Potential optimizations applied to jkeiser/array-assert (#1421)
* Some tuning. * Using table lookups...
This commit is contained in:
Daniel Lemire
GitHub
parent
fe726b0f80
commit
0e18453e34
|
|
@ -423,7 +423,7 @@ simdjson_really_inline error_code parse_exponent(simdjson_unused const uint8_t *
|
|||
return SUCCESS;
|
||||
}
|
||||
|
||||
simdjson_really_inline int significant_digits(const uint8_t * start_digits, int digit_count) {
|
||||
simdjson_really_inline size_t significant_digits(const uint8_t * start_digits, size_t digit_count) {
|
||||
// It is possible that the integer had an overflow.
|
||||
// We have to handle the case where we have 0.0000somenumber.
|
||||
const uint8_t *start = start_digits;
|
||||
|
|
@ -431,11 +431,11 @@ simdjson_really_inline int significant_digits(const uint8_t * start_digits, int
|
|||
start++;
|
||||
}
|
||||
// we over-decrement by one when there is a '.'
|
||||
return digit_count - int(start - start_digits);
|
||||
return digit_count - size_t(start - start_digits);
|
||||
}
|
||||
|
||||
template<typename W>
|
||||
simdjson_really_inline error_code write_float(const uint8_t *const src, bool negative, uint64_t i, const uint8_t * start_digits, int digit_count, int64_t exponent, W &writer) {
|
||||
simdjson_really_inline error_code write_float(const uint8_t *const src, bool negative, uint64_t i, const uint8_t * start_digits, size_t digit_count, int64_t exponent, W &writer) {
|
||||
// If we frequently had to deal with long strings of digits,
|
||||
// we could extend our code by using a 128-bit integer instead
|
||||
// of a 64-bit integer. However, this is uncommon in practice.
|
||||
|
|
@ -529,7 +529,8 @@ simdjson_really_inline error_code parse_number(const uint8_t *const src, W &writ
|
|||
while (parse_digit(*p, i)) { p++; }
|
||||
|
||||
// If there were no digits, or if the integer starts with 0 and has more than one digit, it's an error.
|
||||
int digit_count = int(p - start_digits);
|
||||
// Optimization note: size_t is expected to be unsigned.
|
||||
size_t digit_count = size_t(p - start_digits);
|
||||
if (digit_count == 0 || ('0' == *start_digits && digit_count > 1)) { return INVALID_NUMBER(src); }
|
||||
|
||||
//
|
||||
|
|
@ -549,23 +550,23 @@ simdjson_really_inline error_code parse_number(const uint8_t *const src, W &writ
|
|||
SIMDJSON_TRY( parse_exponent(src, p, exponent) );
|
||||
}
|
||||
if (is_float) {
|
||||
const bool clean_end = jsoncharutils::is_structural_or_whitespace(*p);
|
||||
const bool dirty_end = jsoncharutils::is_not_structural_or_whitespace(*p);
|
||||
SIMDJSON_TRY( write_float(src, negative, i, start_digits, digit_count, exponent, writer) );
|
||||
if (!clean_end) { return INVALID_NUMBER(src); }
|
||||
if (dirty_end) { return INVALID_NUMBER(src); }
|
||||
return SUCCESS;
|
||||
}
|
||||
|
||||
// The longest negative 64-bit number is 19 digits.
|
||||
// The longest positive 64-bit number is 20 digits.
|
||||
// We do it this way so we don't trigger this branch unless we must.
