vis_32.il

来自「支持SSL v2/v3, TLS, PKCS #5, PKCS #7, PKCS」· IL 代码 · 共 1,321 行 · 第 1/2 页

! 
!  The contents of this file are subject to the Mozilla Public
!  License Version 1.1 (the "License"); you may not use this file
!  except in compliance with the License. You may obtain a copy of
!  the License at http://www.mozilla.org/MPL/
!  
!  Software distributed under the License is distributed on an "AS
!  IS" basis, WITHOUT WARRANTY OF ANY KIND, either express or
!  implied. See the License for the specific language governing
!  rights and limitations under the License.
!  
!  The Original Code is vis inline macros (32 bit).  (vis_32.il 3.3)
! 
!  The Initial Developer of the Original Code is Sun Microsystems Inc.
!  Portions created by Sun Microsystems Inc. are 
!  Copyright (C) 1995-2000 Sun Microsystems Inc.  All Rights Reserved.
!  
!  Contributor(s):
!  
!  Alternatively, the contents of this file may be used under the
!  terms of the GNU General Public License Version 2 or later (the
!  "GPL"), in which case the provisions of the GPL are applicable 
!  instead of those above.	If you wish to allow use of your 
!  version of this file only under the terms of the GPL and not to
!  allow others to use your version of this file under the MPL,
!  indicate your decision by deleting the provisions above and
!  replace them with the notice and other provisions required by
!  the GPL.  If you do not delete the provisions above, a recipient
!  may use your version of this file under either the MPL or the
!  GPL.
!   $Id: vis_32.il,v 1.1 2000/09/29 23:38:04 nelsonb%netscape.com Exp $
! 
! @(#)vis_32.il	3.3	00/03/02 SMI

! The interface to the VIS instructions as declared below (and in the VIS
! User's Manual) will not change, but the macro implementation might change
! in the future.

!--------------------------------------------------------------------
! Pure edge handling instructions
!
! int vis_edge8(void */*frs1*/, void */*frs2*/);
!
	.inline vis_edge8,8
	edge8	%o0,%o1,%o0
	.end
!
! int vis_edge8l(void */*frs1*/, void */*frs2*/);
!
	.inline vis_edge8l,8
	edge8l	%o0,%o1,%o0
	.end
!
! int vis_edge16(void */*frs1*/, void */*frs2*/);
!
	.inline vis_edge16,8
	edge16	%o0,%o1,%o0
	.end
!
! int vis_edge16l(void */*frs1*/, void */*frs2*/);
!
	.inline vis_edge16l,8
	edge16l	%o0,%o1,%o0
	.end
!
! int vis_edge32(void */*frs1*/, void */*frs2*/);
!
	.inline vis_edge32,8
	edge32	%o0,%o1,%o0
	.end
!
! int vis_edge32l(void */*frs1*/, void */*frs2*/);
!
	.inline vis_edge32l,8
	edge32l	%o0,%o1,%o0
	.end

!--------------------------------------------------------------------
! Edge handling instructions with negative return values if cc set
!
! int vis_edge8cc(void */*frs1*/, void */*frs2*/);
!
	.inline vis_edge8cc,8
	edge8	%o0,%o1,%o0
	mov     0,%o1
	movgu   %icc,-1024,%o1
	or      %o1,%o0,%o0
	.end
!
! int vis_edge8lcc(void */*frs1*/, void */*frs2*/);
!
	.inline vis_edge8lcc,8
	edge8l	%o0,%o1,%o0
	mov     0,%o1
	movgu   %icc,-1024,%o1
	or      %o1,%o0,%o0
	.end
!
! int vis_edge16cc(void */*frs1*/, void */*frs2*/);
!
	.inline vis_edge16cc,8
	edge16	%o0,%o1,%o0
	mov     0,%o1
	movgu   %icc,-1024,%o1
	or      %o1,%o0,%o0
	.end
!
! int vis_edge16lcc(void */*frs1*/, void */*frs2*/);
!
	.inline vis_edge16lcc,8
	edge16l	%o0,%o1,%o0
	mov     0,%o1
	movgu   %icc,-1024,%o1
	or      %o1,%o0,%o0
	.end
!
! int vis_edge32cc(void */*frs1*/, void */*frs2*/);
!
	.inline vis_edge32cc,8
	edge32	%o0,%o1,%o0
	mov     0,%o1
	movgu   %icc,-1024,%o1
	or      %o1,%o0,%o0
	.end
!
! int vis_edge32lcc(void */*frs1*/, void */*frs2*/);
!
	.inline vis_edge32lcc,8
	edge32l	%o0,%o1,%o0
	mov     0,%o1
	movgu   %icc,-1024,%o1
	or      %o1,%o0,%o0
	.end

