From patchwork Wed Oct 11 08:49:53 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "Li, Pan2" X-Patchwork-Id: 1846400 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=aujiD4Au; 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 4S560y3CRxz23jd for ; Wed, 11 Oct 2023 19:50:26 +1100 (AEDT) Received: from server2.sourceware.org (localhost [IPv6:::1]) by sourceware.org (Postfix) with ESMTP id 6FE873858025 for ; Wed, 11 Oct 2023 08:50:24 +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 [134.134.136.100]) by sourceware.org (Postfix) with ESMTPS id 971183858CDA for ; Wed, 11 Oct 2023 08:50:03 +0000 (GMT) DMARC-Filter: OpenDMARC Filter v1.4.2 sourceware.org 971183858CDA Authentication-Results: sourceware.org; dmarc=pass (p=none dis=none) header.from=intel.com Authentication-Results: sourceware.org; spf=pass smtp.mailfrom=intel.com DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1697014203; x=1728550203; h=from:to:cc:subject:date:message-id:mime-version: content-transfer-encoding; bh=KG1cSNytxfj492J6fDG4jguVrPOGoai+hOFTLo8IqnI=; b=aujiD4Aue3qSxwZs4S3lJvs6Yb1Rm3/YwTk0hQRx/hvCYKeX57OPEnR3 6coRQV8CsMoNYjpZ/d4vf3jQupclRVdEW8T2g1tF28Gq0o8/+JYB+G86/ +BgFfLS0zbOWKol35L7rSPLwv+U722WQEFAonOPGEFtniopw8hEEz1lao M+oq6snYA+2GVaWrGq30Kjn9+sChx8tmlKwrE2Db9AT1ZjNN0F1xOYWbE R17JSpvLu0EsUrgtFscoIINHx1kW+ooBe/RLerd4OzCA/2QfgcYBr6Rb8 3C093Kxr2aLhOP/OgCr9KlEU6TK4ZPGs82E7hN3y8IrlSCwncxChxrcSj A==; X-IronPort-AV: E=McAfee;i="6600,9927,10859"; a="451106401" X-IronPort-AV: E=Sophos;i="6.03,214,1694761200"; d="scan'208";a="451106401" Received: from fmsmga006.fm.intel.com ([10.253.24.20]) by orsmga105.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Oct 2023 01:49:57 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=McAfee;i="6600,9927,10859"; a="1001026834" X-IronPort-AV: E=Sophos;i="6.03,214,1694761200"; d="scan'208";a="1001026834" Received: from shvmail02.sh.intel.com ([10.239.244.9]) by fmsmga006.fm.intel.com with ESMTP; 11 Oct 2023 01:49:55 -0700 Received: from pli-ubuntu.sh.intel.com (pli-ubuntu.sh.intel.com [10.239.159.47]) by shvmail02.sh.intel.com (Postfix) with ESMTP id 4CA5C10050E8; Wed, 11 Oct 2023 16:49:54 +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] RISC-V: Support FP lrint/lrintf auto vectorization Date: Wed, 11 Oct 2023 16:49:53 +0800 Message-Id: <20231011084953.3748731-1-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 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 lrint/lrintf auto vectorization. * long lrint (double) for rv64 * long lrintf (float) for rv32 Due to the limitation that only the same size of data type are allowed in the vectorier, the standard name lrintmn2 only act on DF => DI for rv64, and SF => SI for rv32. Given we have code like: void test_lrint (long *out, double *in, unsigned count) { for (unsigned i = 0; i < count; i++) out[i] = __builtin_lrint (in[i]); } Before this patch: .L3: ... fld fa5,0(a1) fcvt.l.d a5,fa5,dyn sd a5,-8(a0) ... bne a1,a4,.L3 After this patch: .L3: ... vsetvli a3,zero,e64,m1,ta,ma vfcvt.x.f.v v1,v1 vsetvli zero,a2,e64,m1,ta,ma vse32.v v1,0(a0) ... bne a2,zero,.L3 The rest part like SF => DI/HF => DI/DF => SI/HF => SI will be covered by