ASM Community

Here is the latest example. But the source is above 256 Kbytes I cannot give it to you rigth now.


Here is the very basic function to made a circle. Unfortunately FPU is very slow. Im still find another way to make it fast and this is what I know to make it fast.

*Note: The clock information on this code is wrong*

If this code

	push eax				
		fld dword ptr	
	pop eax					
	fimul delta				
	fistp r_cos

replaced with this code

;	xor edx,edx
;	mov ecx,delta
;	mul ecx
;	mov ecx,1000
;	div ecx
;	mov eax,r_cos

I can save time until 15 times on 1.7 GHz celeron machine. I tried it but it crashed. I dont know what causing it. When I debug it with ollydbg, it stop at this function.

GetSin proc uses esi deg:dword						; 3 Clock cycle
	
	mov esi,SCTbl					; 1 Clock cycle
	mov ecx,deg						; 1 Clock cycle
	mov eax,dword ptr	; 1 Clock cycle
	
	ret
GetSin endp

Ecx register on GetSin procedure point to a wrong place and reported access violation. Maybe someone here understand and can solve this?

Phase1 proc uses esi 	; 28.8 Kbyte needed
	LOCAL deg,sin,cos,tan:dword
	
	
	invoke GlobalAlloc,LMEM_DISCARDABLE,28800+14400 + 16*10000 +768
	invoke GlobalLock,eax
	mov SCTbl,eax
	
	
	mov esi,eax					; 1 Clock cycle
	xor ecx,ecx					; 1 Clock cycle
	mov deg,ecx					; 1 Clock cycle
	
	mov edx,3600				; 1 Clock cycle
	shl edx,2					; 2 Clock cycle
	
	
	@@:
	finit						; 17 Clock cycle
	pushad
	invoke Deg2Rad,deg			; 104 Clock cycle
	popad
	fsincos						; 365 Clock cycle
	fstp sin					; 8 Clock cycle
	fstp cos					; 8 Clock cycle
	
;	push 1000
;	fimul dword ptr	
;	fistp sin					
;	pop eax
;	push 1000
;	fimul dword ptr
;	fistp cos					
;	pop eax
	
	mov eax,sin					; 1 Clock cycle
	mov dword ptr,eax		; 1 Clock cycle
	mov eax,cos					; 1 Clock cycle
	mov dword ptr,eax	; 1 Clock cycle
	
	add deg,1					; 3 Clock cycle
	add esi,4					; 1 Clock cycle
	add ecx,4					; 1 Clock cycle
	cmp deg,3600				; 2 Clock cycle
	jl @b						; 3 Clock cycle
								; 513 Clock cycle Each loop
	; 1846800 Clock cycle total loop
	; 1846806 Clock cycle
	mov esi,SCTbl
	add esi,28800
	;Tan
	mov edx,3600				; 1 Clock cycle
	shl edx,2					; 2 Clock cycle
	
	xor ecx,ecx
	mov deg,ecx
	
	@@:
	finit						; 17 Clock cycle
	pushad
	invoke Deg2Rad,deg			; 104 Clock cycle
	popad
	fptan						; 273 Clock cycle
	fstp tan
;	push 1000
;	fimul dword ptr
;	fistp tan
;	pop eax
;	
	push tan
	pop 
	add deg,1					; 3 Clock cycle
	add esi,4					; 1 Clock cycle
	add ecx,4					; 1 Clock cycle
	cmp deg,3600				; 2 Clock cycle
	jl @b						; 3 Clock cycle
	
	
	mov esi,SCTbl
	add esi,28800+14400
	mov Line_Table,esi
	mov eax,16*10000
	mov nLLimit,eax
	mov nLPtr,0
	
	add esi,eax
	mov SCR_TBL,esi
	
	mov ecx,768
	xor eax,eax
	xor edx,edx
	@@:
	mov ,eax
	add eax,1024
	dec ecx
	jnz @b
	
	ret
Phase1 endp


UMGetPosRound proc uses esi delta:dword,deg:dword 	; 138 Clock cycle
	LOCAL r_sin,r_cos:dword
	
	
	cmp deg,3600
	jl @f
		sub deg,3600
	@@:
	invoke GetSin,deg		
	push eax				
		fld dword ptr	
	pop eax					
	fimul delta				
	fistp r_sin
					
;	xor edx,edx
;	mov ecx,delta
;	mul ecx
;	mov ecx,1000
;	div ecx
;	mov eax,r_sin
	
	invoke GetCos,deg		
	push eax				
		fld dword ptr	
	pop eax					
	fimul delta				
	fistp r_cos
		
;	xor edx,edx
;	mov ecx,delta
;	mul ecx
;	mov ecx,1000
;	div ecx
;	mov eax,r_cos
	
	mov edx,r_sin			
	mov eax,r_cos			
							
	
	ret
UMGetPosRound endp

GetSin proc uses esi deg:dword						; 3 Clock cycle
	
	mov esi,SCTbl					; 1 Clock cycle
	mov ecx,deg						; 1 Clock cycle
	mov eax,dword ptr	; 1 Clock cycle
	
	ret
GetSin endp

GetCos proc uses esi deg:dword						; 4 Clock cycle
	
	mov esi,SCTbl					; 1 Clock cycle
	add esi,14400					; 1 Clock cycle
	mov ecx,deg						; 1 Clock cycle
	mov eax,dword ptr	; 1 Clock cycle
	
	ret
GetCos endp

GetTan proc uses esi deg:dword						; 4 Clock cycle
	
	mov esi,SCTbl					; 1 Clock cycle
	add esi,28800					; 1 Clock cycle
	mov ecx,deg						; 1 Clock cycle
	mov eax,dword ptr	; 1 Clock cycle
	
	ret
GetTan endp