From 52ac4c6be8664e9dab5b90e7c64df03985791893 Mon Sep 17 00:00:00 2001 From: Richard Biener Date: Wed, 14 Feb 2024 14:00:23 +0100 Subject: [PATCH] [libiberty] remove TBAA violation in iterative_hash, improve code-gen The following removes the TBAA violation present in iterative_hash. As we eventually LTO that it's important to fix. This also improves code generation for the >= 12 bytes loop by using | to compose the 4 byte words as at least GCC 7 and up can recognize that pattern and perform a 4 byte load while the variant with a + is not recognized (not on trunk either), I think we have an enhancement bug for this somewhere. Given we reliably merge and the bogus "optimized" path might be only relevant for archs that cannot do misaligned loads efficiently I've chosen to keep a specialization for aligned accesses. libiberty/ * hashtab.c (iterative_hash): Remove TBAA violating handling of aligned little-endian case in favor of just keeping the aligned case special-cased. Use | for composing a larger word. --- libiberty/hashtab.c | 23 ++++++++++------------- 1 file changed, 10 insertions(+), 13 deletions(-) diff --git a/libiberty/hashtab.c b/libiberty/hashtab.c index 48f28078114..e3a07256a30 100644 --- a/libiberty/hashtab.c +++ b/libiberty/hashtab.c @@ -940,26 +940,23 @@ iterative_hash (const void *k_in /* the key */, c = initval; /* the previous hash value */ /*---------------------------------------- handle most of the key */ -#ifndef WORDS_BIGENDIAN - /* On a little-endian machine, if the data is 4-byte aligned we can hash - by word for better speed. This gives nondeterministic results on - big-endian machines. */ - if (sizeof (hashval_t) == 4 && (((size_t)k)&3) == 0) - while (len >= 12) /* aligned */ + /* Provide specialization for the aligned case for targets that cannot + efficiently perform misaligned loads of a merged access. */ + if ((((size_t)k)&3) == 0) + while (len >= 12) { - a += *(hashval_t *)(k+0); - b += *(hashval_t *)(k+4); - c += *(hashval_t *)(k+8); + a += (k[0] | ((hashval_t)k[1]<<8) | ((hashval_t)k[2]<<16) | ((hashval_t)k[3]<<24)); + b += (k[4] | ((hashval_t)k[5]<<8) | ((hashval_t)k[6]<<16) | ((hashval_t)k[7]<<24)); + c += (k[8] | ((hashval_t)k[9]<<8) | ((hashval_t)k[10]<<16)| ((hashval_t)k[11]<<24)); mix(a,b,c); k += 12; len -= 12; } else /* unaligned */ -#endif while (len >= 12) { - a += (k[0] +((hashval_t)k[1]<<8) +((hashval_t)k[2]<<16) +((hashval_t)k[3]<<24)); - b += (k[4] +((hashval_t)k[5]<<8) +((hashval_t)k[6]<<16) +((hashval_t)k[7]<<24)); - c += (k[8] +((hashval_t)k[9]<<8) +((hashval_t)k[10]<<16)+((hashval_t)k[11]<<24)); + a += (k[0] | ((hashval_t)k[1]<<8) | ((hashval_t)k[2]<<16) | ((hashval_t)k[3]<<24)); + b += (k[4] | ((hashval_t)k[5]<<8) | ((hashval_t)k[6]<<16) | ((hashval_t)k[7]<<24)); + c += (k[8] | ((hashval_t)k[9]<<8) | ((hashval_t)k[10]<<16)| ((hashval_t)k[11]<<24)); mix(a,b,c); k += 12; len -= 12; }