Skip to content

Instantly share code, notes, and snippets.

@tanakamura
Created December 19, 2020 08:33
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save tanakamura/3ee7f402670f5870a7e28097014eb9b6 to your computer and use it in GitHub Desktop.
Save tanakamura/3ee7f402670f5870a7e28097014eb9b6 to your computer and use it in GitHub Desktop.
ostimer: clock_gettime
userland_timer: rdtscp
perf_counter: yes
Intel(R) Core(TM) i5-8250U CPU @ 1.60GHz
==== actual-freq ====
-> : num_thread
| | 1| 2| 4| 7
=================================================
| iadd64 (0.01 [sec]) |3.39|3.39|3.39|3.39
| fadd64 (0.01 [sec]) |3.39|3.39|3.39|3.39
| iadd32x4 (0.01 [sec]) |3.39|3.39|3.39|3.39
| fadd64x2 (0.01 [sec]) |3.39|3.39|3.39|3.39
| fmul64x2 (0.01 [sec]) |3.39|3.39|3.39|3.39
| busy_iadd32x8 (0.01 [sec]) |3.39|3.39|3.39|3.39
| busy_imul32x8 (0.01 [sec]) |3.39|3.39|3.39|3.39
| busy_fadd64x4 (0.01 [sec]) |3.39|3.39|3.39|3.39
| busy_fmul64x4 (0.01 [sec]) |3.39|3.39|3.39|3.39
| busy_fma64x4 (0.01 [sec]) |3.39|3.39|3.39|3.19
| iadd64 (0.10 [sec]) |3.39|3.39|3.39|3.39
| fadd64 (0.10 [sec]) |3.39|3.39|3.39|3.39
| iadd32x4 (0.10 [sec]) |3.39|3.39|3.39|3.39
| fadd64x2 (0.10 [sec]) |3.39|3.39|3.39|3.39
| fmul64x2 (0.10 [sec]) |3.39|3.39|3.39|3.39
| busy_iadd32x8 (0.10 [sec]) |3.39|3.39|3.39|3.39
| busy_imul32x8 (0.10 [sec]) |3.39|3.39|3.39|3.39
| busy_fadd64x4 (0.10 [sec]) |3.39|3.39|3.39|3.39
| busy_fmul64x4 (0.10 [sec]) |3.39|3.39|3.39|3.39
| busy_fma64x4 (0.10 [sec]) |3.39|3.39|3.39|3.19
| iadd64 (0.20 [sec]) |3.39|3.39|3.39|3.39
| fadd64 (0.20 [sec]) |3.39|3.39|3.39|3.39
| iadd32x4 (0.20 [sec]) |3.39|3.39|3.39|3.39
| fadd64x2 (0.20 [sec]) |3.39|3.39|3.39|3.39
| fmul64x2 (0.20 [sec]) |3.39|3.39|3.39|3.39
| busy_iadd32x8 (0.20 [sec]) |3.39|3.39|3.39|3.39
| busy_imul32x8 (0.20 [sec]) |3.39|3.39|3.39|3.39
| busy_fadd64x4 (0.20 [sec]) |3.39|3.39|3.39|3.39
| busy_fmul64x4 (0.20 [sec]) |3.39|3.39|3.39|3.39
| busy_fma64x4 (0.20 [sec]) |3.39|3.39|3.39|3.19
| iadd64 (0.40 [sec]) |3.39|3.39|3.39|3.39
| fadd64 (0.40 [sec]) |3.39|3.39|3.39|3.39
| iadd32x4 (0.40 [sec]) |3.39|3.39|3.39|3.39
| fadd64x2 (0.40 [sec]) |3.39|3.39|3.39|3.39
| fmul64x2 (0.40 [sec]) |3.39|3.39|3.39|3.39
| busy_iadd32x8 (0.40 [sec]) |3.39|3.39|3.39|3.39
| busy_imul32x8 (0.40 [sec]) |3.39|3.39|3.39|3.39
| busy_fadd64x4 (0.40 [sec]) |3.39|3.39|3.39|3.12
| busy_fmul64x4 (0.40 [sec]) |3.39|3.39|3.39|2.89
| busy_fma64x4 (0.40 [sec]) |3.39|3.39|3.39|2.82
