From patchwork Mon Jun 5 03:57:41 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: =?utf-8?b?6ZKf5bGF5ZOy?= X-Patchwork-Id: 70578 Return-Path: X-Original-To: patchwork@sourceware.org Delivered-To: patchwork@sourceware.org Received: from server2.sourceware.org (localhost [IPv6:::1]) by sourceware.org (Postfix) with ESMTP id 6ECEF3857715 for ; Mon, 5 Jun 2023 03:58:17 +0000 (GMT) X-Original-To: gcc-patches@gcc.gnu.org Delivered-To: gcc-patches@gcc.gnu.org Received: from smtpbgbr2.qq.com (smtpbgbr2.qq.com [54.207.22.56]) by sourceware.org (Postfix) with ESMTPS id 5CECF3858D28 for ; Mon, 5 Jun 2023 03:57:50 +0000 (GMT) DMARC-Filter: OpenDMARC Filter v1.4.2 sourceware.org 5CECF3858D28 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: bizesmtp87t1685937464t7i9f5nh Received: from rios-cad5.localdomain ( [58.60.1.11]) by bizesmtp.qq.com (ESMTP) with id ; Mon, 05 Jun 2023 11:57:43 +0800 (CST) X-QQ-SSF: 01400000000000F0S000000A0000000 X-QQ-FEAT: dKvkn8qoLrEj/nnDyOu9DJzJ4scKdF9AKTlLmne79mBZt45T/0uNkkypZgOdt Qc+bM5FkNf1n3IGfj40pwjl7srfx7jo2zHoK2SrniO/pmOJv5ZvtSEdZbe9up9n6iv8yRMt xebrug05lD2iKamkWk8NGkVKZmqp80s4w10ZYNzgEUXCgNjd0alcMXr642QWjxVus9cjXaR sXXobGz+nIBIJE9uck0LtHLIm9HmlyW+U5TkyLYFcLkmknhZ+CvTvVxyGOl2Wi39yMRMb6P VcYGElNB+G8LTHAjdNgfmpj5Knn1NkouNPB9jHlY0RLrmLHyUA4xDh9TgnIVR+aUQIs1SII dzTMmLjxc2haabatxCI+wRMy0FHbZlwcv7MAi863W4vWBbLaz83I7dUZ2BmNuzg3nZIhYZB X-QQ-GoodBg: 2 X-BIZMAIL-ID: 3950622003906539402 From: juzhe.zhong@rivai.ai To: gcc-patches@gcc.gnu.org Cc: richard.sandiford@arm.com, rguenther@suse.de, Ju-Zhe Zhong Subject: [PATCH V2] VECT: Add SELECT_VL support Date: Mon, 5 Jun 2023 11:57:41 +0800 Message-Id: <20230605035741.613909-1-juzhe.zhong@rivai.ai> X-Mailer: git-send-email 2.36.3 MIME-Version: 1.0 X-QQ-SENDSIZE: 520 Feedback-ID: bizesmtp:rivai.ai:qybglogicsvrgz:qybglogicsvrgz7a-one-0 X-Spam-Status: No, score=-12.6 required=5.0 tests=BAYES_00, GIT_PATCH_0, KAM_DMARC_STATUS, RCVD_IN_DNSWL_NONE, RCVD_IN_MSPIKE_H5, 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 X-BeenThere: gcc-patches@gcc.gnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Gcc-patches mailing list List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: gcc-patches-bounces+patchwork=sourceware.org@gcc.gnu.org Sender: "Gcc-patches" From: Ju-Zhe Zhong This patch address comments from Richard and rebase to trunk. This patch is adding SELECT_VL middle-end support allow target have target dependent optimization in case of length calculation. This patch is inspired by RVV ISA and LLVM: https://reviews.llvm.org/D99750 The SELECT_VL is same behavior as LLVM "get_vector_length" with these following properties: 1. Only apply on single-rgroup. 