lkml.org 
[lkml]   [2014]   [May]   [30]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
SubjectRe: [RFC PATCH] crypto: crc32c-pclmul - Use pmovzxdq to shrink K_table
From
Date
On Fri, 2014-05-30 at 11:45 -0700, Dirk Brandewie wrote:

>
> With turbostat from rc7.
> [root@echolake turbostat]# ./turbostat
> Core CPU Avg_MHz %Busy Bzy_MHz TSC_MHz SMI CPU%c1 CPU%c3 CPU%c6 CPU%c7 CoreTmp PkgTmp Pkg%pc2 Pkg%pc3 Pkg%pc6 Pkg%pc7 PkgWatt CorWatt GFXWatt
> - - 1 0.08 1178 3492 0 0.12 0.08 0.01 99.71 29 29 99.23 0.00 0.00 0.00 2.18 0.00 0.00
> 0 0 2 0.19 1189 3492 0 0.22 0.30 0.00 99.29 29 29 99.24 0.00 0.00 0.00 2.18 0.00 0.00
> 0 4 1 0.12 1253 3492 0 0.29
> 1 1 0 0.03 1065 3492 0 0.03 0.00 0.00 99.93 23
> 1 5 0 0.01 1104 3492 0 0.05
> 2 2 0 0.02 1275 3492 0 0.22 0.00 0.03 99.73 24
> 2 6 2 0.18 1220 3492 0 0.06
> 3 3 0 0.01 992 3492 0 0.07 0.00 0.01 99.90 23
> 3 7 0 0.05 915 3492 0 0.04
> Core CPU Avg_MHz %Busy Bzy_MHz TSC_MHz SMI CPU%c1 CPU%c3 CPU%c6 CPU%c7 CoreTmp PkgTmp Pkg%pc2 Pkg%pc3 Pkg%pc6 Pkg%pc7 PkgWatt CorWatt GFXWatt
> - - 1 0.06 1034 3492 0 0.09 5.15 0.00 94.70 28 28 99.49 0.00 0.00 0.00 2.48 0.01 0.00
> 0 0 1 0.09 1066 3492 0 0.17 0.01 0.00 99.73 28 28 99.49 0.00 0.00 0.00 2.48 0.01 0.00
> 0 4 1 0.12 1036 3492 0 0.14
> 1 1 0 0.04 1009 3492 0 0.05 20.59 0.00 79.32 24
> 1 5 0 0.02 922 3492 0 0.07
> 2 2 0 0.03 924 3492 0 0.15 0.00 0.00 99.82 25
> 2 6 1 0.12 1117 3492 0 0.06
> 3 3 0 0.01 911 3492 0 0.04 0.01 0.00 99.94 22
> 3 7 0 0.03 856 3492 0 0.02
> Core CPU Avg_MHz %Busy Bzy_MHz TSC_MHz SMI CPU%c1 CPU%c3 CPU%c6 CPU%c7 CoreTmp PkgTmp Pkg%pc2 Pkg%pc3 Pkg%pc6 Pkg%pc7 PkgWatt CorWatt GFXWatt
> - - 1 0.08 889 3492 0 0.12 0.03 0.06 99.71 29 29 99.32 0.00 0.00 0.00 2.21 0.00 0.00
> 0 0 1 0.11 867 3492 0 0.20 0.02 0.22 99.44 29 29 99.32 0.00 0.00 0.00 2.21 0.00 0.00
> 0 4 1 0.14 907 3492 0 0.17
> 1 1 1 0.12 809 3492 0 0.04 0.11 0.01 99.73 24
> 1 5 0 0.01 798 3492 0 0.14
> 2 2 0 0.03 863 3492 0 0.18 0.00 0.01 99.78 24
> 2 6 1 0.14 1013 3492 0 0.07
> 3 3 0 0.02 853 3492 0 0.09 0.00 0.00 99.89 23
> 3 7 1 0.06 815 3492 0 0.05
> ^C
> [root@echolake turbostat]# echo 100 > /sys/devices/system/cpu/intel_pstate/min_perf_pct
> [root@echolake turbostat]# ./turbostat
