| | | | | | |

Ryzen 5 3500U vs 2400G


Description
The 3500U is based on Zen+ architecture while the 2400G is based on Zen.

Using the multithread performance as a reference, the 3500U gets a score of 141 k points while the 2400G gets 198.3 k points.

Summarizing, the 2400G is 1.4 times faster than the 3500U. To get a proper comparison between both models, take a look to the data shown below.

Specs
CPUID
810f81
810f10
Core
Picasso
Raven Ridge
Architecture
Base frecuency
2.1 GHz
3.6 GHz
Boost frecuency
3.7 GHz
3.9 GHz
Socket
BGA-FP5
AM4
Cores/Threads
4/8
4/8
TDP
15 W
65 W
Cache L1 (d+i)
4x64+6x32 kB
4x64+4x32 kB
Cache L2
4x512 kB
4x512 kB
Cache L3
4096 kB
4096 kB
Date
January 2019
January 2018
Mean monothread perf.
36.64k points
47.96k points
Mean multithread perf.
140.97k points
198.27k 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
3500U
2400G
Test#1 (Integers)
3.24k
3.8k (x1.17)
Test#2 (FP)
13.16k
17.38k (x1.32)
Test#3 (Generic, ZIP)
4.41k
5.17k (x1.17)
Test#1 (Memory)
3.32k
3.16k (x0.95)
TOTAL
24.12k
29.52k (x1.22)

Multithread

3500U

2400G
Test#1 (Integers)
12.95k
15.28k (x1.18)
Test#2 (FP)
57.84k
76.44k (x1.32)
Test#3 (Generic, ZIP)
21.05k
27.48k (x1.31)
Test#1 (Memory)
3.51k
3.02k (x0.86)
TOTAL
95.36k
122.2k (x1.28)

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
3500U
2400G
Test#1 (Integers)
11.98k
13.95k (x1.16)
Test#2 (FP)
15.85k
20.7k (x1.31)
Test#3 (Generic, ZIP)
4.53k
5.33k (x1.18)
Test#1 (Memory)
3.29k
3.03k (x0.92)
TOTAL
35.65k
43.01k (x1.21)

Multithread

3500U

2400G
Test#1 (Integers)
48.28k
58.56k (x1.21)
Test#2 (FP)
74.19k
92.95k (x1.25)
Test#3 (Generic, ZIP)
23.29k
28.55k (x1.23)
Test#1 (Memory)
3.47k
2.98k (x0.86)
TOTAL
149.23k
183.04k (x1.23)

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
3500U
2400G
Test#1 (Integers)
11.1k
13.04k (x1.17)
Test#2 (FP)
18.97k
22.35k (x1.18)
Test#3 (Generic, ZIP)
3.9k
5.37k (x1.38)
Test#1 (Memory)
3.39k
3.4k (x1)
TOTAL
37.37k
44.15k (x1.18)

Multithread

3500U

2400G
Test#1 (Integers)
45.74k
56.49k (x1.24)
Test#2 (FP)
75.47k
100.74k (x1.33)
Test#3 (Generic, ZIP)
21.89k
28.21k (x1.29)
Test#1 (Memory)
3.49k
3.04k (x0.87)
TOTAL
146.6k
188.49k (x1.29)

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
3500U
2400G
Test#1 (Integers)
10.88k
14.2k (x1.3)
Test#2 (FP)
18.09k
23.23k (x1.28)
Test#3 (Generic, ZIP)
4.29k
5.35k (x1.25)
Test#1 (Memory)
3.36k
5.18k (x1.54)
TOTAL
36.64k
47.96k (x1.31)

Multithread

3500U

2400G
Test#1 (Integers)
42.44k
58.24k (x1.37)
Test#2 (FP)
73.82k
105.72k (x1.43)
Test#3 (Generic, ZIP)
20.76k
28.73k (x1.38)
Test#1 (Memory)
3.96k
5.59k (x1.41)
TOTAL
140.97k
198.27k (x1.41)

Performance/W
3500U
2400G
Test#1 (Integers)
2829 points/W
896 points/W
Test#2 (FP)
4921 points/W
1626 points/W
Test#3 (Generic, ZIP)
1384 points/W
442 points/W
Test#1 (Memory)
264 points/W
86 points/W
TOTAL
9398 points/W
3050 points/W

Performance/GHz
3500U
2400G
Test#1 (Integers)
2942 points/GHz
3641 points/GHz
Test#2 (FP)
4890 points/GHz
5957 points/GHz
Test#3 (Generic, ZIP)
1161 points/GHz
1372 points/GHz
Test#1 (Memory)
909 points/GHz
1327 points/GHz
TOTAL
9901 points/GHz
12298 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