| | | | | | |

Phenom II X6 1035T vs Celeron J4105


Description
The 1035T is based on K10 architecture while the J4105 is based on Goldmont Plus.

Using the multithread performance as a reference, the 1035T gets a score of 80.2 k points while the J4105 gets 61.5 k points.

Summarizing, the 1035T is 1.3 times faster than the J4105. To get a proper comparison between both models, take a look to the data shown below.

Specs
CPUID
100fa0
706a1
Core
Thuban
Gemini Lake
Architecture
Base frecuency
2.6 GHz
1.5 GHz
Boost frecuency
3.1 GHz
2.5 GHz
Socket
Socket AM3
BGA 1090
Cores/Threads
6/6
4/4
TDP
95 W
10 W
Cache L1 (d+i)
128 kB
4x32+4x24 kB
Cache L2
6x512 kB
4096 kB
Cache L3
6144 kB
0 kB
Date
May 2010
December 2017
Mean monothread perf.
16.77k points
18.22k points
Mean multithread perf.
80.19k points
61.49k 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
1035T
J4105
Test#1 (Integers)
1.98k
1.68k (x0.85)
Test#2 (FP)
4.57k
5.29k (x1.16)
Test#3 (Generic, ZIP)
2.57k
2.75k (x1.07)
Test#1 (Memory)
3.51k
3.44k (x0.98)
TOTAL
12.64k
13.16k (x1.04)

Multithread

1035T

J4105
Test#1 (Integers)
11.86k
6.39k (x0.54)
Test#2 (FP)
27.4k
20.02k (x0.73)
Test#3 (Generic, ZIP)
15.39k
10.22k (x0.66)
Test#1 (Memory)
3.46k
4.94k (x1.43)
TOTAL
58.11k
41.57k (x0.72)

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
1035T
J4105
Test#1 (Integers)
5.17k
4.9k (x0.95)
Test#2 (FP)
5.33k
7.26k (x1.36)
Test#3 (Generic, ZIP)
2.76k
2.75k (x1)
Test#1 (Memory)
3.51k
3.32k (x0.94)
TOTAL
16.77k
18.22k (x1.09)

Multithread

1035T

J4105
Test#1 (Integers)
29.82k
18.84k (x0.63)
Test#2 (FP)
30.79k
27.45k (x0.89)
Test#3 (Generic, ZIP)
15.88k
10.35k (x0.65)
Test#1 (Memory)
3.69k
4.85k (x1.31)
TOTAL
80.19k
61.49k (x0.77)

Performance/W
1035T
J4105
Test#1 (Integers)
314 points/W
1884 points/W
Test#2 (FP)
324 points/W
2745 points/W
Test#3 (Generic, ZIP)
167 points/W
1035 points/W
Test#1 (Memory)
39 points/W
485 points/W
TOTAL
844 points/W
6149 points/W

Performance/GHz
1035T
J4105
Test#1 (Integers)
1668 points/GHz
1958 points/GHz
Test#2 (FP)
1718 points/GHz
2902 points/GHz
Test#3 (Generic, ZIP)
890 points/GHz
1102 points/GHz
Test#1 (Memory)
1133 points/GHz
1327 points/GHz
TOTAL
5409 points/GHz
7289 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