From patchwork Wed May 30 14:23:26 2012 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Patchwork-Submitter: =?utf-8?q?Andreas_F=C3=A4rber?= X-Patchwork-Id: 161979 Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@bilbo.ozlabs.org Received: from lists.gnu.org (lists.gnu.org [208.118.235.17]) (using TLSv1 with cipher AES256-SHA (256/256 bits)) (Client did not present a certificate) by ozlabs.org (Postfix) with ESMTPS id F38F0B7063 for ; Thu, 31 May 2012 00:26:52 +1000 (EST) Received: from localhost ([::1]:39365 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1SZjrO-0000Rp-Ph for incoming@patchwork.ozlabs.org; Wed, 30 May 2012 10:26:50 -0400 Received: from eggs.gnu.org ([208.118.235.92]:51857) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1SZjop-0004Jh-Bc for qemu-devel@nongnu.org; Wed, 30 May 2012 10:24:29 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1SZjoe-0003h6-0Y for qemu-devel@nongnu.org; Wed, 30 May 2012 10:24:10 -0400 Received: from cantor2.suse.de ([195.135.220.15]:45820 helo=mx2.suse.de) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1SZjod-0003gO-1f; Wed, 30 May 2012 10:23:59 -0400 Received: from relay2.suse.de (unknown [195.135.220.254]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (No client certificate requested) by mx2.suse.de (Postfix) with ESMTP id B3F489D938; Wed, 30 May 2012 16:23:57 +0200 (CEST) From: =?UTF-8?q?Andreas=20F=C3=A4rber?= To: qemu-devel@nongnu.org Date: Wed, 30 May 2012 16:23:26 +0200 Message-Id: <1338387823-12861-7-git-send-email-afaerber@suse.de> X-Mailer: git-send-email 1.7.7 In-Reply-To: <1338387823-12861-1-git-send-email-afaerber@suse.de> References: <1338387823-12861-1-git-send-email-afaerber@suse.de> MIME-Version: 1.0 X-detected-operating-system: by eggs.gnu.org: GNU/Linux 2.4-2.6 X-Received-From: 195.135.220.15 Cc: blauwirbel@gmail.com, qemu-ppc@nongnu.org, agraf@suse.de, =?UTF-8?q?Andreas=20F=C3=A4rber?= Subject: [Qemu-devel] [PATCH v4 06/23] ppc: Split FPU and SPE ops X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+incoming=patchwork.ozlabs.org@nongnu.org Sender: qemu-devel-bounces+incoming=patchwork.ozlabs.org@nongnu.org From: Blue Swirl Move FPU and SPE helpers from op_helper.c to fpu_helper.c. Signed-off-by: Blue Swirl Signed-off-by: Alexander Graf Signed-off-by: Andreas Färber --- Makefile.target | 5 +- target-ppc/fpu_helper.c | 1731 +++++++++++++++++++++++++++++++++++++++++++++++ target-ppc/op_helper.c | 1710 ---------------------------------------------- 3 files changed, 1735 insertions(+), 1711 deletions(-) create mode 100644 target-ppc/fpu_helper.c diff --git a/Makefile.target b/Makefile.target index b7f477c..906d359 100644 --- a/Makefile.target +++ b/Makefile.target @@ -100,7 +100,7 @@ libobj-$(TARGET_SPARC) += int32_helper.o libobj-$(TARGET_SPARC64) += int64_helper.o libobj-$(TARGET_ALPHA) += int_helper.o fpu_helper.o sys_helper.o mem_helper.o ifeq ($(TARGET_BASE_ARCH), ppc) -libobj-y += excp_helper.o +libobj-y += fpu_helper.o excp_helper.o endif libobj-y += disas.o @@ -115,6 +115,9 @@ $(libobj-y): $(GENERATED_HEADERS) ifneq ($(TARGET_BASE_ARCH), sparc) op_helper.o: QEMU_CFLAGS += $(HELPER_CFLAGS) endif +ifeq ($(TARGET_BASE_ARCH), ppc) +fpu_helper.o: QEMU_CFLAGS += $(HELPER_CFLAGS) +endif user-exec.o: QEMU_CFLAGS += $(HELPER_CFLAGS) # Note: this is a workaround. The real fix is to avoid compiling diff --git a/target-ppc/fpu_helper.c b/target-ppc/fpu_helper.c new file mode 100644 index 0000000..be965d1 --- /dev/null +++ b/target-ppc/fpu_helper.c @@ -0,0 +1,1731 @@ +/* + * PowerPC floating point and SPE emulation helpers for QEMU. + * + * Copyright (c) 2003-2007 Jocelyn Mayer + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see . + */ +#include "cpu.h" +#include "dyngen-exec.h" +#include "helper.h" + +/*****************************************************************************/ +/* Floating point operations helpers */ +uint64_t helper_float32_to_float64(uint32_t arg) +{ + CPU_FloatU f; + CPU_DoubleU d; + + f.l = arg; + d.d = float32_to_float64(f.f, &env->fp_status); + return d.ll; +} + +uint32_t helper_float64_to_float32(uint64_t arg) +{ + CPU_FloatU f; + CPU_DoubleU d; + + d.ll = arg; + f.f = float64_to_float32(d.d, &env->fp_status); + return f.l; +} + +static inline int isden(float64 d) +{ + CPU_DoubleU u; + + u.d = d; + + return ((u.ll >> 52) & 0x7FF) == 0; +} + +uint32_t helper_compute_fprf(uint64_t arg, uint32_t set_fprf) +{ + CPU_DoubleU farg; + int isneg; + int ret; + + farg.ll = arg; + isneg = float64_is_neg(farg.d); + if (unlikely(float64_is_any_nan(farg.d))) { + if (float64_is_signaling_nan(farg.d)) { + /* Signaling NaN: flags are undefined */ + ret = 0x00; + } else { + /* Quiet NaN */ + ret = 0x11; + } + } else if (unlikely(float64_is_infinity(farg.d))) { + /* +/- infinity */ + if (isneg) { + ret = 0x09; + } else { + ret = 0x05; + } + } else { + if (float64_is_zero(farg.d)) { + /* +/- zero */ + if (isneg) { + ret = 0x12; + } else { + ret = 0x02; + } + } else { + if (isden(farg.d)) { + /* Denormalized numbers */ + ret = 0x10; + } else { + /* Normalized numbers */ + ret = 0x00; + } + if (isneg) { + ret |= 0x08; + } else { + ret |= 0x04; + } + } + } + if (set_fprf) { + /* We update FPSCR_FPRF */ + env->fpscr &= ~(0x1F << FPSCR_FPRF); + env->fpscr |= ret << FPSCR_FPRF; + } + /* We just need fpcc to update Rc1 */ + return ret & 0xF; +} + +/* Floating-point invalid operations exception */ +static inline uint64_t fload_invalid_op_excp(int op) +{ + uint64_t ret = 0; + int ve; + + ve = fpscr_ve; + switch (op) { + case POWERPC_EXCP_FP_VXSNAN: + env->fpscr |= 1 << FPSCR_VXSNAN; + break; + case POWERPC_EXCP_FP_VXSOFT: + env->fpscr |= 1 << FPSCR_VXSOFT; + break; + case POWERPC_EXCP_FP_VXISI: + /* Magnitude subtraction of infinities */ + env->fpscr |= 1 << FPSCR_VXISI; + goto update_arith; + case POWERPC_EXCP_FP_VXIDI: + /* Division of infinity by infinity */ + env->fpscr |= 1 << FPSCR_VXIDI; + goto update_arith; + case POWERPC_EXCP_FP_VXZDZ: + /* Division of zero by zero */ + env->fpscr |= 1 << FPSCR_VXZDZ; + goto update_arith; + case POWERPC_EXCP_FP_VXIMZ: + /* Multiplication of zero by infinity */ + env->fpscr |= 1 << FPSCR_VXIMZ; + goto update_arith; + case POWERPC_EXCP_FP_VXVC: + /* Ordered comparison of NaN */ + env->fpscr |= 1 << FPSCR_VXVC; + env->fpscr &= ~(0xF << FPSCR_FPCC); + env->fpscr |= 0x11 << FPSCR_FPCC; + /* We must update the target FPR before raising the exception */ + if (ve != 0) { + env->exception_index = POWERPC_EXCP_PROGRAM; + env->error_code = POWERPC_EXCP_FP | POWERPC_EXCP_FP_VXVC; + /* Update the floating-point enabled exception summary */ + env->fpscr |= 1 << FPSCR_FEX; + /* Exception is differed */ + ve = 0; + } + break; + case POWERPC_EXCP_FP_VXSQRT: + /* Square root of a negative number */ + env->fpscr |= 1 << FPSCR_VXSQRT; + update_arith: + env->fpscr &= ~((1 << FPSCR_FR) | (1 << FPSCR_FI)); + if (ve == 0) { + /* Set the result to quiet NaN */ + ret = 0x7FF8000000000000ULL; + env->fpscr &= ~(0xF << FPSCR_FPCC); + env->fpscr |= 0x11 << FPSCR_FPCC; + } + break; + case POWERPC_EXCP_FP_VXCVI: + /* Invalid conversion */ + env->fpscr |= 1 << FPSCR_VXCVI; + env->fpscr &= ~((1 << FPSCR_FR) | (1 << FPSCR_FI)); + if (ve == 0) { + /* Set the result to quiet NaN */ + ret = 0x7FF8000000000000ULL; + env->fpscr &= ~(0xF << FPSCR_FPCC); + env->fpscr |= 0x11 << FPSCR_FPCC; + } + break; + } + /* Update the floating-point invalid operation summary */ + env->fpscr |= 1 << FPSCR_VX; + /* Update the floating-point exception summary */ + env->fpscr |= 1 << FPSCR_FX; + if (ve != 0) { + /* Update the floating-point enabled exception summary */ + env->fpscr |= 1 << FPSCR_FEX; + if (msr_fe0 != 0 || msr_fe1 != 0) { + helper_raise_exception_err(env, POWERPC_EXCP_PROGRAM, + POWERPC_EXCP_FP | op); + } + } + return ret; +} + +static inline void float_zero_divide_excp(void) +{ + env->fpscr |= 1 << FPSCR_ZX; + env->fpscr &= ~((1 << FPSCR_FR) | (1 << FPSCR_FI)); + /* Update the floating-point exception summary */ + env->fpscr |= 1 << FPSCR_FX; + if (fpscr_ze != 0) { + /* Update the floating-point enabled exception summary */ + env->fpscr |= 1 << FPSCR_FEX; + if (msr_fe0 != 0 || msr_fe1 != 0) { + helper_raise_exception_err(env, POWERPC_EXCP_PROGRAM, + POWERPC_EXCP_FP | POWERPC_EXCP_FP_ZX); + } + } +} + +static inline void float_overflow_excp(void) +{ + env->fpscr |= 1 << FPSCR_OX; + /* Update the floating-point exception summary */ + env->fpscr |= 1 << FPSCR_FX; + if (fpscr_oe != 0) { + /* XXX: should adjust the result */ + /* Update the floating-point enabled exception summary */ + env->fpscr |= 1 << FPSCR_FEX; + /* We must update the target FPR before raising the exception */ + env->exception_index = POWERPC_EXCP_PROGRAM; + env->error_code = POWERPC_EXCP_FP | POWERPC_EXCP_FP_OX; + } else { + env->fpscr |= 1 << FPSCR_XX; + env->fpscr |= 1 << FPSCR_FI; + } +} + +static inline void float_underflow_excp(void) +{ + env->fpscr |= 1 << FPSCR_UX; + /* Update the floating-point exception summary */ + env->fpscr |= 1 << FPSCR_FX; + if (fpscr_ue != 0) { + /* XXX: should adjust the result */ + /* Update the floating-point enabled exception summary */ + env->fpscr |= 1 << FPSCR_FEX; + /* We must update the target FPR before raising the exception */ + env->exception_index = POWERPC_EXCP_PROGRAM; + env->error_code = POWERPC_EXCP_FP | POWERPC_EXCP_FP_UX; + } +} + +static inline void float_inexact_excp(void) +{ + env->fpscr |= 1 << FPSCR_XX; + /* Update the floating-point exception summary */ + env->fpscr |= 1 << FPSCR_FX; + if (fpscr_xe != 0) { + /* Update the floating-point enabled exception summary */ + env->fpscr |= 1 << FPSCR_FEX; + /* We must update the target FPR before raising the exception */ + env->exception_index = POWERPC_EXCP_PROGRAM; + env->error_code = POWERPC_EXCP_FP | POWERPC_EXCP_FP_XX; + } +} + +static inline void fpscr_set_rounding_mode(void) +{ + int rnd_type; + + /* Set rounding mode */ + switch (fpscr_rn) { + case 0: + /* Best approximation (round to nearest) */ + rnd_type = float_round_nearest_even; + break; + case 1: + /* Smaller magnitude (round toward zero) */ + rnd_type = float_round_to_zero; + break; + case 2: + /* Round toward +infinite */ + rnd_type = float_round_up; + break; + default: + case 3: + /* Round toward -infinite */ + rnd_type = float_round_down; + break; + } + set_float_rounding_mode(rnd_type, &env->fp_status); +} + +void helper_fpscr_clrbit(uint32_t bit) +{ + int prev; + + prev = (env->fpscr >> bit) & 1; + env->fpscr &= ~(1 << bit); + if (prev == 1) { + switch (bit) { + case FPSCR_RN1: + case FPSCR_RN: + fpscr_set_rounding_mode(); + break; + default: + break; + } + } +} + +void helper_fpscr_setbit(uint32_t bit) +{ + int prev; + + prev = (env->fpscr >> bit) & 1; + env->fpscr |= 1 << bit; + if (prev == 0) { + switch (bit) { + case