354908cee1
The function that makes NaN-boxing when a 32-bit value is assigned to a 64-bit FP register is split out to a helper gen_nanbox_fpr(). Then it is applied in translating of the FLW instruction. Signed-off-by: Ian Jiang <ianjiang.ict@gmail.com> Message-Id: <20200128003707.17028-1-ianjiang.ict@gmail.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
452 lines
11 KiB
C
452 lines
11 KiB
C
/*
|
|
* RISC-V translation routines for the RV64F Standard Extension.
|
|
*
|
|
* Copyright (c) 2016-2017 Sagar Karandikar, sagark@eecs.berkeley.edu
|
|
* Copyright (c) 2018 Peer Adelt, peer.adelt@hni.uni-paderborn.de
|
|
* Bastian Koppelmann, kbastian@mail.uni-paderborn.de
|
|
*
|
|
* This program is free software; you can redistribute it and/or modify it
|
|
* under the terms and conditions of the GNU General Public License,
|
|
* version 2 or later, as published by the Free Software Foundation.
|
|
*
|
|
* This program is distributed in the hope it will be useful, but WITHOUT
|
|
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
|
|
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
|
|
* more details.
|
|
*
|
|
* You should have received a copy of the GNU General Public License along with
|
|
* this program. If not, see <http://www.gnu.org/licenses/>.
|
|
*/
|
|
|
|
#define REQUIRE_FPU do {\
|
|
if (ctx->mstatus_fs == 0) \
|
|
return false; \
|
|
} while (0)
|
|
|
|
/*
|
|
* RISC-V requires NaN-boxing of narrower width floating
|
|
* point values. This applies when a 32-bit value is
|
|
* assigned to a 64-bit FP register. Thus this does not
|
|
* apply when the RVD extension is not present.
|
|
*/
|
|
static void gen_nanbox_fpr(DisasContext *ctx, int regno)
|
|
{
|
|
if (has_ext(ctx, RVD)) {
|
|
tcg_gen_ori_i64(cpu_fpr[regno], cpu_fpr[regno],
|
|
MAKE_64BIT_MASK(32, 32));
|
|
}
|
|
}
|
|
|
|
static bool trans_flw(DisasContext *ctx, arg_flw *a)
|
|
{
|
|
TCGv t0 = tcg_temp_new();
|
|
gen_get_gpr(t0, a->rs1);
|
|
REQUIRE_FPU;
|
|
REQUIRE_EXT(ctx, RVF);
|
|
tcg_gen_addi_tl(t0, t0, a->imm);
|
|
|
|
tcg_gen_qemu_ld_i64(cpu_fpr[a->rd], t0, ctx->mem_idx, MO_TEUL);
|
|
gen_nanbox_fpr(ctx, a->rd);
|
|
|
|
tcg_temp_free(t0);
|
|
mark_fs_dirty(ctx);
|
|
return true;
|
|
}
|
|
|
|
static bool trans_fsw(DisasContext *ctx, arg_fsw *a)
|
|
{
|
|
TCGv t0 = tcg_temp_new();
|
|
gen_get_gpr(t0, a->rs1);
|
|
|
|
REQUIRE_FPU;
