tinymembench v0.2.9 (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 : 149.1 MB/s (0.8%)
C copy : 570.3 MB/s
C copy prefetched (32 bytes step) : 612.2 MB/s
C copy prefetched (64 bytes step) : 612.3 MB/s
C 2-pass copy : 495.5 MB/s
C 2-pass copy prefetched (32 bytes step) : 533.9 MB/s
C 2-pass copy prefetched (64 bytes step) : 533.8 MB/s
C fill : 1959.1 MB/s
---
standard memcpy : 626.8 MB/s
standard memset : 1931.8 MB/s (0.1%)
---
NEON read : 691.0 MB/s
NEON read prefetched (32 bytes step) : 776.2 MB/s
NEON read prefetched (64 bytes step) : 777.4 MB/s
NEON copy : 572.6 MB/s
NEON copy prefetched (32 bytes step) : 558.1 MB/s
NEON copy prefetched (64 bytes step) : 661.7 MB/s
NEON unrolled copy : 577.7 MB/s
NEON unrolled copy prefetched (32 bytes step) : 597.5 MB/s
NEON unrolled copy prefetched (64 bytes step) : 632.1 MB/s
NEON copy backwards : 560.8 MB/s
NEON copy backwards prefetched (32 bytes step) : 534.6 MB/s
NEON copy backwards prefetched (64 bytes step) : 653.1 MB/s
NEON 2-pass copy : 514.5 MB/s
NEON 2-pass copy prefetched (32 bytes step) : 569.6 MB/s
NEON 2-pass copy prefetched (64 bytes step) : 550.5 MB/s
NEON unrolled 2-pass copy : 475.4 MB/s (0.4%)
NEON unrolled 2-pass copy prefetched (32 bytes step) : 479.4 MB/s
NEON unrolled 2-pass copy prefetched (64 bytes step) : 502.8 MB/s
NEON fill : 1965.5 MB/s
NEON fill backwards : 1987.4 MB/s
ARM fill (STRD) : 1924.7 MB/s
ARM fill (STM with 8 registers) : 1962.4 MB/s
ARM fill (STM with 4 registers) : 1950.3 MB/s
ARM copy prefetched (incr pld) : 637.9 MB/s
ARM copy prefetched (wrap pld) : 548.4 MB/s
ARM 2-pass copy prefetched (incr pld) : 546.1 MB/s
ARM 2-pass copy prefetched (wrap pld) : 517.5 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 total 3 requests to SDRAM for almost every ==
== memory access (though 64MiB is not 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 : read access time (single random read / dual random read)
2 : 0.0 ns / 0.0 ns
4 : 0.0 ns / 0.0 ns
8 : 0.0 ns / 0.0 ns
16 : 0.0 ns / 0.0 ns
32 : 0.0 ns / 0.0 ns
64 : 0.0 ns / 0.0 ns
128 : 0.0 ns / 0.0 ns
256 : 0.0 ns / 0.0 ns
512 : 0.0 ns / 0.0 ns
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 / 10.8 ns
131072 : 9.6 ns / 15.1 ns
262144 : 11.2 ns / 16.8 ns
524288 : 12.1 ns / 17.4 ns
1048576 : 37.5 ns / 65.8 ns
2097152 : 164.9 ns / 258.0 ns
4194304 : 243.2 ns / 334.7 ns
8388608 : 284.4 ns / 364.7 ns
16777216 : 307.6 ns / 382.0 ns
33554432 : 324.2 ns / 400.1 ns
67108864 : 340.2 ns / 423.9 ns