Created
February 23, 2019 19:53
-
-
Save travisdowns/020771ec876a2f6998292c8ed4944069 to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| ========================================================================== | |
| == Memory bandwidth tests == | |
| == == | |
| == Note 1: 1MB = 1000000 bytes == | |
| == Note 2: Results for 'copy' tests show how many bytes can be == | |
| == copied per second (adding together read and writen == | |
| == bytes would have provided twice higher numbers) == | |
| == Note 3: 2-pass copy means that we are using a small temporary buffer == | |
| == to first fetch data into it, and only then write it to the == | |
| == destination (source -> L1 cache, L1 cache -> destination) == | |
| == Note 4: If sample standard deviation exceeds 0.1%, it is shown in == | |
| == brackets == | |
| ========================================================================== | |
| C copy backwards : 7059.9 MB/s | |
| C copy backwards (32 byte blocks) : 7064.2 MB/s | |
| C copy backwards (64 byte blocks) : 7067.9 MB/s | |
| C copy : 7102.5 MB/s | |
| C copy prefetched (32 bytes step) : 7076.6 MB/s | |
| C copy prefetched (64 bytes step) : 7074.6 MB/s | |
| C 2-pass copy : 6518.5 MB/s | |
| C 2-pass copy prefetched (32 bytes step) : 6688.9 MB/s | |
| C 2-pass copy prefetched (64 bytes step) : 6690.1 MB/s | |
| C fill : 10830.9 MB/s | |
| C fill (shuffle within 16 byte blocks) : 10832.0 MB/s | |
| C fill (shuffle within 32 byte blocks) : 10832.0 MB/s | |
| C fill (shuffle within 64 byte blocks) : 10831.8 MB/s | |
| --- | |
| standard memcpy : 10833.6 MB/s | |
| standard memset : 28739.8 MB/s | |
| --- | |
| MOVSB copy : 9615.5 MB/s | |
| MOVSD copy : 9614.6 MB/s | |
| STOSB fill : 28930.8 MB/s | |
| SSE2 copy : 7120.7 MB/s | |
| SSE2 nontemporal copy : 10866.6 MB/s | |
| SSE2 copy prefetched (32 bytes step) : 7084.5 MB/s | |
| SSE2 copy prefetched (64 bytes step) : 7080.9 MB/s | |
| SSE2 nontemporal copy prefetched (32 bytes step) : 10887.6 MB/s | |
| SSE2 nontemporal copy prefetched (64 bytes step) : 10890.5 MB/s | |
| SSE2 2-pass copy : 6729.2 MB/s | |
| SSE2 2-pass copy prefetched (32 bytes step) : 6711.2 MB/s | |
| SSE2 2-pass copy prefetched (64 bytes step) : 6703.2 MB/s | |
| SSE2 2-pass nontemporal copy : 4951.2 MB/s | |
| SSE2 fill : 10705.8 MB/s | |
| SSE2 nontemporal fill : 21444.9 MB/s |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment