… | |
… | |
6 | |
6 | |
7 | - how to include it |
7 | - how to include it |
8 | - it includes inttypes.h |
8 | - it includes inttypes.h |
9 | - no .a |
9 | - no .a |
10 | - whats a bool |
10 | - whats a bool |
|
|
11 | - function mean macro or function |
|
|
12 | - macro means untyped |
11 | |
13 | |
12 | =head2 GCC ATTRIBUTES |
14 | =head2 GCC ATTRIBUTES |
13 | |
15 | |
14 | blabla where to put, what others |
16 | blabla where to put, what others |
15 | |
17 | |
… | |
… | |
87 | return is_constant (n) && !(n & (n - 1)) |
89 | return is_constant (n) && !(n & (n - 1)) |
88 | ? rndm16 () & (num - 1) |
90 | ? rndm16 () & (num - 1) |
89 | : (n * (uint32_t)rndm16 ()) >> 16; |
91 | : (n * (uint32_t)rndm16 ()) >> 16; |
90 | } |
92 | } |
91 | |
93 | |
92 | =item bool ecb_expect(expr,value) |
94 | =item bool ecb_expect (expr, value) |
93 | |
95 | |
|
|
96 | Evaluates C<expr> and returns it. In addition, it tells the compiler that |
|
|
97 | the C<expr> evaluates to C<value> a lot, which can be used for static |
|
|
98 | branch optimisations. |
|
|
99 | |
|
|
100 | Usually, you want to use the more intuitive C<ecb_likely> and |
|
|
101 | C<ecb_unlikely> functions instead. |
|
|
102 | |
|
|
103 | =item bool ecb_likely (bool) |
|
|
104 | |
94 | =item bool ecb_unlikely(bool) |
105 | =item bool ecb_unlikely (bool) |
95 | |
106 | |
96 | =item bool ecb_likely(bool) |
107 | These two functions expect a expression that is true or false and return |
|
|
108 | C<1> or C<0>, respectively, so when used in the condition of an C<if> or |
|
|
109 | other conditional statement, it will not change the program: |
97 | |
110 | |
|
|
111 | /* these two do the same thing */ |
|
|
112 | if (some_condition) ...; |
|
|
113 | if (ecb_likely (some_condition)) ...; |
|
|
114 | |
|
|
115 | However, by using C<ecb_likely>, you tell the compiler that the condition |
|
|
116 | is likely to be true (and for C<ecb_unlikel>, that it is unlikely to be |
|
|
117 | true). |
|
|
118 | |
|
|
119 | For example, when you check for a 0-ptr and expect this to be a rare, |
|
|
120 | exceptional, case, then use C<ecb_unlikely>: |
|
|
121 | |
|
|
122 | void my_free (void *ptr) |
|
|
123 | { |
|
|
124 | if (ecb_unlikely (ptr == 0)) |
|
|
125 | return; |
|
|
126 | } |
|
|
127 | |
|
|
128 | Consequent use of these functions to mark away exceptional cases or to |
|
|
129 | tell the compiler what the hot path through a function is can increase |
|
|
130 | performance considerably. |
|
|
131 | |
|
|
132 | A very good example is in a function that reserves more space for some |
|
|
133 | memory block (for example, inside an implementation of a string stream) - |
|
|
134 | eahc time something is added, you have to check for a buffer overrun, but |
|
|
135 | you expect that most checks will turn out to be false: |
|
|
136 | |
|
|
137 | /* make sure we have "size" extra room in our buffer */ |
|
|
138 | ecb_inline void |
|
|
139 | reserve (int size) |
|
|
140 | { |
|
|
141 | if (ecb_unlikely (current + size > end)) |
|
|
142 | real_reserve_method (size); /* presumably noinline */ |
|
|
143 | } |
|
|
144 | |
98 | =item bool ecb_assume(cond) |
145 | =item bool ecb_assume (cond) |
99 | |
146 | |
|
|
147 | Try to tell the compiler that some condition is true, even if it's not |
|
|
148 | obvious. |
