| | | | | | |

Celeron J4105 vs G1610T


Description
The J4105 is based on Goldmont Plus architecture while the G1610T is based on Ivy Bridge.

Using the multithread performance as a reference, the J4105 gets a score of 61.5 k points while the G1610T gets 38.6 k points.

Summarizing, the J4105 is 1.6 times faster than the G1610T . To get a proper comparison between both models, take a look to the data shown below.

Specs
CPUID
706a1
306a9
Core
Gemini Lake
Ivy Bridge
Architecture
Base frecuency
1.5 GHz
2.3 GHz
Boost frecuency
2.5 GHz
2.3 GHz
Socket
BGA 1090
LGA 1155
Cores/Threads
4/4
2/2
TDP
10 W
35 W
Cache L1 (d+i)
4x32+4x24 kB
32+32 kB
Cache L2
4096 kB
256 kB
Cache L3
0 kB
2048 kB
Date
December 2017
December 2012
Mean monothread perf.
18.22k points
20.84k points
Mean multithread perf.
61.49k points
38.59k 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
J4105
G1610T
Test#1 (Integers)
1.68k
2.34k (x1.39)
Test#2 (FP)
5.29k
6.54k (x1.24)
Test#3 (Generic, ZIP)
2.75k
3k (x1.09)
Test#1 (Memory)
3.44k
2.74k (x0.8)
TOTAL
13.16k
14.62k (x1.11)

Multithread

J4105

G1610T
Test#1 (Integers)
6.39k
4.67k (x0.73)
Test#2 (FP)
20.02k
12.66k (x0.63)
Test#3 (Generic, ZIP)
10.22k
5.95k (x0.58)
Test#1 (Memory)
4.94k
2.53k (x0.51)
TOTAL
41.57k
25.8k (x0.62)

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
J4105
G1610T
Test#1 (Integers)
4.9k
7.87k (x1.61)
Test#2 (FP)
7.26k
7.14k (x0.98)
Test#3 (Generic, ZIP)
2.75k
3.04k (x1.1)
Test#1 (Memory)
3.32k
2.79k (x0.84)
TOTAL
18.22k
20.84k (x1.14)

Multithread

J4105

G1610T
Test#1 (Integers)
18.84k
15.12k (x0.8)
Test#2 (FP)
27.45k
14.05k (x0.51)
Test#3 (Generic, ZIP)
10.35k
5.94k (x0.57)
Test#1 (Memory)
4.85k
3.48k (x0.72)
TOTAL
61.49k
38.59k (x0.63)

Performance/W
J4105
G1610T
Test#1 (Integers)
1884 points/W
432 points/W
Test#2 (FP)
2745 points/W
401 points/W
Test#3 (Generic, ZIP)
1035 points/W
170 points/W
Test#1 (Memory)
485 points/W
99 points/W
TOTAL
6149 points/W
1103 points/W

Performance/GHz
J4105
G1610T
Test#1 (Integers)
1958 points/GHz
3423 points/GHz
Test#2 (FP)
2902 points/GHz
3102 points/GHz
Test#3 (Generic, ZIP)
1102 points/GHz
1323 points/GHz
Test#1 (Memory)
1327 points/GHz
1211 points/GHz
TOTAL
7289 points/GHz
9060 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