1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
|
; ===========================================================================
; Copyright (C) 2011 Thilo Schulz <thilo@tjps.eu>
;
; This file is part of Quake III Arena source code.
;
; Quake III Arena source code is free software; you can redistribute it
; and/or modify it under the terms of the GNU General Public License as
; published by the Free Software Foundation; either version 2 of the License,
; or (at your option) any later version.
;
; Quake III Arena source code is distributed in the hope that it will be
; useful, but WITHOUT ANY WARRANTY; without even the implied warranty of
; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
; GNU General Public License for more details.
;
; You should have received a copy of the GNU General Public License
; along with Quake III Arena source code; if not, write to the Free Software
; Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
; ===========================================================================
; MASM version of snapvector conversion function using SSE or FPU
; assume __cdecl calling convention is being used for x86, __fastcall for x64
;
; function prototype:
; void qsnapvector(vec3_t vec)
IFNDEF idx64
.model flat, c
ENDIF
.data
ALIGN 16
ssemask DWORD 0FFFFFFFFh, 0FFFFFFFFh, 0FFFFFFFFh, 00000000h
ssecw DWORD 00001F80h
IFNDEF idx64
fpucw WORD 037Fh
ENDIF
.code
IFDEF idx64
; qsnapvector using SSE
qsnapvectorsse PROC
sub rsp, 8
movaps xmm1, ssemask ; initialize the mask register
movups xmm0, [rcx] ; here is stored our vector. Read 4 values in one go
movaps xmm2, xmm0 ; keep a copy of the original data
andps xmm0, xmm1 ; set the fourth value to zero in xmm0
andnps xmm1, xmm2 ; copy fourth value to xmm1 and set rest to zero
cvtps2dq xmm0, xmm0 ; convert 4 single fp to int
cvtdq2ps xmm0, xmm0 ; convert 4 int to single fp
orps xmm0, xmm1 ; combine all 4 values again
movups [rcx], xmm0 ; write 3 rounded and 1 unchanged values back to memory
ret
qsnapvectorsse ENDP
ELSE
qsnapvectorsse PROC
mov eax, dword ptr 4[esp] ; store address of vector in eax
movaps xmm1, ssemask ; initialize the mask register for maskmovdqu
movups xmm0, [eax] ; here is stored our vector. Read 4 values in one go
movaps xmm2, xmm0 ; keep a copy of the original data
andps xmm0, xmm1 ; set the fourth value to zero in xmm0
andnps xmm1, xmm2 ; copy fourth value to xmm1 and set rest to zero
cvtps2dq xmm0, xmm0 ; convert 4 single fp to int
cvtdq2ps xmm0, xmm0 ; convert 4 int to single fp
orps xmm0, xmm1 ; combine all 4 values again
movups [eax], xmm0 ; write 3 rounded and 1 unchanged values back to memory
ret
qsnapvectorsse ENDP
qroundx87 macro src
fld dword ptr src
fistp dword ptr src
fild dword ptr src
fstp dword ptr src
endm
qsnapvectorx87 PROC
mov eax, dword ptr 4[esp]
qroundx87 [eax]
qroundx87 4[eax]
qroundx87 8[eax]
ret
qsnapvectorx87 ENDP
ENDIF
end
|
