From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: by sourceware.org (Postfix, from userid 1851) id 13C5A395A050; Wed, 11 May 2022 09:04:15 +0000 (GMT) DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 13C5A395A050 MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Content-Type: text/plain; charset="utf-8" From: Martin Liska To: gcc-cvs@gcc.gnu.org Subject: [gcc r13-316] i386: simplify cpu_feature handling X-Act-Checkin: gcc X-Git-Author: Martin Liska X-Git-Refname: refs/heads/master X-Git-Oldrev: b0fd3e3120e83bcd783d5c2443bade7cef20814a X-Git-Newrev: ef14bba0a6f3836d41d75863e6516d21aef0e936 Message-Id: <20220511090415.13C5A395A050@sourceware.org> Date: Wed, 11 May 2022 09:04:15 +0000 (GMT) X-BeenThere: gcc-cvs@gcc.gnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Gcc-cvs mailing list List-Unsubscribe: , List-Archive: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 11 May 2022 09:04:15 -0000 https://gcc.gnu.org/g:ef14bba0a6f3836d41d75863e6516d21aef0e936 commit r13-316-gef14bba0a6f3836d41d75863e6516d21aef0e936 Author: Martin Liska Date: Wed Dec 15 10:54:23 2021 +0100 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. Diff: --- gcc/common/config/i386/cpuinfo.h | 50 ++++++++++++++----------- 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 239759dc766..6d6171f4555 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 8c6d0fe9631..59c7da25a14 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 (); }