Processor : ARMv7 Processor rev 3 (v7l)
processor : 0
BogoMIPS : 47.99
processor : 2
BogoMIPS : 48.00
Features : swp half thumb fastmult vfp edsp thumbee neon vfpv3 tls vfpv4 idiva
idivt
CPU implementer : 0x41
CPU architecture: 7
CPU variant : 0x0
CPU part : 0xc07
CPU revision : 3
Hardware : sun6i
Revision : 000b
Serial : 51425216353442430f000134cd6b0107
tinymembench v0.3.9 (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 : 858.8 MB/s (2.7%)
C copy : 937.4 MB/s (0.5%)
C copy prefetched (32 bytes step) : 837.1 MB/s
C copy prefetched (64 bytes step) : 837.3 MB/s (2.0%)
C 2-pass copy : 791.6 MB/s
C 2-pass copy prefetched (32 bytes step) : 820.6 MB/s
C 2-pass copy prefetched (64 bytes step) : 820.6 MB/s
C fill : 2713.6 MB/s
---
standard memcpy : 883.1 MB/s (3.5%)
standard memset : 2480.5 MB/s (0.2%)
---
NEON read : 1360.4 MB/s (2.2%)
NEON read prefetched (32 bytes step) : 1505.6 MB/s
NEON read prefetched (64 bytes step) : 1540.6 MB/s
NEON read 2 data streams : 394.2 MB/s (1.4%)
NEON read 2 data streams prefetched (32 bytes step) : 750.8 MB/s
NEON read 2 data streams prefetched (64 bytes step) : 796.1 MB/s
NEON copy : 968.8 MB/s (4.1%)
NEON copy prefetched (32 bytes step) : 942.0 MB/s
NEON copy prefetched (64 bytes step) : 936.7 MB/s
NEON unrolled copy : 822.9 MB/s
NEON unrolled copy prefetched (32 bytes step) : 828.9 MB/s
NEON unrolled copy prefetched (64 bytes step) : 856.9 MB/s (2.8%)
NEON copy backwards : 959.5 MB/s (0.1%)
NEON copy backwards prefetched (32 bytes step) : 932.9 MB/s
NEON copy backwards prefetched (64 bytes step) : 931.2 MB/s
NEON 2-pass copy : 834.7 MB/s (2.7%)
NEON 2-pass copy prefetched (32 bytes step) : 884.1 MB/s
NEON 2-pass copy prefetched (64 bytes step) : 907.8 MB/s
NEON unrolled 2-pass copy : 719.9 MB/s
NEON unrolled 2-pass copy prefetched (32 bytes step) : 677.4 MB/s (1.9%)
NEON unrolled 2-pass copy prefetched (64 bytes step) : 724.1 MB/s
NEON fill : 2713.0 MB/s
NEON fill backwards : 2707.9 MB/s
VFP copy : 824.6 MB/s (2.5%)
VFP 2-pass copy : 734.3 MB/s
ARM fill (STRD) : 2484.1 MB/s (0.3%)
ARM fill (STM with 8 registers) : 2709.5 MB/s (1.5%)
ARM fill (STM with 4 registers) : 2707.5 MB/s (0.1%)
ARM copy prefetched (incr pld) : 957.6 MB/s
ARM copy prefetched (wrap pld) : 922.1 MB/s (3.9%)
ARM 2-pass copy prefetched (incr pld) : 814.7 MB/s
ARM 2-pass copy prefetched (wrap pld) : 796.9 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 / 10.8 ns
131072 : 9.6 ns / 15.1 ns
262144 : 11.3 ns / 16.8 ns
524288 : 12.3 ns / 17.4 ns
1048576 : 14.9 ns / 20.4 ns
2097152 : 105.9 ns / 163.1 ns
4194304 : 153.1 ns / 208.9 ns
8388608 : 178.5 ns / 227.0 ns
16777216 : 194.1 ns / 238.9 ns
33554432 : 205.1 ns / 250.7 ns
67108864 : 215.8 ns / 266.7 ns