Build with PGO

[helpau]

Building with PGO speeds up loda benchmark by 0%-35%. However, this is quite difficult due to at least 3 profiles (cl, gcc, clang, maybe more because of x86_64/arm64?) and the dependency on the toolchain version. Example of changes here #547
Results from Apple M3, clang 17
Without PGO

Sequence	Terms	Reg Eval	Inc Eval	Vir Eval
A000040	1000	3.48s	-	0.43s
A000394	1000	1.72s	-	0.22s
A000401	1000	2.98s	-	0.22s
A000796	300	0.70s	-	-
A001041	300	0.73s	-	-
A001113	300	0.63s	-	-
A002110	300	0.77s	-	-
A002760	200	24.71s	-	1.18s
A057552	300	2.81s	0.03s	-
A079309	300	2.80s	0.03s	-
A002193	400	0.56s	0.23s	-
A035856	500	1.62s	-	-
A001609	1000	0.52s	0.00s	-
A003411	1000	0.59s	0.00s	-
A012866	1000	1.00s	0.00s	-
A000045	2000	1.82s	0.00s	-
A001304	3000	0.98s	0.00s	-
A000005	5000	1.04s	-	-
A130487	5000	1.70s	0.00s	-
A000030	500000	0.38s	-	-

With PGO(instrumented profile, profile generated from loda mine -H 1)

Sequence	Terms	Reg Eval	Inc Eval	Vir Eval
A000040	1000	2.22s	-	0.32s
A000394	1000	1.41s	-	0.17s
A000401	1000	2.34s	-	0.17s
A000796	300	0.67s	-	-
A001041	300	0.72s	-	-
A001113	300	0.60s	-	-
A002110	300	0.73s	-	-
A002760	200	19.51s	-	0.98s
A057552	300	2.79s	0.03s	-
A079309	300	2.77s	0.03s	-
A002193	400	0.56s	0.21s	-
A035856	500	1.55s	-	-
A001609	1000	0.50s	0.00s	-
A003411	1000	0.58s	0.00s	-
A012866	1000	0.99s	0.00s	-
A000045	2000	1.82s	0.00s	-
A001304	3000	0.84s	0.00s	-
A000005	5000	0.74s	-	-
A130487	5000	1.12s	0.00s	-
A000030	500000	0.28s	-	-

[helpau]

Also llvm-bolt seems a good thing. I run this commands in WSL2(there is no good performance counters support, thefore, there is no branch filter -j, --branch-filter in perf record, no -reorder-functions=cdsort in llvm-bolt and there is -nl in perf2bolt). In theory results must be a much better.
pgo(1 iteration of ./loda benchmark), without bolt
laptop@DESKTOP-TNE8HEO:~/loda-cpp$ ./loda benchmark

Operation	Time
mov	0.03µs
add	0.46µs
sub	0.52µs
trn	0.78µs
mul	8.25µs
div	269.85µs
dif	274.62µs
dir	277.31µs
mod	276.61µs
pow	65.44µs
gcd	1043.07µs
lex	275.58µs
bin	37.84µs
fac	101.31µs
log	3.69µs
nrt	13606.13µs
dgs	2172.32µs
dgr	142.67µs
equ	0.33µs
neq	0.32µs
leq	0.56µs
geq	0.92µs
min	0.70µs
max	0.59µs
ban	0.66µs
bor	0.58µs
bxo	0.70µs

Sequence	Terms	Reg Eval	Inc Eval	Vir Eval
A000040	1000	4.699s	-	549.492ms
A000394	1000	2.519s	-	295.547ms
A000401	1000	3.894s	-	293.797ms
A000796	300	1.291s	-	-
A001041	300	969.102ms	-	-
A001113	300	1.010s	-	-
A002110	300	969.727ms	-	-
A002760	200	34.913s	-	1.797s
A057552	300	4.024s	43.202ms	-
A079309	300	4.017s	43.670ms	-
A002193	400	646.763ms	272.097ms	-
A035856	500	2.174s	-	-
A001609	1000	412.717ms	3.263ms	-
A003411	1000	473.046ms	3.656ms	-
A012866	1000	910.200ms	5.094ms	-
A000045	2000	1.515s	5.798ms	-
A001304	3000	1.165s	4.805ms	-
A000005	5000	1.591s	-	-
A130487	5000	2.227s	5.967ms	-
A000030	500000	530.704ms	-	-

pgo+bolt(10 minutes of ./loda benchmark)
sudo perf record -e cycles:u -a -o perf.data -- sleep 600
sudo perf2bolt -nl -p perf.data -o perf.fdata ~/loda-cpp/loda
llvm-bolt ./loda -o loda_bolt -data ~/perf.fdata -reorder-blocks=ext-tsp -split-functions -split-all-cold -split-eh -dyno-stats -update-debug-sections
laptop@DESKTOP-TNE8HEO:~/loda-cpp$ ./loda_bolt benchmark

Operation	Time
mov	0.03µs
add	0.54µs
sub	0.50µs
trn	0.61µs
mul	8.71µs
div	282.97µs
dif	280.33µs
dir	283.74µs
mod	287.72µs
pow	61.54µs
gcd	1087.08µs
lex	279.20µs
bin	37.61µs
fac	110.98µs
log	3.96µs
nrt	13611.88µs
dgs	1659.49µs
dgr	136.82µs
equ	0.34µs
neq	0.37µs
leq	0.84µs
geq	0.57µs
min	0.47µs
max	0.43µs
ban	0.50µs
bor	0.48µs
bxo	1.01µs

Sequence	Terms	Reg Eval	Inc Eval	Vir Eval
A000040	1000	4.400s	-	485.262ms
A000394	1000	2.262s	-	247.808ms
A000401	1000	3.509s	-	243.722ms
A000796	300	1.328s	-	-
A001041	300	974.094ms	-	-
A001113	300	1.026s	-	-
A002110	300	977.123ms	-	-
A002760	200	33.488s	-	1.565s
A057552	300	4.012s	43.978ms	-
A079309	300	4.023s	44.232ms	-
A002193	400	689.756ms	310.205ms	-
A035856	500	2.172s	-	-
A001609	1000	407.027ms	3.137ms	-
A003411	1000	509.278ms	3.826ms	-
A012866	1000	976.275ms	5.475ms	-
A000045	2000	1.611s	5.832ms	-
A001304	3000	1.162s	4.591ms	-
A000005	5000	1.515s	-	-
A130487	5000	2.007s	5.161ms	-
A000030	500000	523.873ms	-	-

[helpau]

But llvm-bolt only supported for Linux binaries

[kotenok2000]

When i run it in wsl1 it misaligns headers, breaking it on wsl1
I have to use this script to fix it.

wsl-fix-exec-format-error.sh.txt