1 |
The flag -mmmx ( like -msse -m3dnow etc...) activate |
2 |
some extensions for C language. |
3 |
|
4 |
See this: |
5 |
http://gcc.gnu.org/onlinedocs/gcc-3.3.3/gcc/X86-Built-in-Functions.html#X86%20Built-in%20Functions |
6 |
|
7 |
So, those flag activate these built-in functions. |
8 |
|
9 |
--- Paul Ingelbrant <pi@×××××.se> ha scritto: > |
10 |
> |
11 |
> |
12 |
> I've been thinking about CFLAGS such as -mmmx... |
13 |
> Does gcc actually have the |
14 |
> ability to actually produce mmx instructions? |
15 |
> |
16 |
> |
17 |
> for example: |
18 |
> |
19 |
> |
20 |
> mmx.c: |
21 |
> |
22 |
> #include <stdio.h> |
23 |
> |
24 |
> |
25 |
> main() |
26 |
> { |
27 |
> short x[100000]; |
28 |
> int i; |
29 |
> |
30 |
> for (i=0; i < 100000; i++) |
31 |
> { |
32 |
> x[i] += 5; |
33 |
> |
34 |
> } |
35 |
> |
36 |
> |
37 |
> } |
38 |
> |
39 |
> gcc -mmmx -O3 --save-temps -funroll-all-loops mmx.c |
40 |
> gives |
41 |
> |
42 |
> |
43 |
> .file "mmx.c" |
44 |
> .def ___main; .scl 2; .type 32; .endef |
45 |
> .text |
46 |
> .align 2 |
47 |
> .p2align 4,,15 |
48 |
> .globl _main |
49 |
> .def _main; .scl 2; .type 32; .endef |
50 |
> _main: |
51 |
> pushl %ebp |
52 |
> movl $200008, %eax |
53 |
> movl %esp, %ebp |
54 |
> call __alloca |
55 |
> xorl %eax, %eax |
56 |
> andl $-16, %esp |
57 |
> call __alloca |
58 |
> call ___main |
59 |
> xorl %eax, %eax |
60 |
> .p2align 4,,7 |
61 |
> L6: |
62 |
> addw $5, -200008(%ebp,%eax,2) |
63 |
> addw $5, -200006(%ebp,%eax,2) |
64 |
> addw $5, -200004(%ebp,%eax,2) |
65 |
> addw $5, -200002(%ebp,%eax,2) |
66 |
> addw $5, -200000(%ebp,%eax,2) |
67 |
> addw $5, -199998(%ebp,%eax,2) |
68 |
> addw $5, -199996(%ebp,%eax,2) |
69 |
> addw $5, -199994(%ebp,%eax,2) |
70 |
> addw $5, -199992(%ebp,%eax,2) |
71 |
> addw $5, -199990(%ebp,%eax,2) |
72 |
> addl $10, %eax |
73 |
> cmpl $99999, %eax |
74 |
> jle L6 |
75 |
> leave |
76 |
> ret |
77 |
> |
78 |
> |
79 |
> |
80 |
> |
81 |
> Shouldn't take too much imagination to see how that |
82 |
> could be improved with mmx... |
83 |
> |
84 |
> Likewise: |
85 |
> |
86 |
> |
87 |
> |
88 |
> fu(int *x) |
89 |
> { |
90 |
> if (*x == 5) |
91 |
> *x = 10; |
92 |
> } |
93 |
> |
94 |
> |
95 |
> |
96 |
> with gcc -march=athlon-xp -O3 --save-temps |
97 |
> -funroll-all-loops mmx.c |
98 |
> |
99 |
> gives |
100 |
> |
101 |
> |
102 |
> |
103 |
> _fu: |
104 |
> pushl %ebp |
105 |
> movl %esp, %ebp |
106 |
> movl 8(%ebp), %eax |
107 |
> cmpl $5, (%eax) |
108 |
> je L33 |
109 |
> L32: |
110 |
> leave |
111 |
> ret |
112 |
> .p2align 6,,7 |
113 |
> L33: |
114 |
> movl $10, (%eax) |
115 |
> jmp L32 |
116 |
> |
117 |
> |
118 |
> the -march=athlon-xp parameter should imply cmov |
119 |
> instruction...(?) |
120 |
> |
121 |
> |
122 |
> (it doesn't even use muliple leave/ret to eliminate |
123 |
> an extra jmp...) |
124 |
> |
125 |
> |
126 |
> |
127 |
> Do the gcc developers include these fancy parameters |
128 |
> just to give us ricers a |
129 |
> false sense of speed? |
130 |
> |
131 |
> |
132 |
> any thoughts? |
133 |
> |
134 |
> |
135 |
> |
136 |
> -- |
137 |
> gentoo-performance@g.o mailing list |
138 |
> |
139 |
> |
140 |
|
141 |
|
142 |
|
143 |
|
144 |
|
145 |
|
146 |
____________________________________________________________ |
147 |
Yahoo! Companion - Scarica gratis la toolbar di Ricerca di Yahoo! |
148 |
http://companion.yahoo.it |
149 |
|
150 |
-- |
151 |
gentoo-performance@g.o mailing list |