| | | | | | |

Core i9-10980XE vs Xeon E5-4640


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

Using the multithread performance as a reference, the i9-10980XE gets a score of 929.8 k points while the E5-4640 gets 610.2 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
50657
206d7
Core
Cascade Lake-X
Sandy Bridge-EP
Architecture
Base frecuency
3 GHz
2.4 GHz
Boost frecuency
4.8 GHz
2.8 GHz
Socket
LGA 2066
LGA 2011
Cores/Threads
18/36
8 /16
TDP
165 W
95 W
Cache L1 (d+i)
18x32+18x32 kB
8x32+8x32 kB
Cache L2
18x1024 kB
8x256 kB
Cache L3
25344 kB
20480 kB
Date
November 2019
May 2012
Mean monothread perf.
68.33k points
13.88k points
Mean multithread perf.
1241.12k points
610.16k 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
i9-10980XE
E5-4640
Test#1 (Integers)
4.52k
1.66k (x0.37)
Test#2 (FP)
17.94k
5.26k (x0.29)
Test#3 (Generic, ZIP)
5.5k
2.13k (x0.39)
Test#1 (Memory)
9.64k
2.53k (x0.26)
TOTAL
37.6k
11.58k (x0.31)

Multithread

i9-10980XE

E5-4640
Test#1 (Integers)
84.93k
77.64k (x0.91)
Test#2 (FP)
409.55k
212.2k (x0.52)
Test#3 (Generic, ZIP)
122.88k
113.11k (x0.92)
Test#1 (Memory)
22.12k
7.54k (x0.34)
TOTAL
639.48k
410.48k (x0.64)

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
i9-10980XE
E5-4640
Test#1 (Integers)
16.03k
6.19k (x0.39)
Test#2 (FP)
23.95k
5.89k (x0.25)
Test#3 (Generic, ZIP)
6.03k
2.11k (x0.35)
Test#1 (Memory)
9.37k
2.51k (x0.27)
TOTAL
55.38k
16.7k (x0.3)

Multithread

i9-10980XE

E5-4640
Test#1 (Integers)
316.11k
244.88k (x0.77)
Test#2 (FP)
503.75k
215.35k (x0.43)
Test#3 (Generic, ZIP)
131.82k
114.64k (x0.87)
Test#1 (Memory)
22.24k
6.76k (x0.3)
TOTAL
973.92k
581.63k (x0.6)

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
i9-10980XE
E5-4640
Test#1 (Integers)
16.4k
5.01k (x0.31)
Test#2 (FP)
20.97k
4.5k (x0.21)
Test#3 (Generic, ZIP)
5.82k
2.18k (x0.37)
Test#1 (Memory)
8.86k
2.19k (x0.25)
TOTAL
52.05k
13.88k (x0.27)

Multithread

i9-10980XE

E5-4640
Test#1 (Integers)
316.84k
251.29k (x0.79)
Test#2 (FP)
461.09k
236.61k (x0.51)
Test#3 (Generic, ZIP)
129.82k
114.89k (x0.88)
Test#1 (Memory)
22.09k
7.36k (x0.33)
TOTAL
929.85k
610.16k (x0.66)

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

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