From patchwork Tue Nov 7 14:30:54 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "Li, Pan2" X-Patchwork-Id: 1861127 Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@legolas.ozlabs.org Authentication-Results: legolas.ozlabs.org; dkim=pass (2048-bit key; unprotected) header.d=intel.com header.i=@intel.com header.a=rsa-sha256 header.s=Intel header.b=fdTR494j; dkim-atps=neutral Authentication-Results: legolas.ozlabs.org; spf=pass (sender SPF authorized) smtp.mailfrom=gcc.gnu.org (client-ip=2620:52:3:1:0:246e:9693:128c; helo=server2.sourceware.org; envelope-from=gcc-patches-bounces+incoming=patchwork.ozlabs.org@gcc.gnu.org; receiver=patchwork.ozlabs.org) Received: from server2.sourceware.org (server2.sourceware.org [IPv6:2620:52:3:1:0:246e:9693:128c]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature ECDSA (secp384r1) server-digest SHA384) (No client certificate requested) by legolas.ozlabs.org (Postfix) with ESMTPS id 4SPrJ76n3fz1yQL for ; Wed, 8 Nov 2023 01:31:35 +1100 (AEDT) Received: from server2.sourceware.org (localhost [IPv6:::1]) by sourceware.org (Postfix) with ESMTP id 3549D3857704 for ; Tue, 7 Nov 2023 14:31:30 +0000 (GMT) X-Original-To: gcc-patches@gcc.gnu.org Delivered-To: gcc-patches@gcc.gnu.org Received: from mgamail.intel.com (mgamail.intel.com [134.134.136.126]) by sourceware.org (Postfix) with ESMTPS id 6877D3858422 for ; Tue, 7 Nov 2023 14:31:13 +0000 (GMT) DMARC-Filter: OpenDMARC Filter v1.4.2 sourceware.org 6877D3858422 Authentication-Results: sourceware.org; dmarc=pass (p=none dis=none) header.from=intel.com Authentication-Results: sourceware.org; spf=pass smtp.mailfrom=intel.com ARC-Filter: OpenARC Filter v1.0.0 sourceware.org 6877D3858422 Authentication-Results: server2.sourceware.org; arc=none smtp.remote-ip=134.134.136.126 ARC-Seal: i=1; a=rsa-sha256; d=sourceware.org; s=key; t=1699367478; cv=none; b=JVS2CvfngXAAi1/IG/BmEyQ1VM/R7HfgDq68+F1Wd6CN2NVJRBP3ztTt/cmBKX8ZtY5GZahOQau3BfsfmbWQGko++LTF6rXAPrAsSMEZGR6JZhYjMjbr7ThBhzORpI4RP19fAjfayurd8oaBSoClpRmZ2kGh39mcEX5stH3PAfw= ARC-Message-Signature: i=1; a=rsa-sha256; d=sourceware.org; s=key; t=1699367478; c=relaxed/simple; bh=a8Duzc2GNiw8jLmjAanX0g6u0ZBbMTijBU4urfdOdNM=; h=DKIM-Signature:From:To:Subject:Date:Message-Id:MIME-Version; b=UaKNWXYAcLWUaE3rc3aQdbVh7MjzvmouLZAeLhCN5o/xQwaUGtQvIArNuEDor8CgJQMNBLMg2+KqRhlwQh9Ao+Ue12g5SNR5ajWlWUjujgwoSYw7g98V/CBt4AWmetPMTnpNEwPpKk9+neWuej+wLzQAnycSUfoRwyVwHgigoAo= ARC-Authentication-Results: i=1; server2.sourceware.org DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1699367473; x=1730903473; h=from:to:cc:subject:date:message-id:mime-version: content-transfer-encoding; bh=a8Duzc2GNiw8jLmjAanX0g6u0ZBbMTijBU4urfdOdNM=; b=fdTR494jxP3zSw2Ksg7JfOGI9AY+cSPqoyCCUgyhHOqo4KRFjGPRT3kv LfzPKl3VEhlifnM1Dr/yv1w6ixLIIwuxilKdyzsimGVgr6U6QIhLG3KcK sXQww9q0ccF6/JP8HMmS2dWkVeORZhOvDJqmYI6Kk1Z/INwifoea0+tq+ WS/wEHOg8jX5aLvXbvR4lUwSoO+joHnFB016umtP4gezu0YZs/C2HpHqp SOw5mDDI+jT2yDcrdiy1ad4ziM1OLT4QzPycfaHo9g7IzQUeJU8xMsnfP Ddu8+CFs3XFbmTIEC6LKaZSLPZGgIy8jcZV0MmEEzQE7rd5rU3tTzT3go Q==; X-IronPort-AV: E=McAfee;i="6600,9927,10887"; a="374548790" X-IronPort-AV: E=Sophos;i="6.03,283,1694761200"; d="scan'208";a="374548790" Received: from orviesa002.jf.intel.com ([10.64.159.142]) by orsmga106.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 07 Nov 2023 06:31:13 -0800 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="6.03,283,1694761200"; d="scan'208";a="3811951" Received: from shvmail03.sh.intel.com ([10.239.245.20]) by orviesa002.jf.intel.com with ESMTP; 07 Nov 2023 06:31:02 -0800 Received: from pli-ubuntu.sh.intel.com (pli-ubuntu.sh.intel.com [10.239.159.47]) by shvmail03.sh.intel.com (Postfix) with ESMTP id E08DD1005666; Tue, 7 Nov 2023 22:31:00 +0800 (CST) From: pan2.li@intel.com To: gcc-patches@gcc.gnu.org Cc: juzhe.zhong@rivai.ai, pan2.li@intel.com, yanzhang.wang@intel.com, kito.cheng@gmail.com Subject: [PATCH v1] ISC-V: Support FP floor to i/l/ll diff size autovec Date: Tue, 7 Nov 2023 22:30:54 +0800 Message-Id: <20231107143054.3011942-1-pan2.li@intel.com> X-Mailer: git-send-email 2.34.1 MIME-Version: 1.0 X-Spam-Status: No, score=-11.2 required=5.0 tests=BAYES_00, DKIMWL_WL_HIGH, DKIM_SIGNED, DKIM_VALID, DKIM_VALID_AU, DKIM_VALID_EF, GIT_PATCH_0, KAM_SHORT, SPF_HELO_NONE, SPF_NONE, 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: 2.1.30 Precedence: list List-Id: Gcc-patches mailing list List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: gcc-patches-bounces+incoming=patchwork.ozlabs.org@gcc.gnu.org From: Pan Li This patch would like to support the FP below API auto vectorization with different type size +----------+-----------+----------+ | API | RV64 | RV32 | +----------+-----------+----------+ | ifloor | DF => SI | DF => SI | | ifloorf | - | - | | lfloor | - | DF => SI | | lfloorf | SF => DI | - | | llfloor | - | - | | llfloorf | SF => DI | SF => DI | +----------+-----------+----------+ Given below code: void test_lfloorf (long *out, float *in, unsigned count) { for (unsigned i = 0; i < count; i++) out[i] = __builtin_lceilf (in[i]); } Before this patch: .L3: flw fa0,0(s0) addi s0,s0,4 addi s1,s1,8 call floorf fcvt.l.s a5,fa0,rtz sd a5,-8(s1) bne s2,s0,.L3 After this patch: fsrmi 2 // RDN mode .L3: vsetvli a5,a2,e32,mf2,ta,ma vle32.v v2,0(a1) slli a3,a5,2 slli a4,a5,3 vfwcvt.x.f.v v1,v2 sub a2,a2,a5 vse64.v v1,0(a0) add a1,a1,a3 add a0,a0,a4 bne a2,zero,.L3 Unfortunately, the HF mode is not include due to it requires additional middle-end support from internal-fun.def. gcc/ChangeLog: * config/riscv/autovec.md: Remove the size check of lfloor. * config/riscv/riscv-v.cc (expand_vec_lfloor): Leverage emit_vec_rounding_to_integer for floor. gcc/testsuite/ChangeLog: * gcc.target/riscv/rvv/autovec/unop/math-ifloor-1.c: New test. * gcc.target/riscv/rvv/autovec/unop/math-ifloor-run-1.c: New test. * gcc.target/riscv/rvv/autovec/unop/math-lfloor-rv32-0.c: New test. * gcc.target/riscv/rvv/autovec/unop/math-lfloor-rv32-run-0.c: New test. * gcc.target/riscv/rvv/autovec/unop/math-lfloorf-rv64-0.c: New test. * gcc.target/riscv/rvv/autovec/unop/math-lfloorf-rv64-run-0.c: New test. * gcc.target/riscv/rvv/autovec/unop/math-llfloorf-0.c: New test. * gcc.target/riscv/rvv/autovec/unop/math-llfloorf-run-0.c: New test. * gcc.target/riscv/rvv/autovec/vls/math-ifloor-1.c: New test. * gcc.target/riscv/rvv/autovec/vls/math-lfloor-rv32-0.c: New test. * gcc.target/riscv/rvv/autovec/vls/math-lfloorf-rv64-0.c: New test. * gcc.target/riscv/rvv/autovec/vls/math-llfloorf-0.c: New test. Signed-off-by: Pan Li Signed-off-by: Pan Li --- gcc/config/riscv/autovec.md | 6 +- gcc/config/riscv/riscv-v.cc | 8 +- .../riscv/rvv/autovec/unop/math-ifloor-1.c | 18 ++++ .../rvv/autovec/unop/math-ifloor-run-1.c | 83 ++++++++++++++++++ .../rvv/autovec/unop/math-lfloor-rv32-0.c | 18 ++++ .../rvv/autovec/unop/math-lfloor-rv32-run-0.c | 83 ++++++++++++++++++ .../rvv/autovec/unop/math-lfloorf-rv64-0.c | 18 ++++ .../autovec/unop/math-lfloorf-rv64-run-0.c | 84 +++++++++++++++++++ .../riscv/rvv/autovec/unop/math-llfloorf-0.c | 19 +++++ .../rvv/autovec/unop/math-llfloorf-run-0.c | 84 +++++++++++++++++++ .../riscv/rvv/autovec/vls/math-ifloor-1.c | 27 ++++++ .../rvv/autovec/vls/math-lfloor-rv32-0.c | 27 ++++++ .../rvv/autovec/vls/math-lfloorf-rv64-0.c | 27 ++++++ .../riscv/rvv/autovec/vls/math-llfloorf-0.c | 27 ++++++ 14 files changed, 520 insertions(+), 9 deletions(-) create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-ifloor-1.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-ifloor-run-1.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-lfloor-rv32-0.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-lfloor-rv32-run-0.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-lfloorf-rv64-0.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-lfloorf-rv64-run-0.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-llfloorf-0.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-llfloorf-run-0.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/vls/math-ifloor-1.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/vls/math-lfloor-rv32-0.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/vls/math-lfloorf-rv64-0.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/vls/math-llfloorf-0.c diff --git a/gcc/config/riscv/autovec.md b/gcc/config/riscv/autovec.md index b59bb880a45..973dc4ac235 100644 --- a/gcc/config/riscv/autovec.md +++ b/gcc/config/riscv/autovec.md @@ -2486,8 +2486,7 @@ (define_expand "lceil2" (define_expand "lfloor2" [(match_operand: 0 "register_operand") (match_operand:V_VLS_F_CONVERT_SI 1 "register_operand")] - "TARGET_VECTOR && !flag_trapping_math && !flag_rounding_math - && known_eq (GET_MODE_SIZE (mode), GET_MODE_SIZE (mode))" + "TARGET_VECTOR && !flag_trapping_math && !flag_rounding_math" { riscv_vector::expand_vec_lfloor (operands[0], operands[1], mode, mode); DONE; @@ -2497,8 +2496,7 @@ (define_expand "lfloor2" (define_expand "lfloor2" [(match_operand: 0 "register_operand") (match_operand:V_VLS_F_CONVERT_DI 1 "register_operand")] - "TARGET_VECTOR && !flag_trapping_math && !flag_rounding_math - && known_eq (GET_MODE_SIZE (mode), GET_MODE_SIZE (mode))" + "TARGET_VECTOR && !flag_trapping_math && !flag_rounding_math" { riscv_vector::expand_vec_lfloor (operands[0], operands[1], mode, mode); DONE; diff --git a/gcc/config/riscv/riscv-v.cc b/gcc/config/riscv/riscv-v.cc index 65a04c47ddf..c32cd8abe6c 100644 --- a/gcc/config/riscv/riscv-v.cc +++ b/gcc/config/riscv/riscv-v.cc @@ -4184,12 +4184,10 @@ expand_vec_lceil (rtx op_0, rtx op_1, machine_mode vec_fp_mode, void expand_vec_lfloor (rtx op_0, rtx op_1, machine_mode vec_fp_mode, - machine_mode vec_long_mode) + machine_mode vec_int_mode) { - gcc_assert (known_eq (GET_MODE_SIZE (vec_fp_mode), - GET_MODE_SIZE (vec_long_mode))); - - emit_vec_cvt_x_f (op_0, op_1, UNARY_OP_FRM_RDN, vec_fp_mode); + emit_vec_rounding_to_integer (op_0, op_1, vec_fp_mode, vec_int_mode, + UNARY_OP_FRM_RDN); } /* Vectorize popcount by the Wilkes-Wheeler-Gill algorithm that libgcc uses as diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-ifloor-1.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-ifloor-1.c new file mode 100644 index 00000000000..4eb63aedb30 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-ifloor-1.c @@ -0,0 +1,18 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gcv -mabi=lp64d -O3 -ftree-vectorize -fno-vect-cost-model -ffast-math -fno-schedule-insns -fno-schedule-insns2" } */ +/* { dg-final { check-function-bodies "**" "" } } */ + +#include "test-math.h" + +/* +** test_double_int___builtin_ifloor: +** frrm\s+[atx][0-9]+ +** ... +** fsrmi\s+2 +** ... +** vfncvt\.x\.f\.w\s+v[0-9]+,\s*v[0-9]+ +** ... +** fsrm\s+[atx][0-9]+ +** ret +*/ +TEST_UNARY_CALL_CVT (double, int, __builtin_ifloor) diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-ifloor-run-1.