… | |
… | |
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 | |
… | |
… | |
37 | #endif |
39 | #endif |
38 | } |
40 | } |
39 | |
41 | |
40 | =item ecb_noinline |
42 | =item ecb_noinline |
41 | |
43 | |
42 | Prevent a function from being inlined - it might be optimsied away, but |
44 | Prevent a function from being inlined - it might be optimised away, but |
43 | not inlined into other functions. This is useful if you know your function |
45 | not inlined into other functions. This is useful if you know your function |
44 | is rarely called and large enough for inlining not to be helpful. |
46 | is rarely called and large enough for inlining not to be helpful. |
45 | |
47 | |
46 | =item ecb_noreturn |
48 | =item ecb_noreturn |
47 | |
49 | |
… | |
… | |
59 | |
61 | |
60 | =head2 OPTIMISATION HINTS |
62 | =head2 OPTIMISATION HINTS |
61 | |
63 | |
62 | =over 4 |
64 | =over 4 |
63 | |
65 | |
64 | =item bool ecb_is_constant(expr) |
66 | =item bool ecb_is_constant(expr) [MACRO] |
65 | |
67 | |
66 | Returns true iff the expression can be deduced to be a compile-time |
68 | Returns true iff the expression can be deduced to be a compile-time |
67 | constant, and false otherwise. |
69 | constant, and false otherwise. |
68 | |
70 | |
69 | For example, when you have a C<rndm16> function that returns a 16 bit |
71 | For example, when you have a C<rndm16> function that returns a 16 bit |
70 | random number, and you have a function that maps this to a range from |
72 | random number, and you have a function that maps this to a range from |
71 | 0..n-1, then you could use this inline fucntion in a header file: |
73 | 0..n-1, then you could use this inline function in a header file: |
72 | |
74 | |
73 | ecb_inline uint32_t |
75 | ecb_inline uint32_t |
74 | rndm (uint32_t n) |
76 | rndm (uint32_t n) |
75 | { |
77 | { |
76 | return n * (uint32_t)rndm16 ()) >> 16; |
78 | return (n * (uint32_t)rndm16 ()) >> 16; |
77 | } |
79 | } |
78 | |
80 | |
79 | However, for powers of two, you could use a normal mask, but that is only |
81 | However, for powers of two, you could use a normal mask, but that is only |
80 | worth it if, at compile time, you can detect this case. This is the case |
82 | worth it if, at compile time, you can detect this case. This is the case |
81 | when the passed number is a constant and also a power of two (C<n & (n - |
83 | when the passed number is a constant and also a power of two (C<n & (n - |
… | |
… | |
84 | ecb_inline uint32_t |
86 | ecb_inline uint32_t |
85 | rndm (uint32_t n) |
87 | rndm (uint32_t n) |
86 | { |
88 | { |
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 | : (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) [MACRO] |
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) [MACRO] |
|
|
104 | |
94 | =item bool ecb_unlikely(bool) |
105 | =item bool ecb_unlikely (bool) [MACRO] |
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_unlikely>, that it is unlikely to be |
|
|
117 | true). |
|
|
118 | |
|
|
119 | For example, when you check for a null pointer and expect this to be a |
|
|
120 | rare, 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 | each 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) [MACRO] |
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 suppressing 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) [MACRO] |
|
|
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 prefetches 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 | |
… | |
… | |
109 | |
222 | |
110 | =item bool ecb_big_endian () |
223 | =item bool ecb_big_endian () |
111 | |
224 | |
112 | =item bool ecb_little_endian () |
225 | =item bool ecb_little_endian () |
113 | |
226 | |
|
|
227 | These two functions return true if the byte order is big endian |
|
|
228 | (most-significant byte first) or little endian (least-significant byte |
|
|
229 | first) respectively. |
|
|
230 | |
114 | =item int ecb_ctz32 (uint32_t x) |
231 | =item int ecb_ctz32 (uint32_t x) |
115 | |
232 | |
|
|
233 | Returns the index of the least significant bit set in C<x> (or |
|
|
234 | equivalently the number of bits set to 0 before the least significant |
|
|
235 | bit set), starting from 0. If C<x> is 0 the result is undefined. A |
|
|
236 | common use case is to compute the integer binary logarithm, i.e., |
|
|
237 | floor(log2(n)). For example: |
|
|
238 | |
|
|
239 | ecb_ctz32(3) = 1 |
|
|
240 | ecb_ctz32(6) = 2 |
|
|
241 | |
116 | =item int ecb_popcount32 (uint32_t x) |
242 | =item int ecb_popcount32 (uint32_t x) |
117 | |
243 | |
|
|
244 | Returns the number of bits set to 1 in C<x>. For example: |
|
|
245 | |
|
|
246 | ecb_popcount32(7) = 3 |
|
|
247 | ecb_popcount32(255) = 8 |
|
|
248 | |
|
|
249 | =item uint32_t ecb_bswap16 (uint32_t x) |
|
|
250 | |
118 | =item uint32_t ecb_bswap32 (uint32_t x) |
251 | =item uint32_t ecb_bswap32 (uint32_t x) |
119 | |
252 | |
120 | =item uint32_t ecb_bswap16 (uint32_t x) |
|
|
121 | |
|
|
122 | =item uint32_t ecb_rotr32 (uint32_t x, unsigned int count) |
253 | =item uint32_t ecb_rotr32 (uint32_t x, unsigned int count) |
123 | |
254 | |
124 | =item uint32_t ecb_rotl32 (uint32_t x, unsigned int count) |
255 | =item uint32_t ecb_rotl32 (uint32_t x, unsigned int count) |
125 | |
256 | |
|
|
257 | These two functions return the value of C<x> after shifting all the bits |
|
|
258 | by C<count> positions to the right or left respectively. |
|
|
259 | |
126 | =back |
260 | =back |
127 | |
261 | |
128 | =head2 ARITHMETIC |
262 | =head2 ARITHMETIC |
129 | |
263 | |
130 | =over 4 |
264 | =over 4 |
131 | |
265 | |
132 | =item x = ecb_mod (m, n) [MACRO] |
266 | =item x = ecb_mod (m, n) [MACRO] |
133 | |
267 | |
|
|
268 | Returns the positive remainder of the modulo operation between C<m> |
|
|
269 | and C<n>. |
|
|
270 | |
134 | =back |
271 | =back |
135 | |
272 | |
136 | =head2 UTILITY |
273 | =head2 UTILITY |
137 | |
274 | |
138 | =over 4 |
275 | =over 4 |
139 | |
276 | |
140 | =item ecb_array_length (name) [MACRO] |
277 | =item element_count = ecb_array_length (name) [MACRO] |
141 | |
278 | |
142 | =back |
279 | =back |
143 | |
280 | |
144 | |
281 | |