Pentium 4 HT 521 vs Pentium D 820
Description
Both models 521 and 820 are based on NetBurst architecture.
Using the multithread performance as a reference, the 521 gets a score of 8.4 k points while the 820 gets 14.1 k points.
Summarizing, the 820 is 1.7 times faster than the 521. To get a proper comparison between both models, take a look to the data shown below.
Using the multithread performance as a reference, the 521 gets a score of 8.4 k points while the 820 gets 14.1 k points.
Summarizing, the 820 is 1.7 times faster than the 521. To get a proper comparison between both models, take a look to the data shown below.
Specs
CPUID
f49
f44
Core
Prescott
Smithfield
Base frecuency
2.8 GHz
2.8 GHz
Socket
LGA 775
LGA 775
Cores/Threads
1/2
2/2
TDP
84 W
130 W
Cache L1 (d+i)
8+8 kB
16+8 kB
Cache L2
1024 kB
2048 kB
Date
2004
May 2005
Mean monothread perf.
7.48k points
7.45k points
Mean multithread perf.
8.42k points
14.07k 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
521
820
Test#1 (Integers)
1.45k
1.46k (x1.01)
Test#2 (FP)
2.6k
2.6k (x1)
Test#3 (Generic, ZIP)
1.26k
1.26k (x1)
Test#1 (Memory)
0.91k
0.91k (x1)
TOTAL
6.22k
6.23k (x1)
Multithread
521
820
Test#1 (Integers)
1.2k
2.93k (x2.43)
Test#2 (FP)
3.04k
5.19k (x1.71)
Test#3 (Generic, ZIP)
1.48k
2.53k (x1.7)
Test#1 (Memory)
0.9k
0.94k (x1.05)
TOTAL
6.62k
11.59k (x1.75)
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
521
820
Test#1 (Integers)
1.96k
1.93k (x0.98)
Test#2 (FP)
3.12k
3.11k (x1)
Test#3 (Generic, ZIP)
1.49k
1.49k (x1)
Test#1 (Memory)
0.91k
0.91k (x1)
TOTAL
7.48k
7.45k (x1)
Multithread
521
820
Test#1 (Integers)
1.77k
3.92k (x2.22)
Test#2 (FP)
3.96k
6.23k (x1.57)
Test#3 (Generic, ZIP)
1.8k
2.99k (x1.66)
Test#1 (Memory)
0.9k
0.94k (x1.04)
TOTAL
8.42k
14.07k (x1.67)
Performance/W
521
820
Test#1 (Integers)
21 points/W
30 points/W
Test#2 (FP)
47 points/W
48 points/W
Test#3 (Generic, ZIP)
21 points/W
23 points/W
Test#1 (Memory)
11 points/W
7 points/W
TOTAL
100 points/W
108 points/W
Performance/GHz
521
820
Test#1 (Integers)
701 points/GHz
690 points/GHz
Test#2 (FP)
1113 points/GHz
1112 points/GHz
Test#3 (Generic, ZIP)
533 points/GHz
534 points/GHz
Test#1 (Memory)
325 points/GHz
324 points/GHz
TOTAL
2672 points/GHz
2660 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.
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]
Test#2 (FP) [points vs time]
Test#3 (Generic, ZIP) [points vs time]
Test#1 (Memory) [points vs time]
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.
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]
Test#2 (FP) [points vs time]
Test#3 (Generic, ZIP) [points vs time]
Test#1 (Memory) [points vs time]
Hardlimit Benchmark Central - Ver. 3.11.4