|
|
REQUIRE_EXT(ctx, RVF);
|
|
tcg_gen_addi_tl(t0, t0, a->imm);
|
|
|
|
tcg_gen_qemu_st_i64(cpu_fpr[a->rs2], t0, ctx->mem_idx, MO_TEUL);
|
|
|
|
tcg_temp_free(t0);
|
|
return true;
|
|
}
|
|
|
|
static bool trans_fmadd_s(DisasContext *ctx, arg_fmadd_s *a)
|
|
{
|
|
REQUIRE_FPU;
|
|
REQUIRE_EXT(ctx, RVF);
|
|
gen_set_rm(ctx, a->rm);
|
|
gen_helper_fmadd_s(cpu_fpr[a->rd], cpu_env, cpu_fpr[a->rs1],
|
|
cpu_fpr[a->rs2], cpu_fpr[a->rs3]);
|
|
mark_fs_dirty(ctx);
|
|
return true;
|
|
}
|
|
|
|
static bool trans_fmsub_s(DisasContext *ctx, arg_fmsub_s *a)
|
|
{
|
|
REQUIRE_FPU;
|
|
REQUIRE_EXT(ctx, RVF);
|
|
gen_set_rm(ctx, a->rm);
|
|
gen_helper_fmsub_s(cpu_fpr[a->rd], cpu_env, cpu_fpr[a->rs1],
|
|
cpu_fpr[a->rs2], cpu_fpr[a->rs3]);
|
|
mark_fs_dirty(ctx);
|
|
return true;
|
|
}
|
|
|
|
static bool trans_fnmsub_s(DisasContext *ctx, arg_fnmsub_s *a)
|
|
{
|
|
REQUIRE_FPU;
|
|
REQUIRE_EXT(ctx, RVF);
|
|
gen_set_rm(ctx, a->rm);
|
|
gen_helper_fnmsub_s(cpu_fpr[a->rd], cpu_env, cpu_fpr[a->rs1],
|
|
cpu_fpr[a->rs2], cpu_fpr[a->rs3]);
|
|
mark_fs_dirty(ctx);
|
|
return true;
|
|
}
|
|
|
|
static bool trans_fnmadd_s(DisasContext *ctx, arg_fnmadd_s *a)
|
|
{
|
|
REQUIRE_FPU;
|
|
REQUIRE_EXT(ctx, RVF);
|
|
gen_set_rm(ctx, a->rm);
|
|
gen_helper_fnmadd_s(cpu_fpr[a->rd], cpu_env, cpu_fpr[a->rs1],
|
|
cpu_fpr[a->rs2], cpu_fpr[a->rs3]);
|
|
mark_fs_dirty(ctx);
|
|
return true;
|
|
}
|
|
|
|
static bool trans_fadd_s(DisasContext *ctx, arg_fadd_s *a)
|
|
{
|
|
REQUIRE_FPU;
|
|
REQUIRE_EXT(ctx, RVF);
|
|
|
|
gen_set_rm(ctx, a->rm);
|
|
gen_helper_fadd_s(cpu_fpr[a->rd], cpu_env,
|
|
cpu_fpr[a->rs1], cpu_fpr[a->rs2]);
|
|
mark_fs_dirty(ctx);
|
|
return true;
|
|
}
|
|
|
|
static bool trans_fsub_s(DisasContext *ctx, arg_fsub_s *a)
|
|
{
|
|
REQUIRE_FPU;
|
|
REQUIRE_EXT(ctx, RVF);
|
|
|
|
gen_set_rm(ctx, a->rm);
|
|
gen_helper_fsub_s(cpu_fpr[a->rd], cpu_env,
|
|
cpu_fpr[a->rs1], cpu_fpr[a->rs2]);
|
|
mark_fs_dirty(ctx);
|
|
return true;
|
|
}
|
|
|
|
static bool trans_fmul_s(DisasContext *ctx, arg_fmul_s *a)
|
|
{
|
|
REQUIRE_FPU;
|
|
REQUIRE_EXT(ctx, RVF);
|
|
|
|
gen_set_rm(ctx, a->rm);
|
|
gen_helper_fmul_s(cpu_fpr[a->rd], cpu_env,
|
|
cpu_fpr[a->rs1], cpu_fpr[a->rs2]);
|
|
mark_fs_dirty(ctx);
|
|
return true;
|
|
}
|
|
|
|
static bool trans_fdiv_s(DisasContext *ctx, arg_fdiv_s *a)
|
|
{
|
|
REQUIRE_FPU;
|
|
REQUIRE_EXT(ctx, RVF);
