| | | | | | |

Ryzen 9 3900 vs Core i5-1235U


Description
The 3900 is based on Zen 2 architecture while the i5-1235U is based on Alder Lake.

Using the multithread performance as a reference, the 3900 gets a score of 687.5 k points while the i5-1235U gets 297.5 k points.

Summarizing, the 3900 is 2.3 times faster than the i5-1235U. To get a proper comparison between both models, take a look to the data shown below.

Specs
CPUID
870f10
906a4
Core
Matisse
Alder Lake-U
Architecture
Base frecuency
3.1 GHz
3.3 GHz
Boost frecuency
4.3 GHz
4.4 GHz
Socket
AM4
BGA 1700
Cores/Threads
12/24
10/12
TDP
65 W
15 W
Cache L1 (d+i)
12x32+12x32 kB
2x32/8x64+2x48/8x32 kB
Cache L2
12x512 kB
1x1280+4x2048 kB
Cache L3
4x16384 kB
12288 kB
Date
September 2019
April 2022
Mean monothread perf.
74.97k points
81.64k points
Mean multithread perf.
687.5k points
297.46k 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
i5-1235U
Test#1 (Integers)
4.39k
7.33k (x1.67)
Test#2 (FP)
16.99k
18.27k (x1.08)
Test#3 (Generic, ZIP)
7.74k
12.8k (x1.65)
Test#1 (Memory)
24.57k
13.2k (x0.54)
TOTAL
53.69k
51.61k (x0.96)

Multithread

3900

i5-1235U
Test#1 (Integers)
48.45k
29.24k (x0.6)
Test#2 (FP)
230.81k
83.32k (x0.36)
Test#3 (Generic, ZIP)
122.82k
54.53k (x0.44)
Test#1 (Memory)
54.73k
4.99k (x0.09)
TOTAL
456.8k
172.07k (x0.38)

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
i5-1235U
Test#1 (Integers)
16.59k
23.53k (x1.42)
Test#2 (FP)
24.55k
23.51k (x0.96)
Test#3 (Generic, ZIP)
8.55k
14.71k (x1.72)
Test#1 (Memory)
26.28k
13.24k (x0.5)
TOTAL
75.97k
74.99k (x0.99)

Multithread

3900

i5-1235U
Test#1 (Integers)
181.33k
106.07k (x0.58)
Test#2 (FP)
261.01k
115.88k (x0.44)
Test#3 (Generic, ZIP)
126.62k
60.53k (x0.48)
Test#1 (Memory)
66.64k
5.88k (x0.09)
TOTAL
635.6k
288.36k (x0.45)

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
i5-1235U
Test#1 (Integers)
16.16k
23.03k (x1.43)
Test#2 (FP)
23.75k
24.11k (x1.02)
Test#3 (Generic, ZIP)
9.32k
13.9k (x1.49)
Test#1 (Memory)
23.17k
12.11k (x0.52)
TOTAL
72.4k
73.15k (x1.01)

Multithread

3900

i5-1235U
Test#1 (Integers)
174.73k
111.78k (x0.64)
Test#2 (FP)
275.63k
124.18k (x0.45)
Test#3 (Generic, ZIP)
125.65k
59.87k (x0.48)
Test#1 (Memory)
44.17k
5.76k (x0.13)
TOTAL
620.18k
301.58k (x0.49)

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
i5-1235U
Test#1 (Integers)
16.85k
36.73k (x2.18)
Test#2 (FP)
26.03k
22.09k (x0.85)
Test#3 (Generic, ZIP)
9.54k
11.24k (x1.18)
Test#1 (Memory)
22.55k
11.58k (x0.51)
TOTAL
74.97k
81.64k (x1.09)

Multithread

3900

i5-1235U
Test#1 (Integers)
229.41k
130.18k (x0.57)
Test#2 (FP)
292.81k
110.21k (x0.38)
Test#3 (Generic, ZIP)
128.48k
50.76k (x0.4)
Test#1 (Memory)
36.8k
6.31k (x0.17)
TOTAL
687.5k
297.46k (x0.43)

Performance/W
3900
i5-1235U
Test#1 (Integers)
3529 points/W
8679 points/W
Test#2 (FP)
4505 points/W
7348 points/W
Test#3 (Generic, ZIP)
1977 points/W
3384 points/W
Test#1 (Memory)
566 points/W
421 points/W
TOTAL
10577 points/W
19831 points/W

Performance/GHz
3900
i5-1235U
Test#1 (Integers)
3920 points/GHz
8349 points/GHz
Test#2 (FP)
6054 points/GHz
5020 points/GHz
Test#3 (Generic, ZIP)
2218 points/GHz
2555 points/GHz
Test#1 (Memory)
5243 points/GHz
2631 points/GHz
TOTAL
17435 points/GHz
18555 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