!--------------------------------------------------------------------
! Alignment instructions
!
! void *vis_alignaddr(void */*rs1*/, int /*rs2*/);
!
	.inline vis_alignaddr,8
	alignaddr	%o0,%o1,%o0
	.end
!
! void *vis_alignaddrl(void */*rs1*/, int /*rs2*/);
!
	.inline vis_alignaddrl,8
	alignaddrl	%o0,%o1,%o0
	.end
!
! double vis_faligndata(double /*frs1*/, double /*frs2*/);
!
	.inline vis_faligndata,16
	std	%o0,[%sp+0x48]
	ldd	[%sp+0x48],%f4
	std	%o2,[%sp+0x48]
	ldd	[%sp+0x48],%f10
	faligndata	%f4,%f10,%f0
	.end

!--------------------------------------------------------------------
! Partitioned comparison instructions
!
! int vis_fcmple16(double /*frs1*/, double /*frs2*/);
!
	.inline vis_fcmple16,16
	std	%o0,[%sp+0x48]
	ldd	[%sp+0x48],%f4
	std	%o2,[%sp+0x48]
	ldd	[%sp+0x48],%f10
	fcmple16	%f4,%f10,%o0
	.end
!
! int vis_fcmpne16(double /*frs1*/, double /*frs2*/);
!
	.inline vis_fcmpne16,16
	std	%o0,[%sp+0x48]
	ldd	[%sp+0x48],%f4
	std	%o2,[%sp+0x48]
	ldd	[%sp+0x48],%f10
	fcmpne16	%f4,%f10,%o0
	.end
!
! int vis_fcmple32(double /*frs1*/, double /*frs2*/);
!
	.inline vis_fcmple32,16
	std	%o0,[%sp+0x48]
	ldd	[%sp+0x48],%f4
	std	%o2,[%sp+0x48]
	ldd	[%sp+0x48],%f10
	fcmple32	%f4,%f10,%o0
	.end
!
! int vis_fcmpne32(double /*frs1*/, double /*frs2*/);
!
	.inline vis_fcmpne32,16
	std	%o0,[%sp+0x48]
	ldd	[%sp+0x48],%f4
	std	%o2,[%sp+0x48]
	ldd	[%sp+0x48],%f10
	fcmpne32	%f4,%f10,%o0
	.end
!
! int vis_fcmpgt16(double /*frs1*/, double /*frs2*/);
!
	.inline vis_fcmpgt16,16
	std	%o0,[%sp+0x48]
	ldd	[%sp+0x48],%f4
	std	%o2,[%sp+0x48]
	ldd	[%sp+0x48],%f10
	fcmpgt16	%f4,%f10,%o0
	.end
!
! int vis_fcmpeq16(double /*frs1*/, double /*frs2*/);
!
	.inline vis_fcmpeq16,16
	std	%o0,[%sp+0x48]
	ldd	[%sp+0x48],%f4
	std	%o2,[%sp+0x48]
	ldd	[%sp+0x48],%f10
	fcmpeq16	%f4,%f10,%o0
	.end
!
! int vis_fcmpgt32(double /*frs1*/, double /*frs2*/);
!
	.inline vis_fcmpgt32,16
	std	%o0,[%sp+0x48]
	ldd	[%sp+0x48],%f4
	std	%o2,[%sp+0x48]
	ldd	[%sp+0x48],%f10
	fcmpgt32	%f4,%f10,%o0
	.end
!
! int vis_fcmpeq32(double /*frs1*/, double /*frs2*/);
!
	.inline vis_fcmpeq32,16
	std	%o0,[%sp+0x48]
	ldd	[%sp+0x48],%f4
	std	%o2,[%sp+0x48]
	ldd	[%sp+0x48],%f10
	fcmpeq32	%f4,%f10,%o0
	.end