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-ifloor-run-1.c new file mode 100644 index 00000000000..ee68f71a05e --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-ifloor-run-1.c @@ -0,0 +1,83 @@ +/* { dg-do run { target { riscv_v } } } */ +/* { dg-additional-options "-std=c99 -O3 -ftree-vectorize -fno-vect-cost-model -ffast-math" } */ + +#include "test-math.h" + +#define ARRAY_SIZE 128 + +double in[ARRAY_SIZE]; +int out[ARRAY_SIZE]; +int ref[ARRAY_SIZE]; + +TEST_UNARY_CALL_CVT (double, int, __builtin_ifloor) +TEST_ASSERT (int) + +TEST_INIT_CVT (double, 0.0, int, __builtin_ifloor (-0.0), 1) +TEST_INIT_CVT (double, -0.0, int, __builtin_ifloor (-0.0), 2) +TEST_INIT_CVT (double, 1.2, int, __builtin_ifloor (1.2), 3) +TEST_INIT_CVT (double, -1.2, int, __builtin_ifloor (-1.2), 4) +TEST_INIT_CVT (double, 1.5, int, __builtin_ifloor (1.5), 5) +TEST_INIT_CVT (double, -1.5, int, __builtin_ifloor (-1.5), 6) +TEST_INIT_CVT (double, 1.8, int, __builtin_ifloor (1.8), 7) +TEST_INIT_CVT (double, -1.8, int, __builtin_ifloor (-1.8), 8) +TEST_INIT_CVT (double, 0.2, int, __builtin_ifloor (0.2), 9) +TEST_INIT_CVT (double, -0.2, int, __builtin_ifloor (-0.2), 10) +TEST_INIT_CVT (double, 0.5, int, __builtin_ifloor (0.5), 11) +TEST_INIT_CVT (double, -0.5, int, __builtin_ifloor (-0.5), 12) +TEST_INIT_CVT (double, 0.8, int, __builtin_ifloor (0.8), 13) +TEST_INIT_CVT (double, -0.8, int, __builtin_ifloor (-0.8), 14) +TEST_INIT_CVT (double, 4.0, int, __builtin_ifloor (4.0), 15) +TEST_INIT_CVT (double, -4.0, int, __builtin_ifloor (-4.0), 16) +TEST_INIT_CVT (double, 4503599627370495.5, int, __builtin_ifloor (4503599627370495.5), 17) +TEST_INIT_CVT (double, 4503599627370497.0, int, __builtin_ifloor (4503599627370497.0), 18) +TEST_INIT_CVT (double, -4503599627370495.5, int, __builtin_ifloor (-4503599627370495.5), 19) +TEST_INIT_CVT (double, -4503599627370496.0, int, __builtin_ifloor (-4503599627370496.0), 20) +TEST_INIT_CVT (double, 2147483647.0, int, __builtin_ifloor (2147483647.0), 21) +TEST_INIT_CVT (double, -2147483648.0, int, __builtin_ifloor (-2147483648.0), 22) +TEST_INIT_CVT (double, 2147483647.0000002384185791, int, __builtin_ifloor (2147483647.0000002384185791), 23) +TEST_INIT_CVT (double, -2147483648.0000004768371582, int, 0x80000000, 24) +TEST_INIT_CVT (double, 9223372036854774784.0, int, __builtin_ifloor (9223372036854774784.0), 25) +TEST_INIT_CVT (double, 9223372036854775808.0, int, 0x7fffffff, 26) +TEST_INIT_CVT (double, -9223372036854775808.0, int, __builtin_ifloor (-9223372036854775808.0), 27) +TEST_INIT_CVT (double, -9223372036854777856.0, int, 0x80000000, 28) +TEST_INIT_CVT (double, __builtin_inf (), int, __builtin_ifloor (__builtin_inf ()), 29) +TEST_INIT_CVT (double, -__builtin_inf (), int, __builtin_ifloor (-__builtin_inf ()), 30) +TEST_INIT_CVT (double, __builtin_nan (""), int, 0x7fffffff, 31) + +int +main () +{ + RUN_TEST_CVT (double, int, 1, __builtin_ifloor, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, int, 2, __builtin_ifloor, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, int, 3, __builtin_ifloor, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, int, 4, __builtin_ifloor, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, int, 5, __builtin_ifloor, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, int, 6, __builtin_ifloor, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, int, 7, __builtin_ifloor, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, int, 8, __builtin_ifloor, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, int, 9, __builtin_ifloor, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, int, 10, __builtin_ifloor, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, int, 11, __builtin_ifloor, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, int, 12, __builtin_ifloor, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, int, 13, __builtin_ifloor, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, int, 14, __builtin_ifloor, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, int, 15, __builtin_ifloor, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, int, 16, __builtin_ifloor, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, int, 17, __builtin_ifloor, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, int, 18, __builtin_ifloor, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, int, 19, __builtin_ifloor, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, int, 20, __builtin_ifloor, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, int, 21, __builtin_ifloor, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, int, 22, __builtin_ifloor, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, int, 23, __builtin_ifloor, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, int, 24, __builtin_ifloor, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, int, 25, __builtin_ifloor, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, int, 26, __builtin_ifloor, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, int, 27, __builtin_ifloor, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, int, 28, __builtin_ifloor, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, int, 29, __builtin_ifloor, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, int, 30, __builtin_ifloor, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, int, 31, __builtin_ifloor, in, out, ref, ARRAY_SIZE); + + return 0; +} diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-lfloor-rv32-0.