From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from smtpbgbr1.qq.com (smtpbgbr1.qq.com [54.207.19.206]) by sourceware.org (Postfix) with ESMTPS id 694DC3858C2B for ; Thu, 20 Jul 2023 06:07:51 +0000 (GMT) DMARC-Filter: OpenDMARC Filter v1.4.2 sourceware.org 694DC3858C2B Authentication-Results: sourceware.org; dmarc=none (p=none dis=none) header.from=rivai.ai Authentication-Results: sourceware.org; spf=pass smtp.mailfrom=rivai.ai X-QQ-mid: bizesmtp81t1689833263trrdqwnq Received: from rios-cad5.localdomain ( [58.60.1.11]) by bizesmtp.qq.com (ESMTP) with id ; Thu, 20 Jul 2023 14:07:42 +0800 (CST) X-QQ-SSF: 01400000000000G0U000000A0000000 X-QQ-FEAT: zT6n3Y95oi2oK3Dyn70Z4ZVO5HLaGz4kGDftoaix/OYITMEbPTBh/b36zvnWH jiKuCwiBCrn+rivDJJwbY+nS8wK83ZxqETBxoQToKp4oAOkjw44RHJQLkzCmozEL+9VjoJJ s0UhScbRJ+OfOrKLHeYjJ+zIJmgEn6k5z94tLvRt1n5U1XuLFcKAllvvoZfzY+9QxgqksFD OWaRw5yhOVu65HYl9ZQCOeBNR6kVYpJVJLVwJxiZZHzcX9S7mjp+xvMuOtHLLX30R0+QiWF XodLgsmrdEHXjBIP/RfHwUC7AdiBDLkpQMyD9FI63yfXd+wUmn0cGfOZfv60PndJFhZFf8q u2KUSdhs816sT7NDinRabT7K1oe9HyhBRT1d6H4jbjak3q6rN5ONhxg7+7puKUuuSVix5Vz X-QQ-GoodBg: 2 X-BIZMAIL-ID: 8872420409887882552 From: juzhe.zhong@rivai.ai To: gcc-patches@gcc.gnu.org Cc: richard.sandiford@arm.com, rguenther@suse.de, Ju-Zhe Zhong Subject: [PATCH] VECT: Support floating-point in-order reduction for length loop control Date: Thu, 20 Jul 2023 14:07:40 +0800 Message-Id: <20230720060740.649611-1-juzhe.zhong@rivai.ai> X-Mailer: git-send-email 2.36.3 MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-QQ-SENDSIZE: 520 Feedback-ID: bizesmtp:rivai.ai:qybglogicsvrgz:qybglogicsvrgz7a-one-0 X-Spam-Status: No, score=-12.2 required=5.0 tests=BAYES_00,GIT_PATCH_0,KAM_DMARC_STATUS,RCVD_IN_DNSWL_NONE,RCVD_IN_MSPIKE_H4,RCVD_IN_MSPIKE_WL,SPF_HELO_PASS,SPF_PASS,TXREP,T_SCC_BODY_TEXT_LINE autolearn=ham autolearn_force=no version=3.4.6 X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on server2.sourceware.org List-Id: From: Ju-Zhe Zhong Hi, Richard and Richi. This patch support floating-point in-order reduction for loop length control. Consider this following case: float foo (float *__restrict a, int n) { float result = 1.0; for (int i = 0; i < n; i++) result += a[i]; return result; } When compile with **NO** -ffast-math on ARM SVE, we will end up with: loop_mask = WHILE_ULT result = MASK_FOLD_LEFT_PLUS (...loop_mask...) For RVV, we don't use length loop control instead of mask: So, with this patch, we expect to see: loop_len = SELECT_VL result = MASK_LEN_FOLD_LEFT_PLUS (...loop_len...) gcc/ChangeLog: * tree-vect-loop.cc (get_masked_reduction_fn): Add mask_len_fold_left. (vectorize_fold_left_reduction): Ditto. (vectorizable_reduction): Ditto. (vect_transform_reduction): Ditto. --- gcc/tree-vect-loop.cc | 41 ++++++++++++++++++++++++++++++++++++----- 1 file changed, 36 insertions(+), 5 deletions(-) diff --git a/gcc/tree-vect-loop.cc b/gcc/tree-vect-loop.cc index b44fb9c7712..59ab7879d55 100644 --- a/gcc/tree-vect-loop.cc +++ b/gcc/tree-vect-loop.cc @@ -6800,11 +6800,13 @@ static internal_fn get_masked_reduction_fn (internal_fn reduc_fn, tree vectype_in) { internal_fn mask_reduc_fn; + internal_fn mask_len_reduc_fn; switch (reduc_fn) { case IFN_FOLD_LEFT_PLUS: mask_reduc_fn = IFN_MASK_FOLD_LEFT_PLUS; + mask_len_reduc_fn = IFN_MASK_LEN_FOLD_LEFT_PLUS; break; default: @@ -6814,6 +6816,9 @@ get_masked_reduction_fn (internal_fn reduc_fn, tree vectype_in) if (direct_internal_fn_supported_p (mask_reduc_fn, vectype_in, OPTIMIZE_FOR_SPEED)) return