!--------------------------------------------------------------------
! Partitioned arithmetic
!
! double vis_fmul8x16(float /*frs1*/, double /*frs2*/);
!
	.inline vis_fmul8x16,12
	st	%o0,[%sp+0x44]
	ld	[%sp+0x44],%f4
	st	%o1,[%sp+0x48]
	st	%o2,[%sp+0x4c]
	ldd	[%sp+0x48],%f10
	fmul8x16	%f4,%f10,%f0
	.end
!
! double vis_fmul8x16_dummy(float /*frs1*/, int /*dummy*/, double /*frs2*/);
!
	.inline vis_fmul8x16_dummy,16
	st	%o0,[%sp+0x44]
	ld	[%sp+0x44],%f4
	std	%o2,[%sp+0x48]
	ldd	[%sp+0x48],%f10
	fmul8x16	%f4,%f10,%f0
	.end
!
! double vis_fmul8x16au(float /*frs1*/, float /*frs2*/);
!
	.inline vis_fmul8x16au,8
	st	%o0,[%sp+0x48]
	ld	[%sp+0x48],%f4
	st	%o1,[%sp+0x48]
	ld	[%sp+0x48],%f10
	fmul8x16au	%f4,%f10,%f0
	.end
!
! double vis_fmul8x16al(float /*frs1*/, float /*frs2*/);
!
	.inline vis_fmul8x16al,8
	st	%o0,[%sp+0x44]
	ld	[%sp+0x44],%f4
	st	%o1,[%sp+0x48]
	ld	[%sp+0x48],%f10
	fmul8x16al	%f4,%f10,%f0
	.end
!
! double vis_fmul8sux16(double /*frs1*/, double /*frs2*/);
!
	.inline vis_fmul8sux16,16
	std	%o0,[%sp+0x48]
	ldd	[%sp+0x48],%f4
	std	%o2,[%sp+0x48]
	ldd	[%sp+0x48],%f10
	fmul8sux16	%f4,%f10,%f0
	.end
!
! double vis_fmul8ulx16(double /*frs1*/, double /*frs2*/);
!
	.inline vis_fmul8ulx16,16
	std	%o0,[%sp+0x48]
	ldd	[%sp+0x48],%f4
	std	%o2,[%sp+0x48]
	ldd	[%sp+0x48],%f10
	fmul8ulx16	%f4,%f10,%f0
	.end
!
! double vis_fmuld8sux16(float /*frs1*/, float /*frs2*/);
!
	.inline vis_fmuld8sux16,8
	st	%o0,[%sp+0x48]
	ld	[%sp+0x48],%f4
	st	%o1,[%sp+0x48]
	ld	[%sp+0x48],%f10
	fmuld8sux16	%f4,%f10,%f0
	.end
!
! double vis_fmuld8ulx16(float /*frs1*/, float /*frs2*/);
!
	.inline vis_fmuld8ulx16,8
	st	%o0,[%sp+0x48]
	ld	[%sp+0x48],%f4
	st	%o1,[%sp+0x48]
	ld	[%sp+0x48],%f10
	fmuld8ulx16	%f4,%f10,%f0
	.end
!
! double vis_fpadd16(double /*frs1*/, double /*frs2*/);
!
	.inline vis_fpadd16,16
	std	%o0,[%sp+0x40]
	ldd	[%sp+0x40],%f4
	std	%o2,[%sp+0x48]
	ldd	[%sp+0x48],%f10
	fpadd16	%f4,%f10,%f0
	.end
!
! float vis_fpadd16s(float /*frs1*/, float /*frs2*/);
!
	.inline vis_fpadd16s,8
	st	%o0,[%sp+0x48]
	ld	[%sp+0x48],%f4
	st	%o1,[%sp+0x48]
	ld	[%sp+0x48],%f10
	fpadd16s	%f4,%f10,%f0
	.end
!
! double vis_fpadd32(double /*frs1*/, double /*frs2*/);
!
	.inline vis_fpadd32,16
	std	%o0,[%sp+0x48]
	ldd	[%sp+0x48],%f4
	std	%o2,[%sp+0x48]
	ldd	[%sp+0x48],%f10
	fpadd32	%f4,%f10,%f0
	.end
!
! float vis_fpadd32s(float /*frs1*/, float /*frs2*/);
!
	.inline vis_fpadd32s,8
	st	%o0,[%sp+0x48]
	ld	[%sp+0x48],%f4
	st	%o1,[%sp+0x48]
	ld	[%sp+0x48],%f10
	fpadd32s	%f4,%f10,%f0
	.end
!
! double vis_fpsub16(double /*frs1*/, double /*frs2*/);
!
	.inline vis_fpsub16,16
	std	%o0,[%sp+0x48]
	ldd	[%sp+0x48],%f4
	std	%o2,[%sp+0x48]
	ldd	[%sp+0x48],%f10
	fpsub16	%f4,%f10,%f0
	.end
!
! float vis_fpsub16s(float /*frs1*/, float /*frs2*/);
!
	.inline vis_fpsub16s,8
	st	%o0,[%sp+0x48]
	ld	[%sp+0x48],%f4
	st	%o1,[%sp+0x48]
	ld	[%sp+0x48],%f10
	fpsub16s	%f4,%f10,%f0
	.end
!
! double vis_fpsub32(double /*frs1*/, double /*frs2*/);
!
	.inline vis_fpsub32,16
	std	%o0,[%sp+0x48]
	ldd	[%sp+0x48],%f4
	std	%o2,[%sp+0x48]
	ldd	[%sp+0x48],%f10
	fpsub32	%f4,%f10,%f0
	.end
!
! float vis_fpsub32s(float /*frs1*/, float /*frs2*/);
!
	.inline vis_fpsub32s,8
	st	%o0,[%sp+0x48]
	ld	[%sp+0x48],%f4
	st	%o1,[%sp+0x48]
	ld	[%sp+0x48],%f10
	fpsub32s	%f4,%f10,%f0
	.end

