Advertisement
Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- macchiato:~/proj/tinymembench$ ./tinymembench
- tinymembench v0.4.9 (simple benchmark for memory throughput and latency)
- ==========================================================================
- == 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 : 3565.5 MB/s
- C copy backwards (32 byte blocks) : 3567.1 MB/s
- C copy backwards (64 byte blocks) : 3570.8 MB/s
- C copy : 3746.0 MB/s (0.6%)
- C copy prefetched (32 bytes step) : 3722.9 MB/s
- C copy prefetched (64 bytes step) : 3727.5 MB/s
- C 2-pass copy : 3793.6 MB/s (1.0%)
- C 2-pass copy prefetched (32 bytes step) : 3796.6 MB/s
- C 2-pass copy prefetched (64 bytes step) : 3959.2 MB/s
- C fill : 9975.1 MB/s
- C fill (shuffle within 16 byte blocks) : 9975.8 MB/s
- C fill (shuffle within 32 byte blocks) : 9975.3 MB/s
- C fill (shuffle within 64 byte blocks) : 9776.7 MB/s
- ---
- standard memcpy : 3748.3 MB/s (0.5%)
- standard memset : 9975.3 MB/s
- ---
- NEON LDP/STP copy : 3685.7 MB/s
- NEON LDP/STP copy pldl2strm (32 bytes step) : 3656.7 MB/s
- NEON LDP/STP copy pldl2strm (64 bytes step) : 3659.8 MB/s
- NEON LDP/STP copy pldl1keep (32 bytes step) : 3744.7 MB/s
- NEON LDP/STP copy pldl1keep (64 bytes step) : 3741.4 MB/s
- NEON LD1/ST1 copy : 3736.2 MB/s (0.4%)
- NEON STP fill : 9975.4 MB/s
- NEON STNP fill : 9968.6 MB/s
- ARM LDP/STP copy : 3749.3 MB/s (0.5%)
- ARM STP fill : 9975.2 MB/s
- ARM STNP fill : 9968.3 MB/s
- ==========================================================================
- == Memory latency test ==
- == ==
- == Average time is measured for random memory accesses in the buffers ==
- == of different sizes. The larger is the buffer, the more significant ==
- == are relative contributions of TLB, L1/L2 cache misses and SDRAM ==
- == accesses. For extremely large buffer sizes we are expecting to see ==
- == page table walk with several requests to SDRAM for almost every ==
- == memory access (though 64MiB is not nearly large enough to experience ==
- == this effect to its fullest). ==
- == ==
- == Note 1: All the numbers are representing extra time, which needs to ==
- == be added to L1 cache latency. The cycle timings for L1 cache ==
- == latency can be usually found in the processor documentation. ==
- == Note 2: Dual random read means that we are simultaneously performing ==
- == two independent memory accesses at a time. In the case if ==
- == the memory subsystem can't handle multiple outstanding ==
- == requests, dual random read has the same timings as two ==
- == single reads performed one after another. ==
- ==========================================================================
- block size : single random read / dual random read, [MADV_NOHUGEPAGE]
- 1024 : 0.0 ns / 0.0 ns
- 2048 : 0.0 ns / 0.0 ns
- 4096 : 0.0 ns / 0.0 ns
- 8192 : 0.0 ns / 0.0 ns
- 16384 : 0.0 ns / 0.0 ns
- 32768 : 0.0 ns / 0.0 ns
- 65536 : 4.6 ns / 7.3 ns
- 131072 : 7.1 ns / 9.9 ns
- 262144 : 10.8 ns / 14.3 ns
- 524288 : 15.1 ns / 21.2 ns
- 1048576 : 36.7 ns / 50.8 ns
- 2097152 : 87.7 ns / 128.2 ns
- 4194304 : 135.8 ns / 183.9 ns
- 8388608 : 168.7 ns / 215.4 ns
- 16777216 : 185.0 ns / 226.5 ns
- 33554432 : 195.4 ns / 239.2 ns
- 67108864 : 210.9 ns / 259.1 ns
- block size : single random read / dual random read, [MADV_HUGEPAGE]
- 1024 : 0.0 ns / 0.0 ns
- 2048 : 0.0 ns / 0.0 ns
- 4096 : 0.0 ns / 0.0 ns
- 8192 : 0.0 ns / 0.0 ns
- 16384 : 0.0 ns / 0.0 ns
- 32768 : 0.0 ns / 0.0 ns
- 65536 : 4.6 ns / 7.3 ns
- 131072 : 7.0 ns / 9.8 ns
- 262144 : 8.2 ns / 10.8 ns
- 524288 : 11.0 ns / 15.4 ns
- 1048576 : 32.9 ns / 46.9 ns
- 2097152 : 81.3 ns / 119.5 ns
- 4194304 : 130.8 ns / 177.9 ns
- 8388608 : 154.7 ns / 194.8 ns
- 16777216 : 167.8 ns / 204.6 ns
- 33554432 : 174.3 ns / 209.4 ns
- 67108864 : 179.8 ns / 213.5 ns
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement
