From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mgamail.intel.com (mgamail.intel.com [192.55.52.43]) by sourceware.org (Postfix) with ESMTPS id 35A423858C27 for ; Fri, 4 Aug 2023 03:28:34 +0000 (GMT) DMARC-Filter: OpenDMARC Filter v1.4.2 sourceware.org 35A423858C27 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=1691119714; x=1722655714; h=from:to:cc:subject:date:message-id:mime-version: content-transfer-encoding; bh=lusMYmYt9g8iBbncAZSUeIAehtq3WCIgwfH5QoVVd7E=; b=NaZdsHxYLzgxEs4e7WigMxKcTIiMQRPLtcldiDlE3zOsjT7nFzd6mQEs kEPRM7lWywgViVViGDS5Pt4mhQ+Zvgp9dOcYVEygG3DdtnkJb/X13wBQS T8KBKjvl6wWBbnhA2nGNMScwWUBVIfp98FE0gKpYNH6GD2HIN74DxIx1Q KUR2muOCN5Y9Kpo2ksiVUZEwCTVY56DueLqNCb3/eNvJ7mn8NbvdOzo4D 7bse+oHUsniJWM5EdnDzk83fuTnPZJ0JK9+9igW2dlLARfrF7Rwty6Jcg YURe7Lu8o8kWKsUVZtNUKYci/BYe351nxTatT1hRjzfEGemRBIqFkixGY w==; X-IronPort-AV: E=McAfee;i="6600,9927,10791"; a="456428540" X-IronPort-AV: E=Sophos;i="6.01,254,1684825200"; d="scan'208";a="456428540" Received: from orsmga001.jf.intel.com ([10.7.209.18]) by fmsmga105.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 03 Aug 2023 20:28:32 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=McAfee;i="6600,9927,10791"; a="764930817" X-IronPort-AV: E=Sophos;i="6.01,254,1684825200"; d="scan'208";a="764930817" Received: from shvmail02.sh.intel.com ([10.239.244.9]) by orsmga001.jf.intel.com with ESMTP; 03 Aug 2023 20:28:30 -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 3A8DC10083A2; Fri, 4 Aug 2023 11:28:29 +0800 (CST) From: pan2.li@intel.com To: gcc-patches@gcc.gnu.org Cc: juzhe.zhong@rivai.ai, kito.cheng@sifive.com, pan2.li@intel.com, yanzhang.wang@intel.com Subject: [PATCH v1] RISC-V: Support RVV VFNMSAC rounding mode intrinsic API Date: Fri, 4 Aug 2023 11:28:28 +0800 Message-Id: <20230804032828.596526-1-pan2.li@intel.com> X-Mailer: git-send-email 2.34.1 MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Spam-Status: No, score=-11.1 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 List-Id: From: Pan Li This patch would like to support the rounding mode API for the VFNMSAC for the below samples. * __riscv_vfnmsac_vv_f32m1_rm * __riscv_vfnmsac_vv_f32m1_rm_m * __riscv_vfnmsac_vf_f32m1_rm * __riscv_vfnmsac_vf_f32m1_rm_m Signed-off-by: Pan Li gcc/ChangeLog: * config/riscv/riscv-vector-builtins-bases.cc (class vfnmsac_frm): New class for vfnmsac frm. (vfnmsac_frm_obj): New declaration. (BASE): Ditto. * config/riscv/riscv-vector-builtins-bases.h: Ditto. * config/riscv/riscv-vector-builtins-functions.def (vfnmsac_frm): New function definition. gcc/testsuite/ChangeLog: * gcc.target/riscv/rvv/base/float-point-single-negate-multiply-sub.c: New test. --- .../riscv/riscv-vector-builtins-bases.cc | 24 ++++++++++ .../riscv/riscv-vector-builtins-bases.h | 1 + .../riscv/riscv-vector-builtins-functions.def | 2 + .../float-point-single-negate-multiply-sub.c | 47 +++++++++++++++++++ 4 files changed, 74 insertions(+) create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/base/float-point-single-negate-multiply-sub.c diff --git a/gcc/config/riscv/riscv-vector-builtins-bases.cc b/gcc/config/riscv/riscv-vector-builtins-bases.cc index e73051bbd89..9c6ca8d1ddc 100644 --- a/gcc/config/riscv/riscv-vector-builtins-bases.cc +++ b/gcc/config/riscv/riscv-vector-builtins-bases.cc @@ -423,6 +423,28 @@ public: } }; +/* Implements below instructions for frm + - vfnmsac +*/ +class vfnmsac_frm : public function_base +{ +public: + bool has_rounding_mode_operand_p () const override { return true; } + + bool has_merge_operand_p () const override { return false; } + + rtx expand (function_expander &e) const override + { + if (e.op_info->op == OP_TYPE_vf) + return e.use_ternop_insn ( + true, code_for_pred_mul_neg_scalar (PLUS, e.vector_mode ())); + if (e.op_info->op == OP_TYPE_vv) + return e.use_ternop_insn ( + true, code_for_pred_mul_neg (PLUS, e.vector_mode ())); + gcc_unreachable (); + } +}; + /* Implements vrsub. */ class