Commit 6d09dfabf5 for qemu.org
commit 6d09dfabf5174a63db73b1afdb80e0e32f453aef
Author: Philippe Mathieu-Daudé <philmd@oss.qualcomm.com>
Date: Wed Oct 28 11:44:42 2026 +0100
tcg/riscv64: Extract elements for vector arithmetic immediates
The .vi emitters pass the whole replicated constant (e.g.
0x0505050505050505) instead of one element. The encoding is still
correct, because encode_vi() keeps the low 5 bits, but it trips the
range assert added in 006352d69f14 on common vectorized guest code
in debug builds. Extract the VECE element with vec_imm(), so the
assert keeps checking that the emitter agrees with the constraint
matcher.
Add vec_imm() to extract the VECE element, and use it.
Fixes: 006352d69f14 ("tcg/riscv64: Assert immediate in range ...")
Signed-off-by: Philippe Mathieu-Daudé <philmd@oss.qualcomm.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-ID: <20261028143330.6518-4-philmd@oss.qualcomm.com>
diff --git a/tcg/riscv64/tcg-target.c.inc b/tcg/riscv64/tcg-target.c.inc
index 002b3b4b78..55685db44f 100644
--- a/tcg/riscv64/tcg-target.c.inc
+++ b/tcg/riscv64/tcg-target.c.inc
@@ -736,6 +736,12 @@ static void tcg_out_opc_vi_u(TCGContext *s, RISCVInsn opc,
tcg_out32(s, encode_vi_u(opc, vd, imm, vs2, true));
}
+/* Constants are replicated by VECE; extract one element for .vi forms. */
+static int64_t vec_imm(TCGArg arg, unsigned vece)
+{
+ return sextract64(arg, 0, 8 << vece);
+}
+
static void tcg_out_opc_vv_vi(TCGContext *s, RISCVInsn o_vv, RISCVInsn o_vi,
TCGReg vd, TCGReg vs2, TCGArg vi1, int c_vi1)
{
@@ -2805,12 +2811,13 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
break;
case INDEX_op_add_vec:
set_vtype_len_sew(s, type, vece);
- tcg_out_opc_vv_vi(s, OPC_VADD_VV, OPC_VADD_VI, a0, a1, a2, c2);
+ tcg_out_opc_vv_vi(s, OPC_VADD_VV, OPC_VADD_VI, a0, a1,
+ c2 ? vec_imm(a2, vece) : a2, c2);
break;
case INDEX_op_sub_vec:
set_vtype_len_sew(s, type, vece);
if (const_args[1]) {
- tcg_out_opc_vi(s, OPC_VRSUB_VI, a0, a2, a1);
+ tcg_out_opc_vi(s, OPC_VRSUB_VI, a0, a2, vec_imm(a1, vece));
} else {
tcg_out_opc_vv(s, OPC_VSUB_VV, a0, a1, a2);
}
@@ -2841,19 +2848,23 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
break;
case INDEX_op_ssadd_vec:
set_vtype_len_sew(s, type, vece);
- tcg_out_opc_vv_vi(s, OPC_VSADD_VV, OPC_VSADD_VI, a0, a1, a2, c2);
+ tcg_out_opc_vv_vi(s, OPC_VSADD_VV, OPC_VSADD_VI, a0, a1,
+ c2 ? vec_imm(a2, vece) : a2, c2);
break;
case INDEX_op_sssub_vec:
set_vtype_len_sew(s, type, vece);
- tcg_out_opc_vv_vi(s, OPC_VSSUB_VV, OPC_VSSUB_VI, a0, a1, a2, c2);
+ tcg_out_opc_vv_vi(s, OPC_VSSUB_VV, OPC_VSSUB_VI, a0, a1,
+ c2 ? vec_imm(a2, vece) : a2, c2);
break;
case INDEX_op_usadd_vec:
set_vtype_len_sew(s, type, vece);
- tcg_out_opc_vv_vi(s, OPC_VSADDU_VV, OPC_VSADDU_VI, a0, a1, a2, c2);
+ tcg_out_opc_vv_vi(s, OPC_VSADDU_VV, OPC_VSADDU_VI, a0, a1,
+ c2 ? vec_imm(a2, vece) : a2, c2);
break;
case INDEX_op_ussub_vec:
set_vtype_len_sew(s, type, vece);
- tcg_out_opc_vv_vi(s, OPC_VSSUBU_VV, OPC_VSSUBU_VI, a0, a1, a2, c2);
+ tcg_out_opc_vv_vi(s, OPC_VSSUBU_VV, OPC_VSSUBU_VI, a0, a1,
+ c2 ? vec_imm(a2, vece) : a2, c2);
break;
case INDEX_op_smax_vec:
set_vtype_len_sew(s, type, vece);