| iadd64 (10.00 [sec]) |3.39|3.39|3.39|2.79
| fadd64 (10.00 [sec]) |3.39|3.39|3.39|3.04
| iadd32x4 (10.00 [sec]) |3.39|3.39|3.39|2.86
| fadd64x2 (10.00 [sec]) |3.39|3.39|3.39|3.10
| fmul64x2 (10.00 [sec]) |3.39|3.39|3.39|3.11
|busy_iadd32x8 (10.00 [sec]) |3.39|3.39|3.39|2.77
|busy_imul32x8 (10.00 [sec]) |3.39|3.39|3.39|3.05
|busy_fadd64x4 (10.00 [sec]) |3.39|3.39|3.39|2.86
|busy_fmul64x4 (10.00 [sec]) |3.39|3.39|3.39|2.88
| busy_fma64x4 (10.00 [sec]) |3.39|3.39|3.39|2.75
v : instruction
ostimer: clock_gettime
userland_timer: rdtscp
perf_counter: yes
AMD Ryzen 7 3700X 8-Core Processor
==== actual-freq ====
-> : num_thread
| | 1| 2| 4| 8| 15
======================================================
| iadd64 (0.01 [sec]) |4.32|4.34|4.33|4.23|4.05
| fadd64 (0.01 [sec]) |4.24|4.35|4.34|4.27|4.09
| iadd32x4 (0.01 [sec]) |4.32|4.33|4.31|4.23|4.11
| fadd64x2 (0.01 [sec]) |4.33|4.34|4.34|4.27|4.11
| fmul64x2 (0.01 [sec]) |4.34|4.36|4.34|4.19|4.09
| busy_iadd32x8 (0.01 [sec]) |4.33|4.34|4.32|4.22|4.07
| busy_imul32x8 (0.01 [sec]) |4.32|4.19|4.34|4.27|4.12
| busy_fadd64x4 (0.01 [sec]) |4.33|4.33|4.34|4.16|4.07
| busy_fmul64x4 (0.01 [sec]) |4.34|4.27|4.34|4.27|4.01
| busy_fma64x4 (0.01 [sec]) |4.34|4.31|4.34|4.27|4.09
| iadd64 (0.10 [sec]) |4.34|4.25|4.27|4.17|4.05
| fadd64 (0.10 [sec]) |4.37|4.29|4.31|4.19|4.06
| iadd32x4 (0.10 [sec]) |4.36|4.23|4.25|4.12|4.01
| fadd64x2 (0.10 [sec]) |4.34|4.29|4.30|4.17|4.05
| fmul64x2 (0.10 [sec]) |4.33|4.26|4.30|4.16|4.07
| busy_iadd32x8 (0.10 [sec]) |4.31|4.23|4.25|4.12|4.05
| busy_imul32x8 (0.10 [sec]) |4.32|4.30|4.33|4.17|4.08
| busy_fadd64x4 (0.10 [sec]) |4.32|4.29|4.29|4.16|4.06
| busy_fmul64x4 (0.10 [sec]) |4.29|4.32|4.31|4.15|4.08
| busy_fma64x4 (0.10 [sec]) |4.36|4.32|4.31|4.15|4.05
| iadd64 (0.20 [sec]) |4.33|4.26|4.25|4.14|4.03
| fadd64 (0.20 [sec]) |4.37|4.31|4.30|4.16|4.05
| iadd32x4 (0.20 [sec]) |4.26|4.26|4.25|4.11|4.03
| fadd64x2 (0.20 [sec]) |4.31|4.33|4.30|4.16|4.04
| fmul64x2 (0.20 [sec]) |4.34|4.32|4.30|4.15|4.05
| busy_iadd32x8 (0.20 [sec]) |4.31|4.25|4.24|4.12|4.02
| busy_imul32x8 (0.20 [sec]) |4.35|4.33|4.32|4.19|4.06
| busy_fadd64x4 (0.20 [sec]) |4.31|4.28|4.31|4.15|4.06
| busy_fmul64x4 (0.20 [sec]) |4.34|4.30|4.29|4.14|4.05
| busy_fma64x4 (0.20 [sec]) |4.37|4.33|4.30|4.15|4.04
| iadd64 (0.40 [sec]) |4.32|4.26|4.24|4.12|4.02
| fadd64 (0.40 [sec]) |4.35|4.32|4.28|4.15|4.02
| iadd32x4 (0.40 [sec]) |4.34|4.25|4.22|4.11|4.01
