From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: by sourceware.org (Postfix, from userid 2063) id F050F398405F; Tue, 20 Jul 2021 03:19:17 +0000 (GMT) DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org F050F398405F MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Content-Type: text/plain; charset="utf-8" From: Kewen Lin To: gcc-cvs@gcc.gnu.org Subject: [gcc r12-2404] vect: Recog mul_highpart pattern [PR100696] X-Act-Checkin: gcc X-Git-Author: Kewen Lin X-Git-Refname: refs/heads/master X-Git-Oldrev: 21ea2f9320d31d3d925031a8ba189d9b19e52bc1 X-Git-Newrev: a1d27560770818c514ad1ad6683f89e1e1bcd0ec Message-Id: <20210720031917.F050F398405F@sourceware.org> Date: Tue, 20 Jul 2021 03:19:17 +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: Tue, 20 Jul 2021 03:19:18 -0000 https://gcc.gnu.org/g:a1d27560770818c514ad1ad6683f89e1e1bcd0ec commit r12-2404-ga1d27560770818c514ad1ad6683f89e1e1bcd0ec Author: Kewen Lin Date: Mon Jul 19 20:49:17 2021 -0500 vect: Recog mul_highpart pattern [PR100696] This patch is to extend the existing pattern mulhs handlings to cover normal multiply highpart pattern recognization, it introduces one new internal function IFN_MULH for 1:1 map to [su]mul_highpart optab. Since it covers MULT_HIGHPART_EXPR with optab support, i386 part change is to ensure it follows the consistent costing path. Bootstrapped & regtested on powerpc64le-linux-gnu P9, x86_64-redhat-linux and aarch64-linux-gnu. gcc/ChangeLog: PR tree-optimization/100696 * internal-fn.c (first_commutative_argument): Add info for IFN_MULH. * internal-fn.def (IFN_MULH): New internal function. * tree-vect-patterns.c (vect_recog_mulhs_pattern): Add support to recog normal multiply highpart as IFN_MULH. * config/i386/i386.c (ix86_add_stmt_cost): Adjust for combined function CFN_MULH. gcc/testsuite/ChangeLog: PR tree-optimization/100696 * gcc.target/i386/pr100637-3w.c: Adjust for mul_highpart recog. Diff: --- gcc/config/i386/i386.c | 3 +++ gcc/internal-fn.c | 1 + gcc/internal-fn.def | 2 ++ gcc/testsuite/gcc.target/i386/pr100637-3w.c | 6 ++--- gcc/tree-vect-patterns.c | 38 +++++++++++++++++++++-------- 5 files changed, 37 insertions(+), 13 deletions(-) diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c index 8481693ab7f..ff96134fb37 100644 --- a/gcc/config/i386/i386.c +++ b/gcc/config/i386/i386.c @@ -22568,6 +22568,9 @@ ix86_add_stmt_cost (class vec_info *vinfo, void *data, int count, mode == SFmode ? ix86_cost->fmass : ix86_cost->fmasd); break; + case CFN_MULH: + stmt_cost = ix86_multiplication_cost (ix86_cost, mode); + break; default: break; } diff --git a/gcc/internal-fn.c b/gcc/internal-fn.c index cd5e63f9acd..1360a00f0b9 100644 --- a/gcc/internal-fn.c +++ b/gcc/internal-fn.c @@ -3703,6 +3703,7 @@ first_commutative_argument (internal_fn fn) case IFN_FNMS: case IFN_AVG_FLOOR: case IFN_AVG_CEIL: + case IFN_MULH: case IFN_MULHS: case IFN_MULHRS: case IFN_FMIN: diff --git a/gcc/internal-fn.def b/gcc/internal-fn.def index a7003d5da8e..3ac9ae68b2a 100644 --- a/gcc/internal-fn.def +++ b/gcc/internal-fn.def @@ -169,6 +169,8 @@ DEF_INTERNAL_SIGNED_OPTAB_FN (AVG_FLOOR, ECF_CONST | ECF_NOTHROW, first, DEF_INTERNAL_SIGNED_OPTAB_FN (AVG_CEIL, ECF_CONST | ECF_NOTHROW, first, savg_ceil, uavg_ceil, binary) +DEF_INTERNAL_SIGNED_OPTAB_FN (MULH, ECF_CONST | ECF_NOTHROW, first, + smul_highpart, umul_highpart, binary) DEF_INTERNAL_SIGNED_OPTAB_FN (MULHS, ECF_CONST | ECF_NOTHROW, first, smulhs, umulhs, binary) DEF_INTERNAL_SIGNED_OPTAB_FN (MULHRS, ECF_CONST | ECF_NOTHROW, first, diff --git a/gcc/testsuite/gcc.target/i386/pr100637-3w.c b/gcc/testsuite/gcc.target/i386/pr100637-3w.c index b951f30f571..4ea467b4af5 100644 --- a/gcc/testsuite/gcc.target/i386/pr100637-3w.c +++ b/gcc/testsuite/gcc.target/i386/pr100637-3w.c @@ -1,6 +1,6 @@ /* PR target/100637 */ /* { dg-do compile } */ -/* { dg-options "-O2 -ftree-vectorize -msse4" } */ +/* { dg-options "-O2 -ftree-vectorize -msse4 -fno-vect-cost-model" } */ short r[2], a[2], b[2]; unsigned short ur[2], ua[2], ub[2]; @@ -13,7 +13,7 @@ void mulh (void) r[i] = ((int) a[i] * b[i]) >> 16; } -/* { dg-final { scan-assembler "pmulhw" { xfail *-*-* } } } */ +/* { dg-final { scan-assembler "pmulhw" } } */ void mulhu (void) { @@ -23,7 +23,7 @@ void mulhu (void) ur[i] = ((unsigned int) ua[i] * ub[i]) >> 16; } -/* { dg-final { scan-assembler "pmulhuw" { xfail *-*-* } } } */ +/* { dg-final { scan-assembler "pmulhuw" } } */ void mulhrs (void) { diff --git a/gcc/tree-vect-patterns.c b/gcc/tree-vect-patterns.c index 44f6c9b2bd6..70bb751865b 100644 --- a/gcc/tree-vect-patterns.c +++ b/gcc/tree-vect-patterns.c @@ -1934,8 +1934,15 @@ vect_recog_over_widening_pattern (vec_info *vinfo, 1) Multiply high with scaling TYPE res = ((TYPE) a * (TYPE) b) >> c; + Here, c is bitsize (TYPE) / 2 - 1. + 2) ... or also with rounding TYPE res = (((TYPE) a * (TYPE) b) >> d + 1) >> 1; + Here, d is bitsize (TYPE) / 2 - 2. + + 3) Normal multiply high + TYPE res = ((TYPE) a * (TYPE) b) >> e; + Here, e is bitsize (TYPE) / 2. where only the bottom half of res is used. */ @@ -1980,7 +1987,6 @@ vect_recog_mulhs_pattern (vec_info *vinfo, stmt_vec_info mulh_stmt_info; tree scale_term; internal_fn ifn; - unsigned int expect_offset; /* Check for the presence of the rounding term. */ if (gimple_assign_rhs_code (rshift_input_stmt) == PLUS_EXPR) @@ -2029,25 +2035,37 @@ vect_recog_mulhs_pattern (vec_info *vinfo, /* Get the scaling term. */ scale_term = gimple_assign_rhs2 (plus_input_stmt); + /* Check that the scaling factor is correct. */ + if (TREE_CODE (scale_term) != INTEGER_CST) + return NULL; + + /* Check pattern 2). */ + if (wi::to_widest (scale_term) + target_precision + 2 + != TYPE_PRECISION (lhs_type)) + return NULL; - expect_offset = target_precision + 2; ifn = IFN_MULHRS; } else { mulh_stmt_info = rshift_input_stmt_info; scale_term = gimple_assign_rhs2 (last_stmt); + /* Check that the scaling factor is correct. */ + if (TREE_CODE (scale_term) != INTEGER_CST) + return NULL; - expect_offset = target_precision + 1; - ifn = IFN_MULHS; + /* Check for pattern 1). */ + if (wi::to_widest (scale_term) + target_precision + 1 + == TYPE_PRECISION (lhs_type)) + ifn = IFN_MULHS; + /* Check for pattern 3). */ + else if (wi::to_widest (scale_term) + target_precision + == TYPE_PRECISION (lhs_type)) + ifn = IFN_MULH; + else + return NULL; } - /* Check that the scaling factor is correct. */ - if (TREE_CODE (scale_term) != INTEGER_CST - || wi::to_widest (scale_term) + expect_offset - != TYPE_PRECISION (lhs_type)) - return NULL; - /* Check whether the scaling input term can be seen as two widened inputs multiplied together. */ vect_unpromoted_value unprom_mult[2];