> Core CPU Avg_MHz %Busy Bzy_MHz TSC_MHz SMI CPU%c1 CPU%c3 CPU%c6 CPU%c7 CoreTmp PkgTmp Pkg%pc2 Pkg%pc3 Pkg%pc6 Pkg%pc7 PkgWatt CorWatt GFXWatt
> - - 1 0.03 3489 3492 0 2.43 0.01 0.00 97.53 30 30 90.20 0.00 0.00 0.00 2.85 0.06 0.00
> 0 0 1 0.04 3470 3492 0 0.09 0.00 0.00 99.88 30 30 90.20 0.00 0.00 0.00 2.85 0.06 0.00
> 0 4 2 0.06 3492 3492 0 0.07
> 1 1 1 0.02 3495 3492 0 0.05 0.03 0.00 99.90 25
> 1 5 0 0.00 3494 3492 0 0.07
> 2 2 0 0.01 3492 3492 0 9.53 0.00 0.01 90.45 25
> 2 6 1 0.04 3492 3492 0 9.50
> 3 3 1 0.03 3492 3492 0 0.05 0.01 0.00 99.91 23
> 3 7 1 0.02 3493 3492 0 0.06
> Core CPU Avg_MHz %Busy Bzy_MHz TSC_MHz SMI CPU%c1 CPU%c3 CPU%c6 CPU%c7 CoreTmp PkgTmp Pkg%pc2 Pkg%pc3 Pkg%pc6 Pkg%pc7 PkgWatt CorWatt GFXWatt
> - - 1 0.02 3492 3492 0 4.93 0.00 0.00 95.04 30 30 80.19 0.00 0.00 0.00 3.54 0.10 0.00
> 0 0 1 0.02 3491 3492 0 0.08 0.01 0.00 99.89 30 30 80.19 0.00 0.00 0.00 3.54 0.10 0.00
> 0 4 2 0.05 3492 3492 0 0.05
> 1 1 0 0.01 3492 3492 0 0.02 0.00 0.00 99.97 24
> 1 5 0 0.01 3493 3492 0 0.02
> 2 2 0 0.01 3493 3492 0 19.65 0.01 0.00 80.34 24
> 2 6 2 0.05 3493 3492 0 19.61
> 3 3 1 0.01 3492 3492 0 0.02 0.00 0.00 99.97 23
> 3 7 0 0.01 3494 3492 0 0.02
> Core CPU Avg_MHz %Busy Bzy_MHz TSC_MHz SMI CPU%c1 CPU%c3 CPU%c6 CPU%c7 CoreTmp PkgTmp Pkg%pc2 Pkg%pc3 Pkg%pc6 Pkg%pc7 PkgWatt CorWatt GFXWatt
> - - 2 0.05 3493 3492 0 1.64 0.01 0.00 98.29 30 30 93.25 0.00 0.00 0.00 2.64 0.04 0.00
> 0 0 4 0.12 3492 3492 0 0.13 0.01 0.00 99.74 30 30 93.25 0.00 0.00 0.00 2.64 0.04 0.00
> 0 4 2 0.06 3493 3492 0 0.19
> 1 1 1 0.02 3492 3492 0 0.03 0.04 0.00 99.91 23
> 1 5 0 0.01 3494 3492 0 0.04
> 2 2 0 0.01 3492 3492 0 6.42 0.00 0.00 93.57 25
> 2 6 6 0.16 3492 3492 0 6.27
> 3 3 0 0.01 3501 3492 0 0.05 0.01 0.00 99.93 22
> 3 7 1 0.03 3492 3492 0 0.03
> [root@echolake turbostat]# grep MH /proc/cpuinfo
> cpu MHz : 997.089
> cpu MHz : 797.480
> cpu MHz : 998.320
> cpu MHz : 800.078
> cpu MHz : 845.878
> cpu MHz : 801.445
> cpu MHz : 800.078
> cpu MHz : 800.351
> [root@echolake turbostat]# echo 100 > /sys/devices/system/cpu/intel_pstate/min_perf_pct
> [root@echolake turbostat]# grep MH /proc/cpuinfo
> cpu MHz : 3497.128
> cpu MHz : 3506.699
> cpu MHz : 3500.273
> cpu MHz : 3500.273
> cpu MHz : 3500.000
> cpu MHz : 3500.000
> cpu MHz : 3500.000
> cpu MHz : 3495.898
>

Dirk,

Thanks for checking things out.

