diff options
Diffstat (limited to 'target/riscv/insn_trans/trans_rvf.c.inc')
-rw-r--r-- | target/riscv/insn_trans/trans_rvf.c.inc | 99 |
1 files changed, 62 insertions, 37 deletions
diff --git a/target/riscv/insn_trans/trans_rvf.c.inc b/target/riscv/insn_trans/trans_rvf.c.inc index 3bfd888..3dfec82 100644 --- a/target/riscv/insn_trans/trans_rvf.c.inc +++ b/target/riscv/insn_trans/trans_rvf.c.inc @@ -23,30 +23,16 @@ 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); + TCGv t0 = tcg_temp_new(); + gen_get_gpr(t0, a->rs1); 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); + gen_nanbox_s(cpu_fpr[a->rd], cpu_fpr[a->rd]); tcg_temp_free(t0); mark_fs_dirty(ctx); @@ -55,11 +41,11 @@ static bool trans_flw(DisasContext *ctx, arg_flw *a) static bool trans_fsw(DisasContext *ctx, arg_fsw *a) { + REQUIRE_FPU; + REQUIRE_EXT(ctx, RVF); 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); @@ -175,11 +161,20 @@ 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]); + gen_check_nanbox_s(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); + TCGv_i64 rs1 = tcg_temp_new_i64(); + TCGv_i64 rs2 = tcg_temp_new_i64(); + + gen_check_nanbox_s(rs1, cpu_fpr[a->rs1]); + gen_check_nanbox_s(rs2, cpu_fpr[a->rs2]); + + /* This formulation retains the nanboxing of rs2. */ + tcg_gen_deposit_i64(cpu_fpr[a->rd], rs2, rs1, 0, 31); + tcg_temp_free_i64(rs1); + tcg_temp_free_i64(rs2); } mark_fs_dirty(ctx); return true; @@ -187,32 +182,65 @@ static bool trans_fsgnj_s(DisasContext *ctx, arg_fsgnj_s *a) static bool trans_fsgnjn_s(DisasContext *ctx, arg_fsgnjn_s *a) { + TCGv_i64 rs1, rs2, mask; + REQUIRE_FPU; REQUIRE_EXT(ctx, RVF); + + rs1 = tcg_temp_new_i64(); + gen_check_nanbox_s(rs1, cpu_fpr[a->rs1]); + if (a->rs1 == a->rs2) { /* FNEG */ - tcg_gen_xori_i64(cpu_fpr[a->rd], cpu_fpr[a->rs1], INT32_MIN); + tcg_gen_xori_i64(cpu_fpr[a->rd], rs1, MAKE_64BIT_MASK(31, 1)); } 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); + rs2 = tcg_temp_new_i64(); + gen_check_nanbox_s(rs2, cpu_fpr[a->rs2]); + + /* + * Replace bit 31 in rs1 with inverse in rs2. + * This formulation retains the nanboxing of rs1. + */ + mask = tcg_const_i64(~MAKE_64BIT_MASK(31, 1)); + tcg_gen_nor_i64(rs2, rs2, mask); + tcg_gen_and_i64(rs1, mask, rs1); + tcg_gen_or_i64(cpu_fpr[a->rd], rs1, rs2); + + tcg_temp_free_i64(mask); + tcg_temp_free_i64(rs2); } + tcg_temp_free_i64(rs1); + mark_fs_dirty(ctx); return true; } static bool trans_fsgnjx_s(DisasContext *ctx, arg_fsgnjx_s *a) { + TCGv_i64 rs1, rs2; + REQUIRE_FPU; REQUIRE_EXT(ctx, RVF); + + rs1 = tcg_temp_new_i64(); + gen_check_nanbox_s(rs1, cpu_fpr[a->rs1]); + if (a->rs1 == a->rs2) { /* FABS */ - tcg_gen_andi_i64(cpu_fpr[a->rd], cpu_fpr[a->rs1], ~INT32_MIN); + tcg_gen_andi_i64(cpu_fpr[a->rd], rs1, ~MAKE_64BIT_MASK(31, 1)); } 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); + rs2 = tcg_temp_new_i64(); + gen_check_nanbox_s(rs2, cpu_fpr[a->rs2]); + + /* + * Xor bit 31 in rs1 with that in rs2. + * This formulation retains the nanboxing of rs1. + */ + tcg_gen_andi_i64(rs2, rs2, MAKE_64BIT_MASK(31, 1)); + tcg_gen_xor_i64(cpu_fpr[a->rd], rs1, rs2); + + tcg_temp_free_i64(rs2); } + tcg_temp_free_i64(rs1); + mark_fs_dirty(ctx); return true; } @@ -378,11 +406,8 @@ static bool trans_fmv_w_x(DisasContext *ctx, arg_fmv_w_x *a) 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 + tcg_gen_extu_tl_i64(cpu_fpr[a->rd], t0); + gen_nanbox_s(cpu_fpr[a->rd], cpu_fpr[a->rd]); mark_fs_dirty(ctx); tcg_temp_free(t0); |