TARGET_VECTORIZE_BUILTIN_VECTORIZED_FUNCTION. gcc/ChangeLog: * config/riscv/autovec.md (lrint2): New pattern for lrint/lintf. * config/riscv/riscv-protos.h (expand_vec_lrint): New func decl for expanding lint. * config/riscv/riscv-v.cc (emit_vec_cvt_x_f): New helper func impl for vfcvt.x.f.v. (expand_vec_lrint): New function impl for expanding lint. * config/riscv/vector-iterators.md: New mode attr and iterator. gcc/testsuite/ChangeLog: * gcc.target/riscv/rvv/autovec/unop/test-math.h: New define for CVT like test case. * gcc.target/riscv/rvv/autovec/vls/def.h: Ditto. * gcc.target/riscv/rvv/autovec/unop/math-lrint-0.c: New test. * gcc.target/riscv/rvv/autovec/unop/math-lrint-1.c: New test. * gcc.target/riscv/rvv/autovec/unop/math-lrint-run-0.c: New test. * gcc.target/riscv/rvv/autovec/unop/math-lrint-run-1.c: New test. * gcc.target/riscv/rvv/autovec/vls/math-lrint-0.c: New test. * gcc.target/riscv/rvv/autovec/vls/math-lrint-1.c: New test. Signed-off-by: Pan Li Signed-off-by: Pan Li --- gcc/config/riscv/autovec.md | 11 +++ gcc/config/riscv/riscv-protos.h | 1 + gcc/config/riscv/riscv-v.cc | 20 ++++++ gcc/config/riscv/vector-iterators.md | 69 +++++++++++++++++++ .../riscv/rvv/autovec/unop/math-lrint-0.c | 14 ++++ .../riscv/rvv/autovec/unop/math-lrint-1.c | 14 ++++ .../riscv/rvv/autovec/unop/math-lrint-run-0.c | 63 +++++++++++++++++ .../riscv/rvv/autovec/unop/math-lrint-run-1.c | 63 +++++++++++++++++ .../riscv/rvv/autovec/unop/test-math.h | 24 +++++++ .../gcc.target/riscv/rvv/autovec/vls/def.h | 9 +++ .../riscv/rvv/autovec/vls/math-lrint-0.c | 30 ++++++++ .../riscv/rvv/autovec/vls/math-lrint-1.c | 30 ++++++++ 12 files changed, 348 insertions(+) create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-lrint-0.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-lrint-1.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-lrint-run-0.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-lrint-run-1.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/vls/math-lrint-0.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/vls/math-lrint-1.c diff --git a/gcc/config/riscv/autovec.md b/gcc/config/riscv/autovec.md index 53e9d34eea1..dc76a01d82c 100644 --- a/gcc/config/riscv/autovec.md +++ b/gcc/config/riscv/autovec.md @@ -2239,6 +2239,7 @@ (define_expand "avg3_ceil" ;; - round/roundf ;; - trunc/truncf ;; - roundeven/roundevenf +;; - lrint/lrintf ;; ------------------------------------------------------------------------- (define_expand "ceil2" [(match_operand:V_VLSF 0 "register_operand") @@ -2309,3 +2310,13 @@ (define_expand "roundeven2" DONE; } ) + +(define_expand "lrint2" + [(match_operand: 0 "register_operand") + (match_operand:V_VLS_FCONVERTL 1 "register_operand")] + "TARGET_VECTOR && !flag_trapping_math && !flag_rounding_math" + { + riscv_vector::expand_vec_lrint (operands[0], operands[1], mode, mode); + DONE; + } +) diff --git a/gcc/config/riscv/riscv-protos.h b/gcc/config/riscv/riscv-protos.h index 43426a5326b..f6bd15b47b0 100644 --- a/gcc/config/riscv/riscv-protos.h +++ b/gcc/config/riscv/riscv-protos.h @@ -474,6 +474,7 @@ void expand_vec_rint (rtx, rtx, machine_mode, machine_mode); void expand_vec_round (rtx, rtx, machine_mode, machine_mode); void expand_vec_trunc (rtx, rtx, machine_mode, machine_mode); void expand_vec_roundeven (rtx, rtx, machine_mode, machine_mode); +void expand_vec_lrint (rtx, rtx, machine_mode, machine_mode); #endif bool sew64_scalar_helper (rtx *, rtx *, rtx, machine_mode, bool, void (*)(rtx *, rtx)); diff --git a/gcc/config/riscv/riscv-v.cc b/gcc/config/riscv/riscv-v.cc index c72e411f125..64f99d85d91 100644 --- a/gcc/config/riscv/riscv-v.cc +++ b/gcc/config/riscv/riscv-v.cc @@ -3911,6 +3911,16 @@ emit_vec_cvt_x_f (rtx op_dest, rtx op_src, rtx mask, emit_vlmax_insn (icode, type, cvt_x_ops); } +static void +emit_vec_cvt_x_f (rtx op_dest, rtx op_src, insn_type type, + machine_mode vec_mode) +{ + rtx ops[] = {op_dest, op_src}; + insn_code icode = code_for_pred_fcvt_x_f (UNSPEC_VFCVT, vec_mode); + + emit_vlmax_insn (icode, type, ops); +} + static void emit_vec_cvt_f_x (rtx op_dest, rtx op_src, rtx mask, insn_type type, machine_mode vec_mode) @@ -4095,4 +4105,14 @@ expand_vec_roundeven (rtx op_0, rtx op_1, machine_mode vec_fp_mode, emit_vec_copysign (op_0, op_0, op_1, vec_fp_mode); } +void +expand_vec_lrint (rtx op_0, rtx op_1, machine_mode vec_fp_mode, + machine_mode vec_long_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_DYN, vec_fp_mode); +} + } // namespace riscv_vector diff --git a/gcc/config/riscv/vector-iterators.md b/gcc/config/riscv/vector-iterators.md index c9a7344b1bc..bb0c46ea30a 100644 --- a/gcc/config/riscv/vector-iterators.md +++ b/gcc/config/riscv/vector-iterators.md @@ -3281,6 +3281,75 @@ (define_mode_attr vnnconvert [ (V512DI "v512hf") ]) +;; L indicates convert to long +(define_mode_attr VLCONVERT [ + (RVVM8SF "RVVM8SI") (RVVM4SF "RVVM4SI") (RVVM2SF "RVVM2SI") + (RVVM1SF "RVVM1SI") (RVVMF2SF "RVVMF2SI") + + (RVVM8DF "RVVM8DI") (RVVM4DF "RVVM4DI") (RVVM2DF "RVVM2DI") + (RVVM1DF "RVVM1DI") + + (V1SF "V1SI") (V2SF "V2SI") (V4SF "V4SI") (V8SF "V8SI") (V16SF "V16SI") + (V32SF "V32SI") (V64SF "V64SI") (V128SF "V128SI") (V256SF "V256SI") + (V512SF "V512SI") (V1024SF "V1024SI") + + (V1DF "V1DI") (V2DF "V2DI") (V4DF "V4DI") (V8DF "V8DI") (V16DF "V16DI") + (V32DF "V32DI") (V64DF "V64DI") (V128DF "V128DI") (V256DF "V256DI") + (V512DF "V512DI") +]) + +(define_mode_attr vlconvert [ + (RVVM8SF "rvvm8si") (RVVM4SF "rvvm4si") (RVVM2SF "rvvm2si") + (RVVM1SF "rvvm1si") (RVVMF2SF "rvvmf2si") + + (RVVM8DF "rvvm8di") (RVVM4DF "rvvm4di") (RVVM2DF "rvvm2di") + (RVVM1DF "rvvm1di") + + (V1SF "v1si") (V2SF "v2si") (V4SF "v4si") (V8SF "v8si") (V16SF "v16si") + (V32SF "v32si") (V64SF "v64si") (V128SF "v128si") (V256SF "v256si") + (V512SF "v512si") (V1024SF "v1024si") + + (V1DF "v1di") (V2DF "v2di") (V4DF "v4di") (V8DF "v8di") (V16DF "v16di") + (V32DF "v32di") (V64DF "v64di") (V128DF "v128di") (V256DF "v256di") + (V512DF "v512di") +]) + +(define_mode_iterator V_VLS_FCONVERTL [ + (RVVM8SF "TARGET_VECTOR_ELEN_FP_32 && !TARGET_64BIT") + (RVVM4SF "TARGET_VECTOR_ELEN_FP_32 && !TARGET_64BIT") + (RVVM2SF "TARGET_VECTOR_ELEN_FP_32 && !TARGET_64BIT") + (RVVM1SF "TARGET_VECTOR_ELEN_FP_32 && !TARGET_64BIT") + (RVVMF2SF "TARGET_VECTOR_ELEN_FP_32 && !TARGET_64BIT && TARGET_MIN_VLEN > 32") + + (RVVM8DF "TARGET_VECTOR_ELEN_FP_64 && TARGET_64BIT") + (RVVM4DF "TARGET_VECTOR_ELEN_FP_64 && TARGET_64BIT") + (RVVM2DF "TARGET_VECTOR_ELEN_FP_64 && TARGET_64BIT") + (RVVM1DF "TARGET_VECTOR_ELEN_FP_64 && TARGET_64BIT") + + (V1SF "TARGET_VECTOR_VLS && TARGET_VECTOR_ELEN_FP_32 && !TARGET_64BIT") + (V2SF "TARGET_VECTOR_VLS && TARGET_VECTOR_ELEN_FP_32 && !TARGET_64BIT") + (V4SF "TARGET_VECTOR_VLS && TARGET_VECTOR_ELEN_FP_32 && !TARGET_64BIT") + (V8SF "TARGET_VECTOR_VLS && TARGET_VECTOR_ELEN_FP_32 && !TARGET_64BIT") + (V16SF "TARGET_VECTOR_VLS && TARGET_VECTOR_ELEN_FP_32 && !TARGET_64BIT && TARGET_MIN_VLEN >= 64") + (V32SF "TARGET_VECTOR_VLS && TARGET_VECTOR_ELEN_FP_32 && !TARGET_64BIT && TARGET_MIN_VLEN >= 128") + (V64SF "TARGET_VECTOR_VLS && TARGET_VECTOR_ELEN_FP_32 && !TARGET_64BIT && TARGET_MIN_VLEN >= 256") + (V128SF "TARGET_VECTOR_VLS && TARGET_VECTOR_ELEN_FP_32 && !TARGET_64BIT && TARGET_MIN_VLEN >= 512") + (V256SF "TARGET_VECTOR_VLS && TARGET_VECTOR_ELEN_FP_32 && !TARGET_64BIT && TARGET_MIN_VLEN >= 1024") + (V512SF "TARGET_VECTOR_VLS && TARGET_VECTOR_ELEN_FP_32 && !TARGET_64BIT && TARGET_MIN_VLEN >= 2048") + (V1024SF "TARGET_VECTOR_VLS && TARGET_VECTOR_ELEN_FP_32 && !TARGET_64BIT && TARGET_MIN_VLEN >= 4096") + + (V1DF "TARGET_VECTOR_VLS && TARGET_VECTOR_ELEN_FP_64 && TARGET_64BIT") + (V2DF "TARGET_VECTOR_VLS && TARGET_VECTOR_ELEN_FP_64 && TARGET_64BIT") + (V4DF "TARGET_VECTOR_VLS && TARGET_VECTOR_ELEN_FP_64 && TARGET_64BIT") + (V8DF "TARGET_VECTOR_VLS && TARGET_VECTOR_ELEN_FP_64 && TARGET_64BIT && TARGET_MIN_VLEN >= 64") + (V16DF "TARGET_VECTOR_VLS && TARGET_VECTOR_ELEN_FP_64 && TARGET_64BIT && TARGET_MIN_VLEN >= 128") + (V32DF "TARGET_VECTOR_VLS && TARGET_VECTOR_ELEN_FP_64 && TARGET_64BIT && TARGET_MIN_VLEN >= 256") + (V64DF "TARGET_VECTOR_VLS && TARGET_VECTOR_ELEN_FP_64 && TARGET_64BIT && TARGET_MIN_VLEN >= 512") + (V128DF "TARGET_VECTOR_VLS && TARGET_VECTOR_ELEN_FP_64 && TARGET_64BIT && TARGET_MIN_VLEN >= 1024") + (V256DF "TARGET_VECTOR_VLS && TARGET_VECTOR_ELEN_FP_64 && TARGET_64BIT && TARGET_MIN_VLEN >= 2048") + (V512DF "TARGET_VECTOR_VLS && TARGET_VECTOR_ELEN_FP_64 && TARGET_64BIT && TARGET_MIN_VLEN >= 4096") +]) + (define_mode_attr VDEMOTE [ (RVVM8DI "RVVM8SI") (RVVM4DI "RVVM4SI") (RVVM2DI "RVVM2SI") (RVVM1DI "RVVM1SI") (V1DI "V1SI") diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-lrint-0.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-lrint-0.c new file mode 100644 index 00000000000..a60ef30efa4 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-lrint-0.c @@ -0,0 +1,14 @@ +/* { 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_long___builtin_lrint: +** ... +** vsetvli\s+[atx][0-9]+,\s*zero,\s*e64,\s*m1,\s*ta,\s*ma +** vfcvt\.x\.f\.v\s+v[0-9]+,\s*v[0-9]+ +** ... +*/ +TEST_UNARY_CALL_CVT (double, long, __builtin_lrint) diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-lrint-1.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-lrint-1.c new file mode 100644 index 00000000000..57e92ffb0e6 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-lrint-1.c @@ -0,0 +1,14 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv32gcv -mabi=ilp32f -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_lrintf: +** ... +** vsetvli\s+[atx][0-9]+,\s*zero,\s*e32,\s*m1,\s*ta,\s*ma +** vfcvt\.x\.f\.v\s+v[0-9]+,\s*v[0-9]+ +** ... +*/ +TEST_UNARY_CALL_CVT (float, long, __builtin_lrintf) diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-lrint-run-0.