mask_reduc_fn; + if (direct_internal_fn_supported_p (mask_len_reduc_fn, vectype_in, + OPTIMIZE_FOR_SPEED)) + return mask_len_reduc_fn; return IFN_LAST; } @@ -6834,7 +6839,8 @@ vectorize_fold_left_reduction (loop_vec_info loop_vinfo, gimple *reduc_def_stmt, tree_code code, internal_fn reduc_fn, tree ops[3], tree vectype_in, - int reduc_index, vec_loop_masks *masks) + int reduc_index, vec_loop_masks *masks, + vec_loop_lens *lens) { class loop *loop = LOOP_VINFO_LOOP (loop_vinfo); tree vectype_out = STMT_VINFO_VECTYPE (stmt_info); @@ -6896,8 +6902,18 @@ vectorize_fold_left_reduction (loop_vec_info loop_vinfo, { gimple *new_stmt; tree mask = NULL_TREE; + tree len = NULL_TREE; + tree bias = NULL_TREE; if (LOOP_VINFO_FULLY_MASKED_P (loop_vinfo)) mask = vect_get_loop_mask (loop_vinfo, gsi, masks, vec_num, vectype_in, i); + if (LOOP_VINFO_FULLY_WITH_LENGTH_P (loop_vinfo)) + { + len = vect_get_loop_len (loop_vinfo, gsi, lens, vec_num, vectype_in, + i, 1); + signed char biasval = LOOP_VINFO_PARTIAL_LOAD_STORE_BIAS (loop_vinfo); + bias = build_int_cst (intQI_type_node, biasval); + mask = build_minus_one_cst (truth_type_for (vectype_in)); + } /* Handle MINUS by adding the negative. */ if (reduc_fn != IFN_LAST && code == MINUS_EXPR) @@ -6917,7 +6933,10 @@ vectorize_fold_left_reduction (loop_vec_info loop_vinfo, the preceding operation. */ if (reduc_fn != IFN_LAST || (mask && mask_reduc_fn != IFN_LAST)) { - if (mask && mask_reduc_fn != IFN_LAST) + if (len && mask && mask_reduc_fn != IFN_LAST) + new_stmt = gimple_build_call_internal (mask_reduc_fn, 5, reduc_var, + def0, mask, len, bias); + else if (mask && mask_reduc_fn != IFN_LAST) new_stmt = gimple_build_call_internal (mask_reduc_fn, 3, reduc_var, def0, mask); else @@ -7979,6 +7998,7 @@ vectorizable_reduction (loop_vec_info loop_vinfo, else if (loop_vinfo && LOOP_VINFO_CAN_USE_PARTIAL_VECTORS_P (loop_vinfo)) { vec_loop_masks *masks = &LOOP_VINFO_MASKS (loop_vinfo); + vec_loop_lens *lens = &LOOP_VINFO_LENS (loop_vinfo); internal_fn cond_fn = get_conditional_internal_fn (op.code, op.type); if (reduction_type != FOLD_LEFT_REDUCTION @@ -8006,8 +8026,17 @@ vectorizable_reduction (loop_vec_info loop_vinfo, LOOP_VINFO_CAN_USE_PARTIAL_VECTORS_P (loop_vinfo) = false; } else - vect_record_loop_mask (loop_vinfo, masks, ncopies * vec_num, - vectype_in, NULL); + { + internal_fn mask_reduc_fn + = get_masked_reduction_fn (reduc_fn, vectype_in); + + if (mask_reduc_fn == IFN_MASK_LEN_FOLD_LEFT_PLUS) + vect_record_loop_len (loop_vinfo, lens, ncopies * vec_num, + vectype_in, 1); + else + vect_record_loop_mask (loop_vinfo, masks, ncopies * vec_num, + vectype_in, NULL); + } } return true; } @@ -8137,6 +8166,7 @@ vect_transform_reduction (loop_vec_info loop_vinfo, code_helper code = canonicalize_code (op.code, op.type); internal_fn cond_fn = get_conditional_internal_fn (code, op.type); vec_loop_masks *masks = &LOOP_VINFO_MASKS (loop_vinfo); + vec_loop_lens *lens = &LOOP_VINFO_LENS (loop_vinfo); bool mask_by_cond_expr = use_mask_by_cond_expr_p (code, cond_fn, vectype_in); /* Transform. */ @@ -8162,7 +8192,8 @@ vect_transform_reduction (loop_vec_info loop_vinfo, gcc_assert (code.is_tree_code ()); return vectorize_fold_left_reduction (loop_vinfo, stmt_info, gsi, vec_stmt, slp_node, reduc_def_phi, - tree_code (code), reduc_fn, op.ops, vectype_in, reduc_index, masks); + tree_code (code), reduc_fn, op.ops, vectype_in, reduc_index, masks, + lens); } bool single_defuse_cycle = STMT_VINFO_FORCE_SINGLE_CYCLE (reduc_info); -- 2.36.3