FPSCR_VX: + env->fpscr |= 1 << FPSCR_FX; + if (fpscr_ve) { + goto raise_ve; + } + case FPSCR_OX: + env->fpscr |= 1 << FPSCR_FX; + if (fpscr_oe) { + goto raise_oe; + } + break; + case FPSCR_UX: + env->fpscr |= 1 << FPSCR_FX; + if (fpscr_ue) { + goto raise_ue; + } + break; + case FPSCR_ZX: + env->fpscr |= 1 << FPSCR_FX; + if (fpscr_ze) { + goto raise_ze; + } + break; + case FPSCR_XX: + env->fpscr |= 1 << FPSCR_FX; + if (fpscr_xe) { + goto raise_xe; + } + break; + case FPSCR_VXSNAN: + case FPSCR_VXISI: + case FPSCR_VXIDI: + case FPSCR_VXZDZ: + case FPSCR_VXIMZ: + case FPSCR_VXVC: + case FPSCR_VXSOFT: + case FPSCR_VXSQRT: + case FPSCR_VXCVI: + env->fpscr |= 1 << FPSCR_VX; + env->fpscr |= 1 << FPSCR_FX; + if (fpscr_ve != 0) { + goto raise_ve; + } + break; + case FPSCR_VE: + if (fpscr_vx != 0) { + raise_ve: + env->error_code = POWERPC_EXCP_FP; + if (fpscr_vxsnan) { + env->error_code |= POWERPC_EXCP_FP_VXSNAN; + } + if (fpscr_vxisi) { + env->error_code |= POWERPC_EXCP_FP_VXISI; + } + if (fpscr_vxidi) { + env->error_code |= POWERPC_EXCP_FP_VXIDI; + } + if (fpscr_vxzdz) { + env->error_code |= POWERPC_EXCP_FP_VXZDZ; + } + if (fpscr_vximz) { + env->error_code |= POWERPC_EXCP_FP_VXIMZ; + } + if (fpscr_vxvc) { + env->error_code |= POWERPC_EXCP_FP_VXVC; + } + if (fpscr_vxsoft) { + env->error_code |= POWERPC_EXCP_FP_VXSOFT; + } + if (fpscr_vxsqrt) { + env->error_code |= POWERPC_EXCP_FP_VXSQRT; + } + if (fpscr_vxcvi) { + env->error_code |= POWERPC_EXCP_FP_VXCVI; + } + goto raise_excp; + } + break; + case FPSCR_OE: + if (fpscr_ox != 0) { + raise_oe: + env->error_code = POWERPC_EXCP_FP | POWERPC_EXCP_FP_OX; + goto raise_excp; + } + break; + case FPSCR_UE: + if (fpscr_ux != 0) { + raise_ue: + env->error_code = POWERPC_EXCP_FP | POWERPC_EXCP_FP_UX; + goto raise_excp; + } + break; + case FPSCR_ZE: + if (fpscr_zx != 0) { + raise_ze: + env->error_code = POWERPC_EXCP_FP | POWERPC_EXCP_FP_ZX; + goto raise_excp; + } + break; + case FPSCR_XE: + if (fpscr_xx != 0) { + raise_xe: + env->error_code = POWERPC_EXCP_FP | POWERPC_EXCP_FP_XX; + goto raise_excp; + } + break; + case FPSCR_RN1: + case FPSCR_RN: + fpscr_set_rounding_mode(); + break; + default: + break; + raise_excp: + /* Update the floating-point enabled exception summary */ + env->fpscr |= 1 << FPSCR_FEX; + /* We have to update Rc1 before raising the exception */ + env->exception_index = POWERPC_EXCP_PROGRAM; + break; + } + } +} + +void helper_store_fpscr(uint64_t arg, uint32_t mask) +{ + /* + * We use only the 32 LSB of the incoming fpr + */ + uint32_t prev, new; + int i; + + prev = env->fpscr; + new = (uint32_t)arg; + new &= ~0x60000000; + new |= prev & 0x60000000; + for (i = 0; i < 8; i++) { + if (mask & (1 << i)) { + env->fpscr &= ~(0xF << (4 * i)); + env->fpscr |= new & (0xF << (4 * i)); + } + } + /* Update VX and FEX */ + if (fpscr_ix != 0) { + env->fpscr |= 1 << FPSCR_VX; + } else { + env->fpscr &= ~(1 << FPSCR_VX); + } + if ((fpscr_ex & fpscr_eex) != 0) { + env->fpscr |= 1 << FPSCR_FEX; + env->exception_index = POWERPC_EXCP_PROGRAM; + /* XXX: we should compute it properly */ + env->error_code = POWERPC_EXCP_FP; + } else { + env->fpscr &= ~(1 << FPSCR_FEX); + } + fpscr_set_rounding_mode(); +} + +void helper_float_check_status(void) +{ + if (env->exception_index == POWERPC_EXCP_PROGRAM && + (env->error_code & POWERPC_EXCP_FP)) { + /* Differred floating-point exception after target FPR update */ + if (msr_fe0 != 0 || msr_fe1 != 0) { + helper_raise_exception_err(env, env->exception_index, + env->error_code); + } + } else { + int status = get_float_exception_flags(&env->fp_status); + if (status & float_flag_divbyzero) { + float_zero_divide_excp(); + } else if (status & float_flag_overflow) { + float_overflow_excp(); + } else if (status & float_flag_underflow) { + float_underflow_excp(); + } else if (status & float_flag_inexact) { + float_inexact_excp(); + } + } +} + +void helper_reset_fpstatus(void) +{ + set_float_exception_flags(0, &env->fp_status); +} + +/* fadd - fadd. */ +uint64_t helper_fadd(uint64_t arg1, uint64_t arg2) +{ + CPU_DoubleU farg1, farg2; + + farg1.ll = arg1; + farg2.ll = arg2; + + if (unlikely(float64_is_infinity(farg1.d) && float64_is_infinity(farg2.d) && + float64_is_neg(farg1.d) != float64_is_neg(farg2.d))) { + /* Magnitude subtraction of infinities */ + farg1.ll = fload_invalid_op_excp(POWERPC_EXCP_FP_VXISI); + } else { + if (unlikely(float64_is_signaling_nan(farg1.d) || + float64_is_signaling_nan(farg2.d))) { + /* sNaN addition */ + fload_invalid_op_excp(POWERPC_EXCP_FP_VXSNAN); + } + farg1.d = float64_add(farg1.d, farg2.d, &env->fp_status); + } + + return farg1.ll; +} + +/* fsub - fsub. */ +uint64_t helper_fsub(uint64_t arg1, uint64_t arg2) +{ + CPU_DoubleU farg1, farg2; + + farg1.ll = arg1; + farg2.ll = arg2; + + if (unlikely(float64_is_infinity(farg1.d) && float64_is_infinity(farg2.d) && + float64_is_neg(farg1.d) == float64_is_neg(farg2.d))) { + /* Magnitude subtraction of infinities */ + farg1.ll = fload_invalid_op_excp(POWERPC_EXCP_FP_VXISI); + } else { + if (unlikely(float64_is_signaling_nan(farg1.d) || + float64_is_signaling_nan(farg2.d))) { + /* sNaN subtraction */ + fload_invalid_op_excp(POWERPC_EXCP_FP_VXSNAN); + } + farg1.d = float64_sub(farg1.d, farg2.d, &env->fp_status); + } + + return farg1.ll; +} + +/* fmul - fmul. */ +uint64_t helper_fmul(uint64_t arg1, uint64_t arg2) +{ + CPU_DoubleU farg1, farg2; + + farg1.ll = arg1; + farg2.ll = arg2; + + if (unlikely((float64_is_infinity(farg1.d) && float64_is_zero(farg2.d)) || + (float64_is_zero(farg1.d) && float64_is_infinity(farg2.d)))) { + /* Multiplication of zero by infinity */ + farg1.ll = fload_invalid_op_excp(POWERPC_EXCP_FP_VXIMZ); + } else { + if (unlikely(float64_is_signaling_nan(farg1.d) || + float64_is_signaling_nan(farg2.d))) { + /* sNaN multiplication */ + fload_invalid_op_excp(POWERPC_EXCP_FP_VXSNAN); + } + farg1.d = float64_mul(farg1.d, farg2.d, &env->fp_status); + } + + return farg1.ll; +} + +/* fdiv - fdiv. */ +uint64_t helper_fdiv(uint64_t arg1, uint64_t arg2) +{ + CPU_DoubleU farg1, farg2; + + farg1.ll = arg1; + farg2.ll = arg2; + + if (unlikely(float64_is_infinity(farg1.d) && + float64_is_infinity(farg2.d))) { + /* Division of infinity by infinity */ + farg1.ll = fload_invalid_op_excp(POWERPC_EXCP_FP_VXIDI); + } else if (unlikely(float64_is_zero(farg1.d) && float64_is_zero(farg2.d))) { + /* Division of zero by zero */ + farg1.ll = fload_invalid_op_excp(POWERPC_EXCP_FP_VXZDZ); + } else { + if (unlikely(float64_is_signaling_nan(farg1.d) || + float64_is_signaling_nan(farg2.d))) { + /* sNaN division */ + fload_invalid_op_excp(POWERPC_EXCP_FP_VXSNAN); + } + farg1.d = float64_div(farg1.d, farg2.d, &env->fp_status); + } + + return farg1.ll; +} + +/* fabs */ +uint64_t helper_fabs(uint64_t arg) +{ + CPU_DoubleU farg; + + farg.ll = arg; + farg.d = float64_abs(farg.d); + return farg.ll; +} + +/* fnabs */ +uint64_t helper_fnabs(uint64_t arg) +{ + CPU_DoubleU farg; + + farg.ll = arg; + farg.d = float64_abs(farg.d); + farg.d = float64_chs(farg.d); + return farg.ll; +} + +/* fneg */ +uint64_t helper_fneg(uint64_t arg) +{ + CPU_DoubleU farg; + + farg.ll = arg; + farg.d = float64_chs(farg.d); + return farg.ll; +} + +/* fctiw - fctiw. */ +uint64_t helper_fctiw(uint64_t arg) +{ + CPU_DoubleU farg; + + farg.ll = arg; + + if (unlikely(float64_is_signaling_nan(farg.d))) { + /* sNaN conversion */ + farg.ll = fload_invalid_op_excp(POWERPC_EXCP_FP_VXSNAN | + POWERPC_EXCP_FP_VXCVI); + } else if (unlikely(float64_is_quiet_nan(farg.d) || + float64_is_infinity(farg.d))) { + /* qNan / infinity conversion */ + farg.ll = fload_invalid_op_excp(POWERPC_EXCP_FP_VXCVI); + } else { + farg.ll = float64_to_int32(farg.d, &env->fp_status); + /* XXX: higher bits are not supposed to be significant. + * to make tests easier, return the same as a real PowerPC 750 + */ + farg.ll |= 0xFFF80000ULL << 32; + } + return farg.ll; +} + +/* fctiwz - fctiwz. */ +uint64_t helper_fctiwz(uint64_t arg) +{ + CPU_DoubleU farg; + + farg.ll = arg; + + if (unlikely(float64_is_signaling_nan(farg.d))) { + /* sNaN conversion */ + farg.ll = fload_invalid_op_excp(POWERPC_EXCP_FP_VXSNAN | + POWERPC_EXCP_FP_VXCVI); + } else if (unlikely(float64_is_quiet_nan(farg.d) || + float64_is_infinity(farg.d))) { + /* qNan / infinity conversion */ + farg.ll = fload_invalid_op_excp(POWERPC_EXCP_FP_VXCVI); + } else { + farg.ll = float64_to_int32_round_to_zero(farg.d, &env->fp_status); + /* XXX: higher bits are not supposed to be significant. + * to make tests easier, return the same as a real PowerPC 750 + */ + farg.ll |= 0xFFF80000ULL << 32; + } + return farg.ll; +} + +#if defined(TARGET_PPC64) +/* fcfid - fcfid. */ +uint64_t helper_fcfid(uint64_t arg) +{ + CPU_DoubleU farg; + + farg.d = int64_to_float64(arg, &env->fp_status); + return farg.ll; +} + +/* fctid - fctid. */ +uint64_t helper_fctid(uint64_t arg) +{ + CPU_DoubleU farg; + + farg.ll = arg; + + if (unlikely(float64_is_signaling_nan(farg.d))) { + /* sNaN conversion */ + farg.ll = fload_invalid_op_excp(POWERPC_EXCP_FP_VXSNAN | + POWERPC_EXCP_FP_VXCVI); + } else if (unlikely(float64_is_quiet_nan(farg.d) || + float64_is_infinity(farg.d))) { + /* qNan / infinity conversion */ + farg.ll = fload_invalid_op_excp(POWERPC_EXCP_FP_VXCVI); + } else { + farg.ll = float64_to_int64(farg.d, &env->fp_status); + } + return farg.ll; +} + +/* fctidz - fctidz. */ +uint64_t helper_fctidz(uint64_t arg) +{ + CPU_DoubleU farg; + + farg.ll = arg; + + if (unlikely(float64_is_signaling_nan(farg.d))) { + /* sNaN conversion */ + farg.ll = fload_invalid_op_excp(POWERPC_EXCP_FP_VXSNAN | + POWERPC_EXCP_FP_VXCVI); + } else if (unlikely(float64_is_quiet_nan(farg.d) || + float64_is_infinity(farg.d))) { + /* qNan / infinity conversion */ + farg.ll = fload_invalid_op_excp(POWERPC_EXCP_FP_VXCVI); + } else { + farg.ll = float64_to_int64_round_to_zero(farg.d, &env->fp_status); + } + return farg.ll; +} + +#endif + +static inline uint64_t do_fri(uint64_t arg, int rounding_mode) +{ + CPU_DoubleU farg; + + farg.ll = arg; + + if (unlikely(float64_is_signaling_nan(farg.d))) { + /* sNaN round */ + farg.ll = fload_invalid_op_excp(POWERPC_EXCP_FP_VXSNAN | + POWERPC_EXCP_FP_VXCVI); + } else if (unlikely(float64_is_quiet_nan(farg.d) || + float64_is_infinity(farg.d))) { + /* qNan / infinity round */ + farg.ll = fload_invalid_op_excp(POWERPC_EXCP_FP_VXCVI); + } else { + set_float_rounding_mode(rounding_mode, &env->fp_status); + farg.ll = float64_round_to_int(farg.d, &env->fp_status); + /* Restore rounding mode from FPSCR */ + fpscr_set_rounding_mode(); + } + return farg.ll; +} + +uint64_t helper_frin(uint64_t arg) +{ + return do_fri(arg, float_round_nearest_even); +} + +uint64_t helper_friz(uint64_t arg) +{ + return do_fri(arg, float_round_to_zero); +} + +uint64_t helper_frip(uint64_t arg) +{ + return do_fri(arg, float_round_up); +} + +uint64_t helper_frim(uint64_t arg) +{ + return do_fri(arg, float_round_down); +} + +/* fmadd - fmadd. */ +uint64_t helper_fmadd(uint64_t arg1, uint64_t arg2, uint64_t arg3) +{ + CPU_DoubleU farg1, farg2, farg3; + + farg1.ll = arg1; + farg2.ll = arg2; + farg3.ll = arg3; + + if (unlikely((float64_is_infinity(farg1.d) && float64_is_zero(farg2.d)) || + (float64_is_zero(farg1.d) && float64_is_infinity(farg2.d)))) { + /* Multiplication of zero by infinity */ + farg1.ll = fload_invalid_op_excp(POWERPC_EXCP_FP_VXIMZ); + } else { + if (unlikely(float64_is_signaling_nan(farg1.d) || + float64_is_signaling_nan(farg2.d) || + float64_is_signaling_nan(farg3.d))) { + /* sNaN operation */ + fload_invalid_op_excp(POWERPC_EXCP_FP_VXSNAN); + } + /* This is the way the PowerPC specification defines it */ + float128 ft0_128, ft1_128; + + ft0_128 = float64_to_float128(farg1.d, &env->fp_status); + ft1_128 = float64_to_float128(farg2.d, &env->fp_status); + ft0_128 = float128_mul(ft0_128, ft1_128, &env->fp_status); + if (unlikely(float128_is_infinity(ft0_128) && + float64_is_infinity(farg3.d) && + float128_is_neg(ft0_128) != float64_is_neg(farg3.d))) { + /* Magnitude subtraction of infinities */ + farg1.ll = fload_invalid_op_excp(POWERPC_EXCP_FP_VXISI); + } else { + ft1_128 = float64_to_float128(farg3.d, &env->fp_status); + ft0_128 = float128_add(ft0_128, ft1_128, &env->fp_status); + farg1.d = float128_to_float64(ft0_128, &env->fp_status); + } + } + + return farg1.ll; +} + +/* fmsub - fmsub. */ +uint64_t helper_fmsub(uint64_t arg1, uint64_t arg2, uint64_t arg3) +{ + CPU_DoubleU farg1, farg2, farg3; + + farg1.ll = arg1; + farg2.ll = arg2; + farg3.ll = arg3; + + if (unlikely((float64_is_infinity(farg1.d) && float64_is_zero(farg2.d)) || + (float64_is_zero(farg1.d) && + float64_is_infinity(farg2.d)))) { + /* Multiplication of zero by infinity */ + farg1.ll = fload_invalid_op_excp(POWERPC_EXCP_FP_VXIMZ); + } else { + if (unlikely(float64_is_signaling_nan(farg1.d) || + float64_is_signaling_nan(farg2.d) || + float64_is_signaling_nan(farg3.d))) { + /* sNaN operation */ + fload_invalid_op_excp(POWERPC_EXCP_FP_VXSNAN); + } + /* This is the way the PowerPC specification defines it */ + float128 ft0_128, ft1_128; + + ft0_128 = float64_to_float128(farg1.d, &env->fp_status); + ft1_128 = float64_to_float128(farg2.d, &env->fp_status); + ft0_128 = float128_mul(ft0_128, ft1_128, &env->fp_status); + if (unlikely(float128_is_infinity(ft0_128) && + float64_is_infinity(farg3.d) && + float128_is_neg(ft0_128) == float64_is_neg(farg3.d))) { + /* Magnitude subtraction of infinities */ + farg1.ll = fload_invalid_op_excp(POWERPC_EXCP_FP_VXISI); + } else { + ft1_128 = float64_to_float128(farg3.d, &env->fp_status); + ft0_128 = float128_sub(ft0_128, ft1_128, &env->fp_status); + farg1.d = float128_to_float64(ft0_128, &env->fp_status); + } + } + return farg1.ll; +} + +/* fnmadd - fnmadd. */ +uint64_t helper_fnmadd(uint64_t arg1, uint64_t arg2, uint64_t arg3) +{ + CPU_DoubleU farg1, farg2, farg3; + + farg1.ll = arg1; + farg2.ll = arg2; + farg3.ll = arg3; + + if (unlikely((float64_is_infinity(farg1.d) && float64_is_zero(farg2.d)) || + (float64_is_zero(farg1.d) && float64_is_infinity(farg2.d)))) { + /* Multiplication of zero by infinity */ + farg1.ll = fload_invalid_op_excp(POWERPC_EXCP_FP_VXIMZ); + } else { + if (unlikely(float64_is_signaling_nan(farg1.d) || + float64_is_signaling_nan(farg2.d) || + float64_is_signaling_nan(farg3.d))) { + /* sNaN operation */ + fload_invalid_op_excp(POWERPC_EXCP_FP_VXSNAN); + } + /* This is the way the PowerPC specification defines it */ + float128 ft0_128, ft1_128; + + ft0_128 = float64_to_float128(farg1.d, &env->fp_status); + ft1_128 = float64_to_float128(farg2.d, &env->fp_status); + ft0_128 = float128_mul(ft0_128, ft1_128, &env->fp_status); + if (unlikely(float128_is_infinity(ft0_128) && + float64_is_infinity(farg3.d) && + float128_is_neg(ft0_128) != float64_is_neg(farg3.d))) { + /* Magnitude subtraction of infinities */ + farg1.ll = fload_invalid_op_excp(POWERPC_EXCP_FP_VXISI); + } else { + ft1_128 = float64_to_float128(farg3.d, &env->fp_status); + ft0_128 = float128_add(ft0_128, ft1_128, &env->fp_status); + farg1.d = float128_to_float64(ft0_128, &env->fp_status); + } + if (likely(!float64_is_any_nan(farg1.d))) { + farg1.d = float64_chs(farg1.d); + } + } + return farg1.ll; +} + +/* fnmsub - fnmsub. */ +uint64_t helper_fnmsub(uint64_t arg1, uint64_t arg2, uint64_t arg3) +{ + CPU_DoubleU farg1, farg2, farg3; + + farg1.ll = arg1; + farg2.ll = arg2; + farg3.ll = arg3; + + if (unlikely((float64_is_infinity(farg1.d) && float64_is_zero(farg2.d)) || + (float64_is_zero(farg1.d) && + float64_is_infinity(farg2.d)))) { + /* Multiplication of zero by infinity */ + farg1.ll = fload_invalid_op_excp(POWERPC_EXCP_FP_VXIMZ); + } else { + if (unlikely(float64_is_signaling_nan(farg1.d) || + float64_is_signaling_nan(farg2.d) || + float64_is_signaling_nan(farg3.d))) { + /* sNaN operation */ + fload_invalid_op_excp(POWERPC_EXCP_FP_VXSNAN); + } + /* This is the way the PowerPC specification defines it */ + float128 ft0_128, ft1_128; + + ft0_128 = float64_to_float128(farg1.d, &env->fp_status); + ft1_128 = float64_to_float128(farg2.d, &env->fp_status); + ft0_128 = float128_mul(ft0_128, ft1_128, &env->fp_status); + if (unlikely(float128_is_infinity(ft0_128) && + float64_is_infinity(farg3.d) && + float128_is_neg(ft0_128) == float64_is_neg(farg3.d))) { + /* Magnitude subtraction of infinities */ + farg1.ll = fload_invalid_op_excp(POWERPC_EXCP_FP_VXISI); + } else { + ft1_128 = float64_to_float128(farg3.d, &env->fp_status); + ft0_128 = float128_sub(ft0_128, ft1_128, &env->fp_status); + farg1.d = float128_to_float64(ft0_128, &env->fp_status); + } + if (likely(!float64_is_any_nan(farg1.d))) { + farg1.d = float64_chs(farg1.d); + } + } + return farg1.ll; +} + +/* frsp - frsp. */ +uint64_t helper_frsp(uint64_t arg) +{ + CPU_DoubleU farg; + float32 f32; + + farg.ll = arg; + + if (unlikely(float64_is_signaling_nan(farg.d))) { + /* sNaN square root */ + fload_invalid_op_excp(POWERPC_EXCP_FP_VXSNAN); + } + f32 = float64_to_float32(farg.d, &env->fp_status); + farg.d = float32_to_float64(f32, &env->fp_status); + + return farg.ll; +} + +/* fsqrt - fsqrt. */ +uint64_t helper_fsqrt(uint64_t arg) +{ + CPU_DoubleU farg; + + farg.ll = arg; + + if (unlikely(float64_is_neg(farg.d) && !float64_is_zero(farg.d))) { + /* Square root of a negative nonzero number */ + farg.ll = fload_invalid_op_excp(POWERPC_EXCP_FP_VXSQRT); + } else { + if (unlikely(float64_is_signaling_nan(farg.d))) { + /* sNaN square root */ + fload_invalid_op_excp(POWERPC_EXCP_FP_VXSNAN); + } + farg.d = float64_sqrt(farg.d, &env->fp_status); + } + return farg.ll; +} + +/* fre - fre. */ +uint64_t helper_fre(uint64_t arg) +{ + CPU_DoubleU farg; + + farg.ll = arg; + + if (unlikely(float64_is_signaling_nan(farg.d))) { + /* sNaN reciprocal */ + fload_invalid_op_excp(POWERPC_EXCP_FP_VXSNAN); + } + farg.d = float64_div(float64_one, farg.d, &env->fp_status); + return farg.d; +} + +/* fres - fres. */ +uint64_t helper_fres(uint64_t arg) +{ + CPU_DoubleU farg; + float32 f32; + + farg.ll = arg; + + if (unlikely(float64_is_signaling_nan(farg.d))) { + /* sNaN reciprocal */ + fload_invalid_op_excp(POWERPC_EXCP_FP_VXSNAN); + } + farg.d = float64_div(float64_one, farg.d, &env->fp_status); + f32 = float64_to_float32(farg.d, &env->fp_status); + farg.d = float32_to_float64(f32, &env->fp_status); + + return farg.ll; +} + +/* frsqrte - frsqrte. */ +uint64_t helper_frsqrte(uint64_t arg) +{ + CPU_DoubleU farg; + float32 f32; + + farg.ll = arg; + + if (unlikely(float64_is_neg(farg.d) && !float64_is_zero(farg.d))) { + /* Reciprocal square root of a negative nonzero number */ + farg.ll = fload_invalid_op_excp(POWERPC_EXCP_FP_VXSQRT); + } else { + if (unlikely(float64_is_signaling_nan(farg.d))) { + /* sNaN reciprocal square root */ + fload_invalid_op_excp(POWERPC_EXCP_FP_VXSNAN); + } + farg.d = float64_sqrt(farg.d, &env->fp_status); + farg.d = float64_div(float64_one, farg.d, &env->fp_status); + f32 = float64_to_float32(farg.d, &env->fp_status); + farg.d = float32_to_float64(f32, &env->fp_status); + } + return farg.ll; +} + +/* fsel - fsel. */ +uint64_t helper_fsel(uint64_t arg1, uint64_t arg2, uint64_t arg3) +{ + CPU_DoubleU farg1; + + farg1.ll = arg1; + + if ((!float64_is_neg(farg1.d) || float64_is_zero(farg1.d)) && + !float64_is_any_nan(farg1.d)) { + return arg2; + } else { + return arg3; + } +} + +void helper_fcmpu(uint64_t arg1, uint64_t arg2, uint32_t crfD) +{ + CPU_DoubleU farg1, farg2; + uint32_t ret = 0; + + farg1.ll = arg1; + farg2.ll = arg2; + + if (unlikely(float64_is_any_nan(farg1.d) || + float64_is_any_nan(farg2.d))) { + ret = 0x01UL; + } else if (float64_lt(farg1.d, farg2.d, &env->fp_status)) { + ret = 0x08UL; + } else if (!float64_le(farg1.d, farg2.d, &env->fp_status)) { + ret = 0x04UL; + } else { + ret = 0x02UL; + } + + env->fpscr &= ~(0x0F << FPSCR_FPRF); + env->fpscr |= ret << FPSCR_FPRF; + env->crf[crfD] = ret; + if (unlikely(ret == 0x01UL + && (float64_is_signaling_nan(farg1.d) || + float64_is_signaling_nan(farg2.d)))) { + /* sNaN comparison */ + fload_invalid_op_excp(POWERPC_EXCP_FP_VXSNAN); + } +} + +void helper_fcmpo(uint64_t arg1, uint64_t arg2, uint32_t crfD) +{ + CPU_DoubleU farg1, farg2; + uint32_t ret = 0; + + farg1.ll = arg1; + farg2.ll = arg2; + + if (unlikely(float64_is_any_nan(farg1.d) || + float64_is_any_nan(farg2.d))) { + ret = 0x01UL; + } else if (float64_lt(farg1.d, farg2.d, &env->fp_status)) { + ret = 0x08UL; + } else if (!float64_le(farg1.d, farg2.d, &env->fp_status)) { + ret = 0x04UL; + } else { + ret = 0x02UL; + } + + env->fpscr &= ~(0x0F << FPSCR_FPRF); + env->fpscr |= ret << FPSCR_FPRF; + env->crf[crfD] = ret; + if (unlikely(ret == 0x01UL)) { + if (float64_is_signaling_nan(farg1.d) || + float64_is_signaling_nan(farg2.d)) { + /* sNaN comparison */ + fload_invalid_op_excp(POWERPC_EXCP_FP_VXSNAN | + POWERPC_EXCP_FP_VXVC); + } else { + /* qNaN comparison */ + fload_invalid_op_excp(POWERPC_EXCP_FP_VXVC); + } + } +} + +/* Single-precision floating-point conversions */ +static inline uint32_t efscfsi(uint32_t val) +{ + CPU_FloatU u; + + u.f = int32_to_float32(val, &env->vec_status); + + return u.l; +} + +static inline uint32_t efscfui(uint32_t val) +{ + CPU_FloatU u; + + u.f = uint32_to_float32(val, &env->vec_status); + + return u.l; +} + +static inline int32_t efsctsi(uint32_t val) +{ + CPU_FloatU u; + + u.l = val; + /* NaN are not treated the same way IEEE 754 does */ + if (unlikely(float32_is_quiet_nan(u.f))) { + return 0; + } + + return float32_to_int32(u.f, &env->vec_status); +} + +static inline uint32_t efsctui(uint32_t val) +{ + CPU_FloatU u; + + u.l = val; + /* NaN are not treated the same way IEEE 754 does */ + if (unlikely(float32_is_quiet_nan(u.f))) { + return 0; + } + + return float32_to_uint32(u.f, &env->vec_status); +} + +static inline uint32_t efsctsiz(uint32_t val) +{ + CPU_FloatU u; + + u.l = val; + /* NaN are not treated the same way IEEE 754 does */ + if (unlikely(float32_is_quiet_nan(u.f))) { + return 0; + } + + return float32_to_int32_round_to_zero(u.f, &env->vec_status); +} + +static inline uint32_t efsctuiz(uint32_t val) +{ + CPU_FloatU u; + + u.l = val; + /* NaN are not treated the same way IEEE 754 does */ + if (unlikely(float32_is_quiet_nan(u.f))) { + return 0; + } + + return float32_to_uint32_round_to_zero(u.f, &env->vec_status); +} + +static inline uint32_t efscfsf(uint32_t val) +{ + CPU_FloatU u; + float32 tmp; + + u.f = int32_to_float32(val, &env->vec_status); + tmp = int64_to_float32(1ULL << 32, &env->vec_status); + u.f = float32_div(u.f, tmp, &env->vec_status); + + return u.l; +} + +static inline uint32_t efscfuf(uint32_t val) +{ + CPU_FloatU u; + float32 tmp; + + u.f = uint32_to_float32(val, &env->vec_status); + tmp = uint64_to_float32(1ULL << 32, &env->vec_status); + u.f = float32_div(u.f, tmp, &env->vec_status); + + return u.l; +} + +static inline uint32_t efsctsf(uint32_t val) +{ + CPU_FloatU u; + float32 tmp; + + u.l = val; + /* NaN are not treated the same way IEEE 754 does */ + if (unlikely(float32_is_quiet_nan(u.f))) { + return 0; + } + tmp = uint64_to_float32(1ULL << 32, &env->vec_status); + u.f = float32_mul(u.f, tmp, &env->vec_status); + + return float32_to_int32(u.f, &env->vec_status); +} + +static inline uint32_t efsctuf(uint32_t val) +{ + CPU_FloatU u; + float32 tmp; + + u.l = val; + /* NaN are not treated the same way IEEE 754 does */ + if (unlikely(float32_is_quiet_nan(u.f))) { + return 0; + } + tmp = uint64_to_float32(1ULL << 32, &env->vec_status); + u.f = float32_mul(u.f, tmp, &env->vec_status); + + return float32_to_uint32(u.f, &env->vec_status); +} + +#define HELPER_SPE_SINGLE_CONV(name) \ + uint32_t helper_e##name(uint32_t val) \ + { \ + return e##name(val); \ + } +/* efscfsi */ +HELPER_SPE_SINGLE_CONV(fscfsi); +/* efscfui */ +HELPER_SPE_SINGLE_CONV(fscfui); +/* efscfuf */ +HELPER_SPE_SINGLE_CONV(fscfuf); +/* efscfsf */ +HELPER_SPE_SINGLE_CONV(fscfsf); +/* efsctsi */ +HELPER_SPE_SINGLE_CONV(fsctsi); +/* efsctui */ +HELPER_SPE_SINGLE_CONV(fsctui); +/* efsctsiz */ +HELPER_SPE_SINGLE_CONV(fsctsiz); +/* efsctuiz */ +HELPER_SPE_SINGLE_CONV(fsctuiz); +/* efsctsf */ +HELPER_SPE_SINGLE_CONV(fsctsf); +/* efsctuf */ +HELPER_SPE_SINGLE_CONV(fsctuf); + +#define HELPER_SPE_VECTOR_CONV(name) \ + uint64_t helper_ev##name(uint64_t val) \ + { \ + return ((uint64_t)e##name(val >> 32) << 32) | \ + (uint64_t)e##name(val); \ + } +/* evfscfsi */ +HELPER_SPE_VECTOR_CONV(fscfsi); +/* evfscfui */ +HELPER_SPE_VECTOR_CONV(fscfui); +/* evfscfuf */ +HELPER_SPE_VECTOR_CONV(fscfuf); +/* evfscfsf */ +HELPER_SPE_VECTOR_CONV(fscfsf); +/* evfsctsi */ +HELPER_SPE_VECTOR_CONV(fsctsi); +/* evfsctui */ +HELPER_SPE_VECTOR_CONV(fsctui); +/* evfsctsiz */ +HELPER_SPE_VECTOR_CONV(fsctsiz); +/* evfsctuiz */ +HELPER_SPE_VECTOR_CONV(fsctuiz); +/* evfsctsf */ +HELPER_SPE_VECTOR_CONV(fsctsf); +/* evfsctuf */ +HELPER_SPE_VECTOR_CONV(fsctuf); + +/* Single-precision floating-point arithmetic */ +static inline uint32_t efsadd(uint32_t op1, uint32_t op2) +{ + CPU_FloatU u1, u2; + + u1.l = op1; + u2.l = op2; + u1.f = float32_add(u1.f, u2.f, &env->vec_status); + return u1.l; +} + +static inline uint32_t efssub(uint32_t op1, uint32_t op2) +{ + CPU_FloatU u1, u2; + + u1.l = op1; + u2.l = op2; + u1.f = float32_sub(u1.f, u2.f, &env->vec_status); + return u1.l; +} + +static inline uint32_t efsmul(uint32_t op1, uint32_t op2) +{ + CPU_FloatU u1, u2; + + u1.l = op1; + u2.l = op2; + u1.f = float32_mul(u1.f, u2.f, &env->vec_status); + return u1.l; +} + +static inline uint32_t efsdiv(uint32_t op1, uint32_t op2) +{ + CPU_FloatU u1, u2; + + u1.l = op1; + u2.l = op2; + u1.f = float32_div(u1.f, u2.f, &env->vec_status); + return u1.l; +} + +#define HELPER_SPE_SINGLE_ARITH(name) \ + uint32_t helper_e##name(uint32_t op1, uint32_t op2) \ + { \ + return e##name(op1, op2); \ + } +/* efsadd */ +HELPER_SPE_SINGLE_ARITH(fsadd); +/* efssub */ +HELPER_SPE_SINGLE_ARITH(fssub); +/* efsmul */ +HELPER_SPE_SINGLE_ARITH(fsmul); +/* efsdiv */ +HELPER_SPE_SINGLE_ARITH(fsdiv); + +#define HELPER_SPE_VECTOR_ARITH(name) \ + uint64_t helper_ev##name(uint64_t op1, uint64_t op2) \ + { \ + return ((uint64_t)e##name(op1 >> 32, op2 >> 32) << 32) | \ + (uint64_t)e##name(op1, op2); \ + } +/* evfsadd */ +HELPER_SPE_VECTOR_ARITH(fsadd); +/* evfssub */ +HELPER_SPE_VECTOR_ARITH(fssub); +/* evfsmul */ +HELPER_SPE_VECTOR_ARITH(fsmul); +/* evfsdiv */ +HELPER_SPE_VECTOR_ARITH(fsdiv); + +/* Single-precision floating-point comparisons */ +static inline uint32_t efscmplt(uint32_t op1, uint32_t op2) +{ + CPU_FloatU u1, u2; + + u1.l = op1; + u2.l = op2; + return float32_lt(u1.f, u2.f, &env->vec_status) ? 4 : 0; +} + +static inline uint32_t efscmpgt(uint32_t op1, uint32_t op2) +{ + CPU_FloatU u1, u2; + + u1.l = op1; + u2.l = op2; + return float32_le(u1.f, u2.f, &env->vec_status) ? 0 : 4; +} + +static inline uint32_t efscmpeq(uint32_t op1, uint32_t op2) +{ + CPU_FloatU u1, u2; + + u1.l = op1; + u2.l = op2; + return float32_eq(u1.f, u2.f, &env->vec_status) ? 4 : 0; +} + +static inline uint32_t efststlt(uint32_t op1, uint32_t op2) +{ + /* XXX: TODO: ignore special values (NaN, infinites, ...) */ + return efscmplt(op1, op2); +} + +static inline uint32_t efststgt(uint32_t op1, uint32_t op2) +{ + /* XXX: TODO: ignore special values (NaN, infinites, ...) */ + return efscmpgt(op1, op2); +} + +static inline uint32_t efststeq(uint32_t op1, uint32_t op2) +{ + /* XXX: TODO: ignore special values (NaN, infinites, ...) */ + return efscmpeq(op1, op2); +} + +#define HELPER_SINGLE_SPE_CMP(name) \ + uint32_t helper_e##name(uint32_t op1, uint32_t op2) \ + { \ + return e##name(op1, op2) << 2; \ + } +/* efststlt */ +HELPER_SINGLE_SPE_CMP(fststlt); +/* efststgt */ +HELPER_SINGLE_SPE_CMP(fststgt); +/* efststeq */ +HELPER_SINGLE_SPE_CMP(fststeq); +/* efscmplt */ +HELPER_SINGLE_SPE_CMP(fscmplt); +/* efscmpgt */ +HELPER_SINGLE_SPE_CMP(fscmpgt); +/* efscmpeq */ +HELPER_SINGLE_SPE_CMP(fscmpeq); + +static inline uint32_t evcmp_merge(int t0, int t1) +{ + return (t0 << 3) | (t1 << 2) | ((t0 | t1) << 1) | (t0 & t1); +} + +#define HELPER_VECTOR_SPE_CMP(name) \ + uint32_t helper_ev##name(uint64_t op1, uint64_t op2) \ + { \ + return evcmp_merge(e##name(op1 >> 32, op2 >> 32), e##name(op1, op2)); \ + } +/* evfststlt */ +HELPER_VECTOR_SPE_CMP(fststlt); +/* evfststgt */ +HELPER_VECTOR_SPE_CMP(fststgt); +/* evfststeq */ +HELPER_VECTOR_SPE_CMP(fststeq); +/* evfscmplt */ +HELPER_VECTOR_SPE_CMP(fscmplt); +/* evfscmpgt */ +HELPER_VECTOR_SPE_CMP(fscmpgt); +/* evfscmpeq */ +HELPER_VECTOR_SPE_CMP(fscmpeq); + +/* Double-precision floating-point conversion */ +uint64_t helper_efdcfsi(uint32_t val) +{ + CPU_DoubleU u; + + u.d = int32_to_float64(val, &env->vec_status); + + return u.ll; +} + +uint64_t helper_efdcfsid(uint64_t val) +{ + CPU_DoubleU u; + + u.d = int64_to_float64(val, &env->vec_status); + + return u.ll; +} + +uint64_t helper_efdcfui(uint32_t val) +{ + CPU_DoubleU u; + + u.d = uint32_to_float64(val, &env->vec_status); + + return u.ll; +} + +uint64_t helper_efdcfuid(uint64_t val) +{ + CPU_DoubleU u; + + u.d = uint64_to_float64(val, &env->vec_status); + + return u.ll; +} + +uint32_t helper_efdctsi(uint64_t val) +{ + CPU_DoubleU u; + + u.ll = val; + /* NaN are not treated the same way IEEE 754 does */ + if (unlikely(float64_is_any_nan(u.d))) { + return 0; + } + + return float64_to_int32(u.d, &env->vec_status); +} + +uint32_t helper_efdctui(uint64_t val) +{ + CPU_DoubleU u; + + u.ll = val; + /* NaN are not treated the same way IEEE 754 does */ + if (unlikely(float64_is_any_nan(u.d))) { + return 0; + } + + return float64_to_uint32(u.d, &env->vec_status); +} + +uint32_t helper_efdctsiz(uint64_t val) +{ + CPU_DoubleU u; + + u.ll = val; + /* NaN are not treated the same way IEEE 754 does */ + if (unlikely(float64_is_any_nan(u.d))) { + return 0; + } + + return float64_to_int32_round_to_zero(u.d, &env->vec_status); +} + +uint64_t helper_efdctsidz(uint64_t val) +{ + CPU_DoubleU u; + + u.ll = val; + /* NaN are not treated the same way IEEE 754 does */ + if (unlikely(float64_is_any_nan(u.d))) { + return 0; + } + + return float64_to_int64_round_to_zero(u.d, &env->vec_status); +} + +uint32_t helper_efdctuiz(uint64_t val) +{ + CPU_DoubleU u; + + u.ll = val; + /* NaN are not treated the same way IEEE 754 does */ + if (unlikely(float64_is_any_nan(u.d))) { + return 0; + } + + return float64_to_uint32_round_to_zero(u.d, &env->vec_status); +} + +uint64_t helper_efdctuidz(uint64_t val) +{ + CPU_DoubleU u; + + u.ll = val; + /* NaN are not treated the same way IEEE 754 does */ + if (unlikely(float64_is_any_nan(u.d))) { + return 0; + } + + return float64_to_uint64_round_to_zero(u.d, &env->vec_status); +} + +uint64_t helper_efdcfsf(uint32_t val) +{ + CPU_DoubleU u; + float64 tmp; + + u.d = int32_to_float64(val, &env->vec_status); + tmp = int64_to_float64(1ULL << 32, &env->vec_status); + u.d = float64_div(u.d, tmp, &env->vec_status); + + return u.ll; +} + +uint64_t helper_efdcfuf(uint32_t val) +{ + CPU_DoubleU u; + float64 tmp; + + u.d = uint32_to_float64(val, &env->vec_status); + tmp = int64_to_float64(1ULL << 32, &env->vec_status); + u.d = float64_div(u.d, tmp, &env->vec_status); + + return u.ll; +} + +uint32_t helper_efdctsf(uint64_t val) +{ + CPU_DoubleU u; + float64 tmp; + + u.ll = val; + /* NaN are not treated the same way IEEE 754 does */ + if (unlikely(float64_is_any_nan(u.d))) { + return 0; + } + tmp = uint64_to_float64(1ULL << 32, &env->vec_status); + u.d = float64_mul(u.d, tmp, &env->vec_status); + + return float64_to_int32(u.d, &env->vec_status); +} + +uint32_t helper_efdctuf(uint64_t val) +{ + CPU_DoubleU u; + float64 tmp; + + u.ll = val; + /* NaN are not treated the same way IEEE 754 does */ + if (unlikely(float64_is_any_nan(u.d))) { + return 0; + } + tmp = uint64_to_float64(1ULL << 32, &env->vec_status); + u.d = float64_mul(u.d, tmp, &env->vec_status); + + return float64_to_uint32(u.d, &env->vec_status); +} + +uint32_t helper_efscfd(uint64_t val) +{ + CPU_DoubleU u1; + CPU_FloatU u2; + + u1.ll = val; + u2.f = float64_to_float32(u1.d, &env->vec_status); + + return u2.l; +} + +uint64_t helper_efdcfs(uint32_t val) +{ + CPU_DoubleU u2; + CPU_FloatU u1; + + u1.l = val; + u2.d = float32_to_float64(u1.f, &env->vec_status); + + return u2.ll; +} + +/* Double precision fixed-point arithmetic */ +uint64_t helper_efdadd(uint64_t op1, uint64_t op2) +{ + CPU_DoubleU u1, u2; + + u1.ll = op1; + u2.ll = op2; + u1.d = float64_add(u1.d, u2.d, &env->vec_status); + return u1.ll; +} + +uint64_t helper_efdsub(uint64_t op1, uint64_t op2) +{ + CPU_DoubleU u1, u2; + + u1.ll = op1; + u2.ll = op2; + u1.d = float64_sub(u1.d, u2.d, &env->vec_status); + return u1.ll; +} + +uint64_t helper_efdmul(uint64_t op1, uint64_t op2) +{ + CPU_DoubleU u1, u2; + + u1.ll = op1; + u2.ll = op2; + u1.d = float64_mul(u1.d, u2.d, &env->vec_status); + return u1.ll; +} + +uint64_t helper_efddiv(uint64_t op1, uint64_t op2) +{ + CPU_DoubleU u1, u2; + + u1.ll = op1; + u2.ll = op2; + u1.d = float64_div(u1.d, u2.d, &env->vec_status); + return u1.ll; +} + +/* Double precision floating point helpers */ +uint32_t helper_efdtstlt(uint64_t op1, uint64_t op2) +{ + CPU_DoubleU u1, u2; + + u1.ll = op1; + u2.ll = op2; + return float64_lt(u1.d, u2.d, &env->vec_status) ? 