From bb6c2b68d6961dfe98bece34e4418d7287ce7089 Mon Sep 17 00:00:00 2001 From: Richard Sandiford Date: Sat, 13 Jan 2018 17:59:59 +0000 Subject: Add support for conditional reductions using SVE CLASTB This patch uses SVE CLASTB to optimise conditional reductions. It means that we no longer need to maintain a separate index vector to record the most recent valid value, and no longer need to worry about overflow cases. 2018-01-13 Richard Sandiford Alan Hayward David Sherwood gcc/ * doc/md.texi (fold_extract_last_@var{m}): Document. * doc/sourcebuild.texi (vect_fold_extract_last): Likewise. * optabs.def (fold_extract_last_optab): New optab. * internal-fn.def (FOLD_EXTRACT_LAST): New internal function. * internal-fn.c (fold_extract_direct): New macro. (expand_fold_extract_optab_fn): Likewise. (direct_fold_extract_optab_supported_p): Likewise. * tree-vectorizer.h (EXTRACT_LAST_REDUCTION): New vect_reduction_type. * tree-vect-loop.c (vect_model_reduction_cost): Handle EXTRACT_LAST_REDUCTION. (get_initial_def_for_reduction): Do not create an initial vector for EXTRACT_LAST_REDUCTION reductions. (vectorizable_reduction): Leave the scalar phi in place for EXTRACT_LAST_REDUCTIONs. Try using EXTRACT_LAST_REDUCTION ahead of INTEGER_INDUC_COND_REDUCTION. Do not check for an epilogue code for EXTRACT_LAST_REDUCTION and defer the transform phase to vectorizable_condition. * tree-vect-stmts.c (vect_finish_stmt_generation_1): New function, split out from... (vect_finish_stmt_generation): ...here. (vect_finish_replace_stmt): New function. (vectorizable_condition): Handle EXTRACT_LAST_REDUCTION. * config/aarch64/aarch64-sve.md (fold_extract_last_): New pattern. * config/aarch64/aarch64.md (UNSPEC_CLASTB): New unspec. gcc/testsuite/ * lib/target-supports.exp (check_effective_target_vect_fold_extract_last): New proc. * gcc.dg/vect/pr65947-1.c: Update dump messages. Add markup for fold_extract_last. * gcc.dg/vect/pr65947-2.c: Likewise. * gcc.dg/vect/pr65947-3.c: Likewise. * gcc.dg/vect/pr65947-4.c: Likewise. * gcc.dg/vect/pr65947-5.c: Likewise. * gcc.dg/vect/pr65947-6.c: Likewise. * gcc.dg/vect/pr65947-9.c: Likewise. * gcc.dg/vect/pr65947-10.c: Likewise. * gcc.dg/vect/pr65947-12.c: Likewise. * gcc.dg/vect/pr65947-14.c: Likewise. * gcc.dg/vect/pr80631-1.c: Likewise. * gcc.target/aarch64/sve/clastb_1.c: New test. * gcc.target/aarch64/sve/clastb_1_run.c: Likewise. * gcc.target/aarch64/sve/clastb_2.c: Likewise. * gcc.target/aarch64/sve/clastb_2_run.c: Likewise. * gcc.target/aarch64/sve/clastb_3.c: Likewise. * gcc.target/aarch64/sve/clastb_3_run.c: Likewise. * gcc.target/aarch64/sve/clastb_4.c: Likewise. * gcc.target/aarch64/sve/clastb_4_run.c: Likewise. * gcc.target/aarch64/sve/clastb_5.c: Likewise. * gcc.target/aarch64/sve/clastb_5_run.c: Likewise. * gcc.target/aarch64/sve/clastb_6.c: Likewise. * gcc.target/aarch64/sve/clastb_6_run.c: Likewise. * gcc.target/aarch64/sve/clastb_7.c: Likewise. * gcc.target/aarch64/sve/clastb_7_run.c: Likewise. Co-Authored-By: Alan Hayward Co-Authored-By: David Sherwood From-SVN: r256633 --- gcc/internal-fn.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'gcc/internal-fn.c') diff --git a/gcc/internal-fn.c b/gcc/internal-fn.c index 23c9224..0cc59e8 100644 --- a/gcc/internal-fn.c +++ b/gcc/internal-fn.c @@ -91,6 +91,7 @@ init_internal_fns () #define cond_unary_direct { 1, 1, true } #define cond_binary_direct { 1, 1, true } #define while_direct { 0, 2, false } +#define fold_extract_direct { 2, 2, false } const direct_internal_fn_info direct_internal_fn_array[IFN_LAST + 1] = { #define DEF_INTERNAL_FN(CODE, FLAGS, FNSPEC) not_direct, @@ -2893,6 +2894,9 @@ expand_while_optab_fn (internal_fn, gcall *stmt, convert_optab optab) #define expand_cond_binary_optab_fn(FN, STMT, OPTAB) \ expand_direct_optab_fn (FN, STMT, OPTAB, 3) +#define expand_fold_extract_optab_fn(FN, STMT, OPTAB) \ + expand_direct_optab_fn (FN, STMT, OPTAB, 3) + /* RETURN_TYPE and ARGS are a return type and argument list that are in principle compatible with FN (which satisfies direct_internal_fn_p). Return the types that should be used to determine whether the @@ -2975,6 +2979,7 @@ multi_vector_optab_supported_p (convert_optab optab, tree_pair types, #define direct_store_lanes_optab_supported_p multi_vector_optab_supported_p #define direct_mask_store_lanes_optab_supported_p multi_vector_optab_supported_p #define direct_while_optab_supported_p convert_optab_supported_p +#define direct_fold_extract_optab_supported_p direct_optab_supported_p /* Return the optab used by internal function FN. */ -- cgit v1.1