2. non SLP. 3. adjust loop control IV. 4. adjust data reference IV. 5. allow non-vf elements processing in non-final iteration Code: # void vvaddint32(size_t n, const int*x, const int*y, int*z) # { for (size_t i=0; i - _36 = MIN_EXPR ; + _36 = (MIN_EXPR | SELECT_VL) ; ... vect__4.8_28 = .LEN_LOAD (_17, 32B, _36, 0); ... @@ -549,15 +549,28 @@ vect_set_loop_controls_directly (class loop *loop, loop_vec_info loop_vinfo, tree step = rgc->controls.length () == 1 ? rgc->controls[0] : make_ssa_name (iv_type); /* Create decrement IV. */ - create_iv (nitems_total, MINUS_EXPR, nitems_step, NULL_TREE, loop, - &incr_gsi, insert_after, &index_before_incr, - &index_after_incr); - gimple_seq_add_stmt (header_seq, gimple_build_assign (step, MIN_EXPR, - index_before_incr, - nitems_step)); + if (LOOP_VINFO_USING_SELECT_VL_P (loop_vinfo)) + { + create_iv (nitems_total, MINUS_EXPR, step, NULL_TREE, loop, &incr_gsi, + insert_after, &index_before_incr, &index_after_incr); + tree len = gimple_build (header_seq, IFN_SELECT_VL, iv_type, + index_before_incr, nitems_step); + gimple_seq_add_stmt (header_seq, gimple_build_assign (step, len)); + } + else + { + create_iv (nitems_total, MINUS_EXPR, nitems_step, NULL_TREE, loop, + &incr_gsi, insert_after, &index_before_incr, + &index_after_incr); + gimple_seq_add_stmt (header_seq, + gimple_build_assign (step, MIN_EXPR, + index_before_incr, + nitems_step)); + } *iv_step = step; *compare_step = nitems_step; - return index_before_incr; + return LOOP_VINFO_USING_SELECT_VL_P (loop_vinfo) ? index_after_incr + : index_before_incr; } /* Create increment IV. */ @@ -888,7 +901,8 @@ vect_set_loop_condition_partial_vectors (class loop *loop, /* Get a boolean result that tells us whether to iterate. */ edge exit_edge = single_exit (loop); gcond *cond_stmt; - if (LOOP_VINFO_USING_DECREMENTING_IV_P (loop_vinfo)) + if (LOOP_VINFO_USING_DECREMENTING_IV_P (loop_vinfo) + && !LOOP_VINFO_USING_SELECT_VL_P (loop_vinfo)) { gcc_assert (compare_step); tree_code code = (exit_edge->flags & EDGE_TRUE_VALUE) ? LE_EXPR : GT_EXPR; diff --git a/gcc/tree-vect-loop.cc b/gcc/tree-vect-loop.cc index 5b7a0da0034..68c3432c0a4 100644 --- a/gcc/tree-vect-loop.cc +++ b/gcc/tree-vect-loop.cc @@ -974,6 +974,7 @@ _loop_vec_info::_loop_vec_info (class loop *loop_in, vec_info_shared *shared) can_use_partial_vectors_p (param_vect_partial_vector_usage != 0), using_partial_vectors_p (false), using_decrementing_iv_p (false), + using_select_vl_p (false), epil_using_partial_vectors_p (false), partial_load_store_bias (0), peeling_for_gaps (false), @@ -2737,6 +2738,53 @@ start_over: LOOP_VINFO_VECT_FACTOR (loop_vinfo)))) LOOP_VINFO_USING_DECREMENTING_IV_P (loop_vinfo) = true; + /* If we're using decrement IV approach in loop control, we can use output of + SELECT_VL to adjust IV of loop control and data reference when it satisfies + the following checks: + + (a) SELECT_VL is supported by the target. + (b) LOOP_VINFO is single-rgroup control. + (c) non-SLP. + (d) LOOP can not be unrolled. + + Otherwise, we use MIN_EXPR approach. + + 1. We only apply SELECT_VL on single-rgroup since: + + (1). Multiple-rgroup controls N vector loads/stores would need N pointer + updates by variable amounts. + (2). SELECT_VL allows flexible length (<=VF) in each iteration. + (3). For decrement IV approach, we calculate the MAX length of