0checksum.lua

local ffi = require("ffi")
local C   = ffi.C
local pmu = require("lib.pmu")
require("lib.checksum")

-- Use /etc/passwd contents as a dummy packet
local data  = core.lib.readfile("/etc/passwd", "*all")
local ptr   = ffi.cast("unsigned char *", data), #data
local len   = #data
local loops = 100000

print("loops: ", loops, "#data:", #data)

local function profile (name, ipsum)
   print("profiling: " .. name)
   pmu.profile(function () 
                  for i = 1, loops do 
                     ipsum(ptr, len, 0) 
                  end
               end,
               {"mem_load_uops_retired.l._hit",
                "mem_load_uops_retired.l3_miss"},
               {packet=loops, byte=loops*len})
end

profile("generic", C.cksum_generic)
profile("sse2",    C.cksum_sse2)
profile("avx2",    C.cksum_avx2)

1output.txt

profiling: generic
EVENT                                             TOTAL       /byte     /packet
instructions                                420,255,210       2.918    4202.552
cycles                                      429,483,566       2.983    4294.836
ref-cycles                                  429,483,552       2.983    4294.836
mem_load_uops_retired.l1_hit                271,618,029       1.886    2716.180
mem_load_uops_retired.l2_hit                        173       0.000       0.002
mem_load_uops_retired.l3_hit                        229       0.000       0.002
mem_load_uops_retired.l3_miss                        60       0.000       0.001
byte                                        144,000,000       1.000    1440.000
packet                                          100,000       0.001       1.000
profiling: sse2
EVENT                                             TOTAL       /byte     /packet
instructions                                116,882,789       0.812    1168.828
cycles                                       32,942,396       0.229     329.424
ref-cycles                                   32,942,400       0.229     329.424
mem_load_uops_retired.l1_hit                 11,508,798       0.080     115.088
mem_load_uops_retired.l2_hit                         65       0.000       0.001
mem_load_uops_retired.l3_hit                        157       0.000       0.002
mem_load_uops_retired.l3_miss                         1       0.000       0.000
byte                                        144,000,000       1.000    1440.000
packet                                          100,000       0.001       1.000
profiling: avx2
EVENT                                             TOTAL       /byte     /packet
instructions                                 56,773,023       0.394     567.730
cycles                                       16,444,852       0.114     164.449
ref-cycles                                   16,444,848       0.114     164.448
mem_load_uops_retired.l1_hit                  6,910,824       0.048      69.108
mem_load_uops_retired.l2_hit                        107       0.000       0.001
mem_load_uops_retired.l3_hit                        100       0.000       0.001
mem_load_uops_retired.l3_miss                         0       0.000       0.000
byte                                        144,000,000       1.000    1440.000
packet                                          100,000       0.001       1.000