I tested on a Haswell system, and I see that the frequency
can dip below the max even when I set the min_perf_pct to 100.
Let me know if you want to log on to my system and check if
there's something I missed. It is odd that the package 1's
cores are at a much higher frequency and close to
max than package 0, once min_perf_pct is set to 100.

Tim

[root@otc-grantly-02 ~]# cat /sys/devices/system/cpu/cpu0/cpufreq/scaling_max_freq
3600000
[root@otc-grantly-02 ~]# cat /sys/devices/system/cpu/cpu0/cpufreq/scaling_min_freq
1200000
[root@otc-grantly-02 ~]# echo 100 > /sys/devices/system/cpu/intel_pstate/min_perf_pct
[root@otc-grantly-02 ~]# cat /sys/devices/system/cpu/intel_pstate/min_perf_pct
100
[root@otc-grantly-02 ~]# uname -a
Linux otc-grantly-02 3.15.0-rc7+ #3 SMP Thu May 29 11:34:39 EDT 2014 x86_64 x86_64 x86_64 GNU/Linux
[root@otc-grantly-02 ~]# cpupower -c 0-1 frequency-info
analyzing CPU 0:
driver: intel_pstate
CPUs which run at the same hardware frequency: 0
CPUs which need to have their frequency coordinated by software: 0
maximum transition latency: 0.97 ms.
hardware limits: 1.20 GHz - 3.60 GHz
available cpufreq governors: performance, powersave
current policy: frequency should be within 1.20 GHz and 3.60 GHz.
The governor "powersave" may decide which speed to use
within this range.
current CPU frequency is 1.20 GHz (asserted by call to hardware).
boost state support:
Supported: yes
Active: yes
analyzing CPU 1:
driver: intel_pstate
CPUs which run at the same hardware frequency: 1
CPUs which need to have their frequency coordinated by software: 1
maximum transition latency: 0.97 ms.
hardware limits: 1.20 GHz - 3.60 GHz
available cpufreq governors: performance, powersave
current policy: frequency should be within 1.20 GHz and 3.60 GHz.
The governor "powersave" may decide which speed to use
within this range.
current CPU frequency is 2.02 GHz (asserted by call to hardware).
boost state support:
Supported: yes
Active: yes
[root@otc-grantly-02 ~]# turbostat
Package Core CPU Avg_MHz %Busy Bzy_MHz TSC_MHz SMI CPU%c1 CPU%c3 CPU%c6 CPU%c7 CoreTmp PkgTmp Pkg%pc2 Pkg%pc3 Pkg%pc6 Pkg%pc7 PkgWatt RAMWatt PKG_% RAM_%
- - - 0 0.02 1964 2594 0 0.13 0.00 99.85 0.00 33 41 4.92 0.00 93.99 0.00 23.04 3.60 0.18 0.00
0 0 0 1 0.07 2154 2594 0 0.21 0.00 99.72 0.00 32 41 4.42 0.00 94.00 0.00 17.16 1.73 0.10 0.00
0 0 28 0 0.01 1465 2594 0 0.26
