From: Andrew Pinski <apin...@marvell.com> This patch adds simple folding of __builtin_aarch64_im_lane_boundsi where we are not going to error out. It fixes the problem by the removal of the function from the IR.
OK? Bootstrapped and tested on aarch64-linux-gnu with no regressions. gcc/ChangeLog: * config/aarch64/aarch64-builtins.c (aarch64_fold_builtin_lane_check): New function. (aarch64_general_fold_builtin): Handle AARCH64_SIMD_BUILTIN_LANE_CHECK. (aarch64_general_gimple_fold_builtin): Likewise. --- gcc/config/aarch64/aarch64-builtins.c | 35 +++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) diff --git a/gcc/config/aarch64/aarch64-builtins.c b/gcc/config/aarch64/aarch64-builtins.c index f6b41d9c200..d4414373aa4 100644 --- a/gcc/config/aarch64/aarch64-builtins.c +++ b/gcc/config/aarch64/aarch64-builtins.c @@ -29,6 +29,7 @@ #include "rtl.h" #include "tree.h" #include "gimple.h" +#include "ssa.h" #include "memmodel.h" #include "tm_p.h" #include "expmed.h" @@ -2333,6 +2334,27 @@ aarch64_general_builtin_rsqrt (unsigned int fn) return NULL_TREE; } +/* Return true if the lane check can be removed as there is no + error going to be emitted. */ +static bool +aarch64_fold_builtin_lane_check (tree arg0, tree arg1, tree arg2) +{ + if (TREE_CODE (arg0) != INTEGER_CST) + return false; + if (TREE_CODE (arg1) != INTEGER_CST) + return false; + if (TREE_CODE (arg2) != INTEGER_CST) + return false; + + auto totalsize = wi::to_widest (arg0); + auto elementsize = wi::to_widest (arg1); + if (totalsize == 0 || elementsize == 0) + return false; + auto lane = wi::to_widest (arg2); + auto high = wi::udiv_trunc (totalsize, elementsize); + return wi::ltu_p (lane, high); +} + #undef VAR1 #define VAR1(T, N, MAP, FLAG, A) \ case AARCH64_SIMD_BUILTIN_##T##_##N##A: @@ -2353,6 +2375,11 @@ aarch64_general_fold_builtin (unsigned int fcode, tree type, VAR1 (UNOP, floatv4si, 2, ALL, v4sf) VAR1 (UNOP, floatv2di, 2, ALL, v2df) return fold_build1 (FLOAT_EXPR, type, args[0]); + case AARCH64_SIMD_BUILTIN_LANE_CHECK: + if (n_args == 3 + && aarch64_fold_builtin_lane_check (args[0], args[1], args[2])) + return fold_convert (void_type_node, integer_zero_node); + break; default: break; } @@ -2440,6 +2467,14 @@ aarch64_general_gimple_fold_builtin (unsigned int fcode, gcall *stmt) } break; } + case AARCH64_SIMD_BUILTIN_LANE_CHECK: + if (aarch64_fold_builtin_lane_check (args[0], args[1], args[2])) + { + unlink_stmt_vdef (stmt); + release_defs (stmt); + new_stmt = gimple_build_nop (); + } + break; default: break; } -- 2.17.1