[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[PATCH v9 17/76] target/riscv: rvv:1.0: add translation-time nan-box hel
From: |
frank . chang |
Subject: |
[PATCH v9 17/76] target/riscv: rvv:1.0: add translation-time nan-box helper function |
Date: |
Fri, 29 Oct 2021 16:58:22 +0800 |
From: Frank Chang <frank.chang@sifive.com>
* Add fp16 nan-box check generator function, if a 16-bit input is not
properly nanboxed, then the input is replaced with the default qnan.
* Add do_nanbox() helper function to utilize gen_check_nanbox_X() to
generate the NaN-boxed floating-point values based on SEW setting.
* Apply nanbox helper in opfvf_trans().
Signed-off-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
---
target/riscv/insn_trans/trans_rvv.c.inc | 35 ++++++++++++++++++++++++-
1 file changed, 34 insertions(+), 1 deletion(-)
diff --git a/target/riscv/insn_trans/trans_rvv.c.inc
b/target/riscv/insn_trans/trans_rvv.c.inc
index 66273afb537..f9ace6ae412 100644
--- a/target/riscv/insn_trans/trans_rvv.c.inc
+++ b/target/riscv/insn_trans/trans_rvv.c.inc
@@ -2098,6 +2098,33 @@ GEN_OPIVI_NARROW_TRANS(vnclip_vi, IMM_ZX, vnclip_vx)
/*
*** Vector Float Point Arithmetic Instructions
*/
+
+/*
+ * As RVF-only cpus always have values NaN-boxed to 64-bits,
+ * RVF and RVD can be treated equally.
+ * We don't have to deal with the cases of: SEW > FLEN.
+ *
+ * If SEW < FLEN, check whether input fp register is a valid
+ * NaN-boxed value, in which case the least-significant SEW bits
+ * of the f regsiter are used, else the canonical NaN value is used.
+ */
+static void do_nanbox(DisasContext *s, TCGv_i64 out, TCGv_i64 in)
+{
+ switch (s->sew) {
+ case 1:
+ gen_check_nanbox_h(out, in);
+ break;
+ case 2:
+ gen_check_nanbox_s(out, in);
+ break;
+ case 3:
+ tcg_gen_mov_i64(out, in);
+ break;
+ default:
+ g_assert_not_reached();
+ }
+}
+
/* Vector Single-Width Floating-Point Add/Subtract Instructions */
/*
@@ -2151,6 +2178,7 @@ static bool opfvf_trans(uint32_t vd, uint32_t rs1,
uint32_t vs2,
{
TCGv_ptr dest, src2, mask;
TCGv_i32 desc;
+ TCGv_i64 t1;
TCGLabel *over = gen_new_label();
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
@@ -2164,11 +2192,16 @@ static bool opfvf_trans(uint32_t vd, uint32_t rs1,
uint32_t vs2,
tcg_gen_addi_ptr(src2, cpu_env, vreg_ofs(s, vs2));
tcg_gen_addi_ptr(mask, cpu_env, vreg_ofs(s, 0));
- fn(dest, mask, cpu_fpr[rs1], src2, cpu_env, desc);
+ /* NaN-box f[rs1] */
+ t1 = tcg_temp_new_i64();
+ do_nanbox(s, t1, cpu_fpr[rs1]);
+
+ fn(dest, mask, t1, src2, cpu_env, desc);
tcg_temp_free_ptr(dest);
tcg_temp_free_ptr(mask);
tcg_temp_free_ptr(src2);
+ tcg_temp_free_i64(t1);
mark_vs_dirty(s);
gen_set_label(over);
return true;
--
2.25.1
- [PATCH v9 06/76] target/riscv: rvv-1.0: introduce writable misa.v field, (continued)
- [PATCH v9 06/76] target/riscv: rvv-1.0: introduce writable misa.v field, frank . chang, 2021/10/29
- [PATCH v9 08/76] target/riscv: rvv-1.0: remove rvv related codes from fcsr registers, frank . chang, 2021/10/29
- [PATCH v9 07/76] target/riscv: rvv-1.0: add translation-time vector context status, frank . chang, 2021/10/29
- [PATCH v9 11/76] target/riscv: rvv-1.0: check MSTATUS_VS when accessing vector csr registers, frank . chang, 2021/10/29
- [PATCH v9 09/76] target/riscv: rvv-1.0: add vcsr register, frank . chang, 2021/10/29
- [PATCH v9 10/76] target/riscv: rvv-1.0: add vlenb register, frank . chang, 2021/10/29
- [PATCH v9 12/76] target/riscv: rvv-1.0: remove MLEN calculations, frank . chang, 2021/10/29
- [PATCH v9 13/76] target/riscv: rvv-1.0: add fractional LMUL, frank . chang, 2021/10/29
- [PATCH v9 14/76] target/riscv: rvv-1.0: add VMA and VTA, frank . chang, 2021/10/29
- [PATCH v9 15/76] target/riscv: rvv-1.0: update check functions, frank . chang, 2021/10/29
- [PATCH v9 17/76] target/riscv: rvv:1.0: add translation-time nan-box helper function,
frank . chang <=
- [PATCH v9 16/76] target/riscv: introduce more imm value modes in translator functions, frank . chang, 2021/10/29
- [PATCH v9 18/76] target/riscv: rvv-1.0: remove amo operations instructions, frank . chang, 2021/10/29
- [PATCH v9 19/76] target/riscv: rvv-1.0: configure instructions, frank . chang, 2021/10/29
- [PATCH v9 20/76] target/riscv: rvv-1.0: stride load and store instructions, frank . chang, 2021/10/29
- [PATCH v9 21/76] target/riscv: rvv-1.0: index load and store instructions, frank . chang, 2021/10/29
- [PATCH v9 23/76] target/riscv: rvv-1.0: fault-only-first unit stride load, frank . chang, 2021/10/29
- [PATCH v9 24/76] target/riscv: rvv-1.0: load/store whole register instructions, frank . chang, 2021/10/29
- [PATCH v9 22/76] target/riscv: rvv-1.0: fix address index overflow bug of indexed load/store insns, frank . chang, 2021/10/29
- [PATCH v9 27/76] target/riscv: rvv-1.0: floating-point square-root instruction, frank . chang, 2021/10/29
- [PATCH v9 29/76] target/riscv: rvv-1.0: count population in mask instruction, frank . chang, 2021/10/29