1 lscpu
2 架构：                           x86_64
3 CPU 运行模式：32-bit, 64-bit
4 字节序：                         Little Endian
5 Address sizes:                   43 bits physical, 48 bits virtual
6 CPU:                             128
7 在线 CPU 列表：0-127
8 每个核的线程数：                 2
9 每个座的核数：                   32
10 座：                             2
11 NUMA 节点：8
12 厂商 ID：HygonGenuine
13 CPU 系列：24
14 型号：                           1
15 型号名称：                       Hygon C86 7280 32-core Processor
16 步进：                           1
17 CPU MHz：2194.586
18 BogoMIPS：                       3999.63
19 虚拟化：                         AMD-V
20 L1d 缓存：2 MiB
21 L1i 缓存：4 MiB
22 L2 缓存：32 MiB
23 L3 缓存：128 MiB
24 NUMA 节点0 CPU：0-7,64-71
25 UMA 节点1 CPU：8-15,72-79
26 NUMA 节点2 CPU：16-23,80-87
27 NUMA 节点3 CPU：24-31,88-95
28 NUMA 节点4 CPU：32-39,96-103
29 NUMA 节点5 CPU：40-47,104-111
30 NUMA 节点6 CPU：48-55,112-119
31 NUMA 节点7 CPU：56-63,120-127
32 //可以看到7号core比15、23、31号core明显要快，就近访问node 0的内存，跨numa node（跨Die）没有内存交织分配
33
34
35 time for i in $(seq 7 8 64); do echo $i; numactl -C $i -m 0 ./bin/stream -W 5 -N 5 -M 64M; done
36 7
37 STREAM copy latency: 1.38 nanoseconds    
38 STREAM copy bandwidth: 11559.53 MB/sec
39 STREAM scale latency: 1.16 nanoseconds
40 STREAM scale bandwidth: 13815.87 MB/sec
41 STREAM add latency: 1.40 nanoseconds
42 STREAM add bandwidth: 17145.85 MB/sec
43 STREAM triad latency: 1.44 nanoseconds
44 STREAM triad bandwidth: 16637.18 MB/sec
45 15
46 STREAM copy latency: 1.67 nanoseconds
47 STREAM copy bandwidth: 9591.77 MB/sec
48 STREAM scale latency: 1.56 nanoseconds
49 STREAM scale bandwidth: 10242.50 MB/sec
50 STREAM add latency: 1.45 nanoseconds
51 STREAM add bandwidth: 16581.00 MB/sec
52 STREAM triad latency: 2.00 nanoseconds
53 STREAM triad bandwidth: 12028.83 MB/sec
54 23
55 STREAM copy latency: 1.65 nanoseconds
56 STREAM copy bandwidth: 9701.49 MB/sec
57 STREAM scale latency: 1.53 nanoseconds
58 STREAM scale bandwidth: 10427.98 MB/sec
59 STREAM add latency: 1.42 nanoseconds
60 STREAM add bandwidth: 16846.10 MB/sec
61 STREAM triad latency: 1.97 nanoseconds
62 STREAM triad bandwidth: 12189.72 MB/sec
63 31
64 STREAM copy latency: 1.64 nanoseconds
65 STREAM copy bandwidth: 9742.86 MB/sec
66 STREAM scale latency: 1.52 nanoseconds
67 STREAM scale bandwidth: 10510.80 MB/sec
68 STREAM add latency: 1.45 nanoseconds
69 STREAM add bandwidth: 16559.86 MB/sec
70 STREAM triad latency: 1.92 nanoseconds
71 STREAM triad bandwidth: 12490.01 MB/sec
72 39
73 STREAM copy latency: 2.55 nanoseconds
74 STREAM copy bandwidth: 6286.25 MB/sec
75 STREAM scale latency: 2.51 nanoseconds
76 STREAM scale bandwidth: 6383.11 MB/sec
77 STREAM add latency: 1.76 nanoseconds
78 STREAM add bandwidth: 13660.83 MB/sec
79 STREAM triad latency: 3.68 nanoseconds
80 STREAM triad bandwidth: 6523.02 MB/sec