Advertisement
Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- Exynos4412 (Odroid-X2)
- 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 : 461.8 MB/s
- C copy : 1244.5 MB/s (0.3%)
- C copy prefetched (32 bytes step) : 803.6 MB/s
- C copy prefetched (64 bytes step) : 807.7 MB/s
- C 2-pass copy : 945.2 MB/s
- C 2-pass copy prefetched (32 bytes step) : 846.0 MB/s
- C 2-pass copy prefetched (64 bytes step) : 839.6 MB/s
- C fill : 2957.1 MB/s (0.8%)
- ---
- standard memcpy : 1198.3 MB/s
- standard memset : 2954.3 MB/s
- ---
- NEON read : 1885.4 MB/s
- NEON read prefetched (32 bytes step) : 1848.5 MB/s
- NEON read prefetched (64 bytes step) : 1907.3 MB/s
- NEON read 2 data streams : 1834.5 MB/s
- NEON read 2 data streams prefetched (32 bytes step) : 1704.5 MB/s
- NEON read 2 data streams prefetched (64 bytes step) : 1578.3 MB/s
- NEON copy : 1140.8 MB/s
- NEON copy prefetched (32 bytes step) : 1210.3 MB/s
- NEON copy prefetched (64 bytes step) : 1210.9 MB/s
- NEON unrolled copy : 1205.9 MB/s
- NEON unrolled copy prefetched (32 bytes step) : 1180.5 MB/s
- NEON unrolled copy prefetched (64 bytes step) : 1178.7 MB/s
- NEON copy backwards : 444.5 MB/s
- NEON copy backwards prefetched (32 bytes step) : 783.9 MB/s
- NEON copy backwards prefetched (64 bytes step) : 985.1 MB/s
- NEON 2-pass copy : 854.0 MB/s
- NEON 2-pass copy prefetched (32 bytes step) : 1006.6 MB/s
- NEON 2-pass copy prefetched (64 bytes step) : 1005.2 MB/s
- NEON unrolled 2-pass copy : 902.5 MB/s
- NEON unrolled 2-pass copy prefetched (32 bytes step) : 1001.4 MB/s
- NEON unrolled 2-pass copy prefetched (64 bytes step) : 1009.7 MB/s
- NEON fill : 2954.4 MB/s
- NEON fill backwards : 2952.0 MB/s
- VFP copy : 1248.5 MB/s
- VFP 2-pass copy : 1023.6 MB/s
- ARM fill (STRD) : 2954.1 MB/s
- ARM fill (STM with 8 registers) : 2954.4 MB/s
- ARM fill (STM with 4 registers) : 2954.2 MB/s
- ARM copy prefetched (incr pld) : 1185.9 MB/s
- ARM copy prefetched (wrap pld) : 1185.8 MB/s
- ARM 2-pass copy prefetched (incr pld) : 1064.1 MB/s
- ARM 2-pass copy prefetched (wrap pld) : 1059.3 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
- 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 : 6.1 ns / 9.2 ns
- 131072 : 9.0 ns / 11.6 ns
- 262144 : 12.9 ns / 15.2 ns
- 524288 : 15.0 ns / 16.6 ns
- 1048576 : 23.8 ns / 32.4 ns
- 2097152 : 77.0 ns / 117.5 ns
- 4194304 : 106.5 ns / 149.3 ns
- 8388608 : 122.5 ns / 163.4 ns
- 16777216 : 133.0 ns / 174.4 ns
- 33554432 : 141.0 ns / 185.2 ns
- 67108864 : 148.7 ns / 198.1 ns
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement