From: TANG Tiancheng <tangtiancheng.ttc@alibaba-inc.com>
Signed-off-by: TANG Tiancheng <tangtiancheng.ttc@alibaba-inc.com>
Reviewed-by: Liu Zhiwei <zhiwei_liu@linux.alibaba.com>
---
tcg/riscv/tcg-target-con-set.h | 1 +
tcg/riscv/tcg-target.c.inc | 86 +++++++++++++++++++++++++++++++++-
tcg/riscv/tcg-target.h | 8 ++--
3 files changed, 90 insertions(+), 5 deletions(-)
diff --git a/tcg/riscv/tcg-target-con-set.h b/tcg/riscv/tcg-target-con-set.h
index cc06102ccf..53649f750c 100644
--- a/tcg/riscv/tcg-target-con-set.h
+++ b/tcg/riscv/tcg-target-con-set.h
@@ -25,5 +25,6 @@ C_O0_I2(v, r)
C_O1_I1(v, r)
C_O1_I1(v, v)
C_O1_I2(v, v, v)
+C_O1_I2(v, v, r)
C_O1_I2(v, v, vL)
C_O1_I4(v, v, vL, vK, vK)
diff --git a/tcg/riscv/tcg-target.c.inc b/tcg/riscv/tcg-target.c.inc
index 2dc6befe09..c09055d514 100644
--- a/tcg/riscv/tcg-target.c.inc
+++ b/tcg/riscv/tcg-target.c.inc
@@ -316,10 +316,13 @@ typedef enum {
OPC_VMSGT_VX = 0x7c000057 | V_OPIVX,
OPC_VSLL_VV = 0x94000057 | V_OPIVV,
+ OPC_VSLL_VI = 0x94000057 | V_OPIVI,
OPC_VSLL_VX = 0x94000057 | V_OPIVX,
OPC_VSRL_VV = 0xa0000057 | V_OPIVV,
+ OPC_VSRL_VI = 0xa0000057 | V_OPIVI,
OPC_VSRL_VX = 0xa0000057 | V_OPIVX,
OPC_VSRA_VV = 0xa4000057 | V_OPIVV,
+ OPC_VSRA_VI = 0xa4000057 | V_OPIVI,
OPC_VSRA_VX = 0xa4000057 | V_OPIVX,
OPC_VMV_V_V = 0x5e000057 | V_OPIVV,
@@ -2494,6 +2497,33 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
riscv_set_vec_config_vl_vece(s, type, vece);
tcg_out_opc_vv(s, OPC_VSRA_VV, a0, a1, a2, true);
break;
+ case INDEX_op_shli_vec:
+ riscv_set_vec_config_vl_vece(s, type, vece);
+ if (a2 > 31) {
+ tcg_out_opc_imm(s, OPC_ADDI, TCG_REG_TMP0, TCG_REG_ZERO, a2);
+ tcg_out_opc_vx(s, OPC_VSLL_VX, a0, a1, TCG_REG_TMP0, true);
+ } else {
+ tcg_out_opc_vi(s, OPC_VSLL_VI, a0, a1, a2, true);
+ }
+ break;
+ case INDEX_op_shri_vec:
+ riscv_set_vec_config_vl_vece(s, type, vece);
+ if (a2 > 31) {
+ tcg_out_opc_imm(s, OPC_ADDI, TCG_REG_TMP0, TCG_REG_ZERO, a2);
+ tcg_out_opc_vx(s, OPC_VSRL_VX, a0, a1, TCG_REG_TMP0, true);
+ } else {
+ tcg_out_opc_vi(s, OPC_VSRL_VI, a0, a1, a2, true);
+ }
+ break;
+ case INDEX_op_sari_vec:
+ riscv_set_vec_config_vl_vece(s, type, vece);
+ if (a2 > 31) {
+ tcg_out_opc_imm(s, OPC_ADDI, TCG_REG_TMP0, TCG_REG_ZERO, a2);
+ tcg_out_opc_vx(s, OPC_VSRA_VX, a0, a1, TCG_REG_TMP0, true);
+ } else {
+ tcg_out_opc_vi(s, OPC_VSRA_VI, a0, a1, a2, true);
+ }
+ break;
case INDEX_op_cmpsel_vec:
TCGArg a3, a4;
int c3, c4;
@@ -2550,7 +2580,8 @@ void tcg_expand_vec_op(TCGOpcode opc, TCGType type, unsigned vece,
TCGArg a0, ...)