the loop + and then deduce the length of each control from this MAX length. + + Base on (1), (2) and (3) situations, if we try to use SELECT_VL on + multiple-rgroup control, we need to generate multiple SELECT_VL to + carefully adjust length of each control. Such approach is very inefficient + and unprofitable for targets that are using a standalone instruction + to configure the length of each operation. + E.g. RISC-V vector use 'vsetvl' to configure the length of each operation. + + 2. We don't apply SELECT_VL on single-rgroup when both (1) and (2) are + satisfied: + + (1). LOOP_VINFO_NITERS_KNOWN_P (loop_vinfo) is true. + (2). LOOP_VINFO_VECT_FACTOR (loop_vinfo).is_constant () is true. + + Since SELECT_VL (variable step) will make SCEV analysis failed and then + we will fail to gain benefits of following unroll optimizations. We prefer + using the MIN_EXPR approach in this situation. */ + if (LOOP_VINFO_USING_DECREMENTING_IV_P (loop_vinfo)) + { + tree iv_type = LOOP_VINFO_RGROUP_IV_TYPE (loop_vinfo); + if (direct_internal_fn_supported_p (IFN_SELECT_VL, iv_type, + OPTIMIZE_FOR_SPEED) + && LOOP_VINFO_LENS (loop_vinfo).length () == 1 + && LOOP_VINFO_LENS (loop_vinfo)[0].factor == 1 && !slp + && (!LOOP_VINFO_NITERS_KNOWN_P (loop_vinfo) + || !LOOP_VINFO_VECT_FACTOR (loop_vinfo).is_constant ())) + LOOP_VINFO_USING_SELECT_VL_P (loop_vinfo) = true; + } + /* If we're vectorizing an epilogue loop, the vectorized loop either needs to be able to handle fewer than VF scalars, or needs to have a lower VF than the main loop. */ diff --git a/gcc/tree-vect-stmts.cc b/gcc/tree-vect-stmts.cc index e37c401b688..b28226b6e7e 100644 --- a/gcc/tree-vect-stmts.cc +++ b/gcc/tree-vect-stmts.cc @@ -3148,6 +3148,57 @@ vect_get_data_ptr_increment (vec_info *vinfo, return iv_step; } +/* Prepare the pointer IVs which needs to be updated by a variable amount. + Such variable amount is the outcome of .SELECT_VL. In this case, we can + allow each iteration process the flexible number of elements as long as + the number <= vf elments. + + Return data reference according to SELECT_VL. + If new statements are needed, insert them before GSI. */ + +static tree +get_select_vl_data_ref_ptr (vec_info *vinfo, stmt_vec_info stmt_info, + tree aggr_type, class loop *at_loop, tree offset, + tree *dummy, gimple_stmt_iterator *gsi, + bool simd_lane_access_p, vec_loop_lens *loop_lens, + dr_vec_info *dr_info, + vect_memory_access_type memory_access_type) +{ + loop_vec_info loop_vinfo = dyn_cast (vinfo); + tree step = vect_dr_behavior (vinfo, dr_info)->step; + + /* TODO: We don't support gather/scatter or load_lanes/store_lanes for pointer + IVs are updated by variable amount but we will support them in the future. + */ + gcc_assert (memory_access_type != VMAT_GATHER_SCATTER + && memory_access_type != VMAT_LOAD_STORE_LANES); + + /* When we support SELECT_VL pattern, we dynamic adjust + the memory address by .SELECT_VL result. + + The result of .SELECT_VL is the number of elements to + be processed of each