… | |
… | |
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 |
|
|
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>). |
58 | |
69 | |
59 | =head2 GCC ATTRIBUTES |
70 | =head2 GCC ATTRIBUTES |
60 | |
71 | |
61 | A major part of libecb deals with GCC attributes. These are additional |
72 | A major part of libecb deals with GCC attributes. These are additional |
62 | attributes that you can assign to functions, variables and sometimes even |
73 | attributes that you can assign to functions, variables and sometimes even |
… | |
… | |
101 | #else |
112 | #else |
102 | return 0; |
113 | return 0; |
103 | #endif |
114 | #endif |
104 | } |
115 | } |
105 | |
116 | |
|
|
117 | =item ecb_inline |
|
|
118 | |
|
|
119 | This is not actually an attribute, but you use it like one. It expands |
|
|
120 | either to C<static inline> or to just C<static>, if inline isn't |
|
|
121 | supported. It should be used to declare functions that should be inlined, |
|
|
122 | for code size or speed reasons. |
|
|
123 | |
|
|
124 | Example: inline this function, it surely will reduce codesize. |
|
|
125 | |
|
|
126 | ecb_inline int |
|
|
127 | negmul (int a, int b) |
|
|
128 | { |
|
|
129 | return - (a * b); |
|
|
130 | } |
|
|
131 | |
106 | =item ecb_noinline |
132 | =item ecb_noinline |
107 | |
133 | |
108 | Prevent a function from being inlined - it might be optimised away, but |
134 | 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 |
135 | 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. |
136 | 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 |
407 | After processing the node, (part of) the next node might already be in |
382 | cache. |
408 | cache. |
383 | |
409 | |
384 | =back |
410 | =back |
385 | |
411 | |
386 | =head2 BIT FIDDLING / BITSTUFFS |
412 | =head2 BIT FIDDLING / BIT WIZARDRY |
387 | |
413 | |
388 | =over 4 |
414 | =over 4 |
389 | |
415 | |
390 | =item bool ecb_big_endian () |
416 | =item bool ecb_big_endian () |
391 | |
417 | |
… | |
… | |
397 | |
423 | |
398 | On systems that are neither, their return values are unspecified. |
424 | On systems that are neither, their return values are unspecified. |
399 | |
425 | |
400 | =item int ecb_ctz32 (uint32_t x) |
426 | =item int ecb_ctz32 (uint32_t x) |
401 | |
427 | |
|
|
428 | =item int ecb_ctz64 (uint64_t x) |
|
|
429 | |
402 | Returns the index of the least significant bit set in C<x> (or |
430 | 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 |
431 | 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 |
432 | 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 |
433 | |
|
|
434 | For smaller types than C<uint32_t> you can safely use C<ecb_ctz32>. |
|
|
435 | |
406 | (n))>. For example: |
436 | For example: |
407 | |
437 | |
408 | ecb_ctz32 (3) = 0 |
438 | ecb_ctz32 (3) = 0 |
409 | ecb_ctz32 (6) = 1 |
439 | ecb_ctz32 (6) = 1 |
410 | |
440 | |
|
|
441 | =item bool ecb_is_pot32 (uint32_t x) |
|
|
442 | |
|
|
443 | =item bool ecb_is_pot64 (uint32_t x) |
|
|
444 | |
|
|
445 | Return true iff C<x> is a power of two or C<x == 0>. |
|
|
446 | |
|
|
447 | For smaller types then C<uint32_t> you can safely use C<ecb_is_pot32>. |
|
|
448 | |
|
|
449 | =item int ecb_ld32 (uint32_t x) |
|
|
450 | |
|
|
451 | =item int ecb_ld64 (uint64_t x) |
|
|
452 | |
|
|
453 | Returns the index of the most significant bit set in C<x>, or the number |
|
|
454 | of digits the number requires in binary (so that C<< 2**ld <= x < |
|
|
455 | 2**(ld+1) >>). If C<x> is 0 the result is undefined. A common use case is |
|
|
456 | to compute the integer binary logarithm, i.e. C<floor (log2 (n))>, for |
|
|
457 | example to see how many bits a certain number requires to be encoded. |
|
|
458 | |
|
|
459 | This function is similar to the "count leading zero bits" function, except |
|
|
460 | that that one returns how many zero bits are "in front" of the number (in |
|
|
461 | the given data type), while C<ecb_ld> returns how many bits the number |
|
|
462 | itself requires. |
|
|
463 | |
|
|
464 | For smaller types than C<uint32_t> you can safely use C<ecb_ld32>. |
|
|
465 | |
411 | =item int ecb_popcount32 (uint32_t x) |
466 | =item int ecb_popcount32 (uint32_t x) |
412 | |
467 | |
|
|
468 | =item int ecb_popcount64 (uint64_t x) |
|
|
469 | |
413 | Returns the number of bits set to 1 in C<x>. For example: |
470 | Returns the number of bits set to 1 in C<x>. |
|
|
471 | |
|
|
472 | For smaller types than C<uint32_t> you can safely use C<ecb_popcount32>. |
|
|
473 | |
|
|
474 | For example: |
414 | |
475 | |
415 | ecb_popcount32 (7) = 3 |
