diff options
author | Martin Liska <mliska@suse.cz> | 2021-12-15 10:54:23 +0100 |
---|---|---|
committer | Martin Liska <mliska@suse.cz> | 2022-05-11 11:03:18 +0200 |
commit | ef14bba0a6f3836d41d75863e6516d21aef0e936 (patch) | |
tree | 83486d168a2b552a62e57d24a8d897b716d37094 | |
parent | b0fd3e3120e83bcd783d5c2443bade7cef20814a (diff) | |
download | gcc-ef14bba0a6f3836d41d75863e6516d21aef0e936.zip gcc-ef14bba0a6f3836d41d75863e6516d21aef0e936.tar.gz gcc-ef14bba0a6f3836d41d75863e6516d21aef0e936.tar.bz2 |
i386: simplify cpu_feature handling
The patch removes unneeded loops for cpu_features2 and CONVERT_EXPR
that can be simplified with NOP_EXPR.
gcc/ChangeLog:
* common/config/i386/cpuinfo.h (has_cpu_feature): Directly
compute index in cpu_features2.
(set_cpu_feature): Likewise.
* config/i386/i386-builtins.cc (fold_builtin_cpu): Also remove
loop for cpu_features2 and use NOP_EXPRs.
-rw-r--r-- | gcc/common/config/i386/cpuinfo.h | 50 | ||||
-rw-r--r-- | gcc/config/i386/i386-builtins.cc | 79 |
2 files changed, 67 insertions, 62 deletions
diff --git a/gcc/common/config/i386/cpuinfo.h b/gcc/common/config/i386/cpuinfo.h index 239759d..6d6171f 100644 --- a/gcc/common/config/i386/cpuinfo.h +++ b/gcc/common/config/i386/cpuinfo.h @@ -55,43 +55,49 @@ struct __processor_model2 static inline int has_cpu_feature (struct __processor_model *cpu_model, unsigned int *cpu_features2, - enum processor_features f) + enum processor_features feature) { - unsigned int i; + unsigned index, offset; + unsigned f = feature; + if (f < 32) { /* The first 32 features. */ - return cpu_model->__cpu_features[0] & (1U << (f & 31)); + return cpu_model->__cpu_features[0] & (1U << f); + } + else + { + /* The rest of features. cpu_features2[i] contains features from + (32 + i * 32) to (31 + 32 + i * 32), inclusively. */ + f -= 32; + index = f / 32; + offset = f % 32; + return cpu_features2[index] & (1U << offset); } - /* The rest of features. cpu_features2[i] contains features from - (32 + i * 32) to (31 + 32 + i * 32), inclusively. */ - for (i = 0; i < SIZE_OF_CPU_FEATURES; i++) - if (f < (32 + 32 + i * 32)) - return cpu_features2[i] & (1U << ((f - (32 + i * 32)) & 31)); - gcc_unreachable (); } static inline void set_cpu_feature (struct __processor_model *cpu_model, unsigned int *cpu_features2, - enum processor_features f) + enum processor_features feature) { - unsigned int i; + unsigned index, offset; + unsigned f = feature; + if (f < 32) { /* The first 32 features. */ - cpu_model->__cpu_features[0] |= (1U << (f & 31)); - return; + cpu_model->__cpu_features[0] |= (1U << f); + } + else + { + /* The rest of features. cpu_features2[i] contains features from + (32 + i * 32) to (31 + 32 + i * 32), inclusively. */ + f -= 32; + index = f / 32; + offset = f % 32; + cpu_features2[index] |= (1U << offset); } - /* The rest of features. cpu_features2[i] contains features from - (32 + i * 32) to (31 + 32 + i * 32), inclusively. */ - for (i = 0; i < SIZE_OF_CPU_FEATURES; i++) - if (f < (32 + 32 + i * 32)) - { - cpu_features2[i] |= (1U << ((f - (32 + i * 32)) & 31)); - return; - } - gcc_unreachable (); } /* Get the specific type of AMD CPU and return AMD CPU name. Return diff --git a/gcc/config/i386/i386-builtins.cc b/gcc/config/i386/i386-builtins.cc index 8c6d0fe..59c7da2 100644 --- a/gcc/config/i386/i386-builtins.cc +++ b/gcc/config/i386/i386-builtins.cc @@ -2280,7 +2280,7 @@ fold_builtin_cpu (tree fndecl, tree *args) /* Check the value. */ final = build2 (EQ_EXPR, unsigned_type_node, ref, build_int_cstu (unsigned_type_node, field_val)); - return build1 (CONVERT_EXPR, integer_type_node, final); + return build1 (NOP_EXPR, integer_type_node, final); } else if (fn_code == IX86_BUILTIN_CPU_SUPPORTS) { @@ -2305,7 +2305,8 @@ fold_builtin_cpu (tree fndecl, tree *args) return integer_zero_node; } - if (isa_names_table[i].feature >= 32) + unsigned feature = isa_names_table[i].feature; + if (feature >= INT_TYPE_SIZE) { if (ix86_cpu_features2_var == nullptr) { @@ -2323,46 +2324,44 @@ fold_builtin_cpu (tree fndecl, tree *args) varpool_node::add (ix86_cpu_features2_var); } - for (unsigned int j = 0; j < SIZE_OF_CPU_FEATURES; j++) - if (isa_names_table[i].feature < (32 + 32 + j * 32)) - { - field_val = (1U << (isa_names_table[i].feature - - (32 + j * 32))); - tree index = size_int (j); - array_elt = build4 (ARRAY_REF, unsigned_type_node, - ix86_cpu_features2_var, - index, NULL_TREE, NULL_TREE); - /* Return __cpu_features2[index] & field_val */ - final = build2 (BIT_AND_EXPR, unsigned_type_node, - array_elt, - build_int_cstu (unsigned_type_node, - field_val)); - return build1 (CONVERT_EXPR, integer_type_node, final); - } + feature -= INT_TYPE_SIZE; + field_val = 1U << (feature % INT_TYPE_SIZE); + tree index = size_int (feature / INT_TYPE_SIZE); + array_elt = build4 (ARRAY_REF, unsigned_type_node, + ix86_cpu_features2_var, + index, NULL_TREE, NULL_TREE); + /* Return __cpu_features2[index] & field_val */ + final = build2 (BIT_AND_EXPR, unsigned_type_node, + array_elt, + build_int_cstu (unsigned_type_node, + field_val)); + return build1 (NOP_EXPR, integer_type_node, final); } - - field = TYPE_FIELDS (ix86_cpu_model_type_node); - /* Get the last field, which is __cpu_features. */ - while (DECL_CHAIN (field)) - field = DECL_CHAIN (field); - - /* Get the appropriate field: __cpu_model.__cpu_features */ - ref = build3 (COMPONENT_REF, TREE_TYPE (field), ix86_cpu_model_var, - field, NULL_TREE); - - /* Access the 0th element of __cpu_features array. */ - array_elt = build4 (ARRAY_REF, unsigned_type_node, ref, - integer_zero_node, NULL_TREE, NULL_TREE); - - field_val = (1U << isa_names_table[i].feature); - /* Return __cpu_model.__cpu_features[0] & field_val */ - final = build2 (BIT_AND_EXPR, unsigned_type_node, array_elt, - build_int_cstu (unsigned_type_node, field_val)); - if (isa_names_table[i].feature == (INT_TYPE_SIZE - 1)) - return build2 (NE_EXPR, integer_type_node, final, - build_int_cst (unsigned_type_node, 0)); else - return build1 (CONVERT_EXPR, integer_type_node, final); + { + field = TYPE_FIELDS (ix86_cpu_model_type_node); + /* Get the last field, which is __cpu_features. */ + while (DECL_CHAIN (field)) + field = DECL_CHAIN (field); + + /* Get the appropriate field: __cpu_model.__cpu_features */ + ref = build3 (COMPONENT_REF, TREE_TYPE (field), ix86_cpu_model_var, + field, NULL_TREE); + + /* Access the 0th element of __cpu_features array. */ + array_elt = build4 (ARRAY_REF, unsigned_type_node, ref, + integer_zero_node, NULL_TREE, NULL_TREE); + + field_val = (1U << feature); + /* Return __cpu_model.__cpu_features[0] & field_val */ + final = build2 (BIT_AND_EXPR, unsigned_type_node, array_elt, + build_int_cstu (unsigned_type_node, field_val)); + if (feature == (INT_TYPE_SIZE - 1)) + return build2 (NE_EXPR, integer_type_node, final, + build_int_cst (unsigned_type_node, 0)); + else + return build1 (NOP_EXPR, integer_type_node, final); + } } gcc_unreachable (); } |