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-lfloor-rv32-0.c new file mode 100644 index 00000000000..29c45f3980e --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-lfloor-rv32-0.c @@ -0,0 +1,18 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv32gcv -mabi=ilp32d -O3 -ftree-vectorize -fno-vect-cost-model -ffast-math -fno-schedule-insns -fno-schedule-insns2" } */ +/* { dg-final { check-function-bodies "**" "" } } */ + +#include "test-math.h" + +/* +** test_double_int___builtin_lfloor: +** frrm\s+[atx][0-9]+ +** ... +** fsrmi\s+2 +** ... +** vfncvt\.x\.f\.w\s+v[0-9]+,\s*v[0-9]+ +** ... +** fsrm\s+[atx][0-9]+ +** ret +*/ +TEST_UNARY_CALL_CVT (double, int, __builtin_lfloor) diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-lfloor-rv32-run-0.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-lfloor-rv32-run-0.c new file mode 100644 index 00000000000..dcecee095f5 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-lfloor-rv32-run-0.c @@ -0,0 +1,83 @@ +/* { dg-do run { target { riscv_v && rv32 } } } */ +/* { dg-additional-options "-std=c99 -O3 -ftree-vectorize -fno-vect-cost-model -ffast-math" } */ + +#include "test-math.h" + +#define ARRAY_SIZE 128 + +double in[ARRAY_SIZE]; +long out[ARRAY_SIZE]; +long ref[ARRAY_SIZE]; + +TEST_UNARY_CALL_CVT (double, long, __builtin_lfloor) +TEST_ASSERT (long) + +TEST_INIT_CVT (double, 0.0, long, __builtin_lfloor (-0.0), 1) +TEST_INIT_CVT (double, -0.0, long, __builtin_lfloor (-0.0), 2) +TEST_INIT_CVT (double, 1.2, long, __builtin_lfloor (1.2), 3) +TEST_INIT_CVT (double, -1.2, long, __builtin_lfloor (-1.2), 4) +TEST_INIT_CVT (double, 1.5, long, __builtin_lfloor (1.5), 5) +TEST_INIT_CVT (double, -1.5, long, __builtin_lfloor (-1.5), 6) +TEST_INIT_CVT (double, 1.8, long, __builtin_lfloor (1.8), 7) +TEST_INIT_CVT (double, -1.8, long, __builtin_lfloor (-1.8), 8) +TEST_INIT_CVT (double, 0.2, long, __builtin_lfloor (0.2), 9) +TEST_INIT_CVT (double, -0.2, long, __builtin_lfloor (-0.2), 10) +TEST_INIT_CVT (double, 0.5, long, __builtin_lfloor (0.5), 11) +TEST_INIT_CVT (double, -0.5, long, __builtin_lfloor (-0.5), 12) +TEST_INIT_CVT (double, 0.8, long, __builtin_lfloor (0.8), 13) +TEST_INIT_CVT (double, -0.8, long, __builtin_lfloor (-0.8), 14) +TEST_INIT_CVT (double, 4.0, long, __builtin_lfloor (4.0), 15) +TEST_INIT_CVT (double, -4.0, long, __builtin_lfloor (-4.0), 16) +TEST_INIT_CVT (double, 4503599627370495.5, long, __builtin_lfloor (4503599627370495.5), 17) +TEST_INIT_CVT (double, 4503599627370497.0, long, __builtin_lfloor (4503599627370497.0), 18) +TEST_INIT_CVT (double, -4503599627370495.5, long, __builtin_lfloor (-4503599627370495.5), 19) +TEST_INIT_CVT (double, -4503599627370496.0, long, __builtin_lfloor (-4503599627370496.0), 20) +TEST_INIT_CVT (double, 2147483647.0, long, __builtin_lfloor (2147483647.0), 21) +TEST_INIT_CVT (double, -2147483648.0, long, __builtin_lfloor (-2147483648.0), 22) +TEST_INIT_CVT (double, 2147483647.0000002384185791, long, __builtin_lfloor (2147483647.0000002384185791), 23) +TEST_INIT_CVT (double, -2147483648.0000004768371582, long, 0x80000000, 24) +TEST_INIT_CVT (double, 9223372036854774784.0, long, __builtin_lfloor (9223372036854774784.0), 25) +TEST_INIT_CVT (double, 9223372036854775808.0, long, 0x7fffffff, 26) +TEST_INIT_CVT (double, -9223372036854775808.0, long, __builtin_lfloor (-9223372036854775808.0), 27) +TEST_INIT_CVT (double, -9223372036854777856.0, long, 0x80000000, 28) +TEST_INIT_CVT (double, __builtin_inf (), long, __builtin_lfloor (__builtin_inf ()), 29) +TEST_INIT_CVT (double, -__builtin_inf (), long, __builtin_lfloor (-__builtin_inf ()), 30) +TEST_INIT_CVT (double, __builtin_nan (""), long, 0x7fffffff, 31) + +long +main () +{ + RUN_TEST_CVT (double, long, 1, __builtin_lfloor, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, long, 2, __builtin_lfloor, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, long, 3, __builtin_lfloor, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, long, 4, __builtin_lfloor, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, long, 5, __builtin_lfloor, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, long, 6, __builtin_lfloor, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, long, 7, __builtin_lfloor, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, long, 8, __builtin_lfloor, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, long, 9, __builtin_lfloor, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, long, 10, __builtin_lfloor, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, long, 11, __builtin_lfloor, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, long, 12, __builtin_lfloor, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, long, 13, __builtin_lfloor, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, long, 14, __builtin_lfloor, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, long, 15, __builtin_lfloor, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, long, 16, __builtin_lfloor, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, long, 