… | |
… | |
53 | C<uint32_t>, then the corresponding function works only with that type. If |
53 | C<uint32_t>, then the corresponding function works only with that type. If |
54 | only a generic name is used (C<expr>, C<cond>, C<value> and so on), then |
54 | only a generic name is used (C<expr>, C<cond>, C<value> and so on), then |
55 | the corresponding function relies on C to implement the correct types, and |
55 | the corresponding function relies on C to implement the correct types, and |
56 | is usually implemented as a macro. Specifically, a "bool" in this manual |
56 | is usually implemented as a macro. Specifically, a "bool" in this manual |
57 | refers to any kind of boolean value, not a specific type. |
57 | refers to any kind of boolean value, not a specific type. |
|
|
58 | |
|
|
59 | =head2 TYPES / TYPE SUPPORT |
|
|
60 | |
|
|
61 | ecb.h makes sure that the following types are defined (in the expected way): |
|
|
62 | |
|
|
63 | int8_t uint8_t int16_t uint16_t |
|
|
64 | int32_t uint32_t int64_t uint64_t |
|
|
65 | intptr_t uintptr_t ptrdiff_t |
|
|
66 | |
|
|
67 | The macro C<ECB_PTRSIZE> is defined to the size of a pointer on this |
|
|
68 | platform (currently C<4> or C<8>) and can be used in preprocessor |
|
|
69 | expressions. |
|
|
70 | |
|
|
71 | =head2 LANGUAGE/COMPILER VERSIONS |
|
|
72 | |
|
|
73 | All the following symbols expand to an expression that can be tested in |
|
|
74 | preprocessor instructions as well as treated as a boolean (use C<!!> to |
|
|
75 | ensure it's either C<0> or C<1> if you need that). |
|
|
76 | |
|
|
77 | =over 4 |
|
|
78 | |
|
|
79 | =item ECB_C |
|
|
80 | |
|
|
81 | True if the implementation defines the C<__STDC__> macro to a true value, |
|
|
82 | which is typically true for both C and C++ compilers. |
|
|
83 | |
|
|
84 | =item ECB_C99 |
|
|
85 | |
|
|
86 | True if the implementation claims to be C99 compliant. |
|
|
87 | |
|
|
88 | =item ECB_C11 |
|
|
89 | |
|
|
90 | True if the implementation claims to be C11 compliant. |
|
|
91 | |
|
|
92 | =item ECB_CPP |
|
|
93 | |
|
|
94 | True if the implementation defines the C<__cplusplus__> macro to a true |
|
|
95 | value, which is typically true for C++ compilers. |
|
|
96 | |
|
|
97 | =item ECB_CPP98 |
|
|
98 | |
|
|
99 | True if the implementation claims to be compliant to ISO/IEC 14882:1998 |
|
|
100 | (the first C++ ISO standard) or any later version. Typically true for all |
|
|
101 | C++ compilers. |
|
|
102 | |
|
|
103 | =item ECB_CPP11 |
|
|
104 | |
|
|
105 | True if the implementation claims to be compliant to ISO/IEC 14882:2011 |
|
|
106 | (C++11) or any later version. |
|
|
107 | |
|
|
108 | =item ECB_GCC_VERSION(major,minor) |
|
|
109 | |
|
|
110 | Expands to a true value (suitable for testing in by the preprocessor) |
|
|
111 | if the compiler used is GNU C and the version is the given version, or |
|
|
112 | higher. |
|
|
113 | |
|
|
114 | This macro tries to return false on compilers that claim to be GCC |
|
|
115 | compatible but aren't. |
|
|
116 | |
|
|
117 | =back |
58 | |
118 | |
59 | =head2 GCC ATTRIBUTES |
119 | =head2 GCC ATTRIBUTES |
60 | |
120 | |
61 | A major part of libecb deals with GCC attributes. These are additional |
121 | A major part of libecb deals with GCC attributes. These are additional |
62 | attributes that you can assign to functions, variables and sometimes even |
122 | attributes that you can assign to functions, variables and sometimes even |
… | |
… | |
101 | #else |
161 | #else |
102 | return 0; |
162 | return 0; |
103 | #endif |
163 | #endif |
104 | } |
164 | } |
105 | |
165 | |
|
|
166 | =item ecb_inline |
|
|
167 | |
|
|
