IFC6410 - ssvb/tinymembench GitHub Wiki

CPU clock speed: 1667MHz

Processor       : ARMv7 Processor rev 0 (v7l)
processor       : 0
BogoMIPS        : 13.53

processor       : 1
BogoMIPS        : 13.53

processor       : 2
BogoMIPS        : 13.53

processor       : 3
BogoMIPS        : 13.53

Features        : swp half thumb fastmult vfp edsp neon vfpv3 tls vfpv4 
CPU implementer : 0x51
CPU architecture: 7
CPU variant     : 0x1
CPU part        : 0x06f
CPU revision    : 0

Hardware        : QCT APQ8064 CDP
Revision        : 0000
Serial          : 0000000000000000
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                                     :   2233.9 MB/s
 C copy                                               :   1972.0 MB/s
 C copy prefetched (32 bytes step)                    :   2551.2 MB/s (0.2%)
 C copy prefetched (64 bytes step)                    :   2541.3 MB/s
 C 2-pass copy                                        :   1445.5 MB/s
 C 2-pass copy prefetched (32 bytes step)             :   1929.7 MB/s
 C 2-pass copy prefetched (64 bytes step)             :   1929.4 MB/s
 C fill                                               :   7622.4 MB/s
 ---
 standard memcpy                                      :   1610.0 MB/s
 standard memset                                      :   5978.1 MB/s
 ---
 NEON read                                            :   1704.8 MB/s (0.2%)
 NEON read prefetched (32 bytes step)                 :   4234.6 MB/s (0.2%)
 NEON read prefetched (64 bytes step)                 :   4231.3 MB/s (0.2%)
 NEON read 2 data streams                             :   1585.6 MB/s
 NEON read 2 data streams prefetched (32 bytes step)  :   4840.0 MB/s (0.1%)
 NEON read 2 data streams prefetched (64 bytes step)  :   4879.2 MB/s
 NEON copy                                            :   1530.1 MB/s (0.1%)
 NEON copy prefetched (32 bytes step)                 :   2513.9 MB/s (0.1%)
 NEON copy prefetched (64 bytes step)                 :   2515.5 MB/s (0.1%)
 NEON unrolled copy                                   :   1545.5 MB/s (0.1%)
 NEON unrolled copy prefetched (32 bytes step)        :   3361.8 MB/s
 NEON unrolled copy prefetched (64 bytes step)        :   3371.1 MB/s
 NEON copy backwards                                  :   1509.9 MB/s (0.2%)
 NEON copy backwards prefetched (32 bytes step)       :   2966.7 MB/s
 NEON copy backwards prefetched (64 bytes step)       :   2983.0 MB/s (0.2%)
 NEON 2-pass copy                                     :   1345.3 MB/s (0.2%)
 NEON 2-pass copy prefetched (32 bytes step)          :   2206.5 MB/s
 NEON 2-pass copy prefetched (64 bytes step)          :   2294.2 MB/s
 NEON unrolled 2-pass copy                            :   1301.3 MB/s
 NEON unrolled 2-pass copy prefetched (32 bytes step) :   2679.9 MB/s (0.2%)
 NEON unrolled 2-pass copy prefetched (64 bytes step) :   2658.7 MB/s
 NEON fill                                            :   7625.7 MB/s
 NEON fill backwards                                  :   7598.1 MB/s
 VFP copy                                             :   1544.8 MB/s
 VFP 2-pass copy                                      :   1454.1 MB/s
 ARM fill (STRD)                                      :   5984.2 MB/s
 ARM fill (STM with 8 registers)                      :   7620.7 MB/s
 ARM fill (STM with 4 registers)                      :   7622.8 MB/s (0.3%)
 ARM copy prefetched (incr pld)                       :   2202.4 MB/s
 ARM copy prefetched (wrap pld)                       :   2048.0 MB/s (0.1%)
 ARM 2-pass copy prefetched (incr pld)                :   1823.2 MB/s (0.2%)
 ARM 2-pass copy prefetched (wrap pld)                :   1713.5 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 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 :    0.9 ns          /     1.1 ns 
     16384 :    1.4 ns          /     1.5 ns 
     32768 :   12.4 ns          /    17.4 ns 
     65536 :   17.3 ns          /    21.4 ns 
    131072 :   19.6 ns          /    22.6 ns 
    262144 :   22.8 ns          /    26.0 ns 
    524288 :   24.5 ns          /    27.4 ns 
   1048576 :   45.2 ns          /    68.4 ns 
   2097152 :   73.6 ns          /   119.6 ns 
   4194304 :  144.8 ns          /   191.0 ns 
   8388608 :  161.7 ns          /   206.9 ns 
  16777216 :  175.0 ns          /   218.9 ns 
  33554432 :  182.7 ns          /   226.4 ns 
  67108864 :  188.7 ns          /   235.3 ns