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-lrint-run-0.c new file mode 100644 index 00000000000..2281c592cda --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-lrint-run-0.c @@ -0,0 +1,63 @@ +/* { dg-do run { target { riscv_v && rv64 } } } */ +/* { 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_lrint) +TEST_ASSERT (long) + +TEST_INIT_CVT (double, 1.2, long, __builtin_lrint (1.2), 1) +TEST_INIT_CVT (double, -1.2, long, __builtin_lrint (-1.2), 2) +TEST_INIT_CVT (double, 0.5, long, __builtin_lrint (0.5), 3) +TEST_INIT_CVT (double, -0.5, long, __builtin_lrint (-0.5), 4) +TEST_INIT_CVT (double, 0.1, long, __builtin_lrint (0.1), 5) +TEST_INIT_CVT (double, -0.1, long, __builtin_lrint (-0.1), 6) +TEST_INIT_CVT (double, 3.0, long, __builtin_lrint (3.0), 7) +TEST_INIT_CVT (double, -3.0, long, __builtin_lrint (-3.0), 8) +TEST_INIT_CVT (double, 4503599627370495.5, long, __builtin_lrint (4503599627370495.5), 9) +TEST_INIT_CVT (double, 4503599627370497.0, long, __builtin_lrint (4503599627370497.0), 10) +TEST_INIT_CVT (double, -4503599627370495.5, long, __builtin_lrint (-4503599627370495.5), 11) +TEST_INIT_CVT (double, -4503599627370496.0, long, __builtin_lrint (-4503599627370496.0), 12) +TEST_INIT_CVT (double, 0.0, long, __builtin_lrint (-0.0), 13) +TEST_INIT_CVT (double, -0.0, long, __builtin_lrint (-0.0), 14) +TEST_INIT_CVT (double, 9223372036854774784.0, long, __builtin_lrint (9223372036854774784.0), 15) +TEST_INIT_CVT (double, 9223372036854775808.0, long, __builtin_lrint (9223372036854775808.0), 16) +TEST_INIT_CVT (double, -9223372036854775808.0, long, __builtin_lrint (-9223372036854775808.0), 17) +TEST_INIT_CVT (double, -9223372036854777856.0, long, __builtin_lrint (-9223372036854777856.0), 18) +TEST_INIT_CVT (double, __builtin_inf (), long, __builtin_lrint (__builtin_inf ()), 19) +TEST_INIT_CVT (double, -__builtin_inf (), long, __builtin_lrint (-__builtin_inf ()), 20) +TEST_INIT_CVT (double, __builtin_nan (""), long, 0x7fffffffffffffff, 21) + +int +main () +{ + RUN_TEST_CVT (double, long, 1, __builtin_lrint, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, long, 2, __builtin_lrint, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, long, 3, __builtin_lrint, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, long, 4, __builtin_lrint, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, long, 5, __builtin_lrint, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, long, 6, __builtin_lrint, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, long, 7, __builtin_lrint, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, long, 8, __builtin_lrint, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, long, 9, __builtin_lrint, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, long, 10, __builtin_lrint, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, long, 11, __builtin_lrint, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, long, 