17, __builtin_lfloor, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, long, 18, __builtin_lfloor, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, long, 19, __builtin_lfloor, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, long, 20, __builtin_lfloor, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, long, 21, __builtin_lfloor, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, long, 22, __builtin_lfloor, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, long, 23, __builtin_lfloor, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, long, 24, __builtin_lfloor, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, long, 25, __builtin_lfloor, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, long, 26, __builtin_lfloor, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, long, 27, __builtin_lfloor, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, long, 28, __builtin_lfloor, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, long, 29, __builtin_lfloor, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, long, 30, __builtin_lfloor, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, long, 31, __builtin_lfloor, in, out, ref, ARRAY_SIZE); + + return 0; +} diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-lfloorf-rv64-0.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-lfloorf-rv64-0.c new file mode 100644 index 00000000000..5c4a619df4a --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-lfloorf-rv64-0.c @@ -0,0 +1,18 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gcv -mabi=lp64d -O3 -ftree-vectorize -fno-vect-cost-model -ffast-math -fno-schedule-insns -fno-schedule-insns2" } */ +/* { dg-final { check-function-bodies "**" "" } } */ + +#include "test-math.h" + +/* +** test_float_long___builtin_lfloorf: +** frrm\s+[atx][0-9]+ +** ... +** fsrmi\s+2 +** ... +** vfwcvt\.x\.f\.v\s+v[0-9]+,\s*v[0-9]+ +** ... +** fsrm\s+[atx][0-9]+ +** ret +*/ +TEST_UNARY_CALL_CVT (float, long, __builtin_lfloorf) diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-lfloorf-rv64-run-0.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-lfloorf-rv64-run-0.c new file mode 100644 index 00000000000..59af94b8167 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-lfloorf-rv64-run-0.c @@ -0,0 +1,84 @@ +/* { dg-do run { target { riscv_v && rv64 } } } */ +/* { dg-additional-options "-std=c99 -O3 -ftree-vectorize -fno-vect-cost-model -ffast-math" } */ + +#include +#include "test-math.h" + +#define ARRAY_SIZE 128 + +float in[ARRAY_SIZE]; +int64_t out[ARRAY_SIZE]; +int64_t ref[ARRAY_SIZE]; + +TEST_UNARY_CALL_CVT (float, int64_t, __builtin_lfloorf) +TEST_ASSERT (int64_t) + +TEST_INIT_CVT (float, 0.0, int64_t, __builtin_lfloorf (-0.0), 1) +TEST_INIT_CVT (float, -0.0, int64_t, __builtin_lfloorf (-0.0), 2) +TEST_INIT_CVT (float, 1.2, int64_t, __builtin_lfloorf (1.2), 3) +TEST_INIT_CVT (float, -1.2, int64_t, __builtin_lfloorf (-1.2), 4) +TEST_INIT_CVT (float, 1.5, int64_t, __builtin_lfloorf (1.5), 5) +TEST_INIT_CVT (float, -1.5, int64_t, __builtin_lfloorf (-1.5), 6) +TEST_INIT_CVT (float, 1.8, int64_t, __builtin_lfloorf (1.8), 7) +TEST_INIT_CVT (float, -1.8, int64_t, __builtin_lfloorf (-1.8), 8) +TEST_INIT_CVT (float, 0.2, int64_t, __builtin_lfloorf (0.2), 9) +TEST_INIT_CVT (float, -0.2, int64_t, __builtin_lfloorf (-0.2), 10) +TEST_INIT_CVT (float, 0.5, int64_t, __builtin_lfloorf (0.5), 11) +TEST_INIT_CVT (float, -0.5, int64_t, __builtin_lfloorf (-0.5), 12) +TEST_INIT_CVT (float, 0.8, int64_t, __builtin_lfloorf (0.8), 13) +TEST_INIT_CVT (float, -0.8, int64_t, __builtin_lfloorf (-0.8), 14) +TEST_INIT_CVT (float, 4.0, int64_t, __builtin_lfloorf (4.0), 15) +TEST_INIT_CVT (float, -4.0, int64_t, __builtin_lfloorf (-4.0), 16) +TEST_INIT_CVT (float, 8388607.5, int64_t, __builtin_lfloorf (8388607.5), 17) +TEST_INIT_CVT (float, 8388609.0, int64_t, __builtin_lfloorf (8388609.0), 18) +TEST_INIT_CVT (float, -8388607.5, int64_t, __builtin_lfloorf (-8388607.5), 19) +TEST_INIT_CVT (float, -8388609.0, int64_t, __builtin_lfloorf (-8388609.0), 20) +TEST_INIT_CVT (float, 2147483520.0, int64_t, __builtin_lfloorf (2147483520.0), 21) +TEST_INIT_CVT (float, 2147483648.0, int64_t, __builtin_lfloorf (2147483648.0), 22) +TEST_INIT_CVT (float, -2147483648.0, int64_t, __builtin_lfloorf (-2147483648.0), 23) +TEST_INIT_CVT (float, -2147483904.0, int64_t, __builtin_lfloorf (-2147483904.0), 24) +TEST_INIT_CVT (float, 9223371487098961920.0, int64_t, __builtin_lfloorf (9223371487098961920.0), 25) +TEST_INIT_CVT (float, 9223372036854775808.0, int64_t, 0x7fffffffffffffff, 26) +TEST_INIT_CVT (float, -9223372036854775808.0, int64_t, __builtin_lfloorf (-9223372036854775808.0), 27) +TEST_INIT_CVT (float, -9223373136366403584.0, int64_t, 0x8000000000000000, 28) +TEST_INIT_CVT (float, __builtin_inf (), int64_t, __builtin_lfloorf (__builtin_inf ()), 29) +TEST_INIT_CVT (float, -__builtin_inf (), int64_t, __builtin_lfloorf (-__builtin_inf ()), 30) +TEST_INIT_CVT (float, __builtin_nan (""), int64_t, 0x7fffffffffffffff, 31) + +int64_t +main () +{ + RUN_TEST_CVT (float, int64_t, 1, __builtin_lfloorf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, int64_t, 2, __builtin_lfloorf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, int64_t, 3, __builtin_lfloorf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, int64_t, 