tinymembench v0.4.10 (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 : 4971.0 MB/s (0.4%) C copy backwards (32 byte blocks) : 4957.6 MB/s (1.0%) C copy backwards (64 byte blocks) : 5031.5 MB/s (2.6%) C copy : 5202.7 MB/s (0.3%) C copy prefetched (32 bytes step) : 5506.8 MB/s (0.2%) C copy prefetched (64 bytes step) : 5492.0 MB/s (0.2%) C 2-pass copy : 3502.3 MB/s (0.3%) C 2-pass copy prefetched (32 bytes step) : 3577.2 MB/s (0.3%) C 2-pass copy prefetched (64 bytes step) : 3580.0 MB/s (0.2%) C fill : 7932.1 MB/s (0.4%) C fill (shuffle within 16 byte blocks) : 7933.5 MB/s (0.4%) C fill (shuffle within 32 byte blocks) : 7951.5 MB/s (0.7%) C fill (shuffle within 64 byte blocks) : 7947.8 MB/s --- standard memcpy : 7093.3 MB/s (0.6%) standard memset : 10988.2 MB/s (0.5%) --- MOVSB copy : 5337.1 MB/s (0.4%) MOVSD copy : 5328.1 MB/s SSE2 copy : 5763.9 MB/s (0.7%) SSE2 nontemporal copy : 7054.7 MB/s (0.4%) SSE2 copy prefetched (32 bytes step) : 5914.2 MB/s (0.2%) SSE2 copy prefetched (64 bytes step) : 5898.9 MB/s (0.2%) SSE2 nontemporal copy prefetched (32 bytes step) : 6581.3 MB/s SSE2 nontemporal copy prefetched (64 bytes step) : 6724.4 MB/s (0.2%) SSE2 2-pass copy : 4219.9 MB/s (0.2%) SSE2 2-pass copy prefetched (32 bytes step) : 4341.9 MB/s (0.2%) SSE2 2-pass copy prefetched (64 bytes step) : 4354.0 MB/s (0.3%) SSE2 2-pass nontemporal copy : 2723.6 MB/s (0.2%) SSE2 fill : 9526.8 MB/s (0.6%) SSE2 nontemporal fill : 16598.3 MB/s (0.1%) ========================================================================== == 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, [MADV_NOHUGEPAGE] 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 : 0.1 ns / 0.1 ns 65536 : 2.5 ns / 3.6 ns 131072 : 3.8 ns / 4.6 ns 262144 : 6.5 ns / 8.7 ns 524288 : 18.7 ns / 25.1 ns 1048576 : 25.8 ns / 31.3 ns 2097152 : 29.4 ns / 33.3 ns 4194304 : 31.8 ns / 34.4 ns 8388608 : 52.0 ns / 64.3 ns 16777216 : 85.6 ns / 104.1 ns 33554432 : 106.1 ns / 121.2 ns 67108864 : 119.8 ns / 132.0 ns block size : single random read / dual random read, [MADV_HUGEPAGE] 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 / 0.1 ns 32768 : 0.0 ns / 0.0 ns 65536 : 2.5 ns / 3.6 ns 131072 : 3.8 ns / 4.6 ns 262144 : 4.5 ns / 5.0 ns 524288 : 15.7 ns / 21.4 ns 1048576 : 20.9 ns / 25.8 ns 2097152 : 23.7 ns / 27.2 ns 4194304 : 25.3 ns / 27.6 ns 8388608 : 39.1 ns / 46.1 ns 16777216 : 69.5 ns / 87.7 ns 33554432 : 84.6 ns / 99.3 ns 67108864 : 91.9 ns / 103.0 ns