| | | | | | |

Ryzen 7 3800X vs Core i5-1035G4


Description
The 3800X is based on Zen 2 architecture while the i5-1035G4 is based on Ice Lake.

Using the multithread performance as a reference, the 3800X gets a score of 497.7 k points while the i5-1035G4 gets 142.7 k points.

Summarizing, the 3800X is 3.5 times faster than the i5-1035G4. To get a proper comparison between both models, take a look to the data shown below.

Specs
CPUID
870f10
706e5
Core
Matisse
Ice Lake-U
Architecture
Base frecuency
3.9 GHz
1.1 GHz
Boost frecuency
4.5 GHz
3.7 GHz
Socket
AM4
BGA 1526
Cores/Threads
8/16
4/8
TDP
105 W
15 W
Cache L1 (d+i)
8x32+8x32 kB
4x32+4x48 kB
Cache L2
8x512 kB
4x512 kB
Cache L3
32768 kB
6144 kB
Date
July 2019
August 2019
Mean monothread perf.
75.81k points
65.64k points
Mean multithread perf.
497.74k points
142.69k 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
3800X
i5-1035G4
Test#1 (Integers)
4.47k
4.05k (x0.91)
Test#2 (FP)
17.41k
15.29k (x0.88)
Test#3 (Generic, ZIP)
8.23k
9.04k (x1.1)
Test#1 (Memory)
25.15k
10.54k (x0.42)
TOTAL
55.26k
38.92k (x0.7)

Multithread

3800X

i5-1035G4
Test#1 (Integers)
36.1k
9.05k (x0.25)
Test#2 (FP)
178.65k
33.88k (x0.19)
Test#3 (Generic, ZIP)
95.98k
15.34k (x0.16)
Test#1 (Memory)
16.03k
6.74k (x0.42)
TOTAL
326.76k
65.01k (x0.2)

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
3800X
i5-1035G4
Test#1 (Integers)
17.17k
7.07k (x0.41)
Test#2 (FP)
25.32k
10.55k (x0.42)
Test#3 (Generic, ZIP)
8.36k
5.27k (x0.63)
Test#1 (Memory)
27.86k
5.66k (x0.2)
TOTAL
78.71k
28.56k (x0.36)

Multithread

3800X

i5-1035G4
Test#1 (Integers)
136.06k
25.28k (x0.19)
Test#2 (FP)
195.06k
37.48k (x0.19)
Test#3 (Generic, ZIP)
97.81k
17.77k (x0.18)
Test#1 (Memory)
12.91k
6.92k (x0.54)
TOTAL
441.85k
87.45k (x0.2)

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
3800X
i5-1035G4
Test#1 (Integers)
16.76k
13.9k (x0.83)
Test#2 (FP)
25.16k
20.13k (x0.8)
Test#3 (Generic, ZIP)
8.76k
9.41k (x1.07)
Test#1 (Memory)
24.3k
10.59k (x0.44)
TOTAL
74.98k
54.03k (x0.72)

Multithread

3800X

i5-1035G4
Test#1 (Integers)
131.36k
55.4k (x0.42)
Test#2 (FP)
198.51k
59.01k (x0.3)
Test#3 (Generic, ZIP)
97.27k
22.83k (x0.23)
Test#1 (Memory)
13.4k
6.7k (x0.5)
TOTAL
440.54k
143.94k (x0.33)

AVX2 optimized benchmark
The benchmark in mode III (AVX2), like AVX1, is optimized to used 256 bits registers beside the second version of the Advanced Vector Extensions (AVX). The first AVX2 compatible CPU was released in 2013.
Monothread
3800X
i5-1035G4
Test#1 (Integers)
17.1k
25.53k (x1.49)
Test#2 (FP)
26.59k
19.99k (x0.75)
Test#3 (Generic, ZIP)
8.91k
9.31k (x1.04)
Test#1 (Memory)
23.21k
10.81k (x0.47)
TOTAL
75.81k
65.64k (x0.87)

Multithread

3800X

i5-1035G4
Test#1 (Integers)
172.04k
58.46k (x0.34)
Test#2 (FP)
214.03k
57.31k (x0.27)
Test#3 (Generic, ZIP)
97.1k
20.1k (x0.21)
Test#1 (Memory)
14.57k
6.81k (x0.47)
TOTAL
497.74k
142.69k (x0.29)

Performance/W
3800X
i5-1035G4
Test#1 (Integers)
1638 points/W
3897 points/W
Test#2 (FP)
2038 points/W
3821 points/W
Test#3 (Generic, ZIP)
925 points/W
1340 points/W
Test#1 (Memory)
139 points/W
454 points/W
TOTAL
4740 points/W
9513 points/W

Performance/GHz
3800X
i5-1035G4
Test#1 (Integers)
3799 points/GHz
6901 points/GHz
Test#2 (FP)
5909 points/GHz
5401 points/GHz
Test#3 (Generic, ZIP)
1981 points/GHz
2515 points/GHz
Test#1 (Memory)
5158 points/GHz
2922 points/GHz
TOTAL
16847 points/GHz
17739 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