4, __builtin_lfloorf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, int64_t, 5, __builtin_lfloorf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, int64_t, 6, __builtin_lfloorf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, int64_t, 7, __builtin_lfloorf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, int64_t, 8, __builtin_lfloorf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, int64_t, 9, __builtin_lfloorf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, int64_t, 10, __builtin_lfloorf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, int64_t, 11, __builtin_lfloorf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, int64_t, 12, __builtin_lfloorf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, int64_t, 13, __builtin_lfloorf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, int64_t, 14, __builtin_lfloorf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, int64_t, 15, __builtin_lfloorf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, int64_t, 16, __builtin_lfloorf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, int64_t, 17, __builtin_lfloorf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, int64_t, 18, __builtin_lfloorf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, int64_t, 19, __builtin_lfloorf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, int64_t, 20, __builtin_lfloorf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, int64_t, 21, __builtin_lfloorf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, int64_t, 22, __builtin_lfloorf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, int64_t, 23, __builtin_lfloorf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, int64_t, 24, __builtin_lfloorf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, int64_t, 25, __builtin_lfloorf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, int64_t, 26, __builtin_lfloorf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, int64_t, 27, __builtin_lfloorf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, int64_t, 28, __builtin_lfloorf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, int64_t, 29, __builtin_lfloorf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, int64_t, 30, __builtin_lfloorf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, int64_t, 31, __builtin_lfloorf, in, out, ref, ARRAY_SIZE); + + return 0; +} diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-llfloorf-0.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-llfloorf-0.c new file mode 100644 index 00000000000..562fc820551 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-llfloorf-0.c @@ -0,0 +1,19 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gcv -mabi=lp64d -O3 -ftree-vectorize -fno-vect-cost-model -ffast-math -fno-schedule-insns -fno-schedule-insns2" } */ +/* { dg-final { check-function-bodies "**" "" } } */ + +#include +#include "test-math.h" + +/* +** test_float_int64_t___builtin_llfloorf: +** frrm\s+[atx][0-9]+ +** ... +** fsrmi\s+2 +** ... +** vfwcvt\.x\.f\.v\s+v[0-9]+,\s*v[0-9]+ +** ... +** fsrm\s+[atx][0-9]+ +** ret +*/ +TEST_UNARY_CALL_CVT (float, int64_t, __builtin_llfloorf) diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-llfloorf-run-0.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-llfloorf-run-0.c new file mode 100644 index 00000000000..da68fd10c3f --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-llfloorf-run-0.c @@ -0,0 +1,84 @@ +/* { dg-do run { target { riscv_v } } } */ +/* { dg-additional-options "-std=c99 -O3 -ftree-vectorize -fno-vect-cost-model -ffast-math" } */ + +#include +#include "test-math.h" + +#define ARRAY_SIZE 128 + +float in[ARRAY_SIZE]; +int64_t out[ARRAY_SIZE]; +int64_t ref[ARRAY_SIZE]; + +TEST_UNARY_CALL_CVT (float, int64_t, __builtin_llfloorf) +TEST_ASSERT (int64_t) + +TEST_INIT_CVT (float, 0.0, int64_t, __builtin_llfloorf (-0.0), 1) +TEST_INIT_CVT (float, -0.0, int64_t, __builtin_llfloorf (-0.0), 2) +TEST_INIT_CVT (float, 1.2, int64_t, __builtin_llfloorf (1.2), 3) +TEST_INIT_CVT (float, -1.2, int64_t, __builtin_llfloorf (-1.2), 4) +TEST_INIT_CVT (float, 1.5, int64_t, __builtin_llfloorf (1.5), 5) +TEST_INIT_CVT (float, -1.5, int64_t, __builtin_llfloorf (-1.5), 6) +TEST_INIT_CVT (float, 1.8, int64_t, __builtin_llfloorf (1.8), 7) +TEST_INIT_CVT (float, -1.8, int64_t, __builtin_llfloorf (-1.8), 8) +TEST_INIT_CVT (float, 0.2, int64_t, __builtin_llfloorf (0.2), 9) +TEST_INIT_CVT (float, -0.2, int64_t, __builtin_llfloorf (-0.2), 10) +TEST_INIT_CVT (float, 0.5, int64_t, __builtin_llfloorf (0.5), 11) +TEST_INIT_CVT (float, -0.5, int64_t, __builtin_llfloorf (-0.5), 12) +TEST_INIT_CVT (float, 0.8, int64_t, __builtin_llfloorf (0.8), 13) +TEST_INIT_CVT (float, -0.8, int64_t, __builtin_llfloorf (-0.8), 14) +TEST_INIT_CVT (float, 4.0, int64_t, __builtin_llfloorf (4.0), 15) +TEST_INIT_CVT (float, -4.0, int64_t, __builtin_llfloorf (-4.0), 16) +TEST_INIT_CVT (float, 8388607.5, int64_t, __builtin_llfloorf (8388607.5), 17) +TEST_INIT_CVT (float, 8388609.0, int64_t, __builtin_llfloorf (8388609.0), 18) +TEST_INIT_CVT (float, -8388607.5, int64_t, __builtin_llfloorf (-8388607.5), 19) +TEST_INIT_CVT (float, -8388609.0, int64_t, __builtin_llfloorf (-8388609.0), 20) +TEST_INIT_CVT (float, 2147483520.0, int64_t, __builtin_llfloorf (2147483520.0), 21) +TEST_INIT_CVT (float, 2147483648.0, int64_t, __builtin_llfloorf (2147483648.0), 22) +TEST_INIT_CVT (float, -2147483648.0, int64_t, __builtin_llfloorf (-2147483648.0), 23) +TEST_INIT_CVT (float, -2147483904.0, int64_t, __builtin_llfloorf (-2147483904.0), 24) +TEST_INIT_CVT (float, 9223371487098961920.0, int64_t, __builtin_llfloorf (9223371487098961920.0), 25) +TEST_INIT_CVT (float, 9223372036854775808.0, int64_t, 0x7fffffffffffffff, 26) +TEST_INIT_CVT (float, -9223372036854775808.0, int64_t, __builtin_llfloorf (-9223372036854775808.0), 27) +TEST_INIT_CVT (float, -9223373136366403584.0, int64_t, 0x8000000000000000, 28) +TEST_INIT_CVT (float, __builtin_inf (), int64_t, __builtin_llfloorf (__builtin_inf ()), 29) +TEST_INIT_CVT (float, -__builtin_inf (), int64_t, __builtin_llfloorf (-__builtin_inf ()), 30) +TEST_INIT_CVT (float, __builtin_nan (""), int64_t, 0x7fffffffffffffff, 31) + +int64_t +main () +{ + RUN_TEST_CVT (float, int64_t, 1, __builtin_llfloorf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, int64_t, 2, __builtin_llfloorf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, int64_t, 3, __builtin_llfloorf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, int64_t, 4, __builtin_llfloorf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, int64_t, 5, __builtin_llfloorf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, int64_t, 6, __builtin_llfloorf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, int64_t, 7, __builtin_llfloorf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, int64_t, 8, __builtin_llfloorf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, int64_t, 9, __builtin_llfloorf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, int64_t, 10, __builtin_llfloorf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, int64_t, 11, __builtin_llfloorf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, int64_t, 12, __builtin_llfloorf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, int64_t, 13, __builtin_llfloorf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, int64_t, 14, __builtin_llfloorf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, int64_t, 15, __builtin_llfloorf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, int64_t, 16, __builtin_llfloorf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, int64_t, 17, __builtin_llfloorf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, int64_t, 18, __builtin_llfloorf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, int64_t, 19, __builtin_llfloorf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, int64_t, 20, __builtin_llfloorf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, int64_t, 21, __builtin_llfloorf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, int64_t, 22, __builtin_llfloorf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, int64_t, 23, __builtin_llfloorf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, int64_t, 24, __builtin_llfloorf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, int64_t, 25, __builtin_llfloorf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, int64_t, 26, __builtin_llfloorf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, int64_t, 27, __builtin_llfloorf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, int64_t, 28, __builtin_llfloorf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, int64_t, 29, __builtin_llfloorf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, int64_t, 30, __builtin_llfloorf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, int64_t, 31, __builtin_llfloorf, in, out, ref, ARRAY_SIZE); + + return 0; +} diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls/math-ifloor-1.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls/math-ifloor-1.c new file mode 100644 index 00000000000..b6a2122c006 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls/math-ifloor-1.c @@ -0,0 +1,27 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gcv_zvl4096b -mabi=lp64d -O3 --param=riscv-autovec-lmul=m8 -ffast-math -fdump-tree-optimized" } */ + +#include "def.h" + +DEF_OP_V_CVT (ifloor, 1, double, int, __builtin_ifloor) +DEF_OP_V_CVT (ifloor, 2, double, int, __builtin_ifloor) +DEF_OP_V_CVT (ifloor, 4, double, int, __builtin_ifloor) +DEF_OP_V_CVT (ifloor, 8, double, int, __builtin_ifloor) +DEF_OP_V_CVT (ifloor, 16, double, int, __builtin_ifloor) +DEF_OP_V_CVT (ifloor, 32, double, int, __builtin_ifloor) +DEF_OP_V_CVT (ifloor, 64, double, int, __builtin_ifloor) +DEF_OP_V_CVT (ifloor, 128, double, int, __builtin_ifloor) +DEF_OP_V_CVT (ifloor, 256, double, int, __builtin_ifloor) +DEF_OP_V_CVT (ifloor, 512, double, int, __builtin_ifloor) + +/* { dg-final { scan-assembler-not {csrr} } } */ +/* { dg-final { scan-tree-dump-not "1,1" "optimized" } } */ +/* { dg-final { scan-tree-dump-not "2,2" "optimized" } } */ +/* { dg-final { scan-tree-dump-not "4,4" "optimized" } } */ +/* { dg-final { scan-tree-dump-not "16,16" "optimized" } } */ +/* { dg-final { scan-tree-dump-not "32,32" "optimized" } } */ +/* { dg-final { scan-tree-dump-not "64,64" "optimized" } } */ +/* { dg-final { scan-tree-dump-not "128,128" "optimized" } } */ +/* { dg-final { scan-tree-dump-not "256,256" "optimized" } } */ +/* { dg-final { scan-tree-dump-not "512,512" "optimized" } } */ +/* { dg-final { scan-assembler-times {vfncvt\.x\.f\.w\s+v[0-9]+,\s*v[0-9]+} 9 } } */ diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls/math-lfloor-rv32-0.