|
|
|
|
gen_set_rm(ctx, a->rm);
|
|
gen_helper_fdiv_s(cpu_fpr[a->rd], cpu_env,
|
|
cpu_fpr[a->rs1], cpu_fpr[a->rs2]);
|
|
mark_fs_dirty(ctx);
|
|
return true;
|
|
}
|
|
|
|
static bool trans_fsqrt_s(DisasContext *ctx, arg_fsqrt_s *a)
|
|
{
|
|
REQUIRE_FPU;
|
|
REQUIRE_EXT(ctx, RVF);
|
|
|
|
gen_set_rm(ctx, a->rm);
|
|
gen_helper_fsqrt_s(cpu_fpr[a->rd], cpu_env, cpu_fpr[a->rs1]);
|
|
mark_fs_dirty(ctx);
|
|
return true;
|
|
}
|
|
|
|
static bool trans_fsgnj_s(DisasContext *ctx, arg_fsgnj_s *a)
|
|
{
|
|
REQUIRE_FPU;
|
|
REQUIRE_EXT(ctx, RVF);
|
|
if (a->rs1 == a->rs2) { /* FMOV */
|
|
tcg_gen_mov_i64(cpu_fpr[a->rd], cpu_fpr[a->rs1]);
|
|
} else { /* FSGNJ */
|
|
tcg_gen_deposit_i64(cpu_fpr[a->rd], cpu_fpr[a->rs2], cpu_fpr[a->rs1],
|
|
0, 31);
|
|
}
|
|
mark_fs_dirty(ctx);
|
|
return true;
|
|
}
|
|
|
|
static bool trans_fsgnjn_s(DisasContext *ctx, arg_fsgnjn_s *a)
|
|
{
|
|
REQUIRE_FPU;
|
|
REQUIRE_EXT(ctx, RVF);
|
|
if (a->rs1 == a->rs2) { /* FNEG */
|
|
tcg_gen_xori_i64(cpu_fpr[a->rd], cpu_fpr[a->rs1], INT32_MIN);
|
|
} else {
|
|
TCGv_i64 t0 = tcg_temp_new_i64();
|
|
tcg_gen_not_i64(t0, cpu_fpr[a->rs2]);
|
|
tcg_gen_deposit_i64(cpu_fpr[a->rd], t0, cpu_fpr[a->rs1], 0, 31);
|
|
tcg_temp_free_i64(t0);
|
|
}
|
|
mark_fs_dirty(ctx);
|
|
return true;
|
|
}
|
|
|
|
static bool trans_fsgnjx_s(DisasContext *ctx, arg_fsgnjx_s *a)
|
|
{
|
|
REQUIRE_FPU;
|
|
REQUIRE_EXT(ctx, RVF);
|
|
if (a->rs1 == a->rs2) { /* FABS */
|
|
tcg_gen_andi_i64(cpu_fpr[a->rd], cpu_fpr[a->rs1], ~INT32_MIN);
|
|
} else {
|
|
TCGv_i64 t0 = tcg_temp_new_i64();
|
|
tcg_gen_andi_i64(t0, cpu_fpr[a->rs2], INT32_MIN);
|
|
tcg_gen_xor_i64(cpu_fpr[a->rd], cpu_fpr[a->rs1], t0);
|
|
tcg_temp_free_i64(t0);
|
|
}
|
|
mark_fs_dirty(ctx);
|
|
return true;
|
|
}
|
|
|
|
static bool trans_fmin_s(DisasContext *ctx, arg_fmin_s *a)
|
|
{
|
|
REQUIRE_FPU;
|
|
REQUIRE_EXT(ctx, RVF);
|
|
|
|
gen_helper_fmin_s(cpu_fpr[a->rd], cpu_env, cpu_fpr[a->rs1],
|
|
cpu_fpr[a->rs2]);
|
|
mark_fs_dirty(ctx);
|
|
return true;
|
|
}
|
|
|
|
static bool trans_fmax_s(DisasContext *ctx, arg_fmax_s *a)
|
|
{
|
|
REQUIRE_FPU;
|
|
REQUIRE_EXT(ctx, RVF);
|
|
|
|
gen_helper_fmax_s(cpu_fpr[a->rd], cpu_env, cpu_fpr[a->rs1],
|
|
cpu_fpr[a->rs2]);
|
|
mark_fs_dirty(ctx);
|
|
return true;
|
|
}
|
|
|
|
static bool trans_fcvt_w_s(DisasContext *ctx, arg_fcvt_w_s *a)
|
|
{
|
|