4 : 0; +} + +uint32_t helper_efdtstgt(uint64_t op1, uint64_t op2) +{ + CPU_DoubleU u1, u2; + + u1.ll = op1; + u2.ll = op2; + return float64_le(u1.d, u2.d, &env->vec_status) ? 0 : 4; +} + +uint32_t helper_efdtsteq(uint64_t op1, uint64_t op2) +{ + CPU_DoubleU u1, u2; + + u1.ll = op1; + u2.ll = op2; + return float64_eq_quiet(u1.d, u2.d, &env->vec_status) ? 4 : 0; +} + +uint32_t helper_efdcmplt(uint64_t op1, uint64_t op2) +{ + /* XXX: TODO: test special values (NaN, infinites, ...) */ + return helper_efdtstlt(op1, op2); +} + +uint32_t helper_efdcmpgt(uint64_t op1, uint64_t op2) +{ + /* XXX: TODO: test special values (NaN, infinites, ...) */ + return helper_efdtstgt(op1, op2); +} + +uint32_t helper_efdcmpeq(uint64_t op1, uint64_t op2) +{ + /* XXX: TODO: test special values (NaN, infinites, ...) */ + return helper_efdtsteq(op1, op2); +} diff --git a/target-ppc/op_helper.c b/target-ppc/op_helper.c index eedbb42..3f677f6 100644 --- a/target-ppc/op_helper.c +++ b/target-ppc/op_helper.c @@ -547,1099 +547,6 @@ target_ulong helper_popcntw(target_ulong val) #endif /*****************************************************************************/ -/* Floating point operations helpers */ -uint64_t helper_float32_to_float64(uint32_t arg) -{ - CPU_FloatU f; - CPU_DoubleU d; - - f.l = arg; - d.d = float32_to_float64(f.f, &env->fp_status); - return d.ll; -} - -uint32_t helper_float64_to_float32(uint64_t arg) -{ - CPU_FloatU f; - CPU_DoubleU d; - - d.ll = arg; - f.f = float64_to_float32(d.d, &env->fp_status); - return f.l; -} - -static inline int isden(float64 d) -{ - CPU_DoubleU u; - - u.d = d; - - return ((u.ll >> 52) & 0x7FF) == 0; -} - -uint32_t helper_compute_fprf(uint64_t arg, uint32_t set_fprf) -{ - CPU_DoubleU farg; - int isneg; - int ret; - - farg.ll = arg; - isneg = float64_is_neg(farg.d); - if (unlikely(float64_is_any_nan(farg.d))) { - if (float64_is_signaling_nan(farg.d)) { - /* Signaling NaN: flags are undefined */ - ret = 0x00; - } else { - /* Quiet NaN */ - ret = 0x11; - } - } else if (unlikely(float64_is_infinity(farg.d))) { - /* +/- infinity */ - if (isneg) { - ret = 0x09; - } else { - ret = 0x05; - } - } else { - if (float64_is_zero(farg.d)) { - /* +/- zero */ - if (isneg) { - ret = 0x12; - } else { - ret = 0x02; - } - } else { - if (isden(farg.d)) { - /* Denormalized numbers */ - ret = 0x10; - } else { - /* Normalized numbers */ - ret = 0x00; - } - if (isneg) { - ret |= 0x08; - } else { - ret |= 0x04; - } - } - } - if (set_fprf) { - /* We update FPSCR_FPRF */ - env->fpscr &= ~(0x1F << FPSCR_FPRF); - env->fpscr |= ret << FPSCR_FPRF; - } - /* We just need fpcc to update Rc1 */ - return ret & 0xF; -} - -/* Floating-point invalid operations exception */ -static inline uint64_t fload_invalid_op_excp(int op) -{ - uint64_t ret = 0; - int ve; - - ve = fpscr_ve; - switch (op) { - case POWERPC_EXCP_FP_VXSNAN: - env->fpscr |= 1 << FPSCR_VXSNAN; - break; - case POWERPC_EXCP_FP_VXSOFT: - env->fpscr |= 1 << FPSCR_VXSOFT; - break; - case POWERPC_EXCP_FP_VXISI: - /* Magnitude subtraction of infinities */ - env->fpscr |= 1 << FPSCR_VXISI; - goto update_arith; - case POWERPC_EXCP_FP_VXIDI: - /* Division of infinity by infinity */ - env->fpscr |= 1 << FPSCR_VXIDI; - goto update_arith; - case POWERPC_EXCP_FP_VXZDZ: - /* Division of zero by zero */ - env->fpscr |= 1 << FPSCR_VXZDZ; - goto update_arith; - case POWERPC_EXCP_FP_VXIMZ: - /* Multiplication of zero by infinity */ - env->fpscr |= 1 << FPSCR_VXIMZ; - goto update_arith; - case POWERPC_EXCP_FP_VXVC: - /* Ordered comparison of NaN */ - env->fpscr |= 1 << FPSCR_VXVC; - env->fpscr &= ~(0xF << FPSCR_FPCC); - env->fpscr |= 0x11 << FPSCR_FPCC; - /* We must update the target FPR before raising the exception */ - if (ve != 0) { - env->exception_index = POWERPC_EXCP_PROGRAM; - env->error_code = POWERPC_EXCP_FP | POWERPC_EXCP_FP_VXVC; - /* Update the floating-point enabled exception summary */ - env->fpscr |= 1 << FPSCR_FEX; - /* Exception is differed */ - ve = 0; - } - break; - case POWERPC_EXCP_FP_VXSQRT: - /* Square root of a negative number */ - env->fpscr |= 1 << FPSCR_VXSQRT; - update_arith: - env->fpscr &= ~((1 << FPSCR_FR) | (1 << FPSCR_FI)); - if (ve == 0) { - /* Set the result to quiet NaN */ - ret = 0x7FF8000000000000ULL; - env->fpscr &= ~(0xF << FPSCR_FPCC); - env->fpscr |= 0x11 << FPSCR_FPCC; - } - break; - case POWERPC_EXCP_FP_VXCVI: - /* Invalid conversion */ - env->fpscr |= 1 << FPSCR_VXCVI; - env->fpscr &= ~((1 << FPSCR_FR) | (1 << FPSCR_FI)); - if (ve == 0) { - /* Set the result to quiet NaN */ - ret = 0x7FF8000000000000ULL; - env->fpscr &= ~(0xF << FPSCR_FPCC); - env->fpscr |= 0x11 << FPSCR_FPCC; - } - break; - } - /* Update the floating-point invalid operation summary */ - env->fpscr |= 1 << FPSCR_VX; - /* Update the floating-point exception summary */ - env->fpscr |= 1 << FPSCR_FX; - if (ve != 0) { - /* Update the floating-point enabled exception summary */ - env->fpscr |= 1 << FPSCR_FEX; - if (msr_fe0 != 0 || msr_fe1 != 0) { - helper_raise_exception_err(env, POWERPC_EXCP_PROGRAM, - POWERPC_EXCP_FP | op); - } - } - return ret; -} - -static inline void float_zero_divide_excp(void) -{ - env->fpscr |= 1 << FPSCR_ZX; - env->fpscr &= ~((1 << FPSCR_FR) | (1 << FPSCR_FI)); - /* Update the floating-point exception summary */ - env->fpscr |= 1 << FPSCR_FX; - if (fpscr_ze != 0) { - /* Update the floating-point enabled exception summary */ - env->fpscr |= 1 << FPSCR_FEX; - if (msr_fe0 != 0 || msr_fe1 != 0) { - helper_raise_exception_err(env, POWERPC_EXCP_PROGRAM, - POWERPC_EXCP_FP | POWERPC_EXCP_FP_ZX); - } - } -} - -static inline void float_overflow_excp(void) -{ - env->fpscr |= 1 << FPSCR_OX; - /* Update the floating-point exception summary */ - env->fpscr |= 1 << FPSCR_FX; - if (fpscr_oe != 0) { - /* XXX: should adjust the result */ - /* Update the floating-point enabled exception summary */ - env->fpscr |= 1 << FPSCR_FEX; - /* We must update the target FPR before raising the exception */ - env->exception_index = POWERPC_EXCP_PROGRAM; - env->error_code = POWERPC_EXCP_FP | POWERPC_EXCP_FP_OX; - } else { - env->fpscr |= 1 << FPSCR_XX; - env->fpscr |= 1 << FPSCR_FI; - } -} - -static inline void float_underflow_excp(void) -{ - env->fpscr |= 1 << FPSCR_UX; - /* Update the floating-point exception summary */ - env->fpscr |= 1 << FPSCR_FX; - if (fpscr_ue != 0) { - /* XXX: should adjust the result */ - /* Update the floating-point enabled exception summary */ - env->fpscr |= 1 << FPSCR_FEX; - /* We must update the target FPR before raising the exception */ - env->exception_index = POWERPC_EXCP_PROGRAM; - env->error_code = POWERPC_EXCP_FP | POWERPC_EXCP_FP_UX; - } -} - -static inline void float_inexact_excp(void) -{ - env->fpscr |= 1 << FPSCR_XX; - /* Update the floating-point exception summary */ - env->fpscr |= 1 << FPSCR_FX; - if (fpscr_xe != 0) { - /* Update the floating-point enabled exception summary */ - env->fpscr |= 1 << FPSCR_FEX; - /* We must update the target FPR before raising the exception */ - env->exception_index = POWERPC_EXCP_PROGRAM; - env->error_code = POWERPC_EXCP_FP | POWERPC_EXCP_FP_XX; - } -} - -static inline void fpscr_set_rounding_mode(void) -{ - int rnd_type; - - /* Set rounding mode */ - switch (fpscr_rn) { - case 0: - /* Best approximation (round to nearest) */ - rnd_type = float_round_nearest_even; - break; - case 1: - /* Smaller magnitude (round toward zero) */ - rnd_type = float_round_to_zero; - break; - case 2: - /* Round toward +infinite */ - rnd_type = float_round_up; - break; - default: - case 3: - /* Round toward -infinite */ - rnd_type = float_round_down; - break; - } - set_float_rounding_mode(rnd_type, &env->fp_status); -} - -void helper_fpscr_clrbit(uint32_t bit) -{ - int prev; - - prev = (env->fpscr >> bit) & 1; - env->fpscr &= ~(1 << bit); - if (prev == 1) { - switch (bit) { - case FPSCR_RN1: - case FPSCR_RN: - fpscr_set_rounding_mode(); - break; - default: - break; - } - } -} - -void helper_fpscr_setbit(uint32_t bit) -{ - int prev; - - prev = (env->fpscr >> bit) & 1; - env->fpscr |= 1 << bit; - if (prev == 0) { - switch (bit) { - case FPSCR_VX: - env->fpscr |= 1 << FPSCR_FX; - if (fpscr_ve) { - goto raise_ve; - } - case FPSCR_OX: - env->fpscr |= 1 << FPSCR_FX; - if (fpscr_oe) { - goto raise_oe; - } - break; - case FPSCR_UX: - env->fpscr |= 1 << FPSCR_FX; - if (fpscr_ue) { - goto raise_ue; - } - break; - case FPSCR_ZX: - env->fpscr |= 1 << FPSCR_FX; - if (fpscr_ze) { - goto raise_ze; - } - break; - case FPSCR_XX: - env->fpscr |= 1 << FPSCR_FX; - if (fpscr_xe) { - goto raise_xe; - } - break; - case FPSCR_VXSNAN: - case FPSCR_VXISI: - case FPSCR_VXIDI: - case FPSCR_VXZDZ: - case FPSCR_VXIMZ: - case FPSCR_VXVC: - case FPSCR_VXSOFT: - case FPSCR_VXSQRT: - case FPSCR_VXCVI: - env->fpscr |= 1 << FPSCR_VX; - env->fpscr |= 1 << FPSCR_FX; - if (fpscr_ve != 0) { - goto raise_ve; - } - break; - case FPSCR_VE: - if (fpscr_vx != 0) { - raise_ve: - env->error_code = POWERPC_EXCP_FP; - if (fpscr_vxsnan) { - env->error_code |= POWERPC_EXCP_FP_VXSNAN; - } - if (fpscr_vxisi) { - env->error_code |= POWERPC_EXCP_FP_VXISI; - } - if (fpscr_vxidi) { - env->error_code |= POWERPC_EXCP_FP_VXIDI; - } - if (fpscr_vxzdz) { - env->error_code |= POWERPC_EXCP_FP_VXZDZ; - } - if (fpscr_vximz) { - env->error_code |= POWERPC_EXCP_FP_VXIMZ; - } - if (fpscr_vxvc) { - env->error_code |= POWERPC_EXCP_FP_VXVC; - } - if (fpscr_vxsoft) { - env->error_code |= POWERPC_EXCP_FP_VXSOFT; - } - if (fpscr_vxsqrt) { - env->error_code |= POWERPC_EXCP_FP_VXSQRT; - } - if (fpscr_vxcvi) { - env->error_code |= POWERPC_EXCP_FP_VXCVI; - } - goto raise_excp; - } - break; - case FPSCR_OE: - if (fpscr_ox != 0) { - raise_oe: - env->error_code = POWERPC_EXCP_FP | POWERPC_EXCP_FP_OX; - goto raise_excp; - } - break; - case FPSCR_UE: - if (fpscr_ux != 0) { - raise_ue: - env->error_code = POWERPC_EXCP_FP | POWERPC_EXCP_FP_UX; - goto raise_excp; - } - break; - case FPSCR_ZE: - if (fpscr_zx != 0) { - raise_ze: - env->error_code = POWERPC_EXCP_FP | POWERPC_EXCP_FP_ZX; - goto raise_excp; - } - break; - case FPSCR_XE: - if (fpscr_xx != 