!--------------------------------------------------------------------
! Pixel packing
!
! float vis_fpack16(double /*frs2*/);
!
	.inline vis_fpack16,8
	std	%o0,[%sp+0x48]
	ldd	[%sp+0x48],%f4
	fpack16	%f4,%f0
	.end

!
! double vis_fpack16_pair(double /*frs2*/, double /*frs2*/);
!
	.inline vis_fpack16_pair,16
	std	%o0,[%sp+0x48]
	ldd	[%sp+0x48],%f4
	std	%o2,[%sp+0x48]
	ldd	[%sp+0x48],%f10
	fpack16	%f4,%f0
	fpack16	%f10,%f1
	.end
!
! void vis_st2_fpack16(double, double, double *)
!
	.inline vis_st2_fpack16,20
 	std	%o0,[%sp+0x48]
 	ldd	[%sp+0x48],%f4
 	std	%o2,[%sp+0x48]
 	ldd	[%sp+0x48],%f10
 	fpack16	%f4,%f0
 	fpack16	%f10,%f1
 	st	%f0,[%o4+0]
 	st	%f1,[%o4+4]
 	.end
!
! void vis_std_fpack16(double, double, double *)
!
	.inline vis_std_fpack16,20
	std     %o0,[%sp+0x48]
	ldd     [%sp+0x48],%f4
	std     %o2,[%sp+0x48]
	ldd     [%sp+0x48],%f10
	fpack16 %f4,%f0
	fpack16 %f10,%f1
	std     %f0,[%o4]
	.end
!
! void vis_st2_fpackfix(double, double, double *)
!
	.inline vis_st2_fpackfix,20
 	std	%o0,[%sp+0x48]
 	ldd	[%sp+0x48],%f4
 	std	%o2,[%sp+0x48]
 	ldd	[%sp+0x48],%f10
 	fpackfix %f4,%f0
 	fpackfix %f10,%f1
 	st	%f0,[%o4+0]
 	st	%f1,[%o4+4]
 	.end
!
! double vis_fpack16_to_hi(double /*frs1*/, double /*frs2*/);
!
	.inline vis_fpack16_to_hi,16
	std	%o0,[%sp+0x48]
	ldd	[%sp+0x48],%f0
	std	%o2,[%sp+0x48]
	ldd	[%sp+0x48],%f4
	fpack16	%f4,%f0
	.end

! double vis_fpack16_to_lo(double /*frs1*/, double /*frs2*/);
!
	.inline vis_fpack16_to_lo,16
	std	%o0,[%sp+0x48]
	ldd	[%sp+0x48],%f0
	std	%o2,[%sp+0x48]
	ldd	[%sp+0x48],%f4
	fpack16	%f4,%f3
	fmovs	%f3,%f1		/* without this, optimizer goes wrong */
	.end

!
! double vis_fpack32(double /*frs1*/, double /*frs2*/);
!
	.inline vis_fpack32,16
	std	%o0,[%sp+0x48]
	ldd	[%sp+0x48],%f4
	std	%o2,[%sp+0x48]
	ldd	[%sp+0x48],%f10
	fpack32	%f4,%f10,%f0
	.end
!
! float vis_fpackfix(double /*frs2*/);
!
	.inline vis_fpackfix,8
	std	%o0,[%sp+0x48]
	ldd	[%sp+0x48],%f4
	fpackfix	%f4,%f0
	.end
!
! double vis_fpackfix_pair(double /*frs2*/, double /*frs2*/);
!
	.inline vis_fpackfix_pair,16
	std	%o0,[%sp+0x48]
	ldd	[%sp+0x48],%f4
	std	%o2,[%sp+0x48]
	ldd	[%sp+0x48],%f6
	fpackfix	%f4,%f0
	fpackfix	%f6,%f1
	.end

