18/36
TDP
95 W
165 W
Cache L1 (d+i)
8x32+8x32 kB
18x32+18x32 kB
Cache L2
8x256 kB
18x1024 kB
Cache L3
20480 kB
25344 kB
Date
May 2012
November 2019
Mean monothread perf.
13.88k points
68.33k points
Mean multithread perf.
610.16k points
1241.12k 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
E5-4640
i9-10980XE
Test#1 (Integers)
1.66k
4.52k (x2.72)
Test#2 (FP)
5.26k
17.94k (x3.41)
Test#3 (Generic, ZIP)
2.13k
5.5k (x2.58)
Test#1 (Memory)
2.53k
9.64k (x3.81)
TOTAL
11.58k
37.6k (x3.25)

Multithread

E5-4640

i9-10980XE
Test#1 (Integers)
77.64k
84.93k (x1.09)
Test#2 (FP)
212.2k
409.55k (x1.93)
Test#3 (Generic, ZIP)
113.11k
122.88k (x1.09)
Test#1 (Memory)
7.54k
22.12k (x2.93)
TOTAL
410.48k
639.48k (x1.56)

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
i9-10980XE
Test#1 (Integers)
6.19k
16.03k (x2.59)
Test#2 (FP)
5.89k
23.95k (x4.06)
Test#3 (Generic, ZIP)
2.11k
6.03k (x2.85)
Test#1 (Memory)
2.51k
9.37k (x3.74)
TOTAL
16.7k
55.38k (x3.32)

Multithread

E5-4640

i9-10980XE
Test#1 (Integers)
244.88k
316.11k (x1.29)
Test#2 (FP)
215.35k
503.75k (x2.34)
Test#3 (Generic, ZIP)
114.64k
131.82k (x1.15)
Test#1 (Memory)
6.76k
22.24k (x3.29)
TOTAL
581.63k
973.92k (x1.67)

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
i9-10980XE
Test#1 (Integers)
5.01k
16.4k (x3.27)
Test#2 (FP)
4.5k
20.97k (x4.66)
Test#3 (Generic, ZIP)
2.18k
5.82k (x2.68)
Test#1 (Memory)
2.19k
8.86k (x4.05)
TOTAL
13.88k
52.05k (x3.75)

Multithread

E5-4640

i9-10980XE
Test#1 (Integers)
251.29k
316.84k (x1.26)
Test#2 (FP)
236.61k
461.09k (x1.95)
Test#3 (Generic, ZIP)
114.89k
129.82k (x1.13)
Test#1 (Memory)
7.36k
22.09k (x3)
TOTAL
610.16k
929.85k (x1.52)

Performance/W
E5-4640
i9-10980XE
Test#1 (Integers)
2645 points/W
1920 points/W
Test#2 (FP)
2491 points/W
2794 points/W
Test#3 (Generic, ZIP)
1209 points/W
787 points/W
Test#1 (Memory)
78 points/W
134 points/W
TOTAL
6423 points/W
5635 points/W

Performance/GHz
E5-4640
i9-10980XE
Test#1 (Integers)
1790 points/GHz
3417 points/GHz
Test#2 (FP)
1609 points/GHz
4369 points/GHz
Test#3 (Generic, ZIP)
777 points/GHz
1213 points/GHz
Test#1 (Memory)
782 points/GHz
1845 points/GHz
TOTAL
4957 points/GHz
10844 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