| | | | | | |

Core i5-1035G1 vs Ryzen 9 3900


Description
The i5-1035G1 is based on Ice Lake architecture while the 3900 is based on Zen 2.

Using the multithread performance as a reference, the i5-1035G1 gets a score of 171.6 k points while the 3900 gets 687.5 k points.

Summarizing, the 3900 is 4 times faster than the i5-1035G1. To get a proper comparison between both models, take a look to the data shown below.

Specs
CPUID
706e5
870f10
Core
Ice Lake-U
Matisse
Architecture
Base frecuency
1 GHz
3.1 GHz
Boost frecuency
3.6 GHz
4.3 GHz
Socket
BGA 1526
AM4
Cores/Threads
4/8
12/24
TDP
15 W
65 W
Cache L1 (d+i)
4x32+4x48 kB
12x32+12x32 kB
Cache L2
4x512 kB
12x512 kB
Cache L3
6144 kB
4x16384 kB
Date
August 2019
September 2019
Mean monothread perf.
55.37k points
74.97k points
Mean multithread perf.
171.65k points
687.5k 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
i5-1035G1
3900
Test#1 (Integers)
3.88k
4.39k (x1.13)
Test#2 (FP)
14.98k
16.99k (x1.13)
Test#3 (Generic, ZIP)
9.7k
7.74k (x0.8)
Test#1 (Memory)
8.6k
24.57k (x2.86)
TOTAL
37.15k
53.69k (x1.45)

Multithread

i5-1035G1

3900
Test#1 (Integers)
14.61k
48.45k (x3.32)
Test#2 (FP)
54.9k
230.81k (x4.2)
Test#3 (Generic, ZIP)
27.58k
122.82k (x4.45)
Test#1 (Memory)
5.04k
54.73k (x10.85)
TOTAL
102.13k
456.8k (x4.47)

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
i5-1035G1
3900
Test#1 (Integers)
12.89k
16.59k (x1.29)
Test#2 (FP)
18.55k
24.55k (x1.32)
Test#3 (Generic, ZIP)
9.93k
8.55k (x0.86)
Test#1 (Memory)
9.54k
26.28k (x2.76)
TOTAL
50.91k
75.97k (x1.49)

Multithread

i5-1035G1

3900
Test#1 (Integers)
50.06k
181.33k (x3.62)
Test#2 (FP)
66.1k
261.01k (x3.95)
Test#3 (Generic, ZIP)
20.24k
126.62k (x6.26)
Test#1 (Memory)
5.51k
66.64k (x12.08)
TOTAL
141.91k
635.6k (x4.48)

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
i5-1035G1
3900
Test#1 (Integers)
13.58k
16.16k (x1.19)
Test#2 (FP)
19.53k
23.75k (x1.22)
Test#3 (Generic, ZIP)
9.37k
9.32k (x0.99)
Test#1 (Memory)
9.23k
23.17k (x2.51)
TOTAL
51.7k
72.4k (x1.4)

Multithread

i5-1035G1

3900
Test#1 (Integers)
56.25k
174.73k (x3.11)
Test#2 (FP)
73.73k
275.63k (x3.74)
Test#3 (Generic, ZIP)
29.56k
125.65k (x4.25)
Test#1 (Memory)
5.39k
44.17k (x8.19)
TOTAL
164.94k
620.18k (x3.76)

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
i5-1035G1
3900
Test#1 (Integers)
21.5k
16.85k (x0.78)
Test#2 (FP)
17.71k
26.03k (x1.47)
Test#3 (Generic, ZIP)
7.92k
9.54k (x1.2)
Test#1 (Memory)
8.24k
22.55k (x2.74)
TOTAL
55.37k
74.97k (x1.35)

Multithread

i5-1035G1

3900
Test#1 (Integers)
73.03k
229.41k (x3.14)
Test#2 (FP)
68.19k
292.81k (x4.29)
Test#3 (Generic, ZIP)
24.89k
128.48k (x5.16)
Test#1 (Memory)
5.54k
36.8k (x6.65)
TOTAL
171.65k
687.5k (x4.01)

Performance/W
i5-1035G1
3900
Test#1 (Integers)
4869 points/W
3529 points/W
Test#2 (FP)
4546 points/W
4505 points/W
Test#3 (Generic, ZIP)
1660 points/W
1977 points/W
Test#1 (Memory)
369 points/W
566 points/W
TOTAL
11443 points/W
10577 points/W

Performance/GHz
i5-1035G1
3900
Test#1 (Integers)
5972 points/GHz
3920 points/GHz
Test#2 (FP)
4919 points/GHz
6054 points/GHz
Test#3 (Generic, ZIP)
2201 points/GHz
2218 points/GHz
Test#1 (Memory)
2290 points/GHz
5243 points/GHz
TOTAL
15381 points/GHz
17435 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