168 | This is not actually an attribute, but you use it like one. It expands |
|
|
169 | either to C<static inline> or to just C<static>, if inline isn't |
|
|
170 | supported. It should be used to declare functions that should be inlined, |
|
|
171 | for code size or speed reasons. |
|
|
172 | |
|
|
173 | Example: inline this function, it surely will reduce codesize. |
|
|
174 | |
|
|
175 | ecb_inline int |
|
|
176 | negmul (int a, int b) |
|
|
177 | { |
|
|
178 | return - (a * b); |
|
|
179 | } |
|
|
180 | |
106 | =item ecb_noinline |
181 | =item ecb_noinline |
107 | |
182 | |
108 | Prevent a function from being inlined - it might be optimised away, but |
183 | Prevent a function from being inlined - it might be optimised away, but |
109 | not inlined into other functions. This is useful if you know your function |
184 | not inlined into other functions. This is useful if you know your function |
110 | is rarely called and large enough for inlining not to be helpful. |
185 | is rarely called and large enough for inlining not to be helpful. |
… | |
… | |
381 | After processing the node, (part of) the next node might already be in |
456 | After processing the node, (part of) the next node might already be in |
382 | cache. |
457 | cache. |
383 | |
458 | |
384 | =back |
459 | =back |
385 | |
460 | |
386 | =head2 BIT FIDDLING / BITSTUFFS |
461 | =head2 BIT FIDDLING / BIT WIZARDRY |
387 | |
462 | |
388 | =over 4 |
463 | =over 4 |
389 | |
464 | |
390 | =item bool ecb_big_endian () |
465 | =item bool ecb_big_endian () |
391 | |
466 | |
… | |
… | |
397 | |
472 | |
398 | On systems that are neither, their return values are unspecified. |
473 | On systems that are neither, their return values are unspecified. |
399 | |
474 | |
400 | =item int ecb_ctz32 (uint32_t x) |
475 | =item int ecb_ctz32 (uint32_t x) |
401 | |
476 | |
|
|
477 | =item int ecb_ctz64 (uint64_t x) |
|
|
478 | |
402 | Returns the index of the least significant bit set in C<x> (or |
479 | Returns the index of the least significant bit set in C<x> (or |
403 | equivalently the number of bits set to 0 before the least significant bit |
480 | equivalently the number of bits set to 0 before the least significant bit |
404 | set), starting from 0. If C<x> is 0 the result is undefined. A common use |
481 | set), starting from 0. If C<x> is 0 the result is undefined. |
405 | case is to compute the integer binary logarithm, i.e., C<floor (log2 |
482 | |
|
|
483 | For smaller types than C<uint32_t> you can safely use C<ecb_ctz32>. |
|
|
484 | |
406 | (n))>. For example: |
485 | For example: |
407 | |
486 | |
408 | ecb_ctz32 (3) = 0 |
487 | ecb_ctz32 (3) = 0 |
409 | ecb_ctz32 (6) = 1 |
488 | ecb_ctz32 (6) = 1 |
410 | |
489 | |
|
|
490 | =item bool ecb_is_pot32 (uint32_t x) |
|
|
491 | |
|
|
492 | =item bool ecb_is_pot64 (uint32_t x) |
|
|
493 | |
|
|
494 | Return true iff C<x> is a power of two or C<x == 0>. |
|
|
495 | |
|
|
496 | For smaller types then C<uint32_t> you can safely use C<ecb_is_pot32>. |
|
|
497 | |
|
|
498 | =item int ecb_ld32 (uint32_t x) |
|
|
499 | |
|
|
500 | =item int ecb_ld64 (uint64_t x) |
|
|
501 | |
|
|
502 | Returns the index of the most significant bit set in C<x>, or the number |
|
|
503 | of digits the number requires in binary (so that C<< 2**ld <= x < |
|
|
504 | 2**(ld+1) >>). If C<x> is 0 the result is undefined. A common use case is |
|
|
505 | to compute the integer binary logarithm, i.e. C<floor (log2 (n))>, for |
|
|
506 | example to see how many bits a certain number requires to be encoded. |
|
|
507 | |
|
|
508 | This function is similar to the "count leading zero bits" function, except |
|
|