!--------------------------------------------------------------------
! Motion estimation
!
! double vis_pdist(double /*frs1*/, double /*frs2*/, double /*frd*/);
!
	.inline vis_pdist,24
	std	%o4,[%sp+0x48]
	ldd	[%sp+0x48],%f0
	std	%o0,[%sp+0x48]
	ldd	[%sp+0x48],%f4
	std	%o2,[%sp+0x48]
	ldd	[%sp+0x48],%f10
	pdist	%f4,%f10,%f0
	.end

!--------------------------------------------------------------------
! Channel merging
!
! double vis_fpmerge(float /*frs1*/, float /*frs2*/);
!
	.inline vis_fpmerge,8
	st	%o0,[%sp+0x48]
	ld	[%sp+0x48],%f4
	st	%o1,[%sp+0x48]
	ld	[%sp+0x48],%f10
	fpmerge	%f4,%f10,%f0
	.end

!--------------------------------------------------------------------
! Pixel expansion
!
! double vis_fexpand(float /*frs2*/);
!
	.inline vis_fexpand,4
	st	%o0,[%sp+0x48]
	ld	[%sp+0x48],%f4
	fexpand	%f4,%f0
	.end

! double vis_fexpand_hi(double /*frs2*/);
!
	.inline vis_fexpand_hi,8
	std	%o0,[%sp+0x48]
	ldd	[%sp+0x48],%f4
	fexpand	%f4,%f0
	.end

! double vis_fexpand_lo(double /*frs2*/);
!
	.inline vis_fexpand_lo,8
	std	%o0,[%sp+0x48]
	ldd	[%sp+0x48],%f4
	fmovs	%f5, %f2
	fexpand	%f2,%f0
	.end

!--------------------------------------------------------------------
! Bitwise logical operations
!
! double vis_fnor(double /*frs1*/, double /*frs2*/);
!
	.inline vis_fnor,16
	std	%o0,[%sp+0x48]
	ldd	[%sp+0x48],%f4
	std	%o2,[%sp+0x48]
	ldd	[%sp+0x48],%f10
	fnor	%f4,%f10,%f0
	.end
!
! float vis_fnors(float /*frs1*/, float /*frs2*/);
!
	.inline vis_fnors,8
	st	%o0,[%sp+0x48]
	ld	[%sp+0x48],%f4
	st	%o1,[%sp+0x48]
	ld	[%sp+0x48],%f10
	fnors	%f4,%f10,%f0
	.end
!
! double vis_fandnot(double /*frs1*/, double /*frs2*/);
!
	.inline vis_fandnot,16
	std	%o0,[%sp+0x48]
	ldd	[%sp+0x48],%f4
	std	%o2,[%sp+0x48]
	ldd	[%sp+0x48],%f10
	fandnot1	%f4,%f10,%f0
	.end
!
! float vis_fandnots(float /*frs1*/, float /*frs2*/);
!
	.inline vis_fandnots,8
	st	%o0,[%sp+0x48]
	ld	[%sp+0x48],%f4
	st	%o1,[%sp+0x48]
	ld	[%sp+0x48],%f10
	fandnot1s	%f4,%f10,%f0
	.end
!
! double vis_fnot(double /*frs1*/);
!
	.inline vis_fnot,8
	std	%o0,[%sp+0x48]
	ldd	[%sp+0x48],%f4
	fnot1	%f4,%f0
	.end
!
! float vis_fnots(float /*frs1*/);
!
	.inline vis_fnots,4
	st	%o0,[%sp+0x48]
	ld	[%sp+0x48],%f4
	fnot1s	%f4,%f0
	.end
!
! double vis_fxor(double /*frs1*/, double /*frs2*/);
!
	.inline vis_fxor,16
	std	%o0,[%sp+0x48]
	ldd	[%sp+0x48],%f4
	std	%o2,[%sp+0x48]
	ldd	[%sp+0x48],%f10
	fxor	%f4,%f10,%f0
	.end
!
! float vis_fxors(float /*frs1*/, float /*frs2*/);
!
	.inline vis_fxors,8
	st	%o0,[%sp+0x48]
	ld	[%sp+0x48],%f4
	st	%o1,[%sp+0x48]
	ld	[%sp+0x48],%f10
	fxors	%f4,%f10,%f0
	.end
!
! double vis_fnand(double /*frs1*/, double /*frs2*/);
!
	.inline vis_fnand,16
	std	%o0,[%sp+0x48]
	ldd	[%sp+0x48],%f4
	std	%o2,[%sp+0x48]
	ldd	[%sp+0x48],%f10
	fnand	%f4,%f10,%f0