| | | | | | |

Core i3-1005G1 vs Ryzen 9 3900


Description
The i3-1005G1 is based on Ice Lake architecture while the 3900 is based on Zen 2.

Using the multithread performance as a reference, the i3-1005G1 gets a score of 116.6 k points while the 3900 gets 687.5 k points.

Summarizing, the 3900 is 5.9 times faster than the i3-1005G1. 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
1.2 GHz
3.1 GHz
Boost frecuency
3.4 GHz
4.3 GHz
Socket
BGA 1526
AM4
Cores/Threads
2/4
12/24
TDP
15 W
65 W
Cache L1 (d+i)
2x32+2x48 kB
12x32+12x32 kB
Cache L2
2x512 kB
12x512 kB
Cache L3
4096 kB
4x16384 kB
Date
August 2019
September 2019
Mean monothread perf.
50.62k points
74.97k points
Mean multithread perf.
116.63k 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
i3-1005G1
3900
Test#1 (Integers)
3.07k
4.39k (x1.43)
Test#2 (FP)
13.76k
16.99k (x1.23)
Test#3 (Generic, ZIP)
8k
7.74k (x0.97)
Test#1 (Memory)
6.59k
24.57k (x3.73)
TOTAL
31.42k
53.69k (x1.71)

Multithread

i3-1005G1

3900
Test#1 (Integers)
8k
48.45k (x6.05)
Test#2 (FP)
35.53k
230.81k (x6.5)
Test#3 (Generic, ZIP)
18.53k
122.82k (x6.63)
Test#1 (Memory)
4.3k
54.73k (x12.73)
TOTAL
66.36k
456.8k (x6.88)

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
i3-1005G1
3900
Test#1 (Integers)
10.52k
16.59k (x1.58)
Test#2 (FP)
17.6k
24.55k (x1.39)
Test#3 (Generic, ZIP)
8.76k
8.55k (x0.98)
Test#1 (Memory)
6.55k
26.28k (x4.01)
TOTAL
43.44k
75.97k (x1.75)

Multithread

i3-1005G1

3900
Test#1 (Integers)
26.86k
181.33k (x6.75)
Test#2 (FP)
42.38k
261.01k (x6.16)
Test#3 (Generic, ZIP)
20.65k
126.62k (x6.13)
Test#1 (Memory)
4.21k
66.64k (x15.83)
TOTAL
94.1k
635.6k (x6.75)

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
i3-1005G1
3900
Test#1 (Integers)
11.93k
16.16k (x1.35)
Test#2 (FP)
16.99k
23.75k (x1.4)
Test#3 (Generic, ZIP)
6.43k
9.32k (x1.45)
Test#1 (Memory)
4.59k
23.17k (x5.05)
TOTAL
39.93k
72.4k (x1.81)

Multithread

i3-1005G1

3900
Test#1 (Integers)
29.07k
174.73k (x6.01)
Test#2 (FP)
46.14k
275.63k (x5.97)
Test#3 (Generic, ZIP)
19.47k
125.65k (x6.45)
Test#1 (Memory)
4.18k
44.17k (x10.56)
TOTAL
98.86k
620.18k (x6.27)

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
i3-1005G1
3900
Test#1 (Integers)
19.45k
16.85k (x0.87)
Test#2 (FP)
16.75k
26.03k (x1.55)
Test#3 (Generic, ZIP)
8.04k
9.54k (x1.19)
Test#1 (Memory)
6.38k
22.55k (x3.53)
TOTAL
50.62k
74.97k (x1.48)

Multithread

i3-1005G1

3900
Test#1 (Integers)
46.52k
229.41k (x4.93)
Test#2 (FP)
48.76k
292.81k (x6.01)
Test#3 (Generic, ZIP)
17.12k
128.48k (x7.5)
Test#1 (Memory)
4.23k
36.8k (x8.7)
TOTAL
116.63k
687.5k (x5.89)

Performance/W
i3-1005G1
3900
Test#1 (Integers)
3102 points/W
3529 points/W
Test#2 (FP)
3251 points/W
4505 points/W
Test#3 (Generic, ZIP)
1141 points/W
1977 points/W
Test#1 (Memory)
282 points/W
566 points/W
TOTAL
7776 points/W
10577 points/W

Performance/GHz
i3-1005G1
3900
Test#1 (Integers)
5721 points/GHz
3920 points/GHz
Test#2 (FP)
4926 points/GHz
6054 points/GHz
Test#3 (Generic, ZIP)
2365 points/GHz
2218 points/GHz
Test#1 (Memory)
1877 points/GHz
5243 points/GHz
TOTAL
14889 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