509 | that that one returns how many zero bits are "in front" of the number (in |
|
|
510 | the given data type), while C<ecb_ld> returns how many bits the number |
|
|
511 | itself requires. |
|
|
512 | |
|
|
513 | For smaller types than C<uint32_t> you can safely use C<ecb_ld32>. |
|
|
514 | |
411 | =item int ecb_popcount32 (uint32_t x) |
515 | =item int ecb_popcount32 (uint32_t x) |
412 | |
516 | |
|
|
517 | =item int ecb_popcount64 (uint64_t x) |
|
|
518 | |
413 | Returns the number of bits set to 1 in C<x>. For example: |
519 | Returns the number of bits set to 1 in C<x>. |
|
|
520 | |
|
|
521 | For smaller types than C<uint32_t> you can safely use C<ecb_popcount32>. |
|
|
522 | |
|
|
523 | For example: |
414 | |
524 | |
415 | ecb_popcount32 (7) = 3 |
525 | ecb_popcount32 (7) = 3 |
416 | ecb_popcount32 (255) = 8 |
526 | ecb_popcount32 (255) = 8 |
417 | |
527 | |
|
|
528 | =item uint8_t ecb_bitrev8 (uint8_t x) |
|
|
529 | |
|
|
530 | =item uint16_t ecb_bitrev16 (uint16_t x) |
|
|
531 | |
|
|
532 | =item uint32_t ecb_bitrev32 (uint32_t x) |
|
|
533 | |
|
|
534 | Reverses the bits in x, i.e. the MSB becomes the LSB, MSB-1 becomes LSB+1 |
|
|
535 | and so on. |
|
|
536 | |
|
|
537 | Example: |
|
|
538 | |
|
|
539 | ecb_bitrev8 (0xa7) = 0xea |
|
|
540 | ecb_bitrev32 (0xffcc4411) = 0x882233ff |
|
|
541 | |
418 | =item uint32_t ecb_bswap16 (uint32_t x) |
542 | =item uint32_t ecb_bswap16 (uint32_t x) |
419 | |
543 | |
420 | =item uint32_t ecb_bswap32 (uint32_t x) |
544 | =item uint32_t ecb_bswap32 (uint32_t x) |
421 | |
545 | |
|
|
546 | =item uint64_t ecb_bswap64 (uint64_t x) |
|
|
547 | |
422 | These two functions return the value of the 16-bit (32-bit) value C<x> |
548 | These functions return the value of the 16-bit (32-bit, 64-bit) value |
423 | after reversing the order of bytes (0x11223344 becomes 0x44332211). |
549 | C<x> after reversing the order of bytes (0x11223344 becomes 0x44332211 in |
|
|
550 | C<ecb_bswap32>). |
|
|
551 | |
|
|
552 | =item uint8_t ecb_rotl8 (uint8_t x, unsigned int count) |
|
|
553 | |
|
|
554 | =item uint16_t ecb_rotl16 (uint16_t x, unsigned int count) |
|
|
555 | |
|
|
556 | =item uint32_t ecb_rotl32 (uint32_t x, unsigned int count) |
|
|
557 | |
|
|
558 | =item uint64_t ecb_rotl64 (uint64_t x, unsigned int count) |
|
|
559 | |
|
|
560 | =item uint8_t ecb_rotr8 (uint8_t x, unsigned int count) |
|
|
561 | |
|
|
562 | =item uint16_t ecb_rotr16 (uint16_t x, unsigned int count) |
424 | |
563 | |
425 | =item uint32_t ecb_rotr32 (uint32_t x, unsigned int count) |
564 | =item uint32_t ecb_rotr32 (uint32_t x, unsigned int count) |
426 | |
565 | |
427 | =item uint32_t ecb_rotl32 (uint32_t x, unsigned int count) |
566 | =item uint64_t ecb_rotr64 (uint64_t x, unsigned int count) |
428 | |
567 | |
429 | These two functions return the value of C<x> after rotating all the bits |
568 | These two families of functions return the value of C<x> after rotating |
430 | by C<count> positions to the right or left respectively. |
569 | all the bits by C<count> positions to the right (C<ecb_rotr>) or left |
|
|
570 | (C<ecb_rotl>). |
431 | |
571 | |
432 | Current GCC versions understand these functions and usually compile them |
572 | Current GCC versions understand these functions and usually compile them |
433 | to "optimal" code (e.g. a single C<roll> on x86). |
573 | to "optimal" code (e.g. a single C<rol> or a combination of C<shld> on |
|
|
574 | x86). |
434 | |
575 | |
435 | =back |
576 | =back |
436 | |
577 | |
437 | =head2 ARITHMETIC |
578 | =head2 ARITHMETIC |
438 | |
579 | |
… | |
… | |
448 | C<ecb_mod> implements the mathematical modulo operation, which is missing |
