view src/hermes/mmx_main.asm @ 689:5bb080d35049

Date: Tue, 19 Aug 2003 17:57:00 +0200 From: Stephane Marchesin Subject: Re: [SDL] [patch] MMX alpha blit patches with MMX detection I think everything is correct now. I've done as much testing as I could, but some real-world testing wouldn't hurt, I think. The patch is here : http://icps.u-strasbg.fr/~marchesin/sdl_mmxblit.patch If you do byte-by-byte comparison of the output between C and MMX functions, you'll notice that the results for 555 and 565 RGB alpha blits aren't exactly the same. This is because MMX functions for 555 and 565 RGB have an higher accuracy. If you want the exact same behaviour that's possible by masking the three lower alpha bits in the MMX functions. Just ask ! I removed one MMX function because after I fixed it to match its C equivalent, it revealed to be slower than the C version on a PIII (although a bit faster on an Athlon XP). I've also added MMX and PIII replacements for SDL_memcpy. Those provide some speed up in testvidinfo -benchmark (at least for me, under linux & X11).
author Sam Lantinga <slouken@libsdl.org>
date Fri, 22 Aug 2003 05:51:19 +0000
parents 74212992fb08
children da33b7e6d181
line wrap: on
line source

;
; mmx format converter main loops for HERMES
; Some routines Copyright (c) 1998 Christian Nentwich (c.nentwich@cs.ucl.ac.uk)
; This source code is licensed under the GNU LGPL
; 
; Please refer to the file COPYING.LIB contained in the distribution for
; licensing conditions		
;

BITS 32

GLOBAL _ConvertMMX
GLOBAL _mmxreturn


SECTION .text
		
;; _ConvertMMX:	 
;; [ESP+8] ConverterInfo*
;; --------------------------------------------------------------------------
;; ConverterInfo (ebp+..)
;;   0:	void *s_pixels
;;   4:	int s_width
;;   8:	int s_height
;;  12:	int s_add
;;  16:	void *d_pixels
;;  20:	int d_width
;;  24:	int d_height
;;  28:	int d_add
;;  32:	void (*converter_function)() 
;;  36: int32 *lookup
	
_ConvertMMX:
	push ebp
	mov ebp,esp

; Save the registers used by the blitters, necessary for optimized code
	pusha

	mov eax,[ebp+8]

        cmp dword [eax+4],BYTE 0
	je endconvert
	
	mov ebp,eax
	
	mov esi,[ebp+0]
	mov edi,[ebp+16]
	
y_loop:	
	mov ecx,[ebp+4]

	jmp [ebp+32]

_mmxreturn:	
	add esi,[ebp+12]
	add edi,[ebp+28]
	
	dec dword  [ebp+8]
	jnz y_loop

	
; Restore the registers used by the blitters, necessary for optimized code
	popa

	pop ebp

endconvert:
	emms
	
	ret