| | | | | | |

Pentium G2020 vs Celeron G3900TE


Description
The G2020 is based on Ivy Bridge architecture while the G3900TE is based on Skylake.

Using the multithread performance as a reference, the G2020 gets a score of 42.4 k points while the G3900TE gets 49.3 k points.

Summarizing, the G3900TE is 1.2 times faster than the G2020 . To get a proper comparison between both models, take a look to the data shown below.

Specs
CPUID
306a9
506e3
Core
Ivy Bridge
Skylake-S
Architecture
Base frecuency
1.6 GHz
2.3 GHz
Boost frecuency
2.9 GHz
2.3 GHz
Socket
LGA 1155
LGA 1151
Cores/Threads
2/2
2/2
TDP
55 W
35 W
Cache L1 (d+i)
32+32 kB
2x32+2x32 kB
Cache L2
256 kB
2x256 kB
Cache L3
3072 kB
2048 kB
Date
January 2013
December 2015
Mean monothread perf.
25.87k points
27.33k points
Mean multithread perf.
42.39k points
49.34k 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
G2020
G3900TE
Test#1 (Integers)
2.94k
2.36k (x0.8)
Test#2 (FP)
8.23k
9.79k (x1.19)
Test#3 (Generic, ZIP)
3.69k
3.08k (x0.83)
Test#1 (Memory)
2.46k
3.36k (x1.36)
TOTAL
17.33k
18.59k (x1.07)

Multithread

G2020

G3900TE
Test#1 (Integers)
5.54k
4.45k (x0.8)
Test#2 (FP)
15.47k
18.16k (x1.17)
Test#3 (Generic, ZIP)
7.06k
5.48k (x0.78)
Test#1 (Memory)
2.99k
3.5k (x1.17)
TOTAL
31.05k
31.59k (x1.02)

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
G2020
G3900TE
Test#1 (Integers)
9.9k
8.56k (x0.86)
Test#2 (FP)
9.01k
12.25k (x1.36)
Test#3 (Generic, ZIP)
3.87k
3.17k (x0.82)
Test#1 (Memory)
3.09k
3.35k (x1.08)
TOTAL
25.87k
27.33k (x1.06)

Multithread

G2020

G3900TE
Test#1 (Integers)
18.83k
16.42k (x0.87)
Test#2 (FP)
14.15k
23.61k (x1.67)
Test#3 (Generic, ZIP)
6.61k
5.75k (x0.87)
Test#1 (Memory)
2.81k
3.55k (x1.26)
TOTAL
42.39k
49.34k (x1.16)

Performance/W
G2020
G3900TE
Test#1 (Integers)
342 points/W
469 points/W
Test#2 (FP)
257 points/W
675 points/W
Test#3 (Generic, ZIP)
120 points/W
164 points/W
Test#1 (Memory)
51 points/W
101 points/W
TOTAL
771 points/W
1410 points/W

Performance/GHz
G2020
G3900TE
Test#1 (Integers)
3415 points/GHz
3724 points/GHz
Test#2 (FP)
3107 points/GHz
5326 points/GHz
Test#3 (Generic, ZIP)
1334 points/GHz
1380 points/GHz
Test#1 (Memory)
1065 points/GHz
1455 points/GHz
TOTAL
8921 points/GHz
11885 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