476 | ecb_popcount32 (7) = 3 |
416 | ecb_popcount32 (255) = 8 |
477 | ecb_popcount32 (255) = 8 |
417 | |
478 | |
|
|
479 | =item uint8_t ecb_bitrev8 (uint8_t x) |
|
|
480 | |
|
|
481 | =item uint16_t ecb_bitrev16 (uint16_t x) |
|
|
482 | |
|
|
483 | =item uint32_t ecb_bitrev32 (uint32_t x) |
|
|
484 | |
|
|
485 | Reverses the bits in x, i.e. the MSB becomes the LSB, MSB-1 becomes LSB+1 |
|
|
486 | and so on. |
|
|
487 | |
|
|
488 | Example: |
|
|
489 | |
|
|
490 | ecb_bitrev8 (0xa7) = 0xea |
|
|
491 | ecb_bitrev32 (0xffcc4411) = 0x882233ff |
|
|
492 | |
418 | =item uint32_t ecb_bswap16 (uint32_t x) |
493 | =item uint32_t ecb_bswap16 (uint32_t x) |
419 | |
494 | |
420 | =item uint32_t ecb_bswap32 (uint32_t x) |
495 | =item uint32_t ecb_bswap32 (uint32_t x) |
421 | |
496 | |
|
|
497 | =item uint64_t ecb_bswap64 (uint64_t x) |
|
|
498 | |
422 | These two functions return the value of the 16-bit (32-bit) value C<x> |
499 | These functions return the value of the 16-bit (32-bit, 64-bit) value |
423 | after reversing the order of bytes (0x11223344 becomes 0x44332211). |
500 | C<x> after reversing the order of bytes (0x11223344 becomes 0x44332211 in |
|
|
501 | C<ecb_bswap32>). |
|
|
502 | |
|
|
503 | =item uint8_t ecb_rotl8 (uint8_t x, unsigned int count) |
|
|
504 | |
|
|
505 | =item uint16_t ecb_rotl16 (uint16_t x, unsigned int count) |
|
|
506 | |
|
|
507 | =item uint32_t ecb_rotl32 (uint32_t x, unsigned int count) |
|
|
508 | |
|
|
509 | =item uint64_t ecb_rotl64 (uint64_t x, unsigned int count) |
|
|
510 | |
|
|
511 | =item uint8_t ecb_rotr8 (uint8_t x, unsigned int count) |
|
|
512 | |
|
|
513 | =item uint16_t ecb_rotr16 (uint16_t x, unsigned int count) |
424 | |
514 | |
425 | =item uint32_t ecb_rotr32 (uint32_t x, unsigned int count) |
515 | =item uint32_t ecb_rotr32 (uint32_t x, unsigned int count) |
426 | |
516 | |
427 | =item uint32_t ecb_rotl32 (uint32_t x, unsigned int count) |
517 | =item uint64_t ecb_rotr64 (uint64_t x, unsigned int count) |
428 | |
518 | |
429 | These two functions return the value of C<x> after rotating all the bits |
519 | These two families of functions return the value of C<x> after rotating |
430 | by C<count> positions to the right or left respectively. |
520 | all the bits by C<count> positions to the right (C<ecb_rotr>) or left |
|
|
521 | (C<ecb_rotl>). |
431 | |
522 | |
432 | Current GCC versions understand these functions and usually compile them |
523 | Current GCC versions understand these functions and usually compile them |
433 | to "optimal" code (e.g. a single C<roll> on x86). |
524 | to "optimal" code (e.g. a single C<rol> or a combination of C<shld> on |
|
|
525 | x86). |
434 | |
526 | |
435 | =back |
527 | =back |
436 | |
528 | |
437 | =head2 ARITHMETIC |
529 | =head2 ARITHMETIC |
438 | |
530 | |
… | |
… | |
448 | C<ecb_mod> implements the mathematical modulo operation, which is missing |
540 | C<ecb_mod> implements the mathematical modulo operation, which is missing |
449 | in the language. |
541 | in the language. |
450 | |
542 | |
451 | C<n> must be strictly positive (i.e. C<< >= 1 >>), while C<m> must be |
543 | 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 |
544 | 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 |
545 | type (this typically excludes the minimum signed integer value, the same |
454 | limitation as for C</> and C<%> in C). |
546 | limitation as for C</> and C<%> in C). |
455 | |
547 | |
456 | Current GCC versions compile this into an efficient branchless sequence on |
548 | Current GCC versions compile this into an efficient branchless sequence on |
457 | almost all CPUs. |
549 | almost all CPUs. |
458 | |
550 | |
… | |
… | |
462 | change direction for negative values: |
554 | change direction for negative values: |
463 | |
555 | |
464 | for (m = -100; m <= 100; ++m) |
556 | for (m = -100; m <= 100; ++m) |
465 | int elem = myarray [ecb_mod (m, ecb_array_length (myarray))]; |
557 | int elem = myarray [ecb_mod (m, ecb_array_length (myarray))]; |
466 | |
558 | |
|
|
559 | =item x = ecb_div_rd (val, div) |
|
|
560 | |
|
|
561 | =item x = ecb_div_ru (val, div) |
|
|
562 | |
|
|
563 | Returns C<val> divided by C<div> rounded down or up, respectively. |
|
|
564 | C<val> and C<div> must have integer types and C<div> must be strictly |
|
|
565 | positive. Note that these functions are implemented with macros in C |
|
|
566 | and with function templates in C++. |
|
|
567 | |
467 | =back |
568 | =back |
468 | |
569 | |
469 | =head2 UTILITY |
570 | =head2 UTILITY |
470 | |
571 | |
471 | =over 4 |
572 | =over 4 |