| fadd64x2 (0.40 [sec]) |4.37|4.32|4.31|4.15|4.03
| fmul64x2 (0.40 [sec]) |4.36|4.31|4.30|4.15|4.03
| busy_iadd32x8 (0.40 [sec]) |4.35|4.22|4.23|4.11|4.01
| busy_imul32x8 (0.40 [sec]) |4.38|4.33|4.32|4.18|4.05
| busy_fadd64x4 (0.40 [sec]) |4.36|4.32|4.30|4.14|4.04
| busy_fmul64x4 (0.40 [sec]) |4.37|4.32|4.29|4.14|4.03
| busy_fma64x4 (0.40 [sec]) |4.35|4.31|4.29|4.14|4.03
| iadd64 (10.00 [sec]) |4.33|4.23|4.23|4.10|4.00
| fadd64 (10.00 [sec]) |4.33|4.33|4.29|4.15|4.02
| iadd32x4 (10.00 [sec]) |4.27|4.25|4.22|4.08|3.98
| fadd64x2 (10.00 [sec]) |4.34|4.32|4.29|4.14|4.01
| fmul64x2 (10.00 [sec]) |4.35|4.33|4.29|4.13|4.01
|busy_iadd32x8 (10.00 [sec]) |4.32|4.26|4.22|4.07|3.97
|busy_imul32x8 (10.00 [sec]) |4.37|4.35|4.31|4.16|4.02
|busy_fadd64x4 (10.00 [sec]) |4.34|4.33|4.28|4.13|4.01
|busy_fmul64x4 (10.00 [sec]) |4.34|4.32|4.27|4.12|4.00
| busy_fma64x4 (10.00 [sec]) |4.36|4.32|4.27|4.11|4.00
v : instruction
ostimer: clock_gettime
userland_timer: rdtscp
perf_counter: yes
11th Gen Intel(R) Core(TM) i5-1135G7 @ 2.40GHz
==== actual-freq ====
-> : num_thread
| | 1| 2| 4| 7
==================================================
| iadd64 (0.01 [sec]) |4.18|4.19|4.18|3.78
| fadd64 (0.01 [sec]) |4.18|4.19|4.18|3.79
| iadd32x4 (0.01 [sec]) |4.19|4.19|4.18|3.79
| fadd64x2 (0.01 [sec]) |4.19|4.19|4.18|3.79
| fmul64x2 (0.01 [sec]) |4.19|4.19|4.18|3.79
| busy_iadd32x8 (0.01 [sec]) |4.19|4.19|4.17|3.79
| busy_imul32x8 (0.01 [sec]) |4.19|4.19|4.18|3.79
| busy_fadd64x4 (0.01 [sec]) |4.19|4.19|4.18|3.79
| busy_fmul64x4 (0.01 [sec]) |4.19|4.19|4.18|3.79
| busy_fma64x4 (0.01 [sec]) |4.19|4.19|4.18|3.79
| busy_iadd32x16 (0.01 [sec]) |4.09|4.09|4.08|3.79
| busy_imul32x16 (0.01 [sec]) |4.09|4.09|4.07|3.79
| busy_fadd64x8 (0.01 [sec]) |4.09|4.08|4.08|3.79
| busy_fmul64x8 (0.01 [sec]) |4.09|4.08|4.08|3.79
| busy_fma64x8 (0.01 [sec]) |4.09|4.09|4.08|3.79
| iadd64 (0.10 [sec]) |4.19|4.19|4.18|3.79
| fadd64 (0.10 [sec]) |4.19|4.19|4.18|3.79
| iadd32x4 (0.10 [sec]) |4.19|4.19|4.18|3.79
| fadd64x2 (0.10 [sec]) |4.19|4.19|4.18|3.79
| fmul64x2 (0.10 [sec]) |4.19|4.19|4.18|3.79
| busy_iadd32x8 (0.10 [sec]) |4.19|4.19|4.18|3.79
| busy_imul32x8 (0.10 [sec]) |4.19|4.19|4.18|3.79
| busy_fadd64x4 (0.10 [sec]) |4.19|4.19|4.18|3.79
| busy_fmul64x4 (0.10 [sec]) |4.19|4.19|4.18|3.79
| busy_fma64x4 (0.10 [sec]) |4.19|4.19|4.18|3.79
| busy_iadd32x16 (0.10 [sec]) |4.09|4.09|4.06|3.79
| busy_imul32x16 (0.10 [sec]) |4.09|4.09|4.08|3.79