|
||||
int longest_digit_count = negative ? 19 : 20;
|
||||
size_t longest_digit_count = negative ? 19 : 20;
|
||||
if (digit_count > longest_digit_count) { return INVALID_NUMBER(src); }
|
||||
if (digit_count == longest_digit_count) {
|
||||
if (negative) {
|
||||
// Anything negative above INT64_MAX+1 is invalid
|
||||
if (i > uint64_t(INT64_MAX)+1) { return INVALID_NUMBER(src); }
|
||||
WRITE_INTEGER(~i+1, src, writer);
|
||||
if (!jsoncharutils::is_structural_or_whitespace(*p)) { return INVALID_NUMBER(src); }
|
||||
if (jsoncharutils::is_not_structural_or_whitespace(*p)) { return INVALID_NUMBER(src); }
|
||||
return SUCCESS;
|
||||
// Positive overflow check:
|
||||
// - A 20 digit number starting with 2-9 is overflow, because 18,446,744,073,709,551,615 is the
|
||||
|
|
@ -588,16 +589,81 @@ simdjson_really_inline error_code parse_number(const uint8_t *const src, W &writ
|
|||
} else {
|
||||
WRITE_INTEGER(negative ? (~i+1) : i, src, writer);
|
||||
}
|
||||
if (!jsoncharutils::is_structural_or_whitespace(*p)) { return INVALID_NUMBER(src); }
|
||||
if (jsoncharutils::is_not_structural_or_whitespace(*p)) { return INVALID_NUMBER(src); }
|
||||
return SUCCESS;
|
||||
}
|
||||
|
||||
// SAX functions
|
||||
// Inlineable functions
|
||||
namespace {
|
||||
|
||||
// This table can be used to characterize the final character of an integer
|
||||
// string. For JSON structural character and allowable white space characters,
|
||||
// we return SUCCESS. For 'e', '.' and 'E', we return INCORRECT_TYPE. Otherwise
|
||||
// we return NUMBER_ERROR.
|
||||
// Optimization note: we could easily reduce the size of the table by half (to 128)
|
||||
// at the cost of an extra branch.
|
||||
// Optimization note: we want the values to use at most 8 bits (not, e.g., 32 bits):
|
||||
static_assert(error_code(uint8_t(NUMBER_ERROR))== NUMBER_ERROR, "bad NUMBER_ERROR cast");
|
||||
static_assert(error_code(uint8_t(SUCCESS))== SUCCESS, "bad NUMBER_ERROR cast");
|
||||
static_assert(error_code(uint8_t(INCORRECT_TYPE))== INCORRECT_TYPE, "bad NUMBER_ERROR cast");
|
||||
|
||||
const uint8_t integer_string_finisher[256] = {
|
||||
NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR,
|
||||
NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, SUCCESS,
|
||||
SUCCESS, NUMBER_ERROR, NUMBER_ERROR, SUCCESS, NUMBER_ERROR,
|
||||
NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR,
|
||||
NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR,
|
||||
NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR,
|
||||
NUMBER_ERROR, NUMBER_ERROR, SUCCESS, NUMBER_ERROR, NUMBER_ERROR,
|
||||
NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR,
|
||||
NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, SUCCESS,
|
||||
NUMBER_ERROR, INCORRECT_TYPE, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR,
|
||||
NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR,
|
||||
NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, SUCCESS, NUMBER_ERROR,
|
||||
NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR,
|
||||
NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, INCORRECT_TYPE,
|
||||
NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR,
|
||||
NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR,
|
||||
NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR,
|
||||
NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR,
|
||||
NUMBER_ERROR, SUCCESS, NUMBER_ERROR, SUCCESS, NUMBER_ERROR,
|
||||
NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR,
|
||||
NUMBER_ERROR, INCORRECT_TYPE, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR,
|
||||
NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR,
|
||||
NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR,
|
||||
NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR,
|
||||
NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, SUCCESS, NUMBER_ERROR,
|
||||
SUCCESS, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR,
|
||||
NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR,
|
||||
NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR,
|
||||
NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR,
|
||||
NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR,
|
||||
NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR,
|
||||
NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR,
|
||||
NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR,
|
||||
NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR,
|
||||
NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR,
|
||||
NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR,
|
||||
NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR,
|
||||
NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR,
|
||||
NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR,
|
||||
NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR,
|
||||
NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR,
|
||||
NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR,
|
||||
NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR,
|
||||
NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR,
|
||||
NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR,
|
||||
NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR,
|
||||
NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR,
|
||||
NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR,
|
||||
NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR,
|
||||
NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR,
|
||||
NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR, NUMBER_ERROR,
|
||||
NUMBER_ERROR};
|
||||
|
||||
// Parse any number from 0 to 18,446,744,073,709,551,615
|
||||
simdjson_unused simdjson_really_inline simdjson_result<uint64_t> parse_unsigned(const uint8_t * const src) noexcept {
|
||||
const uint8_t *p = src;
|
||||
|
||||
//
|
||||
// Parse the integer part.
|
||||
//
|
||||
|
|
@ -607,16 +673,23 @@ simdjson_unused simdjson_really_inline simdjson_result<uint64_t> parse_unsigned(
|
|||
while (parse_digit(*p, i)) { p++; }
|
||||
|
||||
// If there were no digits, or if the integer starts with 0 and has more than one digit, it's an error.