vrsub : public function_base { @@ -2185,6 +2207,7 @@ static CONSTEXPR const widen_binop_frm vfwmul_frm_obj; static CONSTEXPR const vfmacc vfmacc_obj; static CONSTEXPR const vfmacc_frm vfmacc_frm_obj; static CONSTEXPR const vfnmsac vfnmsac_obj; +static CONSTEXPR const vfnmsac_frm vfnmsac_frm_obj; static CONSTEXPR const vfmadd vfmadd_obj; static CONSTEXPR const vfnmsub vfnmsub_obj; static CONSTEXPR const vfnmacc vfnmacc_obj; @@ -2423,6 +2446,7 @@ BASE (vfwmul_frm) BASE (vfmacc) BASE (vfmacc_frm) BASE (vfnmsac) +BASE (vfnmsac_frm) BASE (vfmadd) BASE (vfnmsub) BASE (vfnmacc) diff --git a/gcc/config/riscv/riscv-vector-builtins-bases.h b/gcc/config/riscv/riscv-vector-builtins-bases.h index ca8a6dc1cc3..28eec2c3e99 100644 --- a/gcc/config/riscv/riscv-vector-builtins-bases.h +++ b/gcc/config/riscv/riscv-vector-builtins-bases.h @@ -162,6 +162,7 @@ extern const function_base *const vfwmul_frm; extern const function_base *const vfmacc; extern const function_base *const vfmacc_frm; extern const function_base *const vfnmsac; +extern const function_base *const vfnmsac_frm; extern const function_base *const vfmadd; extern const function_base *const vfnmsub; extern const function_base *const vfnmacc; diff --git a/gcc/config/riscv/riscv-vector-builtins-functions.def b/gcc/config/riscv/riscv-vector-builtins-functions.def index 8bae7e616ba..9c964ae6fcb 100644 --- a/gcc/config/riscv/riscv-vector-builtins-functions.def +++ b/gcc/config/riscv/riscv-vector-builtins-functions.def @@ -354,6 +354,8 @@ DEF_RVV_FUNCTION (vfnmacc_frm, alu_frm, full_preds, f_vvvv_ops) DEF_RVV_FUNCTION (vfnmacc_frm, alu_frm, full_preds, f_vvfv_ops) DEF_RVV_FUNCTION (vfmsac_frm, alu_frm, full_preds, f_vvvv_ops) DEF_RVV_FUNCTION (vfmsac_frm, alu_frm, full_preds, f_vvfv_ops) +DEF_RVV_FUNCTION (vfnmsac_frm, alu_frm, full_preds, f_vvvv_ops) +DEF_RVV_FUNCTION (vfnmsac_frm, alu_frm, full_preds, f_vvfv_ops) // 13.7. Vector Widening Floating-Point Fused Multiply-Add Instructions DEF_RVV_FUNCTION (vfwmacc, alu, full_preds, f_wwvv_ops) diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/float-point-single-negate-multiply-sub.c b/gcc/testsuite/gcc.target/riscv/rvv/base/float-point-single-negate-multiply-sub.c new file mode 100644 index 00000000000..c3089234272 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/base/float-point-single-negate-multiply-sub.c @@ -0,0 +1,47 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gcv -mabi=lp64 -O3 -Wno-psabi" } */ + +#include "riscv_vector.h" + +typedef float float32_t; + +vfloat32m1_t +test_riscv_vfnmsac_vv_f32m1_rm (vfloat32m1_t vd, vfloat32m1_t op1, + vfloat32m1_t op2, size_t vl) { + return __riscv_vfnmsac_vv_f32m1_rm (vd, op1, op2, 0, vl); +} + +vfloat32m1_t +test_vfnmsac_vv_f32m1_rm_m (vbool32_t mask, vfloat32m1_t vd, vfloat32m1_t op1, + vfloat32m1_t op2, size_t vl) { + return __riscv_vfnmsac_vv_f32m1_rm_m (mask, vd, op1, op2, 1, vl); +} + +vfloat32m1_t +test_vfnmsac_vf_f32m1_rm (vfloat32m1_t vd, float32_t op1, vfloat32m1_t op2, + size_t vl) { + return __riscv_vfnmsac_vf_f32m1_rm (vd, op1, op2, 2, vl); +} + +vfloat32m1_t +test_vfnmsac_vf_f32m1_rm_m (vfloat32m1_t vd, vbool32_t mask, float32_t op1, + vfloat32m1_t op2, size_t vl) { + return __riscv_vfnmsac_vf_f32m1_rm_m (mask, vd, op1, op2, 3, vl); +} + +vfloat32m1_t +test_riscv_vfnmsac_vv_f32m1 (vfloat32m1_t vd, vfloat32m1_t op1, + vfloat32m1_t op2, size_t vl) { + return __riscv_vfnmsac_vv_f32m1 (vd, op1, op2, vl); +} + +vfloat32m1_t +test_vfnmsac_vv_f32m1_m (vbool32_t mask, vfloat32m1_t vd, vfloat32m1_t op1, + vfloat32m1_t op2, size_t vl) { + return __riscv_vfnmsac_vv_f32m1_m (mask, vd, op1, op2, vl); +} + +/* { dg-final { scan-assembler-times {vfnmsac\.v[vf]\s+v[0-9]+,\s*[fav]+[0-9]+,\s*v[0-9]+} 6 } } */ +/* { dg-final { scan-assembler-times {frrm\s+[axs][0-9]+} 4 } } */ +/* { dg-final { scan-assembler-times {fsrm\s+[axs][0-9]+} 4 } } */ +/* { dg-final { scan-assembler-times {fsrmi\s+[01234]} 4 } } */ -- 2.34.1