12, __builtin_lrint, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, long, 13, __builtin_lrint, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, long, 14, __builtin_lrint, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, long, 15, __builtin_lrint, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, long, 16, __builtin_lrint, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, long, 17, __builtin_lrint, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, long, 18, __builtin_lrint, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, long, 19, __builtin_lrint, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, long, 20, __builtin_lrint, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (double, long, 21, __builtin_lrint, in, out, ref, ARRAY_SIZE); + + return 0; +} diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-lrint-run-1.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-lrint-run-1.c new file mode 100644 index 00000000000..ee7ec3c271b --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-lrint-run-1.c @@ -0,0 +1,63 @@ +/* { 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 + +float in[ARRAY_SIZE]; +long out[ARRAY_SIZE]; +long ref[ARRAY_SIZE]; + +TEST_UNARY_CALL_CVT (float, long, __builtin_lrintf) +TEST_ASSERT (long) + +TEST_INIT_CVT (float, 1.2, long, __builtin_lrintf (1.2), 1) +TEST_INIT_CVT (float, -1.2, long, __builtin_lrintf (-1.2), 2) +TEST_INIT_CVT (float, 0.5, long, __builtin_lrintf (0.5), 3) +TEST_INIT_CVT (float, -0.5, long, __builtin_lrintf (-0.5), 4) +TEST_INIT_CVT (float, 0.1, long, __builtin_lrintf (0.1), 5) +TEST_INIT_CVT (float, -0.1, long, __builtin_lrintf (-0.1), 6) +TEST_INIT_CVT (float, 3.0, long, __builtin_lrintf (3.0), 7) +TEST_INIT_CVT (float, -3.0, long, __builtin_lrintf (-3.0), 8) +TEST_INIT_CVT (float, 8388607.5, long, __builtin_lrintf (8388607.5), 9) +TEST_INIT_CVT (float, 8388609.0, long, __builtin_lrintf (8388609.0), 10) +TEST_INIT_CVT (float, -8388607.5, long, __builtin_lrintf (-8388607.5), 11) +TEST_INIT_CVT (float, -8388609.0, long, __builtin_lrintf (-8388609.0), 12) +TEST_INIT_CVT (float, 0.0, long, __builtin_lrintf (-0.0), 13) +TEST_INIT_CVT (float, -0.0, long, __builtin_lrintf (-0.0), 14) +TEST_INIT_CVT (float, 2147483520.0, long, __builtin_lrintf (2147483520.0), 15) +TEST_INIT_CVT (float, 2147483648.0, long, __builtin_lrintf (2147483648.0), 16) +TEST_INIT_CVT (float, -2147483648.0, long, __builtin_lrintf (-2147483648.0), 17) +TEST_INIT_CVT (float, -2147483904.0, long, __builtin_lrintf (-2147483904.0), 18) +TEST_INIT_CVT (float, __builtin_inf (), long, __builtin_lrintf (__builtin_inff ()), 19) +TEST_INIT_CVT (float, -__builtin_inf (), long, __builtin_lrintf (-__builtin_inff ()), 20) +TEST_INIT_CVT (float, __builtin_nanf (""), long, 0x7fffffff, 21) + +int +main () +{ + RUN_TEST_CVT (float, long, 1, __builtin_lrintf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, long, 2, __builtin_lrintf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, long, 3, __builtin_lrintf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, long, 4, __builtin_lrintf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, long, 5, __builtin_lrintf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, long, 