589 | C<ecb_mod> implements the mathematical modulo operation, which is missing |
449 | in the language. |
590 | in the language. |
450 | |
591 | |
451 | C<n> must be strictly positive (i.e. C<< >= 1 >>), while C<m> must be |
592 | C<n> must be strictly positive (i.e. C<< >= 1 >>), while C<m> must be |
452 | negatable, that is, both C<m> and C<-m> must be representable in its |
593 | negatable, that is, both C<m> and C<-m> must be representable in its |
453 | type (this typically includes the minimum signed integer value, the same |
594 | type (this typically excludes the minimum signed integer value, the same |
454 | limitation as for C</> and C<%> in C). |
595 | limitation as for C</> and C<%> in C). |
455 | |
596 | |
456 | Current GCC versions compile this into an efficient branchless sequence on |
597 | Current GCC versions compile this into an efficient branchless sequence on |
457 | many systems. |
598 | almost all CPUs. |
458 | |
599 | |
459 | For example, when you want to rotate forward through the members of an |
600 | For example, when you want to rotate forward through the members of an |
460 | array for increasing C<m> (which might be negative), then you should use |
601 | array for increasing C<m> (which might be negative), then you should use |
461 | C<ecb_mod>, as the C<%> operator might give either negative results, or |
602 | C<ecb_mod>, as the C<%> operator might give either negative results, or |
462 | change direction for negative values: |
603 | change direction for negative values: |
463 | |
604 | |
464 | for (m = -100; m <= 100; ++m) |
605 | for (m = -100; m <= 100; ++m) |
465 | int elem = myarray [ecb_mod (m, ecb_array_length (myarray))]; |
606 | int elem = myarray [ecb_mod (m, ecb_array_length (myarray))]; |
466 | |
607 | |
|
|
608 | =item x = ecb_div_rd (val, div) |
|
|
609 | |
|
|
610 | =item x = ecb_div_ru (val, div) |
|
|
611 | |
|
|
612 | Returns C<val> divided by C<div> rounded down or up, respectively. |
|
|
613 | C<val> and C<div> must have integer types and C<div> must be strictly |
|
|
614 | positive. Note that these functions are implemented with macros in C |
|
|
615 | and with function templates in C++. |
|
|
616 | |
467 | =back |
617 | =back |
468 | |
618 | |
469 | =head2 UTILITY |
619 | =head2 UTILITY |
470 | |
620 | |
471 | =over 4 |
621 | =over 4 |
… | |
… | |
480 | for (i = 0; i < ecb_array_length (primes); i++) |
630 | for (i = 0; i < ecb_array_length (primes); i++) |
481 | sum += primes [i]; |
631 | sum += primes [i]; |
482 | |
632 | |
483 | =back |
633 | =back |
484 | |
634 | |
|
|
635 | =head2 SYMBOLS GOVERNING COMPILATION OF ECB.H ITSELF |
485 | |
636 | |
|
|
637 | These symbols need to be defined before including F<ecb.h> the first time. |
|
|
638 | |
|
|
639 | =over 4 |
|
|
640 | |
|
|
641 | =item ECB_NO_THRADS |
|
|
642 | |
|
|
643 | If F<ecb.h> is never used from multiple threads, then this symbol can |
|
|
644 | be defined, in which case memory fences (and similar constructs) are |
|
|
645 | completely removed, leading to more efficient code and fewer dependencies. |
|
|
646 | |
|
|
647 | Setting this symbol to a true value implies C<ECB_NO_SMP>. |
|
|
648 | |
|
|
649 | =item ECB_NO_SMP |
|
|
650 | |
|
|
651 | The weaker version of C<ECB_NO_THREADS> - if F<ecb.h> is used from |
|
|
652 | multiple threads, but never concurrently (e.g. if the system the program |
|
|
653 | runs on has only a single CPU with a single core, no hyperthreading and so |
|
|
654 | on), then this symbol can be defined, leading to more efficient code and |
|
|
655 | fewer dependencies. |
|
|
656 | |
|
|
657 | =back |
|
|
658 | |
|
|
659 | |