diff options
| author | Jakub Jelinek <jakub@redhat.com> | 2013-06-28 11:28:40 +0200 |
|---|---|---|
| committer | Jakub Jelinek <jakub@gcc.gnu.org> | 2013-06-28 11:28:40 +0200 |
| commit | 4ea3d77451d330e8bae29bae981814673dc3b746 (patch) | |
| tree | 6bb2542aeca126f3ed7209d470724896cf4de0ba /libgcc/libgcc2.c | |
| parent | ebf8f0eaebb0ede888d8d86719d7cbd82a5f6270 (diff) | |
| download | gcc-4ea3d77451d330e8bae29bae981814673dc3b746.zip gcc-4ea3d77451d330e8bae29bae981814673dc3b746.tar.gz gcc-4ea3d77451d330e8bae29bae981814673dc3b746.tar.bz2 | |
re PR middle-end/36041 (Speed up builtin_popcountll)
PR middle-end/36041
* libgcc2.c (POPCOUNTCST2, POPCOUNTCST4, POPCOUNTCST8, POPCOUNTCST):
Define.
(__popcountSI2): For __SIZEOF_INT__ > 2 targets use arithmetics
instead of table lookups.
(__popcountDI2): Likewise.
From-SVN: r200506
Diffstat (limited to 'libgcc/libgcc2.c')
| -rw-r--r-- | libgcc/libgcc2.c | 41 |
1 files changed, 41 insertions, 0 deletions
diff --git a/libgcc/libgcc2.c b/libgcc/libgcc2.c index 9138c1e..a47d8af 100644 --- a/libgcc/libgcc2.c +++ b/libgcc/libgcc2.c @@ -819,17 +819,42 @@ const UQItype __popcount_tab[256] = }; #endif +#if defined(L_popcountsi2) || defined(L_popcountdi2) +#define POPCOUNTCST2(x) (((UWtype) x << BITS_PER_UNIT) | x) +#define POPCOUNTCST4(x) (((UWtype) x << (2 * BITS_PER_UNIT)) | x) +#define POPCOUNTCST8(x) (((UWtype) x << (4 * BITS_PER_UNIT)) | x) +#if W_TYPE_SIZE == BITS_PER_UNIT +#define POPCOUNTCST(x) x +#elif W_TYPE_SIZE == 2 * BITS_PER_UNIT +#define POPCOUNTCST(x) POPCOUNTCST2 (x) +#elif W_TYPE_SIZE == 4 * BITS_PER_UNIT +#define POPCOUNTCST(x) POPCOUNTCST4 (POPCOUNTCST2 (x)) +#elif W_TYPE_SIZE == 8 * BITS_PER_UNIT +#define POPCOUNTCST(x) POPCOUNTCST8 (POPCOUNTCST4 (POPCOUNTCST2 (x))) +#endif +#endif + #ifdef L_popcountsi2 #undef int int __popcountSI2 (UWtype x) { + /* Force table lookup on targets like AVR and RL78 which only + pretend they have LIBGCC2_UNITS_PER_WORD 4, but actually + have 1, and other small word targets. */ +#if __SIZEOF_INT__ > 2 && defined (POPCOUNTCST) && BITS_PER_UNIT == 8 + x = x - ((x >> 1) & POPCOUNTCST (0x55)); + x = (x & POPCOUNTCST (0x33)) + ((x >> 2) & POPCOUNTCST (0x33)); + x = (x + (x >> 4)) & POPCOUNTCST (0x0F); + return (x * POPCOUNTCST (0x01)) >> (W_TYPE_SIZE - BITS_PER_UNIT); +#else int i, ret = 0; for (i = 0; i < W_TYPE_SIZE; i += 8) ret += __popcount_tab[(x >> i) & 0xff]; return ret; +#endif } #endif @@ -838,12 +863,28 @@ __popcountSI2 (UWtype x) int __popcountDI2 (UDWtype x) { + /* Force table lookup on targets like AVR and RL78 which only + pretend they have LIBGCC2_UNITS_PER_WORD 4, but actually + have 1, and other small word targets. */ +#if __SIZEOF_INT__ > 2 && defined (POPCOUNTCST) && BITS_PER_UNIT == 8 + const DWunion uu = {.ll = x}; + UWtype x1 = uu.s.low, x2 = uu.s.high; + x1 = x1 - ((x1 >> 1) & POPCOUNTCST (0x55)); + x2 = x2 - ((x2 >> 1) & POPCOUNTCST (0x55)); + x1 = (x1 & POPCOUNTCST (0x33)) + ((x1 >> 2) & POPCOUNTCST (0x33)); + x2 = (x2 & POPCOUNTCST (0x33)) + ((x2 >> 2) & POPCOUNTCST (0x33)); + x1 = (x1 + (x1 >> 4)) & POPCOUNTCST (0x0F); + x2 = (x2 + (x2 >> 4)) & POPCOUNTCST (0x0F); + x1 += x2; + return (x1 * POPCOUNTCST (0x01)) >> (W_TYPE_SIZE - BITS_PER_UNIT); +#else int i, ret = 0; for (i = 0; i < 2*W_TYPE_SIZE; i += 8) ret += __popcount_tab[(x >> i) & 0xff]; return ret; +#endif } #endif |