|
||||
int digit_count = int(p - start_digits);
|
||||
if (digit_count == 0) { return INCORRECT_TYPE; }
|
||||
if ('0' == *start_digits && digit_count > 1) { return NUMBER_ERROR; }
|
||||
if (!jsoncharutils::is_structural_or_whitespace(*p)) {
|
||||
return (*p == '.' || *p == 'e' || *p == 'E') ? INCORRECT_TYPE : NUMBER_ERROR;
|
||||
}
|
||||
|
||||
// Optimization note: size_t is expected to be unsigned.
|
||||
size_t digit_count = size_t(p - start_digits);
|
||||
// The longest positive 64-bit number is 20 digits.
|
||||
// We do it this way so we don't trigger this branch unless we must.
|
||||
if (digit_count > 20) { return INCORRECT_TYPE; }
|
||||
// Optimization note: the compiler can probably merge
|
||||
// ((digit_count == 0) || (digit_count > 20))
|
||||
// into a single branch since digit_count is unsigned.
|
||||
if ((digit_count == 0) || (digit_count > 20)) { return INCORRECT_TYPE; }
|
||||
// Here digit_count > 0.
|
||||
if (('0' == *start_digits) && (digit_count > 1)) { return NUMBER_ERROR; }
|
||||
// We can do the following...
|
||||
// if (!jsoncharutils::is_structural_or_whitespace(*p)) {
|
||||
// return (*p == '.' || *p == 'e' || *p == 'E') ? INCORRECT_TYPE : NUMBER_ERROR;
|
||||
// }
|
||||
// as a single table lookup:
|
||||
if (integer_string_finisher[*p] != SUCCESS) { return error_code(integer_string_finisher[*p]); }
|
||||
|
||||
if (digit_count == 20) {
|
||||
// Positive overflow check:
|
||||
// - A 20 digit number starting with 2-9 is overflow, because 18,446,744,073,709,551,615 is the
|
||||
|
|
@ -653,18 +726,24 @@ simdjson_unused simdjson_really_inline simdjson_result<int64_t> parse_integer(co
|
|||
while (parse_digit(*p, i)) { p++; }
|
||||
|
||||
// If there were no digits, or if the integer starts with 0 and has more than one digit, it's an error.
|
||||
int digit_count = int(p - start_digits);
|
||||
if (digit_count == 0) { return INCORRECT_TYPE; }
|
||||
if ('0' == *start_digits && digit_count > 1) { return NUMBER_ERROR; }
|
||||
if (!jsoncharutils::is_structural_or_whitespace(*p)) {
|
||||
return (*p == '.' || *p == 'e' || *p == 'E') ? INCORRECT_TYPE : NUMBER_ERROR;
|
||||
}
|
||||
|
||||
// Optimization note: size_t is expected to be unsigned.
|
||||
size_t digit_count = size_t(p - start_digits);
|
||||
// The longest negative 64-bit number is 19 digits.
|
||||
// The longest positive 64-bit number is 20 digits.
|
||||
// We do it this way so we don't trigger this branch unless we must.
|
||||
int longest_digit_count = negative ? 19 : 20;
|
||||
if (digit_count > longest_digit_count) { return INCORRECT_TYPE; }
|
||||
size_t longest_digit_count = negative ? 19 : 20;
|
||||
// Optimization note: the compiler can probably merge
|
||||
// ((digit_count == 0) || (digit_count > longest_digit_count))
|
||||
// into a single branch since digit_count is unsigned.
|
||||
if ((digit_count == 0) || (digit_count > longest_digit_count)) { return INCORRECT_TYPE; }
|
||||
// Here digit_count > 0.
|
||||
if (('0' == *start_digits) && (digit_count > 1)) { return NUMBER_ERROR; }
|
||||
// We can do the following...
|
||||
// if (!jsoncharutils::is_structural_or_whitespace(*p)) {
|
||||
// return (*p == '.' || *p == 'e' || *p == 'E') ? INCORRECT_TYPE : NUMBER_ERROR;
|
||||
// }
|
||||
// as a single table lookup:
|
||||
if(integer_string_finisher[*p] != SUCCESS) { return error_code(integer_string_finisher[*p]); }
|
||||
if (digit_count == longest_digit_count) {
|
||||
if (negative) {
|
||||
// Anything negative above INT64_MAX+1 is invalid
|
||||
|
|
|
|||
Loading…
Reference in New Issue