| | | | | | |

Ryzen 9 3900 vs Core i7-11800H (ES)


Description
The 3900 is based on Zen 2 architecture while the i7-11800H (ES) is based on Tiger Lake.

Using the multithread performance as a reference, the 3900 gets a score of 687.5 k points while the i7-11800H (ES) gets 709.9 k points.

Summarizing, the i7-11800H (ES) is 1 times faster than the 3900. To get a proper comparison between both models, take a look to the data shown below.

Specs
CPUID
870f10
806d0
Core
Matisse
Tiger Lake-H
Architecture
Base frecuency
3.1 GHz
2.3 GHz
Boost frecuency
4.3 GHz
4.6 GHz
Socket
AM4
BGA 1787
Cores/Threads
12/24
8/16
TDP
65 W
45 W
Cache L1 (d+i)
12x32+12x32 kB
8x32+8x48 kB
Cache L2
12x512 kB
8x1280 kB
Cache L3
4x16384 kB
24576 kB
Date
September 2019
May 2021
Mean monothread perf.
74.97k points
81.62k points
Mean multithread perf.
687.5k points
709.85k 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
i7-11800H (ES)
Test#1 (Integers)
4.39k
4.4k (x1)
Test#2 (FP)
16.99k
20.25k (x1.19)
Test#3 (Generic, ZIP)
7.74k
11.69k (x1.51)
Test#1 (Memory)
24.57k
11.66k (x0.47)
TOTAL
53.69k
48.01k (x0.89)

Multithread

3900

i7-11800H (ES)
Test#1 (Integers)
48.45k
38.93k (x0.8)
Test#2 (FP)
230.81k
191.89k (x0.83)
Test#3 (Generic, ZIP)
122.82k
108.8k (x0.89)
Test#1 (Memory)
54.73k
14.95k (x0.27)
TOTAL
456.8k
354.57k (x0.78)

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
i7-11800H (ES)
Test#1 (Integers)
16.59k
15.22k (x0.92)
Test#2 (FP)
24.55k
25.2k (x1.03)
Test#3 (Generic, ZIP)
8.55k
12.66k (x1.48)
Test#1 (Memory)
26.28k
11.66k (x0.44)
TOTAL
75.97k
64.74k (x0.85)

Multithread

3900

i7-11800H (ES)
Test#1 (Integers)
181.33k
155.37k (x0.86)
Test#2 (FP)
261.01k
260.27k (x1)
Test#3 (Generic, ZIP)
126.62k
115.37k (x0.91)
Test#1 (Memory)
66.64k
20.04k (x0.3)
TOTAL
635.6k
551.04k (x0.87)

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
i7-11800H (ES)
Test#1 (Integers)
16.16k
17.25k (x1.07)
Test#2 (FP)
23.75k
25.53k (x1.07)
Test#3 (Generic, ZIP)
9.32k
12.56k (x1.35)
Test#1 (Memory)
23.17k
11.4k (x0.49)
TOTAL
72.4k
66.74k (x0.92)

Multithread

3900

i7-11800H (ES)
Test#1 (Integers)
174.73k
144.5k (x0.83)
Test#2 (FP)
275.63k
243.41k (x0.88)
Test#3 (Generic, ZIP)
125.65k
109.02k (x0.87)
Test#1 (Memory)
44.17k
16k (x0.36)
TOTAL
620.18k
512.94k (x0.83)

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
i7-11800H (ES)
Test#1 (Integers)
16.85k
30.84k (x1.83)
Test#2 (FP)
26.03k
26.38k (x1.01)
Test#3 (Generic, ZIP)
9.54k
12.66k (x1.33)
Test#1 (Memory)
22.55k
11.74k (x0.52)
TOTAL
74.97k
81.62k (x1.09)

Multithread

3900

i7-11800H (ES)
Test#1 (Integers)
229.41k
294.86k (x1.29)
Test#2 (FP)
292.81k
280.92k (x0.96)
Test#3 (Generic, ZIP)
128.48k
113.9k (x0.89)
Test#1 (Memory)
36.8k
20.16k (x0.55)
TOTAL
687.5k
709.85k (x1.03)

Performance/W
3900
i7-11800H (ES)
Test#1 (Integers)
3529 points/W
6553 points/W
Test#2 (FP)
4505 points/W
6243 points/W
Test#3 (Generic, ZIP)
1977 points/W
2531 points/W
Test#1 (Memory)
566 points/W
448 points/W
TOTAL
10577 points/W
15774 points/W

Performance/GHz
3900
i7-11800H (ES)
Test#1 (Integers)
3920 points/GHz
6705 points/GHz
Test#2 (FP)
6054 points/GHz
5734 points/GHz
Test#3 (Generic, ZIP)
2218 points/GHz
2752 points/GHz
Test#1 (Memory)
5243 points/GHz
2552 points/GHz
TOTAL
17435 points/GHz
17744 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