Advertisement
Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- admin@miqi-6:~$ /tmp/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 : 2145.1 MB/s
- C copy backwards (32 byte blocks) : 2184.9 MB/s
- C copy backwards (64 byte blocks) : 2178.6 MB/s
- C copy : 2205.8 MB/s
- C copy prefetched (32 bytes step) : 2388.3 MB/s
- C copy prefetched (64 bytes step) : 2548.0 MB/s (0.8%)
- C 2-pass copy : 1411.9 MB/s
- C 2-pass copy prefetched (32 bytes step) : 2193.4 MB/s
- C 2-pass copy prefetched (64 bytes step) : 2309.7 MB/s
- C fill : 6320.1 MB/s (0.2%)
- C fill (shuffle within 16 byte blocks) : 6294.2 MB/s (0.1%)
- C fill (shuffle within 32 byte blocks) : 6278.4 MB/s
- C fill (shuffle within 64 byte blocks) : 6286.3 MB/s
- ---
- standard memcpy : 2718.7 MB/s (2.6%)
- standard memset : 5474.8 MB/s (0.2%)
- ---
- NEON read : 6125.8 MB/s
- NEON read prefetched (32 bytes step) : 5943.5 MB/s
- NEON read prefetched (64 bytes step) : 6391.1 MB/s (0.3%)
- NEON read 2 data streams : 6628.1 MB/s (0.1%)
- NEON read 2 data streams prefetched (32 bytes step) : 5951.2 MB/s
- NEON read 2 data streams prefetched (64 bytes step) : 5893.8 MB/s
- NEON copy : 4046.0 MB/s
- NEON copy prefetched (32 bytes step) : 3513.1 MB/s (0.6%)
- NEON copy prefetched (64 bytes step) : 3285.3 MB/s
- NEON unrolled copy : 3981.8 MB/s
- NEON unrolled copy prefetched (32 bytes step) : 3750.4 MB/s (0.1%)
- NEON unrolled copy prefetched (64 bytes step) : 4057.0 MB/s
- NEON copy backwards : 4174.0 MB/s
- NEON copy backwards prefetched (32 bytes step) : 2803.7 MB/s (0.6%)
- NEON copy backwards prefetched (64 bytes step) : 2839.5 MB/s (0.2%)
- NEON 2-pass copy : 2147.1 MB/s
- NEON 2-pass copy prefetched (32 bytes step) : 2106.5 MB/s
- NEON 2-pass copy prefetched (64 bytes step) : 1759.2 MB/s
- NEON unrolled 2-pass copy : 2169.1 MB/s
- NEON unrolled 2-pass copy prefetched (32 bytes step) : 2118.9 MB/s (0.1%)
- NEON unrolled 2-pass copy prefetched (64 bytes step) : 2248.3 MB/s
- NEON fill : 6319.2 MB/s (0.2%)
- NEON fill backwards : 6289.2 MB/s
- VFP copy : 3976.7 MB/s
- VFP 2-pass copy : 2146.3 MB/s
- ARM fill (STRD) : 6298.0 MB/s (0.1%)
- ARM fill (STM with 8 registers) : 6295.0 MB/s (0.2%)
- ARM fill (STM with 4 registers) : 6292.4 MB/s
- ARM copy prefetched (incr pld) : 3743.6 MB/s
- ARM copy prefetched (wrap pld) : 3665.4 MB/s
- ARM 2-pass copy prefetched (incr pld) : 2057.8 MB/s
- ARM 2-pass copy prefetched (wrap pld) : 2030.8 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
- 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 : 6.2 ns / 10.6 ns
- 131072 : 9.2 ns / 14.6 ns
- 262144 : 12.5 ns / 17.8 ns
- 524288 : 14.1 ns / 19.4 ns
- 1048576 : 15.6 ns / 20.8 ns
- 2097152 : 51.7 ns / 75.2 ns
- 4194304 : 70.2 ns / 92.8 ns
- 8388608 : 83.8 ns / 103.6 ns
- 16777216 : 92.1 ns / 110.1 ns
- 33554432 : 98.5 ns / 116.2 ns
- 67108864 : 104.0 ns / 122.9 ns
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement