#include

#define NOINLINE $\_\_$attribute$\_\_(($noinline$))$

static NOINLINE int function$1($int x$,$ int y$)$

$\{$

int i;

int sum;

int values$[10]$;

sum $=0$;

for $($i $=0$; i $<10$; i$++)\{$

values$[$i$]=10+$ i $+2*$ x $*$ y;

sum $+=$ values$[$i$]$;

$\}$

return $($sum$)$;

$\}$

static int NOINLINE function$2($int $*$values$,$ int valuesLen$)$

$\{$

int i;

int sum$1$;

int sum$2$;

int v;

sum$1=0$;

sum$2=0$;

for $($i $=0$; i $<$ valuesLen; i$++)\{$

v $=$ values$[$i$]$;

if $($v $>0)$

sum$1+=$ v;

else

sum$2+=$ v;

$\}$

return $($sum$1+$ sum$2)$;

$\}$

static NOINLINE int function$3($int x$)$

$\{$

int y;

y $=$ x $/20$;

return $($y$)$;

$\}$

static NOINLINE int function$4($int a$,$ int b$,$ int c$,$ int d$)$

$\{$

int r;

if $($a $>$ b$)$

r $=$ b;

else if $($a $>$ c$)$

r $=4*$ a;

else if $($a $>$ d$)$

r $=8*$ a;

else

r $=-1$;

return $($r$)$;

$\}$

static NOINLINE unsigned int function$5($unsigned int x$)$

$\{$

unsigned int x$1$;

unsigned int x$2$;

unsigned int x$3$;

x$1=$ x $*16$;

x$2=$ x $/8$;

x$3=$ x $\%8$;

return $($x$1+$ x$2+$ x$3)$;

$\}$

int main$($int argc, char $**$argv$)$

$\{$

int i;

int j;

int k;

int values$[10]$;

i $=5$;

j $=8$;

k $=$ function$1($i$,$ j$)$;

printf$("$function$1$: i $=\%$d$,$ j $=\%$d$,$ k $=\%$d

$",$ i$,$ j$,$ k$)$;

for $($i $=0$; i $<10$; i$++)\{$

values$[$i$]=$ i;

$\}$

k $=$ function$2($values$,10)$;

printf$("$function$2$: k $=\%$d

$",$ k$)$;

k $=$ function$3(100)$;

printf$("$function$3$: k $=\%$d

$",$ k$)$;

k $=$ function$4(1,2,3,4)$;

printf$("$function$4$: k $=\%$d

$",$ k$)$;

k $=$ function$5(100)$;

printf$("$function$5$: k $=\%$d

$",$ k$)$;

return $(0)$;

$\}$

CODESEG

public strlen

strlen proc $\backslash$

buf:ptr byte

OPTION PROLOGUE:NONE, EPILOGUE:NONE

$.$FPO $(0,1,0,0,0,0)$

string equ $[$esp $+4]$

mov ecx,string ; ecx $->$ string

test ecx,$3$ ; test if string is aligned on $32$ bits

je short main$\_$loop

str$\_$misaligned:

; simple byte loop until string is aligned

mov al$,$byte ptr $[$ecx$]$

add ecx,$1$

test al$,$al

je short byte$\_3$

test ecx,$3$

jne short str$\_$misaligned

add eax,dword ptr $0$ ; $5$ byte nop to align label below

align $16$ ; should be redundant

main$\_$loop:

mov eax,dword ptr $[$ecx$]$ ; read $4$ bytes

mov edx,$7$efefeffh

add edx,eax

xor eax,$-1$

xor eax,edx

add ecx,$4$

test eax,$81010100$h

je short main$\_$loop

; found zero byte in the loop

mov eax,$[$ecx $-4]$

test al$,$al ; is it byte $0$

je short byte$\_0$

test ah$,$ah ; is it byte $1$

je short byte$\_1$

test eax,$00$ff$0000$h ; is it byte $2$

je short byte$\_2$

test eax,$0$ff$000000$h ; is it byte $3$

je short byte$\_3$

jmp short main$\_$loop ; taken if bits $24-30$ are clear and bit

; $31$ is set

byte$\_3$:

lea eax,$[$ecx $-1]$

mov ecx,string

sub eax,ecx

ret

byte$\_2$:

lea eax,$[$ecx $-2]$

mov ecx,string

sub eax,ecx

ret

byte$\_1$:

lea eax,$[$ecx $-3]$

mov ecx,string

sub eax,ecx

ret

byte$\_0$:

lea eax,$[$ecx $-4]$

mov ecx,string

sub eax,ecx

ret

strlen endp

end

$1.$ Describe the stack at line $25($return $($sum$)$;$).$ The bottom of the stack is the first row below. The top of the stack will be the last item. The first few items are provided. You will probably need to add some additional rows to the table below.

Description Value

First argument to main argv

Second argument to main argc

Return address of main Caller$$s return address

C runtime value of bp Caller$$s bp register

Local variable i in main $[$bp$-12]5$

$2.$ In detail explain the code generated for line $105($k $=$ function$1($i$,$ j$)$;$).$ For this and all further questions in which you are asked to explain the code generated in detail, I expect you to copy the generated code and add a comment for each line. For example:

$006$e C$745$FC$00$ mov DWORD PTR $-4[$ebp$],0$ ; initialize i

You can also refer to Week$9-$CAssembly$-$g$.$asm for examples of what you should submit.

$3.$ In detail explain the code generated for function$2($line $29$ through $49).$

$4.$ In detail explain the code generated for function$5($line $80$ through $93).$

The following questions should be answered using the optimized code.

$5.$ In detail explain the code generated for function$1($line $12$ through $27).$ Why does this work?

$6.$ How are function calls optimized? For example, see lines $114$ and $117.$

The following questions should be answered using by comparing the unoptimized code and the optimized code.

$7.$ Compare the code generated by function$4$ in the unoptimized and optimized versions. Explain the optimizations.

Bonus $10$ points

In detail explain the code generated for function$3.$ This a hard. Try your best. Why is the compiler doing