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls/math-lfloor-rv32-0.c new file mode 100644 index 00000000000..f5a8311a3e8 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls/math-lfloor-rv32-0.c @@ -0,0 +1,27 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv32gcv_zvl4096b -mabi=ilp32d -O3 --param=riscv-autovec-lmul=m8 -ffast-math -fdump-tree-optimized" } */ + +#include "def.h" + +DEF_OP_V_CVT (lfloor, 1, double, int, __builtin_lfloor) +DEF_OP_V_CVT (lfloor, 2, double, int, __builtin_lfloor) +DEF_OP_V_CVT (lfloor, 4, double, int, __builtin_lfloor) +DEF_OP_V_CVT (lfloor, 8, double, int, __builtin_lfloor) +DEF_OP_V_CVT (lfloor, 16, double, int, __builtin_lfloor) +DEF_OP_V_CVT (lfloor, 32, double, int, __builtin_lfloor) +DEF_OP_V_CVT (lfloor, 64, double, int, __builtin_lfloor) +DEF_OP_V_CVT (lfloor, 128, double, int, __builtin_lfloor) +DEF_OP_V_CVT (lfloor, 256, double, int, __builtin_lfloor) +DEF_OP_V_CVT (lfloor, 512, double, int, __builtin_lfloor) + +/* { dg-final { scan-assembler-not {csrr} } } */ +/* { dg-final { scan-tree-dump-not "1,1" "optimized" } } */ +/* { dg-final { scan-tree-dump-not "2,2" "optimized" } } */ +/* { dg-final { scan-tree-dump-not "4,4" "optimized" } } */ +/* { dg-final { scan-tree-dump-not "16,16" "optimized" } } */ +/* { dg-final { scan-tree-dump-not "32,32" "optimized" } } */ +/* { dg-final { scan-tree-dump-not "64,64" "optimized" } } */ +/* { dg-final { scan-tree-dump-not "128,128" "optimized" } } */ +/* { dg-final { scan-tree-dump-not "256,256" "optimized" } } */ +/* { dg-final { scan-tree-dump-not "512,512" "optimized" } } */ +/* { dg-final { scan-assembler-times {vfncvt\.x\.f\.w\s+v[0-9]+,\s*v[0-9]+} 9 } } */ diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls/math-lfloorf-rv64-0.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls/math-lfloorf-rv64-0.c new file mode 100644 index 00000000000..08b1b7f9137 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls/math-lfloorf-rv64-0.c @@ -0,0 +1,27 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gcv_zvl4096b -mabi=lp64d -O3 --param=riscv-autovec-lmul=m8 -ffast-math -fdump-tree-optimized" } */ + +#include "def.h" + +DEF_OP_V_CVT (lfloorf, 1, float, long, __builtin_lfloorf) +DEF_OP_V_CVT (lfloorf, 2, float, long, __builtin_lfloorf) +DEF_OP_V_CVT (lfloorf, 4, float, long, __builtin_lfloorf) +DEF_OP_V_CVT (lfloorf, 8, float, long, __builtin_lfloorf) +DEF_OP_V_CVT (lfloorf, 16, float, long, __builtin_lfloorf) +DEF_OP_V_CVT (lfloorf, 32, float, long, __builtin_lfloorf) +DEF_OP_V_CVT (lfloorf, 64, float, long, __builtin_lfloorf) +DEF_OP_V_CVT (lfloorf, 128, float, long, __builtin_lfloorf) +DEF_OP_V_CVT (lfloorf, 256, float, long, __builtin_lfloorf) +DEF_OP_V_CVT (lfloorf, 512, float, long, __builtin_lfloorf) + +/* { dg-final { scan-assembler-not {csrr} } } */ +/* { dg-final { scan-tree-dump-not "1,1" "optimized" } } */ +/* { dg-final { scan-tree-dump-not "2,2" "optimized" } } */ +/* { dg-final { scan-tree-dump-not "4,4" "optimized" } } */ +/* { dg-final { scan-tree-dump-not "16,16" "optimized" } } */ +/* { dg-final { scan-tree-dump-not "32,32" "optimized" } } */ +/* { dg-final { scan-tree-dump-not "64,64" "optimized" } } */ +/* { dg-final { scan-tree-dump-not "128,128" "optimized" } } */ +/* { dg-final { scan-tree-dump-not "256,256" "optimized" } } */ +/* { dg-final { scan-tree-dump-not "512,512" "optimized" } } */ +/* { dg-final { scan-assembler-times {vfwcvt\.x\.f\.v\s+v[0-9]+,\s*v[0-9]+} 9 } } */ diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls/math-llfloorf-0.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls/math-llfloorf-0.c new file mode 100644 index 00000000000..b72eaf975c3 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls/math-llfloorf-0.c @@ -0,0 +1,27 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gcv_zvl4096b -mabi=lp64d -O3 --param=riscv-autovec-lmul=m8 -ffast-math -fdump-tree-optimized" } */ + +#include "def.h" + +DEF_OP_V_CVT (llfloorf, 1, float, int64_t, __builtin_llfloorf) +DEF_OP_V_CVT (llfloorf, 2, float, int64_t, __builtin_llfloorf) +DEF_OP_V_CVT (llfloorf, 4, float, int64_t, __builtin_llfloorf) +DEF_OP_V_CVT (llfloorf, 8, float, int64_t, __builtin_llfloorf) +DEF_OP_V_CVT (llfloorf, 16, float, int64_t, __builtin_llfloorf) +DEF_OP_V_CVT (llfloorf, 32, float, int64_t, __builtin_llfloorf) +DEF_OP_V_CVT (llfloorf, 64, float, int64_t, __builtin_llfloorf) +DEF_OP_V_CVT (llfloorf, 128, float, int64_t, __builtin_llfloorf) +DEF_OP_V_CVT (llfloorf, 256, float, int64_t, __builtin_llfloorf) +DEF_OP_V_CVT (llfloorf, 512, float, int64_t, __builtin_llfloorf) + +/* { dg-final { scan-assembler-not {csrr} } } */ +/* { dg-final { scan-tree-dump-not "1,1" "optimized" } } */ +/* { dg-final { scan-tree-dump-not "2,2" "optimized" } } */ +/* { dg-final { scan-tree-dump-not "4,4" "optimized" } } */ +/* { dg-final { scan-tree-dump-not "16,16" "optimized" } } */ +/* { dg-final { scan-tree-dump-not "32,32" "optimized" } } */ +/* { dg-final { scan-tree-dump-not "64,64" "optimized" } } */ +/* { dg-final { scan-tree-dump-not "128,128" "optimized" } } */ +/* { dg-final { scan-tree-dump-not "256,256" "optimized" } } */ +/* { dg-final { scan-tree-dump-not "512,512" "optimized" } } */ +/* { dg-final { scan-assembler-times {vfwcvt\.x\.f\.v\s+v[0-9]+,\s*v[0-9]+} 9 } } */