0) { - raise_xe: - env->error_code = POWERPC_EXCP_FP | POWERPC_EXCP_FP_XX; - goto raise_excp; - } - break; - case FPSCR_RN1: - case FPSCR_RN: - fpscr_set_rounding_mode(); - break; - default: - break; - raise_excp: - /* Update the floating-point enabled exception summary */ - env->fpscr |= 1 << FPSCR_FEX; - /* We have to update Rc1 before raising the exception */ - env->exception_index = POWERPC_EXCP_PROGRAM; - break; - } - } -} - -void helper_store_fpscr(uint64_t arg, uint32_t mask) -{ - /* - * We use only the 32 LSB of the incoming fpr - */ - uint32_t prev, new; - int i; - - prev = env->fpscr; - new = (uint32_t)arg; - new &= ~0x60000000; - new |= prev & 0x60000000; - for (i = 0; i < 8; i++) { - if (mask & (1 << i)) { - env->fpscr &= ~(0xF << (4 * i)); - env->fpscr |= new & (0xF << (4 * i)); - } - } - /* Update VX and FEX */ - if (fpscr_ix != 0) { - env->fpscr |= 1 << FPSCR_VX; - } else { - env->fpscr &= ~(1 << FPSCR_VX); - } - if ((fpscr_ex & fpscr_eex) != 0) { - env->fpscr |= 1 << FPSCR_FEX; - env->exception_index = POWERPC_EXCP_PROGRAM; - /* XXX: we should compute it properly */ - env->error_code = POWERPC_EXCP_FP; - } else { - env->fpscr &= ~(1 << FPSCR_FEX); - } - fpscr_set_rounding_mode(); -} - -void helper_float_check_status(void) -{ - if (env->exception_index == POWERPC_EXCP_PROGRAM && - (env->error_code & POWERPC_EXCP_FP)) { - /* Differred floating-point exception after target FPR update */ - if (msr_fe0 != 0 || msr_fe1 != 0) { - helper_raise_exception_err(env, env->exception_index, - env->error_code); - } - } else { - int status = get_float_exception_flags(&env->fp_status); - if (status & float_flag_divbyzero) { - float_zero_divide_excp(); - } else if (status & float_flag_overflow) { - float_overflow_excp(); - } else if (status & float_flag_underflow) { - float_underflow_excp(); - } else if (status & float_flag_inexact) { - float_inexact_excp(); - } - } -} - -void helper_reset_fpstatus(void) -{ - set_float_exception_flags(0, &env->fp_status); -} - -/* fadd - fadd. */ -uint64_t helper_fadd(uint64_t arg1, uint64_t arg2) -{ - CPU_DoubleU farg1, farg2; - - farg1.ll = arg1; - farg2.ll = arg2; - - if (unlikely(float64_is_infinity(farg1.d) && float64_is_infinity(farg2.d) && - float64_is_neg(farg1.d) != float64_is_neg(farg2.d))) { - /* Magnitude subtraction of infinities */ - farg1.ll = fload_invalid_op_excp(POWERPC_EXCP_FP_VXISI); - } else { - if (unlikely(float64_is_signaling_nan(farg1.d) || - float64_is_signaling_nan(farg2.d))) { - /* sNaN addition */ - fload_invalid_op_excp(POWERPC_EXCP_FP_VXSNAN); - } - farg1.d = float64_add(farg1.d, farg2.d, &env->fp_status); - } - - return farg1.ll; -} - -/* fsub - fsub. */ -uint64_t helper_fsub(uint64_t arg1, uint64_t arg2) -{ - CPU_DoubleU farg1, farg2; - - farg1.ll = arg1; - farg2.ll = arg2; - - if (unlikely(float64_is_infinity(farg1.d) && float64_is_infinity(farg2.d) && - float64_is_neg(farg1.d) == float64_is_neg(farg2.d))) { - /* Magnitude subtraction of infinities */ - farg1.ll = fload_invalid_op_excp(POWERPC_EXCP_FP_VXISI); - } else { - if (unlikely(float64_is_signaling_nan(farg1.d) || - float64_is_signaling_nan(farg2.d))) { - /* sNaN subtraction */ - fload_invalid_op_excp(POWERPC_EXCP_FP_VXSNAN); - } - farg1.d = float64_sub(farg1.d, farg2.d, &env->fp_status); - } - - return farg1.ll; -} - -/* fmul - fmul. */ -uint64_t helper_fmul(uint64_t arg1, uint64_t arg2) -{ - CPU_DoubleU farg1, farg2; - - farg1.ll = arg1; - farg2.ll = arg2; - - if (unlikely((float64_is_infinity(farg1.d) && float64_is_zero(farg2.d)) || - (float64_is_zero(farg1.d) && float64_is_infinity(farg2.d)))) { - /* Multiplication of zero by infinity */ - farg1.ll = fload_invalid_op_excp(POWERPC_EXCP_FP_VXIMZ); - } else { - if (unlikely(float64_is_signaling_nan(farg1.d) || - float64_is_signaling_nan(farg2.d))) { - /* sNaN multiplication */ - fload_invalid_op_excp(POWERPC_EXCP_FP_VXSNAN); - } - farg1.d = float64_mul(farg1.d, farg2.d, &env->fp_status); - } - - return farg1.ll; -} - -/* fdiv - fdiv. */ -uint64_t helper_fdiv(uint64_t arg1, uint64_t arg2) -{ - CPU_DoubleU farg1, farg2; - - farg1.ll = arg1; - farg2.ll = arg2; - - if (unlikely(float64_is_infinity(farg1.d) && - float64_is_infinity(farg2.d))) { - /* Division of infinity by infinity */ - farg1.ll = fload_invalid_op_excp(POWERPC_EXCP_FP_VXIDI); - } else if (unlikely(float64_is_zero(farg1.d) && float64_is_zero(farg2.d))) { - /* Division of zero by zero */ - farg1.ll = fload_invalid_op_excp(POWERPC_EXCP_FP_VXZDZ); - } else { - if (unlikely(float64_is_signaling_nan(farg1.d) || - float64_is_signaling_nan(farg2.d))) { - /* sNaN division */ - fload_invalid_op_excp(POWERPC_EXCP_FP_VXSNAN); - } - farg1.d = float64_div(farg1.d, farg2.d, &env->fp_status); - } - - return farg1.ll; -} - -/* fabs */ -uint64_t helper_fabs(uint64_t arg) -{ - CPU_DoubleU farg; - - farg.ll = arg; - farg.d = float64_abs(farg.d); - return farg.ll; -} - -/* fnabs */ -uint64_t helper_fnabs(uint64_t arg) -{ - CPU_DoubleU farg; - - farg.ll = arg; - farg.d = float64_abs(farg.d); - farg.d = float64_chs(farg.d); - return farg.ll; -} - -/* fneg */ -uint64_t helper_fneg(uint64_t arg) -{ - CPU_DoubleU farg; - - farg.ll = arg; - farg.d = float64_chs(farg.d); - return farg.ll; -} - -/* fctiw - fctiw. */ -uint64_t helper_fctiw(uint64_t arg) -{ - CPU_DoubleU farg; - - farg.ll = arg; - - if (unlikely(float64_is_signaling_nan(farg.d))) { - /* sNaN conversion */ - farg.ll = fload_invalid_op_excp(POWERPC_EXCP_FP_VXSNAN | - POWERPC_EXCP_FP_VXCVI); - } else if (unlikely(float64_is_quiet_nan(farg.d) || - float64_is_infinity(farg.d))) { - /* qNan / infinity conversion */ - farg.ll = fload_invalid_op_excp(POWERPC_EXCP_FP_VXCVI); - } else { - farg.ll = float64_to_int32(farg.d, &env->fp_status); - /* XXX: higher bits are not supposed to be significant. - * to make tests easier, return the same as a real PowerPC 750 - */ - farg.ll |= 0xFFF80000ULL << 32; - } - return farg.ll; -} - -/* fctiwz - fctiwz. */ -uint64_t helper_fctiwz(uint64_t arg) -{ - CPU_DoubleU farg; - - farg.ll = arg; - - if (unlikely(float64_is_signaling_nan(farg.d))) { - /* sNaN conversion */ - farg.ll = fload_invalid_op_excp(POWERPC_EXCP_FP_VXSNAN | - POWERPC_EXCP_FP_VXCVI); - } else if (unlikely(float64_is_quiet_nan(farg.d) || - float64_is_infinity(farg.d))) { - /* qNan / infinity conversion */ - farg.ll = fload_invalid_op_excp(POWERPC_EXCP_FP_VXCVI); - } else { - farg.ll = float64_to_int32_round_to_zero(farg.d, &env->fp_status); - /* XXX: higher bits are not supposed to be significant. - * to make tests easier, return the same as a real PowerPC 750 - */ - farg.ll |= 0xFFF80000ULL << 32; - } - return farg.ll; -} - -#if defined(TARGET_PPC64) -/* fcfid - fcfid. */ -uint64_t helper_fcfid(uint64_t arg) -{ - CPU_DoubleU farg; - - farg.d = int64_to_float64(arg, &env->fp_status); - return farg.ll; -} - -/* fctid - fctid. */ -uint64_t helper_fctid(uint64_t arg) -{ - CPU_DoubleU farg; - - farg.ll = arg; - - if (unlikely(float64_is_signaling_nan(farg.d))) { - /* sNaN conversion */ - farg.ll = fload_invalid_op_excp(POWERPC_EXCP_FP_VXSNAN | - POWERPC_EXCP_FP_VXCVI); - } else if (unlikely(float64_is_quiet_nan(farg.d) || - float64_is_infinity(farg.d))) { - /* qNan / infinity conversion */ - farg.ll = fload_invalid_op_excp(POWERPC_EXCP_FP_VXCVI); - } else { - farg.ll = float64_to_int64(farg.d, &env->fp_status); - } - return farg.ll; -} - -/* fctidz - fctidz. */ -uint64_t helper_fctidz(uint64_t arg) -{ - CPU_DoubleU farg; - - farg.ll = arg; - - if (unlikely(float64_is_signaling_nan(farg.d))) { - /* sNaN conversion */ - farg.ll = fload_invalid_op_excp(POWERPC_EXCP_FP_VXSNAN | - POWERPC_EXCP_FP_VXCVI); - } else if (unlikely(float64_is_quiet_nan(farg.d) || - float64_is_infinity(farg.d))) { - /* qNan / infinity conversion */ - farg.ll = fload_invalid_op_excp(POWERPC_EXCP_FP_VXCVI); - } else { - farg.ll = float64_to_int64_round_to_zero(farg.d, &env->fp_status); - } - return farg.ll; -} - -#endif - -static inline uint64_t do_fri(uint64_t arg, int rounding_mode) -{ - CPU_DoubleU farg; - - farg.ll = arg; - - if (unlikely(float64_is_signaling_nan(farg.d))) { - /* sNaN round */ - farg.ll = fload_invalid_op_excp(POWERPC_EXCP_FP_VXSNAN | - POWERPC_EXCP_FP_VXCVI); - } else if (unlikely(float64_is_quiet_nan(farg.d) || - float64_is_infinity(farg.d))) { - /* qNan / infinity round */ - farg.ll = fload_invalid_op_excp(POWERPC_EXCP_FP_VXCVI); - } else { - set_float_rounding_mode(rounding_mode, &env->fp_status); - farg.ll = float64_round_to_int(farg.d, &env->fp_status); - /* Restore rounding mode from FPSCR */ - fpscr_set_rounding_mode(); - } - return farg.ll; -} - -uint64_t helper_frin(uint64_t arg) -{ - return do_fri(arg, float_round_nearest_even); -} - -uint64_t helper_friz(uint64_t arg) -{ - return do_fri(arg, float_round_to_zero); -} - -uint64_t helper_frip(uint64_t arg) -{ - return do_fri(arg, float_round_up); -} - -uint64_t helper_frim(uint64_t arg) -{ - return do_fri(arg, float_round_down); -} - -/* fmadd - fmadd. */ -uint64_t helper_fmadd(uint64_t arg1, uint64_t arg2, uint64_t arg3) -{ - CPU_DoubleU farg1, farg2, farg3; - - farg1.ll = arg1; - farg2.ll = arg2; - farg3.ll = arg3; - - if (unlikely((float64_is_infinity(farg1.d) && float64_is_zero(farg2.d)) || - (float64_is_zero(farg1.d) && float64_is_infinity(farg2.d)))) { - /* Multiplication of zero by infinity */ - farg1.ll = fload_invalid_op_excp(POWERPC_EXCP_FP_VXIMZ); - } else { - if (unlikely(float64_is_signaling_nan(farg1.d) || - float64_is_signaling_nan(farg2.d) || - float64_is_signaling_nan(farg3.d))) { - /* sNaN operation */ - fload_invalid_op_excp(POWERPC_EXCP_FP_VXSNAN); - } - /* This is the way the PowerPC specification defines it */ - float128 ft0_128, ft1_128; - - ft0_128 = float64_to_float128(farg1.d, &env->fp_status); - ft1_128 = float64_to_float128(farg2.d, &env->fp_status); - ft0_128 = float128_mul(ft0_128, ft1_128, &env->fp_status); - if (unlikely(float128_is_infinity(ft0_128) && - float64_is_infinity(farg3.d) && - float128_is_neg(ft0_128) != float64_is_neg(farg3.d))) { - /* Magnitude subtraction of infinities */ - farg1.ll = fload_invalid_op_excp(POWERPC_EXCP_FP_VXISI); - } else { - ft1_128 = float64_to_float128(farg3.d, &env->fp_status); - ft0_128 = float128_add(ft0_128, ft1_128, &env->fp_status); - farg1.d = float128_to_float64(ft0_128, &env->fp_status); - } - } - - return farg1.ll; -} - -/* fmsub - fmsub. */ -uint64_t helper_fmsub(uint64_t arg1, uint64_t arg2, uint64_t arg3) -{ - CPU_DoubleU farg1, farg2, farg3; - - farg1.ll = arg1; - farg2.ll = arg2; - farg3.ll = arg3; - - if (unlikely((float64_is_infinity(farg1.d) && float64_is_zero(farg2.d)) || - (float64_is_zero(farg1.d) && - float64_is_infinity(farg2.d)))) { - /* Multiplication of zero by infinity */ - farg1.ll = fload_invalid_op_excp(POWERPC_EXCP_FP_VXIMZ); - } else { - if (unlikely(float64_is_signaling_nan(farg1.d) || - float64_is_signaling_nan(farg2.d) || - float64_is_signaling_nan(farg3.d))) { - /* sNaN operation */ - fload_invalid_op_excp(POWERPC_EXCP_FP_VXSNAN); - } - /* This is the way the PowerPC specification defines it */ - float128 ft0_128, ft1_128; - - ft0_128 = float64_to_float128(farg1.d, &env->fp_status); - ft1_128 = float64_to_float128(farg2.d, &env->fp_status); - ft0_128 = float128_mul(ft0_128, ft1_128, &env->fp_status); - if (unlikely(float128_is_infinity(ft0_128) && - float64_is_infinity(farg3.d) && - float128_is_neg(ft0_128) == float64_is_neg(farg3.d))) { - /* Magnitude subtraction of infinities */ - farg1.ll = fload_invalid_op_excp(POWERPC_EXCP_FP_VXISI); - } else { - ft1_128 = float64_to_float128(farg3.d, &env->fp_status); - ft0_128 = float128_sub(ft0_128, ft1_128, &env->fp_status); - farg1.d = float128_to_float64(ft0_128, &env->fp_status); - } - } - return farg1.ll; -} - -/* fnmadd - fnmadd. */ -uint64_t helper_fnmadd(uint64_t arg1, uint64_t arg2, uint64_t arg3) -{ - CPU_DoubleU farg1, farg2, farg3; - - farg1.ll = arg1; - farg2.ll = arg2; - farg3.ll = arg3; - - if (unlikely((float64_is_infinity(farg1.d) && float64_is_zero(farg2.d)) || - (float64_is_zero(farg1.d) && float64_is_infinity(farg2.d)))) { - /* Multiplication of zero by infinity */ - farg1.ll = fload_invalid_op_excp(POWERPC_EXCP_FP_VXIMZ); - } else { - if (unlikely(float64_is_signaling_nan(farg1.d) || - float64_is_signaling_nan(farg2.d) || - float64_is_signaling_nan(farg3.d))) { - /* sNaN operation */ - fload_invalid_op_excp(POWERPC_EXCP_FP_VXSNAN); - } - /* This is the way the PowerPC specification defines it */ - float128 ft0_128, ft1_128; - - ft0_128 = float64_to_float128(farg1.d, &env->fp_status); - ft1_128 = float64_to_float128(farg2.d, &env->fp_status); - ft0_128 = float128_mul(ft0_128, ft1_128, &env->fp_status); - if (unlikely(float128_is_infinity(ft0_128) && - float64_is_infinity(farg3.d) && - float128_is_neg(ft0_128) != float64_is_neg(farg3.d))) { - /* Magnitude subtraction of infinities */ - farg1.ll = fload_invalid_op_excp(POWERPC_EXCP_FP_VXISI); - } else { - ft1_128 = float64_to_float128(farg3.d, &env->fp_status); - ft0_128 = float128_add(ft0_128, ft1_128, &env->fp_status); - farg1.d = float128_to_float64(ft0_128, &env->fp_status); - } - if (likely(!float64_is_any_nan(farg1.d))) { - farg1.d = float64_chs(farg1.d); - } - } - return farg1.ll; -} - -/* fnmsub - fnmsub. */ -uint64_t helper_fnmsub(uint64_t arg1, uint64_t arg2, uint64_t arg3) -{ - CPU_DoubleU farg1, farg2, farg3; - - farg1.ll = arg1; - farg2.ll = arg2; - farg3.ll = arg3; - - if (unlikely((float64_is_infinity(farg1.d) && float64_is_zero(farg2.d)) || - (float64_is_zero(farg1.d) && - float64_is_infinity(farg2.d)))) { - /* Multiplication of zero by infinity */ - farg1.ll = fload_invalid_op_excp(POWERPC_EXCP_FP_VXIMZ); - } else { - if (unlikely(float64_is_signaling_nan(farg1.d) || - float64_is_signaling_nan(farg2.d) || - float64_is_signaling_nan(farg3.d))) { - /* sNaN operation */ - fload_invalid_op_excp(POWERPC_EXCP_FP_VXSNAN); - } - /* This is the way the PowerPC specification defines it */ - float128 ft0_128, ft1_128; - - ft0_128 = float64_to_float128(farg1.d, &env->fp_status); - ft1_128 = float64_to_float128(farg2.d, &env->fp_status); - ft0_128 = float128_mul(ft0_128, ft1_128, &env->fp_status); - if (unlikely(float128_is_infinity(ft0_128) && - float64_is_infinity(farg3.d) && - float128_is_neg(ft0_128) == float64_is_neg(farg3.d))) { - /* Magnitude subtraction of infinities */ - farg1.ll = fload_invalid_op_excp(POWERPC_EXCP_FP_VXISI); - } else { - ft1_128 = float64_to_float128(farg3.d, &env->fp_status); - ft0_128 = float128_sub(ft0_128, ft1_128, &env->fp_status); - farg1.d = float128_to_float64(ft0_128, &env->fp_status); - } - if (likely(!float64_is_any_nan(farg1.d))) { - farg1.d = float64_chs(farg1.d); - } - } - return farg1.ll; -} - -/* frsp - frsp. */ -uint64_t helper_frsp(uint64_t arg) -{ - CPU_DoubleU farg; - float32 f32; - - farg.ll = arg; - - if (unlikely(float64_is_signaling_nan(farg.d))) { - /* sNaN square root */ - fload_invalid_op_excp(POWERPC_EXCP_FP_VXSNAN); - } - f32 = float64_to_float32(farg.d, &env->fp_status); - farg.d = float32_to_float64(f32, &env->fp_status); - - return farg.ll; -} - -/* fsqrt - fsqrt. */ -uint64_t helper_fsqrt(uint64_t arg) -{ - CPU_DoubleU farg; - - farg.ll = arg; - - if (unlikely(float64_is_neg(farg.d) && !float64_is_zero(farg.d))) { - /* Square root of a negative nonzero number */ - farg.ll = fload_invalid_op_excp(POWERPC_EXCP_FP_VXSQRT); - } else { - if (unlikely(float64_is_signaling_nan(farg.d))) { - /* sNaN square root */ - fload_invalid_op_excp(POWERPC_EXCP_FP_VXSNAN); - } - farg.d = float64_sqrt(farg.d, &env->fp_status); - } - return farg.ll; -} - -/* fre - fre. */ -uint64_t helper_fre(uint64_t arg) -{ - CPU_DoubleU farg; - - farg.ll = arg; - - if (unlikely(float64_is_signaling_nan(farg.d))) { - /* sNaN reciprocal */ - fload_invalid_op_excp(POWERPC_EXCP_FP_VXSNAN); - } - farg.d = float64_div(float64_one, farg.d, &env->fp_status); - return farg.d; -} - -/* fres - fres. */ -uint64_t helper_fres(uint64_t arg) -{ - CPU_DoubleU farg; - float32 f32; - - farg.ll = arg; - - if (unlikely(float64_is_signaling_nan(farg.d))) { - /* sNaN reciprocal */ - fload_invalid_op_excp(POWERPC_EXCP_FP_VXSNAN); - } - farg.d = float64_div(float64_one, farg.d, &env->fp_status); - f32 = float64_to_float32(farg.d, &env->fp_status); - farg.d = float32_to_float64(f32, &env->fp_status); - - return farg.ll; -} - -/* frsqrte - frsqrte. */ -uint64_t helper_frsqrte(uint64_t arg) -{ - CPU_DoubleU farg; - float32 f32; - - farg.ll = arg; - - if (unlikely(float64_is_neg(farg.d) && !float64_is_zero(farg.d))) { - /* Reciprocal square root of a negative nonzero number */ - farg.ll = fload_invalid_op_excp(POWERPC_EXCP_FP_VXSQRT); - } else { - if (unlikely(float64_is_signaling_nan(farg.d))) { - /* sNaN reciprocal square root */ - fload_invalid_op_excp(POWERPC_EXCP_FP_VXSNAN); - } - farg.d = float64_sqrt(farg.d, &env->fp_status); - farg.d = float64_div(float64_one, farg.d, &env->fp_status); - f32 = float64_to_float32(farg.d, &env->fp_status); - farg.d = float32_to_float64(f32, &env->fp_status); - } - return farg.ll; -} - -/* fsel - fsel. */ -uint64_t helper_fsel(uint64_t arg1, uint64_t arg2, uint64_t arg3) -{ - CPU_DoubleU farg1; - - farg1.ll = arg1; - - if ((!float64_is_neg(farg1.d) || float64_is_zero(farg1.d)) && - !float64_is_any_nan(farg1.d)) { - return arg2; - } else { - return arg3; - } -} - -void helper_fcmpu(uint64_t arg1, uint64_t arg2, uint32_t crfD) -{ - CPU_DoubleU farg1, farg2; - uint32_t ret = 0; - - farg1.ll = arg1; - farg2.ll = arg2; - - if (unlikely(float64_is_any_nan(farg1.d) || - float64_is_any_nan(farg2.d))) { - ret = 0x01UL; - } else if (float64_lt(farg1.d, farg2.d, &env->fp_status)) { - ret = 0x08UL; - } else if (!float64_le(farg1.d, farg2.d, &env->fp_status)) { - ret = 0x04UL; - } else { - ret = 0x02UL; - } - - env->fpscr &= ~(0x0F << FPSCR_FPRF); - env->fpscr |= ret << FPSCR_FPRF; - env->crf[crfD] = ret; - if (unlikely(ret == 0x01UL - && (float64_is_signaling_nan(farg1.d) || - float64_is_signaling_nan(farg2.d)))) { - /* sNaN comparison */ - fload_invalid_op_excp(POWERPC_EXCP_FP_VXSNAN); - } -} - -void helper_fcmpo(uint64_t arg1, uint64_t arg2, uint32_t crfD) -{ - CPU_DoubleU farg1, farg2; - uint32_t ret = 0; - - farg1.ll = arg1; - farg2.ll = arg2; - - if (unlikely(float64_is_any_nan(farg1.d) || - float64_is_any_nan(farg2.d))) { - ret = 0x01UL; - } else if (float64_lt(farg1.d, farg2.d, &env->fp_status)) { - ret = 0x08UL; - } else if (!float64_le(farg1.d, farg2.d, &env->fp_status)) { - ret = 0x04UL; - } else { - ret = 0x02UL; - } - - env->fpscr &= ~(0x0F << FPSCR_FPRF); - env->fpscr |= ret << FPSCR_FPRF; - env->crf[crfD] = ret; - if (unlikely(ret == 0x01UL)) { - if (float64_is_signaling_nan(farg1.d) || - float64_is_signaling_nan(farg2.d)) { - /* sNaN comparison */ - fload_invalid_op_excp(POWERPC_EXCP_FP_VXSNAN | - POWERPC_EXCP_FP_VXVC); - } else { - /* qNaN comparison */ - fload_invalid_op_excp(POWERPC_EXCP_FP_VXVC); - } - } -} - -/*****************************************************************************/ /* PowerPC 601 specific instructions (POWER bridge) */ target_ulong helper_clcs(uint32_t arg) @@ -3125,623 +2032,6 @@ uint32_t helper_cntlzw32(uint32_t val) return clz32(val); } -/* Single-precision floating-point conversions */ -static inline uint32_t efscfsi(uint32_t val) -{ - CPU_FloatU u; - - u.f = int32_to_float32(val, &env->vec_status); - - return u.l; -} - -static inline uint32_t efscfui(uint32_t val) -{ - CPU_FloatU u; - - u.f = uint32_to_float32(val, &env->vec_status); - - return u.l; -} - -static inline int32_t efsctsi(uint32_t val) -{ - CPU_FloatU u; - - u.l = val; - /* NaN are not treated the same way IEEE 754 does */ - if (unlikely(float32_is_quiet_nan(u.f))) { - return 0; - } - - return float32_to_int32(u.f, &env->vec_status); -} - -static inline uint32_t efsctui(uint32_t val) -{ - CPU_FloatU u; - - u.l = val; - /* NaN are not treated the same way IEEE 754 does */ - if (unlikely(float32_is_quiet_nan(u.f))) { - return 0; - } - - return float32_to_uint32(u.f, &env->vec_status); -} - -static inline uint32_t efsctsiz(uint32_t val) -{ - CPU_FloatU u; - - u.l = val; - /* NaN are not treated the same way IEEE 754 does */ - if (unlikely(float32_is_quiet_nan(u.f))) { - return 0; - } - - return float32_to_int32_round_to_zero(u.f, &env->vec_status); -} - -static inline uint32_t efsctuiz(uint32_t val) -{ - CPU_FloatU u; - - u.l = val; - /* NaN are not treated the same way IEEE 754 does */ - if (unlikely(float32_is_quiet_nan(u.f))) { - return 0; - } - - return float32_to_uint32_round_to_zero(u.f, &env->vec_status); -} - -static inline uint32_t efscfsf(uint32_t val) -{ - CPU_FloatU u; - float32 tmp; - - u.f = int32_to_float32(val, &env->vec_status); - tmp = int64_to_float32(1ULL << 32, &env->vec_status); - u.f = float32_div(u.f, tmp, &env->vec_status); - - return u.l; -} - -static inline uint32_t efscfuf(uint32_t val) -{ - CPU_FloatU u; - float32 tmp; - - u.f = uint32_to_float32(val, &env->vec_status); - tmp = uint64_to_float32(1ULL << 32, &env->vec_status); - u.f = float32_div(u.f, tmp, &env->vec_status); - - return u.l; -} - -static inline uint32_t efsctsf(uint32_t val) -{ - CPU_FloatU u; - float32 tmp; - - u.l = val; - /* NaN are not treated the same way IEEE 754 does */ - if (unlikely(float32_is_quiet_nan(u.f))) { - return 0; - } - tmp = uint64_to_float32(1ULL << 32, &env->vec_status); - u.f = float32_mul(u.f, tmp, &env->vec_status); - - return float32_to_int32(u.f, &env->vec_status); -} - -static inline uint32_t efsctuf(uint32_t val) -{ - CPU_FloatU u; - float32 tmp; - - u.l = val; - /* NaN are not treated the same way IEEE 754 does */ - if (unlikely(float32_is_quiet_nan(u.f))) { - return 0; - } - tmp = uint64_to_float32(1ULL << 32, &env->vec_status); - u.f = float32_mul(u.f, tmp, &env->vec_status); - - return float32_to_uint32(u.f, &env->vec_status); -} - -#define HELPER_SPE_SINGLE_CONV(name) \ - uint32_t helper_e##name(uint32_t val) \ - { \ - return e##name(val); \ - } -/* efscfsi */ -HELPER_SPE_SINGLE_CONV(fscfsi); -/* efscfui */ -HELPER_SPE_SINGLE_CONV(fscfui); -/* efscfuf */ -HELPER_SPE_SINGLE_CONV(fscfuf); -/* efscfsf */ -HELPER_SPE_SINGLE_CONV(fscfsf); -/* efsctsi */ -HELPER_SPE_SINGLE_CONV(fsctsi); -/* efsctui */ -HELPER_SPE_SINGLE_CONV(fsctui); -/* efsctsiz */ -HELPER_SPE_SINGLE_CONV(fsctsiz); -/* efsctuiz */ -HELPER_SPE_SINGLE_CONV(fsctuiz); -/* efsctsf */ -HELPER_SPE_SINGLE_CONV(fsctsf); -/* efsctuf */ -HELPER_SPE_SINGLE_CONV(fsctuf); - -#define HELPER_SPE_VECTOR_CONV(name) \ - uint64_t helper_ev##name(uint64_t val) \ - { \ - return ((uint64_t)e##name(val >> 32) << 32) | \ - (uint64_t)e##name(val); \ - } -/* evfscfsi */ -HELPER_SPE_VECTOR_CONV(fscfsi); -/* evfscfui */ -HELPER_SPE_VECTOR_CONV(fscfui); -/* evfscfuf */ -HELPER_SPE_VECTOR_CONV(fscfuf); -/* evfscfsf */ -HELPER_SPE_VECTOR_CONV(fscfsf); -/* evfsctsi */ -HELPER_SPE_VECTOR_CONV(fsctsi); -/* evfsctui */ -HELPER_SPE_VECTOR_CONV(fsctui); -/* evfsctsiz */ -HELPER_SPE_VECTOR_CONV(fsctsiz); -/* evfsctuiz */ -HELPER_SPE_VECTOR_CONV(fsctuiz); -/* evfsctsf */ -HELPER_SPE_VECTOR_CONV(fsctsf); -/* evfsctuf */ -HELPER_SPE_VECTOR_CONV(fsctuf); - -/* Single-precision floating-point arithmetic */ -static inline uint32_t efsadd(uint32_t op1, uint32_t op2) -{ - CPU_FloatU u1, u2; - - u1.l = op1; - u2.l = op2; - u1.f = float32_add(u1.f, u2.f, &env->vec_status); - return u1.l; -} - -static inline uint32_t efssub(uint32_t op1, uint32_t op2) -{ - CPU_FloatU u1, u2; - - u1.l = op1; - u2.l = op2; - u1.f = float32_sub(u1.f, u2.f, &env->vec_status); - return u1.l; -} - -static inline uint32_t efsmul(uint32_t op1, uint32_t op2) -{ - CPU_FloatU u1, u2; - - u1.l = op1; - u2.l = op2; - u1.f = float32_mul(u1.f, u2.f, &env->vec_status); - return u1.l; -} - -static inline uint32_t efsdiv(uint32_t op1, uint32_t op2) -{ - CPU_FloatU u1, u2; - - u1.l = op1; - u2.l = op2; - u1.f = float32_div(u1.f, u2.f, &env->vec_status); - return u1.l; -} - -#define HELPER_SPE_SINGLE_ARITH(name) \ - uint32_t helper_e##name(uint32_t op1, uint32_t op2) \ - { \ - return e##name(op1, op2); \ - } -/* efsadd */ -HELPER_SPE_SINGLE_ARITH(fsadd); -/* efssub */ -HELPER_SPE_SINGLE_ARITH(fssub); -/* efsmul */ -HELPER_SPE_SINGLE_ARITH(fsmul); -/* efsdiv */ -HELPER_SPE_SINGLE_ARITH(fsdiv); - -#define HELPER_SPE_VECTOR_ARITH(name) \ - uint64_t helper_ev##name(uint64_t op1, uint64_t op2) \ - { \ - return ((uint64_t)e##name(op1 >> 32, op2 >> 32) << 32) | \ - (uint64_t)e##name(op1, op2); \ - } -/* evfsadd */ -HELPER_SPE_VECTOR_ARITH(fsadd); -/* evfssub */ -HELPER_SPE_VECTOR_ARITH(fssub); -/* evfsmul */ -HELPER_SPE_VECTOR_ARITH(fsmul); -/* evfsdiv */ -HELPER_SPE_VECTOR_ARITH(fsdiv); - -/* Single-precision floating-point comparisons */ -static inline uint32_t efscmplt(uint32_t op1, uint32_t op2) -{ - CPU_FloatU u1, u2; - - u1.l = op1; - u2.l = op2; - return float32_lt(u1.f, u2.f, &env->vec_status) ? 4 : 0; -} - -static inline uint32_t efscmpgt(uint32_t op1, uint32_t op2) -{ - CPU_FloatU u1, u2; - - u1.l = op1; - u2.l = op2; - return float32_le(u1.f, u2.f, &env->vec_status) ? 0 : 4; -} - -static inline uint32_t efscmpeq(uint32_t op1, uint32_t op2) -{ - CPU_FloatU u1, u2; - - u1.l = op1; - u2.l = op2; - return float32_eq(u1.f, u2.f, &env->vec_status) ? 4 : 0; -} - -static inline uint32_t efststlt(uint32_t op1, uint32_t op2) -{ - /* XXX: TODO: ignore special values (NaN, infinites, ...) */ - return efscmplt(op1, op2); -} - -static inline uint32_t efststgt(uint32_t op1, uint32_t op2) -{ - /* XXX: TODO: ignore special values (NaN, infinites, ...) */ - return efscmpgt(op1, op2); -} - -static inline uint32_t efststeq(uint32_t op1, uint32_t op2) -{ - /* XXX: TODO: ignore special values (NaN, infinites, ...) */ - return efscmpeq(op1, op2); -} - -#define HELPER_SINGLE_SPE_CMP(name) \ - uint32_t helper_e##name(uint32_t op1, uint32_t op2) \ - { \ - return e##name(op1, op2) << 2; \ - } -/* efststlt */ -HELPER_SINGLE_SPE_CMP(fststlt); -/* efststgt */ -HELPER_SINGLE_SPE_CMP(fststgt); -/* efststeq */ -HELPER_SINGLE_SPE_CMP(fststeq); -/* efscmplt */ -HELPER_SINGLE_SPE_CMP(fscmplt); -/* efscmpgt */ -HELPER_SINGLE_SPE_CMP(fscmpgt); -/* efscmpeq */ -HELPER_SINGLE_SPE_CMP(fscmpeq); - -static inline uint32_t evcmp_merge(int t0, int t1) -{ - return (t0 << 3) | (t1 << 2) | ((t0 | t1) << 1) | (t0 & t1); -} - -#define HELPER_VECTOR_SPE_CMP(name) \ - uint32_t helper_ev##name(uint64_t op1, uint64_t op2) \ - { \ - return evcmp_merge(e##name(op1 >> 32, op2 >> 32), e##name(op1, op2)); \ - } -/* evfststlt */ -HELPER_VECTOR_SPE_CMP(fststlt); -/* evfststgt */ -HELPER_VECTOR_SPE_CMP(fststgt); -/* evfststeq */ -HELPER_VECTOR_SPE_CMP(fststeq); -/* evfscmplt */ -HELPER_VECTOR_SPE_CMP(fscmplt); -/* evfscmpgt */ -HELPER_VECTOR_SPE_CMP(fscmpgt); -/* evfscmpeq */ -HELPER_VECTOR_SPE_CMP(fscmpeq); - -/* Double-precision floating-point conversion */ -uint64_t helper_efdcfsi(uint32_t val) -{ - CPU_DoubleU u; - - u.d = int32_to_float64(val, &env->vec_status); - - return u.ll; -} - -uint64_t helper_efdcfsid(uint64_t val) -{ - CPU_DoubleU u; - - u.d = int64_to_float64(val, &env->vec_status); - - return u.ll; -} - -uint64_t helper_efdcfui(uint32_t val) -{ - CPU_DoubleU u; - - u.d = uint32_to_float64(val, &env->vec_status); - - return u.ll; -} - -uint64_t helper_efdcfuid(uint64_t val) -{ - CPU_DoubleU u; - - u.d = uint64_to_float64(val, &env->vec_status); - - return u.ll; -} - -uint32_t helper_efdctsi(uint64_t val) -{ - CPU_DoubleU u; - - u.ll = val; - /* NaN are not treated the same way IEEE 754 does */ - if (unlikely(float64_is_any_nan(u.d))) { - return 0; - } - - return float64_to_int32(u.d, &env->vec_status); -} - -uint32_t helper_efdctui(uint64_t val) -{ - CPU_DoubleU u; - - u.ll = val; - /* NaN are not treated the same way IEEE 754 does */ - if (unlikely(float64_is_any_nan(u.d))) { - return 0; - } - - return float64_to_uint32(u.d, &env->vec_status); -} - -uint32_t helper_efdctsiz(uint64_t val) -{ - CPU_DoubleU u; - - u.ll = val; - /* NaN are not treated the same way IEEE 754 does */ - if (unlikely(float64_is_any_nan(u.d))) { - return 0; - } - - return float64_to_int32_round_to_zero(u.d, &env->vec_status); -} - -uint64_t helper_efdctsidz(uint64_t val) -{ - CPU_DoubleU u; - - u.ll = val; - /* NaN are not treated the same way IEEE 754 does */ - if (unlikely(float64_is_any_nan(u.d))) { - return 0; - } - - return float64_to_int64_round_to_zero(u.d, &env->vec_status); -} - -uint32_t helper_efdctuiz(uint64_t val) -{ - CPU_DoubleU u; - - u.ll = val; - /* NaN are not treated the same way IEEE 754 does */ - if (unlikely(float64_is_any_nan(u.d))) { - return 0; - } - - return float64_to_uint32_round_to_zero(u.d, &env->vec_status); -} - -uint64_t helper_efdctuidz(uint64_t val) -{ - CPU_DoubleU u; - - u.ll = val; - /* NaN are not treated the same way IEEE 754 does */ - if (unlikely(float64_is_any_nan(u.d))) { - return 0; - } - - return float64_to_uint64_round_to_zero(u.d, &env->vec_status); -} - -uint64_t helper_efdcfsf(uint32_t val) -{ - CPU_DoubleU u; - float64 tmp; - - u.d = int32_to_float64(val, &env->vec_status); - tmp = int64_to_float64(1ULL << 32, &env->vec_status); - u.d = float64_div(u.d, tmp, &env->vec_status); - - return u.ll; -} - -uint64_t helper_efdcfuf(uint32_t val) -{ - CPU_DoubleU u; - float64 tmp; - - u.d = uint32_to_float64(val, &env->vec_status); - tmp = int64_to_float64(1ULL << 32, &env->vec_status); - u.d = float64_div(u.d, tmp, &env->vec_status); - - return u.ll; -} - -uint32_t helper_efdctsf(uint64_t val) -{ - CPU_DoubleU u; - float64 tmp; - - u.ll = val; - /* NaN are not treated the same way IEEE 754 does */ - if (unlikely(float64_is_any_nan(u.d))) { - return 0; - } - tmp = uint64_to_float64(1ULL << 32, &env->vec_status); - u.d = float64_mul(u.d, tmp, &env->vec_status); - - return float64_to_int32(u.d, &env->vec_status); -} - -uint32_t helper_efdctuf(uint64_t val) -{ - CPU_DoubleU u; - float64 tmp; - - u.ll = val; - /* NaN are not treated the same way IEEE 754 does */ - if (unlikely(float64_is_any_nan(u.d))) { - return 0; - } - tmp = uint64_to_float64(1ULL << 32, &env->vec_status); - u.d = float64_mul(u.d, tmp, &env->vec_status); - - return float64_to_uint32(u.d, &env->vec_status); -} - -uint32_t helper_efscfd(uint64_t val) -{ - CPU_DoubleU u1; - CPU_FloatU u2; - - u1.ll = val; - u2.f = float64_to_float32(u1.d, &env->vec_status); - - return u2.l; -} - -uint64_t helper_efdcfs(uint32_t val) -{ - CPU_DoubleU u2; - CPU_FloatU u1; - - u1.l = val; - u2.d = float32_to_float64(u1.f, &env->vec_status); - - return u2.ll; -} - -/* Double precision fixed-point arithmetic */ -uint64_t helper_efdadd(uint64_t op1, uint64_t op2) -{ - CPU_DoubleU u1, u2; - - u1.ll = op1; - u2.ll = op2; - u1.d = float64_add(u1.d, u2.d, &env->vec_status); - return u1.ll; -} - -uint64_t helper_efdsub(uint64_t op1, uint64_t op2) -{ - CPU_DoubleU u1, u2; - - u1.ll = op1; - u2.ll = op2; - u1.d = float64_sub(u1.d, u2.d, &env->vec_status); - return u1.ll; -} - -uint64_t helper_efdmul(uint64_t op1, uint64_t op2) -{ - CPU_DoubleU u1, u2; - - u1.ll = op1; - u2.ll = op2; - u1.d = float64_mul(u1.d, u2.d, &env->vec_status); - return u1.ll; -} - -uint64_t helper_efddiv(uint64_t op1, uint64_t op2) -{ - CPU_DoubleU u1, u2; - - u1.ll = op1; - u2.ll = op2; - u1.d = float64_div(u1.d, u2.d, &env->vec_status); - return u1.ll; -} - -/* Double precision floating point helpers */ -uint32_t helper_efdtstlt(uint64_t op1, uint64_t op2) -{ - CPU_DoubleU u1, u2; - - u1.ll = op1; - u2.ll = op2; - return float64_lt(u1.d, u2.d, &env->vec_status) ? 4 : 0; -} - -uint32_t helper_efdtstgt(uint64_t op1, uint64_t op2) -{ - CPU_DoubleU u1, u2; - - u1.ll = op1; - u2.ll = op2; - return float64_le(u1.d, u2.d, &env->vec_status) ? 0 : 4; -} - -uint32_t helper_efdtsteq(uint64_t op1, uint64_t op2) -{ - CPU_DoubleU u1, u2; - - u1.ll = op1; - u2.ll = op2; - return float64_eq_quiet(u1.d, u2.d, &env->vec_status) ? 4 : 0; -} - -uint32_t helper_efdcmplt(uint64_t op1, uint64_t op2) -{ - /* XXX: TODO: test special values (NaN, infinites, ...) */ - return helper_efdtstlt(op1, op2); -} - -uint32_t helper_efdcmpgt(uint64_t op1, uint64_t op2) -{ - /* XXX: TODO: test special values (NaN, infinites, ...) */ - return helper_efdtstgt(op1, op2); -} - -uint32_t helper_efdcmpeq(uint64_t op1, uint64_t op2) -{ - /* XXX: TODO: test special values (NaN, infinites, ...) */ - return helper_efdtsteq(op1, op2); -} - /*****************************************************************************/ /* Softmmu support */ #if !defined(CONFIG_USER_ONLY)