やっぱりDDR3は速いなぁ…STREAMでメモリベンチ
cd /usr/src/
mkdir stream
cd ./stream
wget http://www.cs.virginia.edu/stream/FTP/Code/stream.c
gcc -O stream.c -o stream
./stream
gcc -O2 stream.c -o stream
./stream
gcc -O3 stream.c -o stream
./stream
Intel(R) Xeon(TM) CPU 2.80GHz、2GB(DDR2)の場合
————————————————————-
STREAM version $Revision: 5.9 $
————————————————————-
This system uses 8 bytes per DOUBLE PRECISION word.
————————————————————-
Array size = 2000000, Offset = 0
Total memory required = 45.8 MB.
Each test is run 10 times, but only
the *best* time for each is used.
————————————————————-
Printing one line per active thread….
————————————————————-
Your clock granularity/precision appears to be 1 microseconds.
Each test below will take on the order of 10828 microseconds.
(= 10828 clock ticks)
Increase the size of the arrays if this shows that
you are not getting at least 20 clock ticks per test.
————————————————————-
WARNING — The above is only a rough guideline.
For best results, please be sure you know the
precision of your system timer.
————————————————————-
Function Rate (MB/s) Avg time Min time Max time
Copy: 2117.8006 0.0151 0.0151 0.0153
Scale: 2148.5149 0.0149 0.0149 0.0151
Add: 2566.0102 0.0188 0.0187 0.0190
Triad: 2566.5663 0.0187 0.0187 0.0188
————————————————————-
Solution Validates
————————————————————-
Intel(R) Core(TM) i3 CPU 550 @ 3.20GHz、4GB(DDR3)の場合
————————————————————-
STREAM version $Revision: 5.9 $
————————————————————-
This system uses 8 bytes per DOUBLE PRECISION word.
————————————————————-
Array size = 2000000, Offset = 0
Total memory required = 45.8 MB.
Each test is run 10 times, but only
the *best* time for each is used.
————————————————————-
Printing one line per active thread….
————————————————————-
Your clock granularity/precision appears to be 1 microseconds.
Each test below will take on the order of 2913 microseconds.
(= 2913 clock ticks)
Increase the size of the arrays if this shows that
you are not getting at least 20 clock ticks per test.
————————————————————-
WARNING — The above is only a rough guideline.
For best results, please be sure you know the
precision of your system timer.
————————————————————-
Function Rate (MB/s) Avg time Min time Max time
Copy: 8513.1123 0.0040 0.0038 0.0041
Scale: 8510.9529 0.0041 0.0038 0.0043
Add: 9052.8617 0.0055 0.0053 0.0057
Triad: 9158.2856 0.0055 0.0052 0.0057
————————————————————-
Solution Validates
————————————————————-
ヽ(;´Д`)ノ
追伸:
先日買ったFB-DIMM(PC-5300F/DDR2)なマシンでも試してみました。
————————————————————-
STREAM version $Revision: 5.9 $
————————————————————-
This system uses 8 bytes per DOUBLE PRECISION word.
————————————————————-
Array size = 2000000, Offset = 0
Total memory required = 45.8 MB.
Each test is run 10 times, but only
the *best* time for each is used.
————————————————————-
Printing one line per active thread….
————————————————————-
Your clock granularity/precision appears to be 1 microseconds.
Each test below will take on the order of 7155 microseconds.
(= 7155 clock ticks)
Increase the size of the arrays if this shows that
you are not getting at least 20 clock ticks per test.
————————————————————-
WARNING — The above is only a rough guideline.
For best results, please be sure you know the
precision of your system timer.
————————————————————-
Function Rate (MB/s) Avg time Min time Max time
Copy: 3028.5833 0.0106 0.0106 0.0109
Scale: 3052.5536 0.0105 0.0105 0.0106
Add: 3410.7543 0.0142 0.0141 0.0151
Triad: 3423.6305 0.0141 0.0140 0.0144
————————————————————-
Solution Validates
————————————————————-
やっぱりDDR3はすごいなー。