iteration. So the memory address + adjustment operation should be: + + addr = addr + .SELECT_VL (ARG..) * step; + */ + gimple *ptr_incr; + tree loop_len + = vect_get_loop_len (loop_vinfo, gsi, loop_lens, 1, aggr_type, 0, 0); + tree len_type = TREE_TYPE (loop_len); + /* Since the outcome of .SELECT_VL is element size, we should adjust + it into bytesize so that it can be used in address pointer variable + amount IVs adjustment. */ + tree tmp = fold_build2 (MULT_EXPR, len_type, loop_len, + wide_int_to_tree (len_type, wi::to_widest (step))); + tree bump = make_temp_ssa_name (len_type, NULL, "ivtmp"); + gassign *assign = gimple_build_assign (bump, tmp); + gsi_insert_before (gsi, assign, GSI_SAME_STMT); + return vect_create_data_ref_ptr (vinfo, stmt_info, aggr_type, at_loop, offset, + dummy, gsi, &ptr_incr, simd_lane_access_p, + bump); +} + /* Check and perform vectorization of BUILT_IN_BSWAP{16,32,64,128}. */ static bool @@ -8631,6 +8682,14 @@ vectorizable_store (vec_info *vinfo, vect_get_gather_scatter_ops (loop_vinfo, loop, stmt_info, slp_node, &gs_info, &dataref_ptr, &vec_offsets); + else if (loop_lens && LOOP_VINFO_USING_SELECT_VL_P (loop_vinfo) + && memory_access_type != VMAT_INVARIANT) + dataref_ptr + = get_select_vl_data_ref_ptr (vinfo, stmt_info, aggr_type, + simd_lane_access_p ? loop : NULL, + offset, &dummy, gsi, + simd_lane_access_p, loop_lens, + dr_info, memory_access_type); else dataref_ptr = vect_create_data_ref_ptr (vinfo, first_stmt_info, aggr_type, @@ -10022,6 +10081,13 @@ vectorizable_load (vec_info *vinfo, slp_node, &gs_info, &dataref_ptr, &vec_offsets); } + else if (loop_lens && LOOP_VINFO_USING_SELECT_VL_P (loop_vinfo) + && memory_access_type != VMAT_INVARIANT) + dataref_ptr + = get_select_vl_data_ref_ptr (vinfo, stmt_info, aggr_type, + at_loop, offset, &dummy, gsi, + simd_lane_access_p, loop_lens, + dr_info, memory_access_type); else dataref_ptr = vect_create_data_ref_ptr (vinfo, first_stmt_info, aggr_type, diff --git a/gcc/tree-vectorizer.h b/gcc/tree-vectorizer.h index 34552f6bf9e..c6e0140a0b5 100644 --- a/gcc/tree-vectorizer.h +++ b/gcc/tree-vectorizer.h @@ -825,6 +825,11 @@ public: (b) can iterate more than once. */ bool using_decrementing_iv_p; + /* True if we've decided to use output of select_vl to adjust IV of + both loop control and data reference pointer. This is only true + for single-rgroup control. */ + bool using_select_vl_p; + /* True if we've decided to use partially-populated vectors for the epilogue of loop. */ bool epil_using_partial_vectors_p; @@ -898,6 +903,7 @@ public: #define LOOP_VINFO_CAN_USE_PARTIAL_VECTORS_P(L) (L)->can_use_partial_vectors_p #define LOOP_VINFO_USING_PARTIAL_VECTORS_P(L) (L)->using_partial_vectors_p #define LOOP_VINFO_USING_DECREMENTING_IV_P(L) (L)->using_decrementing_iv_p +#define LOOP_VINFO_USING_SELECT_VL_P(L) (L)->using_select_vl_p #define LOOP_VINFO_EPIL_USING_PARTIAL_VECTORS_P(L) \ (L)->epil_using_partial_vectors_p #define LOOP_VINFO_PARTIAL_LOAD_STORE_BIAS(L) (L)->partial_load_store_bias