6, __builtin_lrintf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, long, 7, __builtin_lrintf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, long, 8, __builtin_lrintf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, long, 9, __builtin_lrintf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, long, 10, __builtin_lrintf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, long, 11, __builtin_lrintf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, long, 12, __builtin_lrintf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, long, 13, __builtin_lrintf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, long, 14, __builtin_lrintf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, long, 15, __builtin_lrintf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, long, 16, __builtin_lrintf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, long, 17, __builtin_lrintf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, long, 18, __builtin_lrintf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, long, 19, __builtin_lrintf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, long, 20, __builtin_lrintf, in, out, ref, ARRAY_SIZE); + RUN_TEST_CVT (float, long, 21, __builtin_lrintf, in, out, ref, ARRAY_SIZE); + + return 0; +} diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/test-math.h b/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/test-math.h index b63ca56d848..a1c9d55bd48 100644 --- a/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/test-math.h +++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/test-math.h @@ -5,6 +5,14 @@ out[i] = CALL (in[i]); \ } +#define TEST_UNARY_CALL_CVT(TYPE_IN, TYPE_OUT, CALL) \ + void test_##TYPE_IN##_##TYPE_OUT##_##CALL ( \ + TYPE_OUT *out, TYPE_IN *in, unsigned count) \ + { \ + for (unsigned i = 0; i < count; i++) \ + out[i] = CALL (in[i]); \ + } + #define TEST_COND_UNARY_CALL(TYPE, CALL) \ void test_##TYPE##_##CALL (TYPE *out, int *cond, TYPE *in, unsigned count) \ { \ @@ -22,6 +30,17 @@ } \ } +#define TEST_INIT_CVT(TYPE_IN, VAL_IN, TYPE_REF, VAL_REF, NUM) \ + void test_##TYPE_IN##_##TYPE_REF##_init_##NUM ( \ + TYPE_IN *in, TYPE_REF *ref, unsigned size) \ + { \ + for (unsigned i = 0; i < size; i++) \ + { \ + in[i] = VAL_IN; \ + ref[i] = VAL_REF; \ + } \ + } + #define TEST_ASSERT(TYPE) \ void test_##TYPE##_assert (TYPE *out, TYPE *ref, unsigned size) \ { \ @@ -37,6 +56,11 @@ test_##TYPE##_##CALL (OUT, IN, SIZE); \ test_##TYPE##_assert (OUT, REF, SIZE); +#define RUN_TEST_CVT(TYPE_IN, TYPE_OUT, NUM, CALL, IN, OUT, REF, SIZE) \ + test_##TYPE_IN##_##TYPE_OUT##_init_##NUM (IN, REF, SIZE); \ + test_##TYPE_IN##_##TYPE_OUT##_##CALL (OUT, IN, SIZE); \ + test_##TYPE_OUT##_assert (OUT, REF, SIZE); + #define FRM_RNE 0 #define FRM_RTZ 1 #define FRM_RDN 2 diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls/def.h b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls/def.h index fa124ffd698..b4148f29d8a 100644 --- a/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls/def.h +++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls/def.h @@ -213,6 +213,15 @@ typedef double v512df __attribute__ ((vector_size (4096))); a[i] = OP (b[i]); \ } +#define DEF_OP_V_CVT(PREFIX, NUM, TYPE_IN, TYPE_OUT, OP) \ + void __attribute__ ((noinline, noclone)) \ + PREFIX##_##TYPE_IN##_##TYPE_OUT##_##NUM (TYPE_OUT *restrict a, \ + TYPE_IN *restrict b) \ + { \ + for (int i = 0; i < NUM; ++i) \ + a[i] = OP (b[i]); \ + } + #define DEF_CALL_VV(PREFIX, NUM, TYPE, CALL) \ void __attribute__ ((noinline, noclone)) \ PREFIX##_##TYPE##NUM (TYPE *restrict a, TYPE *restrict b, TYPE *restrict c) \ diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls/math-lrint-0.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls/math-lrint-0.c new file mode 100644 index 00000000000..561edef7d3d --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls/math-lrint-0.c @@ -0,0 +1,30 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gcv_zvfh_zvl4096b -mabi=lp64d -O3 --param=riscv-autovec-lmul=m8 -ffast-math -fdump-tree-optimized" } */ + +#include "def.h" + +DEF_OP_V_CVT (lrint, 1, double, long, __builtin_lrint) +DEF_OP_V_CVT (lrint, 2, double, long, __builtin_lrint) +DEF_OP_V_CVT (lrint, 4, double, long, __builtin_lrint) +DEF_OP_V_CVT (lrint, 8, double, long, __builtin_lrint) +DEF_OP_V_CVT (lrint, 16, double, long, __builtin_lrint) +DEF_OP_V_CVT (lrint, 32, double, long, __builtin_lrint) +DEF_OP_V_CVT (lrint, 64, double, long, __builtin_lrint) +DEF_OP_V_CVT (lrint, 128, double, long, __builtin_lrint) +DEF_OP_V_CVT (lrint, 256, double, long, __builtin_lrint) +DEF_OP_V_CVT (lrint, 512, double, long, __builtin_lrint) + +/* { 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-tree-dump-not "1024,1024" "optimized" } } */ +/* { dg-final { scan-tree-dump-not "2048,2048" "optimized" } } */ +/* { dg-final { scan-tree-dump-not "4096,4096" "optimized" } } */ +/* { dg-final { scan-assembler-times {vfcvt\.x\.f\.v\s+v[0-9]+,\s*v[0-9]+} 9 } } */ diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls/math-lrint-1.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls/math-lrint-1.c new file mode 100644 index 00000000000..5414352fbbe --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls/math-lrint-1.c @@ -0,0 +1,30 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv32gcv_zvfh_zvl4096b -mabi=ilp32f -O3 --param=riscv-autovec-lmul=m8 -ffast-math -fdump-tree-optimized" } */ + +#include "def.h" + +DEF_OP_V_CVT (lrintf, 1, float, long, __builtin_lrintf) +DEF_OP_V_CVT (lrintf, 2, float, long, __builtin_lrintf) +DEF_OP_V_CVT (lrintf, 4, float, long, __builtin_lrintf) +DEF_OP_V_CVT (lrintf, 8, float, long, __builtin_lrintf) +DEF_OP_V_CVT (lrintf, 16, float, long, __builtin_lrintf) +DEF_OP_V_CVT (lrintf, 32, float, long, __builtin_lrintf) +DEF_OP_V_CVT (lrintf, 64, float, long, __builtin_lrintf) +DEF_OP_V_CVT (lrintf, 128, float, long, __builtin_lrintf) +DEF_OP_V_CVT (lrintf, 256, float, long, __builtin_lrintf) +DEF_OP_V_CVT (lrintf, 512, float, long, __builtin_lrintf) + +/* { 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-tree-dump-not "1024,1024" "optimized" } } */ +/* { dg-final { scan-tree-dump-not "2048,2048" "optimized" } } */ +/* { dg-final { scan-tree-dump-not "4096,4096" "optimized" } } */ +/* { dg-final { scan-assembler-times {vfcvt\.x\.f\.v\s+v[0-9]+,\s*v[0-9]+} 9 } } */