0 1 1 1 0.04 1941 2594 0 0.18 0.00 99.78 0.00 33
0 1 29 0 0.02 1587 2594 0 0.20
0 2 2 1 0.04 1586 2594 0 0.15 0.00 99.81 0.00 28
0 2 30 0 0.01 1539 2594 0 0.17
0 3 3 1 0.04 1656 2594 0 0.17 0.00 99.79 0.00 31
0 3 31 0 0.01 1723 2594 0 0.19
0 4 4 1 0.06 1800 2594 0 0.21 0.00 99.74 0.00 33
0 4 32 0 0.02 1725 2594 0 0.24
0 5 5 1 0.04 1917 2594 0 0.15 0.00 99.81 0.00 29
0 5 33 0 0.02 1707 2594 0 0.17
0 6 6 1 0.04 1820 2594 0 0.17 0.00 99.79 0.00 33
0 6 34 0 0.01 1564 2594 0 0.20
0 8 7 0 0.02 1655 2594 0 0.11 0.00 99.86 0.00 29
0 8 35 0 0.01 1687 2594 0 0.12
0 9 8 0 0.03 1748 2594 0 0.15 0.00 99.83 0.00 32
0 9 36 0 0.02 2001 2594 0 0.15
0 10 9 1 0.06 1604 2594 0 0.20 0.00 99.74 0.00 32
0 10 37 0 0.02 1679 2594 0 0.24
0 11 10 1 0.04 1644 2594 0 0.12 0.00 99.84 0.00 30
0 11 38 0 0.01 1509 2594 0 0.14
0 12 11 1 0.04 1773 2594 0 0.13 0.00 99.83 0.00 30
0 12 39 0 0.01 1529 2594 0 0.16
0 13 12 0 0.02 1907 2594 0 0.11 0.00 99.87 0.00 30
0 13 40 0 0.01 1574 2594 0 0.12
0 14 13 1 0.04 1831 2594 0 0.19 0.00 99.77 0.00 31
0 14 41 0 0.01 1735 2594 0 0.22
1 0 14 1 0.04 1831 2594 0 0.11 0.00 99.85 0.00 28 37 5.43 0.00 93.98 0.00 5.88 1.87 0.08 0.00
1 0 42 0 0.01 2238 2594 0 0.14
1 1 15 1 0.04 1869 2594 0 0.15 0.00 99.81 0.00 31
1 1 43 0 0.01 2407 2594 0 0.18
1 2 16 0 0.02 2164 2594 0 0.10 0.00 99.88 0.00 28
1 2 44 0 0.01 2326 2594 0 0.11
1 3 17 1 0.04 2101 2594 0 0.10 0.00 99.86 0.00 30
1 3 45 0 0.01 2355 2594 0 0.13
1 4 18 0 0.01 2429 2594 0 0.08 0.00 99.90 0.00 29
1 4 46 0 0.01 2545 2594 0 0.08
1 5 19 0 0.01 2412 2594 0 0.08 0.00 99.91 0.00 29
1 5 47 0 0.01 2392 2594 0 0.08
1 6 20 0 0.01 2448 2594 0 0.08 0.00 99.90 0.00 29
1 6 48 0 0.01 2430 2594 0 0.08
1 8 21 0 0.01 2574 2594 0 0.08 0.00 99.90 0.00 29
1 8 49 0 0.01 2450 2594 0 0.09
1 9 22 0 0.02 2470 2594 0 0.08 0.00 99.90 0.00 31
1 9 50 0 0.01 2555 2594 0 0.08
1 10 23 0 0.01 2540 2594 0 0.07 0.00 99.92 0.00 26
1 10 51 0 0.01 2672 2594 0 0.07
1 11 24 0 0.01 2472 2594 0 0.08 0.00 99.91 0.00 28
1 11 52 0 0.01 2461 2594 0 0.08
1 12 25 0 0.01 2438 2594 0 0.07 0.00 99.92 0.00 29
1 12 53 0 0.01 2316 2594 0 0.07
1 13 26 0 0.01 2363 2594 0 0.08 0.00 99.90 0.00 28
1 13 54 0 0.01 2586 2594 0 0.09
1 14 27 0 0.01 2459 2594 0 0.09 0.00 99.90 0.00 27
1 14 55 1 0.02 2939 2594 0 0.08

Tim



\
 
 \ /
  Last update: 2014-05-30 22:01    [W:0.082 / U:0.768 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site