REQUIRE_FPU;
|
|
REQUIRE_EXT(ctx, RVF);
|
|
|
|
TCGv t0 = tcg_temp_new();
|
|
gen_set_rm(ctx, a->rm);
|
|
gen_helper_fcvt_w_s(t0, cpu_env, cpu_fpr[a->rs1]);
|
|
gen_set_gpr(a->rd, t0);
|
|
tcg_temp_free(t0);
|
|
|
|
return true;
|
|
}
|
|
|
|
static bool trans_fcvt_wu_s(DisasContext *ctx, arg_fcvt_wu_s *a)
|
|
{
|
|
REQUIRE_FPU;
|
|
REQUIRE_EXT(ctx, RVF);
|
|
|
|
TCGv t0 = tcg_temp_new();
|
|
gen_set_rm(ctx, a->rm);
|
|
gen_helper_fcvt_wu_s(t0, cpu_env, cpu_fpr[a->rs1]);
|
|
gen_set_gpr(a->rd, t0);
|
|
tcg_temp_free(t0);
|
|
|
|
return true;
|
|
}
|
|
|
|
static bool trans_fmv_x_w(DisasContext *ctx, arg_fmv_x_w *a)
|
|
{
|
|
/* NOTE: This was FMV.X.S in an earlier version of the ISA spec! */
|
|
REQUIRE_FPU;
|
|
REQUIRE_EXT(ctx, RVF);
|
|
|
|
TCGv t0 = tcg_temp_new();
|
|
|
|
#if defined(TARGET_RISCV64)
|
|
tcg_gen_ext32s_tl(t0, cpu_fpr[a->rs1]);
|
|
#else
|
|
tcg_gen_extrl_i64_i32(t0, cpu_fpr[a->rs1]);
|
|
#endif
|
|
|
|
gen_set_gpr(a->rd, t0);
|
|
tcg_temp_free(t0);
|
|
|
|
return true;
|
|
}
|
|
|
|
static bool trans_feq_s(DisasContext *ctx, arg_feq_s *a)
|
|
{
|
|
REQUIRE_FPU;
|
|
REQUIRE_EXT(ctx, RVF);
|
|
TCGv t0 = tcg_temp_new();
|
|
gen_helper_feq_s(t0, cpu_env, cpu_fpr[a->rs1], cpu_fpr[a->rs2]);
|
|
gen_set_gpr(a->rd, t0);
|
|
tcg_temp_free(t0);
|
|
return true;
|
|
}
|
|
|
|
static bool trans_flt_s(DisasContext *ctx, arg_flt_s *a)
|
|
{
|
|
REQUIRE_FPU;
|
|
REQUIRE_EXT(ctx, RVF);
|
|
TCGv t0 = tcg_temp_new();
|
|
gen_helper_flt_s(t0, cpu_env, cpu_fpr[a->rs1], cpu_fpr[a->rs2]);
|
|
gen_set_gpr(a->rd, t0);
|
|
tcg_temp_free(t0);
|
|
return true;
|
|
}
|
|
|
|
static bool trans_fle_s(DisasContext *ctx, arg_fle_s *a)
|
|
{
|
|
REQUIRE_FPU;
|
|
REQUIRE_EXT(ctx, RVF);
|
|
TCGv t0 = tcg_temp_new();
|
|
gen_helper_fle_s(t0, cpu_env, cpu_fpr[a->rs1], cpu_fpr[a->rs2]);
|
|
gen_set_gpr(a->rd, t0);
|
|
tcg_temp_free(t0);
|
|
return true;
|
|
}
|
|
|
|
static bool trans_fclass_s(DisasContext *ctx, arg_fclass_s *a)
|
|
{
|
|
REQUIRE_FPU;
|
|
REQUIRE_EXT(ctx, RVF);
|
|
|
|
TCGv t0 = tcg_temp_new();
|
|
|
|
gen_helper_fclass_s(t0, cpu_fpr[a->rs1]);
|
|
|
|
gen_set_gpr(a->rd, t0);
|
|
tcg_temp_free(t0);
|
|
|
|
return true;
|
|
}
|
|
|
|
static bool trans_fcvt_s_w(DisasContext *ctx, arg_fcvt_s_w *a)
|
|
{
|
|
REQUIRE_FPU;
|
|
REQUIRE_EXT(ctx, RVF);
|
|
|
|
TCGv t0 = tcg_temp_new();
|
|
gen_get_gpr(t0, a->rs1);
|