|
|
149 | |
|
|
150 | This can be used to teach the compiler about invariants or other |
|
|
151 | conditions that might improve code generation, but which are impossible to |
|
|
152 | deduce form the code itself. |
|
|
153 | |
|
|
154 | For example, the example reservation function from the C<ecb_unlikely> |
|
|
155 | description could be written thus (only C<ecb_assume> was added): |
|
|
156 | |
|
|
157 | ecb_inline void |
|
|
158 | reserve (int size) |
|
|
159 | { |
|
|
160 | if (ecb_unlikely (current + size > end)) |
|
|
161 | real_reserve_method (size); /* presumably noinline */ |
|
|
162 | |
|
|
163 | ecb_assume (current + size <= end); |
|
|
164 | } |
|
|
165 | |
|
|
166 | If you then call this function twice, like this: |
|
|
167 | |
|
|
168 | reserve (10); |
|
|
169 | reserve (1); |
|
|
170 | |
|
|
171 | Then the compiler I<might> be able to optimise out the second call |
|
|
172 | completely, as it knows that C<< current + 1 > end >> is false and the |
|
|
173 | call will never be executed. |
|
|
174 | |
100 | =item bool ecb_unreachable() |
175 | =item bool ecb_unreachable () |
101 | |
176 | |
|
|
177 | This function does nothing itself, except tell the compiler that it will |
|
|
178 | never be executed. Apart from supressing a warning in some cases, this |
|
|
179 | function can be used to implement C<ecb_assume> or similar functions. |
|
|
180 | |
102 | =item bool ecb_prefetch(addr,rw,locality) |
181 | =item bool ecb_prefetch (addr, rw, locality) |
|
|
182 | |
|
|
183 | Tells the compiler to try to prefetch memory at the given C<addr>ess |
|
|
184 | for either reading (c<rw> = 0) or writing (C<rw> = 1). A C<locality> of |
|
|
185 | C<0> means that there will only be one access later, C<3> means that |
|
|
186 | the data will likely be accessed very often, and values in between mean |
|
|
187 | something... in between. The memory pointed to by the address does not |
|
|
188 | need to be accessible (it could be a null pointer for example), but C<rw> |
|
|
189 | and C<locality> must be compile-time constants. |
|
|
190 | |
|
|
191 | An obvious way to use this is to prefetch some data far away, in a big |
|
|
192 | array you loop over. This prefethces memory some 128 array elements later, |
|
|
193 | in the hope that it will be ready when the CPU arrives at that location. |
|
|
194 | |
|
|
195 | int sum = 0; |
|
|
196 | |
|
|
197 | for (i = 0; i < N; ++i) |
|
|
198 | { |
|
|
199 | sum += arr [i] |
|
|
200 | ecb_prefetch (arr + i + 128, 0, 0); |
|
|
201 | } |
|
|
202 | |
|
|
203 | It's hard to predict how far to prefetch, and most CPUs that can prefetch |
|
|
204 | are often good enough to predict this kind of behaviour themselves. It |
|
|
205 | gets more interesting with linked lists, especially when you do some fair |
|
|
206 | processing on each list element: |
|
|
207 | |
|
|
208 | for (node *n = start; n; n = n->next) |
|
|
209 | { |
|
|
210 | ecb_prefetch (n->next, 0, 0); |
|
|
211 | ... do medium amount of work with *n |
|
|
212 | } |
|
|
213 | |
|
|
214 | After processing the node, (part of) the next node might already be in |
|
|
215 | cache. |
103 | |
216 | |
104 | =back |
217 | =back |
105 | |
218 | |
106 | =head2 BIT FIDDLING / BITSTUFFS |
219 | =head2 BIT FIDDLING / BITSTUFFS |
107 | |
220 | |