rust packed_simd库学习

1. aobench各算法性能验证

4 核Intel i7-7700 CPU@ 3.60GHz, ispc_tasks性能比tiled_par性能更优。

# export FEATURES=ispc
# ./benchmark.sh
+ export WIDTH=800
+ WIDTH=800
+ export HEIGHT=600
+ HEIGHT=600
+ [[ '' != 1 ]]
+ hash hyperfine
+ ALGS=("scalar" "scalar_par" "vector" "vector_par" "tiled" "tiled_par")
+ echo ispc
+ grep -q ispc
+ hash ispc
+ ALGS+=("ispc" "ispc_tasks")
+ echo 'Benchmark 256-bit wide vectors'
Benchmark 256-bit wide vectors
+ RUSTFLAGS='-C target-cpu=native '
+ cargo build --release --no-default-features --features=ispc,256bit
    Finished release [optimized] target(s) in 0.09s
+ [[ '' == \1 ]]
+ [[ '' == \1 ]]
+ for alg in '"${ALGS[@]}"'
+ hyperfine '../target/release/aobench 800 600 --algo scalar'
Benchmark #1: ../target/release/aobench 800 600 --algo scalar
  Time (mean ± σ):      3.591 s ±  0.096 s    [User: 3.442 s, System: 0.042 s]
  Range (min … max):    3.463 s …  3.702 s    10 runs

+ for alg in '"${ALGS[@]}"'
+ hyperfine '../target/release/aobench 800 600 --algo scalar_par'
Benchmark #1: ../target/release/aobench 800 600 --algo scalar_par
  Time (mean ± σ):      1.052 s ±  0.042 s    [User: 3.112 s, System: 0.281 s]
  Range (min … max):    1.010 s …  1.149 s    10 runs

+ for alg in '"${ALGS[@]}"'
+ hyperfine '../target/release/aobench 800 600 --algo vector'
Benchmark #1: ../target/release/aobench 800 600 --algo vector
  Time (mean ± σ):      1.544 s ±  0.048 s    [User: 1.482 s, System: 0.016 s]
  Range (min … max):    1.497 s …  1.630 s    10 runs

+ for alg in '"${ALGS[@]}"'
+ hyperfine '../target/release/aobench 800 600 --algo vector_par'
Benchmark #1: ../target/release/aobench 800 600 --algo vector_par
  Time (mean ± σ):     511.1 ms ±  43.5 ms    [User: 1.368 s, System: 0.219 s]
  Range (min … max):   471.1 ms … 603.7 ms    10 runs

  Warning: Statistical outliers were detected. Consider re-running this benchmark on a quiet PC without any interferences from other programs. It might help to use the'--warmup' or '--prepare' options.

+ for alg in '"${ALGS[@]}"'
+ hyperfine '../target/release/aobench 800 600 --algo tiled'
Benchmark #1: ../target/release/aobench 800 600 --algo tiled
  Time (mean ± σ):      1.665 s ±  0.120 s    [User: 1.605 s, System: 0.028 s]
  Range (min … max):    1.540 s …  1.970 s    10 runs

  Warning: The first benchmarking run for this command was significantly slower than the rest (1.970 s). This could be caused by (filesystem) caches that were not filled until after the first run. You should consider using the '--warmup' option to fill those caches before the actual benchmark. Alternatively, use the '--prepare' option to clear the caches before each timing run.

+ for alg in '"${ALGS[@]}"'
+ hyperfine '../target/release/aobench 800 600 --algo tiled_par'
Benchmark #1: ../target/release/aobench 800 600 --algo tiled_par
  Time (mean ± σ):     568.6 ms ±  38.6 ms    [User: 1.486 s, System: 0.222 s]
  Range (min … max):   519.4 ms … 654.5 ms    10 runs

+ for alg in '"${ALGS[@]}"'
+ hyperfine '../target/release/aobench 800 600 --algo ispc'
Benchmark #1: ../target/release/aobench 800 600 --algo ispc
  Time (mean ± σ):     794.9 ms ±  46.3 ms    [User: 729.2 ms, System: 21.3 ms]
  Range (min … max):   723.2 ms … 844.7 ms    10 runs