|
|
|
gen_set_rm(ctx, a->rm);
|
|
gen_helper_fcvt_s_w(cpu_fpr[a->rd], cpu_env, t0);
|
|
|
|
mark_fs_dirty(ctx);
|
|
tcg_temp_free(t0);
|
|
|
|
return true;
|
|
}
|
|
|
|
static bool trans_fcvt_s_wu(DisasContext *ctx, arg_fcvt_s_wu *a)
|
|
{
|
|
REQUIRE_FPU;
|
|
REQUIRE_EXT(ctx, RVF);
|
|
|
|
TCGv t0 = tcg_temp_new();
|
|
gen_get_gpr(t0, a->rs1);
|
|
|
|
gen_set_rm(ctx, a->rm);
|
|
gen_helper_fcvt_s_wu(cpu_fpr[a->rd], cpu_env, t0);
|
|
|
|
mark_fs_dirty(ctx);
|
|
tcg_temp_free(t0);
|
|
|
|
return true;
|
|
}
|
|
|
|
static bool trans_fmv_w_x(DisasContext *ctx, arg_fmv_w_x *a)
|
|
{
|
|
/* NOTE: This was FMV.S.X in an earlier version of the ISA spec! */
|
|
REQUIRE_FPU;
|
|
REQUIRE_EXT(ctx, RVF);
|
|
|
|
TCGv t0 = tcg_temp_new();
|
|
gen_get_gpr(t0, a->rs1);
|
|
|
|
#if defined(TARGET_RISCV64)
|
|
tcg_gen_mov_i64(cpu_fpr[a->rd], t0);
|
|
#else
|
|
tcg_gen_extu_i32_i64(cpu_fpr[a->rd], t0);
|
|
#endif
|
|
|
|
mark_fs_dirty(ctx);
|
|
tcg_temp_free(t0);
|
|
|
|
return true;
|
|
}
|
|
|
|
#ifdef TARGET_RISCV64
|
|
static bool trans_fcvt_l_s(DisasContext *ctx, arg_fcvt_l_s *a)
|
|
{
|
|
REQUIRE_FPU;
|
|
REQUIRE_EXT(ctx, RVF);
|
|
|
|
TCGv t0 = tcg_temp_new();
|
|
gen_set_rm(ctx, a->rm);
|
|
gen_helper_fcvt_l_s(t0, cpu_env, cpu_fpr[a->rs1]);
|
|
gen_set_gpr(a->rd, t0);
|
|
tcg_temp_free(t0);
|
|
return true;
|
|
}
|
|
|
|
static bool trans_fcvt_lu_s(DisasContext *ctx, arg_fcvt_lu_s *a)
|
|
{
|
|
REQUIRE_FPU;
|
|
REQUIRE_EXT(ctx, RVF);
|
|
|
|
TCGv t0 = tcg_temp_new();
|
|
gen_set_rm(ctx, a->rm);
|
|
gen_helper_fcvt_lu_s(t0, cpu_env, cpu_fpr[a->rs1]);
|
|
gen_set_gpr(a->rd, t0);
|
|
tcg_temp_free(t0);
|
|
return true;
|
|
}
|
|
|
|
static bool trans_fcvt_s_l(DisasContext *ctx, arg_fcvt_s_l *a)
|
|
{
|
|
REQUIRE_FPU;
|
|
REQUIRE_EXT(ctx, RVF);
|
|
|
|
TCGv t0 = tcg_temp_new();
|
|
gen_get_gpr(t0, a->rs1);
|
|
|
|
gen_set_rm(ctx, a->rm);
|
|
gen_helper_fcvt_s_l(cpu_fpr[a->rd], cpu_env, t0);
|
|
|
|
mark_fs_dirty(ctx);
|
|
tcg_temp_free(t0);
|
|
return true;
|
|
}
|
|
|
|
static bool trans_fcvt_s_lu(DisasContext *ctx, arg_fcvt_s_lu *a)
|
|
{
|
|
REQUIRE_FPU;
|
|
REQUIRE_EXT(ctx, RVF);
|
|
|
|
TCGv t0 = tcg_temp_new();
|
|
gen_get_gpr(t0, a->rs1);
|
|
|
|
gen_set_rm(ctx, a->rm);
|
|
gen_helper_fcvt_s_lu(cpu_fpr[a->rd], cpu_env, t0);
|
|
|
|
mark_fs_dirty(ctx);
|
|
tcg_temp_free(t0);
|
|
return true;
|
|
}
|
|
#endif
|