| | | | | | |

Ryzen 9 3900 vs Core i5-1135G7


Description
The 3900 is based on Zen 2 architecture while the i5-1135G7 is based on Tiger Lake.

Using the multithread performance as a reference, the 3900 gets a score of 687.5 k points while the i5-1135G7 gets 262.1 k points.

Summarizing, the 3900 is 2.6 times faster than the i5-1135G7. To get a proper comparison between both models, take a look to the data shown below.

Specs
CPUID
870f10
806c1
Core
Matisse
Tiger Lake UP3
Architecture
Base frecuency
3.1 GHz
2.4 GHz
Boost frecuency
4.3 GHz
4.2 GHz
Socket
AM4
BGA 1449
Cores/Threads
12/24
4/8
TDP
65 W
28 W
Cache L1 (d+i)
12x32+12x32 kB
4x32+4x48 kB
Cache L2
12x512 kB
4x1280 kB
Cache L3
4x16384 kB
8192 kB
Date
September 2019
September 2020
Mean monothread perf.
74.97k points
69.38k points
Mean multithread perf.
687.5k points
262.07k 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
3900
i5-1135G7
Test#1 (Integers)
4.39k
3.77k (x0.86)
Test#2 (FP)
16.99k
17.26k (x1.02)
Test#3 (Generic, ZIP)
7.74k
9.24k (x1.19)
Test#1 (Memory)
24.57k
8.39k (x0.34)
TOTAL
53.69k
38.66k (x0.72)

Multithread

3900

i5-1135G7
Test#1 (Integers)
48.45k
16.86k (x0.35)
Test#2 (FP)
230.81k
76.62k (x0.33)
Test#3 (Generic, ZIP)
122.82k
34.56k (x0.28)
Test#1 (Memory)
54.73k
4.5k (x0.08)
TOTAL
456.8k
132.53k (x0.29)

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
3900
i5-1135G7
Test#1 (Integers)
16.59k
13.43k (x0.81)
Test#2 (FP)
24.55k
22.29k (x0.91)
Test#3 (Generic, ZIP)
8.55k
11.18k (x1.31)
Test#1 (Memory)
26.28k
9.75k (x0.37)
TOTAL
75.97k
56.64k (x0.75)

Multithread

3900

i5-1135G7
Test#1 (Integers)
181.33k
40.24k (x0.22)
Test#2 (FP)
261.01k
65.99k (x0.25)
Test#3 (Generic, ZIP)
126.62k
28.51k (x0.23)
Test#1 (Memory)
66.64k
6.66k (x0.1)
TOTAL
635.6k
141.4k (x0.22)

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
3900
i5-1135G7
Test#1 (Integers)
16.16k
15.2k (x0.94)
Test#2 (FP)
23.75k
23.46k (x0.99)
Test#3 (Generic, ZIP)
9.32k
11.05k (x1.19)
Test#1 (Memory)
23.17k
9.53k (x0.41)
TOTAL
72.4k
59.23k (x0.82)

Multithread

3900

i5-1135G7
Test#1 (Integers)
174.73k
43.69k (x0.25)
Test#2 (FP)
275.63k
70.25k (x0.25)
Test#3 (Generic, ZIP)
125.65k
28.48k (x0.23)
Test#1 (Memory)
44.17k
6.24k (x0.14)
TOTAL
620.18k
148.66k (x0.24)

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
3900
i5-1135G7
Test#1 (Integers)
16.85k
26.46k (x1.57)
Test#2 (FP)
26.03k
23.63k (x0.91)
Test#3 (Generic, ZIP)
9.54k
10.24k (x1.07)
Test#1 (Memory)
22.55k
9.05k (x0.4)
TOTAL
74.97k
69.38k (x0.93)

Multithread

3900

i5-1135G7
Test#1 (Integers)
229.41k
105.02k (x0.46)
Test#2 (FP)
292.81k
108.51k (x0.37)
Test#3 (Generic, ZIP)
128.48k
36.5k (x0.28)
Test#1 (Memory)
36.8k
12.04k (x0.33)
TOTAL
687.5k
262.07k (x0.38)

Performance/W
3900
i5-1135G7
Test#1 (Integers)
3529 points/W
3751 points/W
Test#2 (FP)
4505 points/W
3875 points/W
Test#3 (Generic, ZIP)
1977 points/W
1304 points/W
Test#1 (Memory)
566 points/W
430 points/W
TOTAL
10577 points/W
9359 points/W

Performance/GHz
3900
i5-1135G7
Test#1 (Integers)
3920 points/GHz
6299 points/GHz
Test#2 (FP)
6054 points/GHz
5626 points/GHz
Test#3 (Generic, ZIP)
2218 points/GHz
2439 points/GHz
Test#1 (Memory)
5243 points/GHz
2154 points/GHz
TOTAL
17435 points/GHz
16518 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