+ for alg in '"${ALGS[@]}"'
+ hyperfine '../target/release/aobench 800 600 --algo ispc_tasks'
Benchmark #1: ../target/release/aobench 800 600 --algo ispc_tasks
  Time (mean ± σ):     369.3 ms ±  25.5 ms    [User: 775.5 ms, System: 224.7 ms]
  Range (min … max):   338.8 ms … 413.0 ms    10 runs

+ echo 'Benchmark 128-bit wide vectors'
Benchmark 128-bit wide vectors
+ RUSTFLAGS='-C target-cpu=native '
+ cargo build --release --no-default-features --features=ispc
    Finished release [optimized] target(s) in 0.10s
+ for alg in '"${ALGS[@]}"'
+ hyperfine '../target/release/aobench 800 600 --algo scalar'
Benchmark #1: ../target/release/aobench 800 600 --algo scalar
  Time (mean ± σ):      4.056 s ±  0.163 s    [User: 3.898 s, System: 0.047 s]
  Range (min … max):    3.811 s …  4.264 s    10 runs

+ for alg in '"${ALGS[@]}"'
+ hyperfine '../target/release/aobench 800 600 --algo scalar_par'
Benchmark #1: ../target/release/aobench 800 600 --algo scalar_par
  Time (mean ± σ):      1.409 s ±  0.072 s    [User: 3.736 s, System: 0.454 s]
  Range (min … max):    1.263 s …  1.506 s    10 runs

+ for alg in '"${ALGS[@]}"'
+ hyperfine '../target/release/aobench 800 600 --algo vector'
Benchmark #1: ../target/release/aobench 800 600 --algo vector
  Time (mean ± σ):      1.980 s ±  0.154 s    [User: 1.935 s, System: 0.018 s]
  Range (min … max):    1.816 s …  2.250 s    10 runs

+ for alg in '"${ALGS[@]}"'
+ hyperfine '../target/release/aobench 800 600 --algo vector_par'
Benchmark #1: ../target/release/aobench 800 600 --algo vector_par
  Time (mean ± σ):     665.0 ms ±  66.5 ms    [User: 1.735 s, System: 0.254 s]
  Range (min … max):   597.1 ms … 767.1 ms    10 runs

+ for alg in '"${ALGS[@]}"'
+ hyperfine '../target/release/aobench 800 600 --algo tiled'
Benchmark #1: ../target/release/aobench 800 600 --algo tiled
  Time (mean ± σ):      1.802 s ±  0.050 s    [User: 1.707 s, System: 0.031 s]
  Range (min … max):    1.724 s …  1.872 s    10 runs

+ for alg in '"${ALGS[@]}"'
+ hyperfine '../target/release/aobench 800 600 --algo tiled_par'
Benchmark #1: ../target/release/aobench 800 600 --algo tiled_par
  Time (mean ± σ):     592.8 ms ±  38.1 ms    [User: 1.635 s, System: 0.206 s]
  Range (min … max):   553.6 ms … 643.2 ms    10 runs

+ for alg in '"${ALGS[@]}"'
+ hyperfine '../target/release/aobench 800 600 --algo ispc'
Benchmark #1: ../target/release/aobench 800 600 --algo ispc
  Time (mean ± σ):     728.3 ms ±  23.4 ms    [User: 670.4 ms, System: 21.7 ms]
  Range (min … max):   701.5 ms … 774.4 ms    10 runs

+ for alg in '"${ALGS[@]}"'
+ hyperfine '../target/release/aobench 800 600 --algo ispc_tasks'
Benchmark #1: ../target/release/aobench 800 600 --algo ispc_tasks
  Time (mean ± σ):     290.9 ms ±  13.5 ms    [User: 646.4 ms, System: 155.7 ms]
  Range (min … max):   263.2 ms … 312.9 ms    10 runs

如遇到提示找不到libclang.so或者stdtool.h等bug,做如下操作可解决:

apt-get install libclang-dev
apt-get update
apt-get install clang

ispc的安装直接从github下载相应的安装包,解压出来,ln -s ispc-v1.12.0-linux/bin/ispc /usr/bin/即可。

参考资料:
[1] https://github.com/rust-lang-nursery/packed_simd/tree/master/examples/aobench

  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值