| busy_fadd64x8 (0.10 [sec]) |4.09|4.09|4.06|3.79
| busy_fmul64x8 (0.10 [sec]) |4.09|4.09|4.08|3.79
| busy_fma64x8 (0.10 [sec]) |4.09|4.09|4.08|3.79
| iadd64 (0.20 [sec]) |4.19|4.19|4.18|3.79
| fadd64 (0.20 [sec]) |4.19|4.19|4.18|3.79
| iadd32x4 (0.20 [sec]) |4.19|4.19|4.18|3.79
| fadd64x2 (0.20 [sec]) |4.19|4.19|4.18|3.79
| fmul64x2 (0.20 [sec]) |4.19|4.19|4.18|3.79
| busy_iadd32x8 (0.20 [sec]) |4.19|4.19|4.18|3.79
| busy_imul32x8 (0.20 [sec]) |4.19|4.19|4.18|3.79
| busy_fadd64x4 (0.20 [sec]) |4.19|4.19|4.17|3.79
| busy_fmul64x4 (0.20 [sec]) |4.19|4.19|4.18|3.79
| busy_fma64x4 (0.20 [sec]) |4.19|4.19|4.18|3.79
| busy_iadd32x16 (0.20 [sec]) |4.09|4.09|4.08|3.79
| busy_imul32x16 (0.20 [sec]) |4.09|4.09|4.08|3.79
| busy_fadd64x8 (0.20 [sec]) |4.09|4.09|4.08|3.79
| busy_fmul64x8 (0.20 [sec]) |4.09|4.09|4.08|3.79
| busy_fma64x8 (0.20 [sec]) |4.09|4.09|4.08|3.79
| iadd64 (0.40 [sec]) |4.19|4.19|4.18|3.79
| fadd64 (0.40 [sec]) |4.19|4.19|4.18|3.79
| iadd32x4 (0.40 [sec]) |4.19|4.19|4.18|3.79
| fadd64x2 (0.40 [sec]) |4.19|4.19|4.18|3.79
| fmul64x2 (0.40 [sec]) |4.19|4.19|4.18|3.79
| busy_iadd32x8 (0.40 [sec]) |4.19|4.18|4.18|3.79
| busy_imul32x8 (0.40 [sec]) |4.19|4.19|4.18|3.79
| busy_fadd64x4 (0.40 [sec]) |4.19|4.19|4.18|3.79
| busy_fmul64x4 (0.40 [sec]) |4.19|4.19|4.18|3.79
| busy_fma64x4 (0.40 [sec]) |4.19|4.19|4.18|3.79
| busy_iadd32x16 (0.40 [sec]) |4.09|4.09|4.08|3.79
| busy_imul32x16 (0.40 [sec]) |4.09|4.09|4.08|3.79
| busy_fadd64x8 (0.40 [sec]) |4.09|4.09|4.08|3.79
| busy_fmul64x8 (0.40 [sec]) |4.09|4.09|4.08|3.79
| busy_fma64x8 (0.40 [sec]) |4.09|4.09|4.08|3.79
| iadd64 (10.00 [sec]) |4.19|4.19|4.18|3.58
| fadd64 (10.00 [sec]) |4.19|4.19|4.18|3.73
| iadd32x4 (10.00 [sec]) |4.19|4.19|4.15|3.56
| fadd64x2 (10.00 [sec]) |4.19|4.19|4.17|3.73
| fmul64x2 (10.00 [sec]) |4.19|4.19|4.18|3.74
| busy_iadd32x8 (10.00 [sec]) |4.19|4.19|4.16|3.43
| busy_imul32x8 (10.00 [sec]) |4.19|4.19|4.17|3.73
| busy_fadd64x4 (10.00 [sec]) |4.19|4.19|4.18|3.59
| busy_fmul64x4 (10.00 [sec]) |4.19|4.19|4.15|3.58
| busy_fma64x4 (10.00 [sec]) |4.19|4.19|4.17|3.53
|busy_iadd32x16 (10.00 [sec]) |4.09|4.09|4.07|3.34
|busy_imul32x16 (10.00 [sec]) |4.09|4.09|4.08|3.54
| busy_fadd64x8 (10.00 [sec]) |4.09|4.09|4.07|3.53
| busy_fmul64x8 (10.00 [sec]) |4.09|4.09|4.06|3.51
| busy_fma64x8 (10.00 [sec]) |4.09|4.09|4.07|3.50
v : instruction
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment