diff options
Diffstat (limited to 'src/backend/utils/adt/numeric.c')
| -rw-r--r-- | src/backend/utils/adt/numeric.c | 15 |
1 files changed, 12 insertions, 3 deletions
diff --git a/src/backend/utils/adt/numeric.c b/src/backend/utils/adt/numeric.c index ed825a1fddf..d2a42b811da 100644 --- a/src/backend/utils/adt/numeric.c +++ b/src/backend/utils/adt/numeric.c @@ -8191,6 +8191,7 @@ mul_var(const NumericVar *var1, const NumericVar *var2, NumericVar *result, int res_weight; int maxdigits; int *dig; + int *dig_i1_2; int carry; int maxdig; int newdig; @@ -8327,10 +8328,18 @@ mul_var(const NumericVar *var1, const NumericVar *var2, NumericVar *result, * * As above, digits of var2 can be ignored if they don't contribute, * so we only include digits for which i1+i2+2 <= res_ndigits - 1. + * + * This inner loop is the performance bottleneck for multiplication, + * so we want to keep it simple enough so that it can be + * auto-vectorized. Accordingly, process the digits left-to-right + * even though schoolbook multiplication would suggest right-to-left. + * Since we aren't propagating carries in this loop, the order does + * not matter. */ - for (i2 = Min(var2ndigits - 1, res_ndigits - i1 - 3), i = i1 + i2 + 2; - i2 >= 0; i2--) - dig[i--] += var1digit * var2digits[i2]; + i = Min(var2ndigits - 1, res_ndigits - i1 - 3); + dig_i1_2 = &dig[i1 + 2]; + for (i2 = 0; i2 <= i; i2++) + dig_i1_2[i2] += var1digit * var2digits[i2]; } /* |