{
va_list va;
- TCGv_vec v0, v1;
+ TCGv_vec v0, v1, v2, t1;
+ TCGv_i32 t2;
TCGArg a2, a3;
va_start(va, a0);
@@ -2566,6 +2597,45 @@ void tcg_expand_vec_op(TCGOpcode opc, TCGType type, unsigned vece,
tcgv_i64_arg(tcg_constant_i64(-1)),
tcgv_i64_arg(tcg_constant_i64(0)), a3);
break;
+ case INDEX_op_rotli_vec:
+ t1 = tcg_temp_new_vec(type);
+ tcg_gen_shli_vec(vece, t1, v1, a2);
+ tcg_gen_shri_vec(vece, v0, v1, (8 << vece) - a2);
+ tcg_gen_or_vec(vece, v0, v0, t1);
+ tcg_temp_free_vec(t1);
+ break;
+ case INDEX_op_rotls_vec:
+ t1 = tcg_temp_new_vec(type);
+ t2 = tcg_temp_new_i32();
+ tcg_gen_neg_i32(t2, temp_tcgv_i32(arg_temp(a2)));
+ tcg_gen_shrs_vec(vece, v0, v1, t2);
+ tcg_gen_shls_vec(vece, t1, v1, temp_tcgv_i32(arg_temp(a2)));
+ tcg_gen_or_vec(vece, v0, v0, t1);
+ tcg_temp_free_vec(t1);
+ tcg_temp_free_i32(t2);
+ break;
+ case INDEX_op_rotlv_vec:
+ v2 = temp_tcgv_vec(arg_temp(a2));
+ t1 = tcg_temp_new_vec(type);
+ tcg_gen_neg_vec(vece, t1, v2);
+ vec_gen_3(INDEX_op_shrv_vec, type, vece, tcgv_vec_arg(t1),
+ tcgv_vec_arg(v1), tcgv_vec_arg(t1));
+ vec_gen_3(INDEX_op_shlv_vec, type, vece, tcgv_vec_arg(v0),
+ tcgv_vec_arg(v1), tcgv_vec_arg(v2));
+ tcg_gen_or_vec(vece, v0, v0, t1);
+ tcg_temp_free_vec(t1);
+ break;
+ case INDEX_op_rotrv_vec:
+ v2 = temp_tcgv_vec(arg_temp(a2));
+ t1 = tcg_temp_new_vec(type);
+ tcg_gen_neg_vec(vece, t1, v2);
+ vec_gen_3(INDEX_op_shlv_vec, type, vece, tcgv_vec_arg(t1),
+ tcgv_vec_arg(v1), tcgv_vec_arg(t1));
+ vec_gen_3(INDEX_op_shrv_vec, type, vece, tcgv_vec_arg(v0),
+ tcgv_vec_arg(v1), tcgv_vec_arg(v2));
+ tcg_gen_or_vec(vece, v0, v0, t1);
+ tcg_temp_free_vec(t1);
+ break;
default:
g_assert_not_reached();
}
@@ -2597,8 +2667,15 @@ int tcg_can_emit_vec_op(TCGOpcode opc, TCGType type, unsigned vece)
case INDEX_op_shlv_vec:
case INDEX_op_shrv_vec:
case INDEX_op_sarv_vec:
+ case INDEX_op_shri_vec:
+ case INDEX_op_shli_vec:
+ case INDEX_op_sari_vec:
case INDEX_op_cmpsel_vec:
return 1;
+ case INDEX_op_rotls_vec:
+ case INDEX_op_rotlv_vec:
+ case INDEX_op_rotrv_vec:
+ case INDEX_op_rotli_vec:
case INDEX_op_cmp_vec:
return -1;
default:
@@ -2753,6 +2830,10 @@ static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode op)
return C_O1_I1(v, r);
case INDEX_op_neg_vec:
case INDEX_op_not_vec:
+ case INDEX_op_rotli_vec:
+ case INDEX_op_shli_vec:
+ case INDEX_op_shri_vec:
+ case INDEX_op_sari_vec:
return C_O1_I1(v, v);
case INDEX_op_add_vec:
case INDEX_op_sub_vec:
@@ -2771,10 +2852,13 @@ static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode op)
case INDEX_op_shlv_vec:
case INDEX_op_shrv_vec:
case INDEX_op_sarv_vec:
+ case INDEX_op_rotlv_vec:
+ case INDEX_op_rotrv_vec:
return C_O1_I2(v, v, v);
case INDEX_op_shls_vec:
case INDEX_op_shrs_vec:
case INDEX_op_sars_vec:
+ case INDEX_op_rotls_vec:
return C_O1_I2(v, v, r);
case INDEX_op_cmp_vec:
return C_O1_I2(v, v, vL);
diff --git a/tcg/riscv/tcg-target.h b/tcg/riscv/tcg-target.h
index 3bd8b811ef..082942d858 100644
--- a/tcg/riscv/tcg-target.h
+++ b/tcg/riscv/tcg-target.h
@@ -154,10 +154,10 @@ typedef enum {
#define TCG_TARGET_HAS_not_vec 1
#define TCG_TARGET_HAS_neg_vec 1
#define TCG_TARGET_HAS_abs_vec 0
-#define TCG_TARGET_HAS_roti_vec 0
-#define TCG_TARGET_HAS_rots_vec 0
-#define TCG_TARGET_HAS_rotv_vec 0
-#define TCG_TARGET_HAS_shi_vec 0
+#define TCG_TARGET_HAS_roti_vec -1
+#define TCG_TARGET_HAS_rots_vec -1
+#define TCG_TARGET_HAS_rotv_vec -1
+#define TCG_TARGET_HAS_shi_vec 1
#define TCG_TARGET_HAS_shs_vec 1
#define TCG_TARGET_HAS_shv_vec 1
#define TCG_TARGET_HAS_mul_vec 1
--
2.43.0