diff options
Diffstat (limited to 'gcc/config/i386/i386.c')
| -rw-r--r-- | gcc/config/i386/i386.c | 190 |
1 files changed, 190 insertions, 0 deletions
diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c index fd4bb671ad9..6d2fd69350d 100644 --- a/gcc/config/i386/i386.c +++ b/gcc/config/i386/i386.c @@ -43690,6 +43690,184 @@ ix86_memmodel_check (unsigned HOST_WIDE_INT val) return val; } +/* Set CLONEI->vecsize_mangle, CLONEI->vecsize_int, + CLONEI->vecsize_float and if CLONEI->simdlen is 0, also + CLONEI->simdlen. Return 0 if SIMD clones shouldn't be emitted, + or number of vecsize_mangle variants that should be emitted. */ + +static int +ix86_simd_clone_compute_vecsize_and_simdlen (struct cgraph_node *node, + struct cgraph_simd_clone *clonei, + tree base_type, int num) +{ + int ret = 1; + + if (clonei->simdlen + && (clonei->simdlen < 2 + || clonei->simdlen > 16 + || (clonei->simdlen & (clonei->simdlen - 1)) != 0)) + { + warning_at (DECL_SOURCE_LOCATION (node->decl), 0, + "unsupported simdlen %d\n", clonei->simdlen); + return 0; + } + + tree ret_type = TREE_TYPE (TREE_TYPE (node->decl)); + if (TREE_CODE (ret_type) != VOID_TYPE) + switch (TYPE_MODE (ret_type)) + { + case QImode: + case HImode: + case SImode: + case DImode: + case SFmode: + case DFmode: + /* case SCmode: */ + /* case DCmode: */ + break; + default: + warning_at (DECL_SOURCE_LOCATION (node->decl), 0, + "unsupported return type %qT for simd\n", ret_type); + return 0; + } + + tree t; + int i; + + for (t = DECL_ARGUMENTS (node->decl), i = 0; t; t = DECL_CHAIN (t), i++) + /* FIXME: Shouldn't we allow such arguments if they are uniform? */ + switch (TYPE_MODE (TREE_TYPE (t))) + { + case QImode: + case HImode: + case SImode: + case DImode: + case SFmode: + case DFmode: + /* case SCmode: */ + /* case DCmode: */ + break; + default: + warning_at (DECL_SOURCE_LOCATION (node->decl), 0, + "unsupported argument type %qT for simd\n", TREE_TYPE (t)); + return 0; + } + + if (clonei->cilk_elemental) + { + /* Parse here processor clause. If not present, default to 'b'. */ + clonei->vecsize_mangle = 'b'; + } + else if (!TREE_PUBLIC (node->decl)) + { + /* If the function isn't exported, we can pick up just one ISA + for the clones. */ + if (TARGET_AVX2) + clonei->vecsize_mangle = 'd'; + else if (TARGET_AVX) + clonei->vecsize_mangle = 'c'; + else + clonei->vecsize_mangle = 'b'; + ret = 1; + } + else + { + clonei->vecsize_mangle = "bcd"[num]; + ret = 3; + } + switch (clonei->vecsize_mangle) + { + case 'b': + clonei->vecsize_int = 128; + clonei->vecsize_float = 128; + break; + case 'c': + clonei->vecsize_int = 128; + clonei->vecsize_float = 256; + break; + case 'd': + clonei->vecsize_int = 256; + clonei->vecsize_float = 256; + break; + } + if (clonei->simdlen == 0) + { + if (SCALAR_INT_MODE_P (TYPE_MODE (base_type))) + clonei->simdlen = clonei->vecsize_int; + else + clonei->simdlen = clonei->vecsize_float; + clonei->simdlen /= GET_MODE_BITSIZE (TYPE_MODE (base_type)); + if (clonei->simdlen > 16) + clonei->simdlen = 16; + } + return ret; +} + +/* Add target attribute to SIMD clone NODE if needed. */ + +static void +ix86_simd_clone_adjust (struct cgraph_node *node) +{ + const char *str = NULL; + gcc_assert (node->decl == cfun->decl); + switch (node->simdclone->vecsize_mangle) + { + case 'b': + if (!TARGET_SSE2) + str = "sse2"; + break; + case 'c': + if (!TARGET_AVX) + str = "avx"; + break; + case 'd': + if (!TARGET_AVX2) + str = "avx2"; + break; + default: + gcc_unreachable (); + } + if (str == NULL) + return; + push_cfun (NULL); + tree args = build_tree_list (NULL_TREE, build_string (strlen (str), str)); + bool ok = ix86_valid_target_attribute_p (node->decl, NULL, args, 0); + gcc_assert (ok); + pop_cfun (); + ix86_previous_fndecl = NULL_TREE; + ix86_set_current_function (node->decl); +} + +/* If SIMD clone NODE can't be used in a vectorized loop + in current function, return -1, otherwise return a badness of using it + (0 if it is most desirable from vecsize_mangle point of view, 1 + slightly less desirable, etc.). */ + +static int +ix86_simd_clone_usable (struct cgraph_node *node) +{ + switch (node->simdclone->vecsize_mangle) + { + case 'b': + if (!TARGET_SSE2) + return -1; + if (!TARGET_AVX) + return 0; + return TARGET_AVX2 ? 2 : 1; + case 'c': + if (!TARGET_AVX) + return -1; + return TARGET_AVX2 ? 1 : 0; + break; + case 'd': + if (!TARGET_AVX2) + return -1; + return 0; + default: + gcc_unreachable (); + } +} + /* Implement TARGET_FLOAT_EXCEPTIONS_ROUNDING_SUPPORTED_P. */ static bool @@ -44178,6 +44356,18 @@ ix86_atomic_assign_expand_fenv (tree *hold, tree *clear, tree *update) #undef TARGET_SPILL_CLASS #define TARGET_SPILL_CLASS ix86_spill_class +#undef TARGET_SIMD_CLONE_COMPUTE_VECSIZE_AND_SIMDLEN +#define TARGET_SIMD_CLONE_COMPUTE_VECSIZE_AND_SIMDLEN \ + ix86_simd_clone_compute_vecsize_and_simdlen + +#undef TARGET_SIMD_CLONE_ADJUST +#define TARGET_SIMD_CLONE_ADJUST \ + ix86_simd_clone_adjust + +#undef TARGET_SIMD_CLONE_USABLE +#define TARGET_SIMD_CLONE_USABLE \ + ix86_simd_clone_usable + #undef TARGET_FLOAT_EXCEPTIONS_ROUNDING_SUPPORTED_P #define TARGET_FLOAT_EXCEPTIONS_ROUNDING_SUPPORTED_P \ ix86_float_exceptions_rounding_supported_p |