[v2,06/14] tcg/riscv: Implement vector mov/dup{m/i}

Commit Message

LIU Zhiwei Aug. 30, 2024, 6:15 a.m. UTC

From: TANG Tiancheng <[e-mail]>

Signed-off-by: TANG Tiancheng <[e-mail]>
Reviewed-by: Liu Zhiwei <[e-mail]>
---
 tcg/riscv/tcg-target.c.inc | 54 ++++++++++++++++++++++++++++++++++++++
 1 file changed, 54 insertions(+)

Comments

Richard Henderson Sept. 2, 2024, 1:36 a.m. UTC | #1

On 8/30/24 16:15, LIU Zhiwei wrote:
> From: TANG Tiancheng<[e-mail]>
> 
> Signed-off-by: TANG Tiancheng<[e-mail]>
> Reviewed-by: Liu Zhiwei<[e-mail]>
> ---
>   tcg/riscv/tcg-target.c.inc | 54 ++++++++++++++++++++++++++++++++++++++
>   1 file changed, 54 insertions(+)

Reviewed-by: Richard Henderson <[e-mail]>


r~

Patch

diff --git a/tcg/riscv/tcg-target.c.inc b/tcg/riscv/tcg-target.c.inc
index 6f8814564a..b6b4bdc269 100644
--- a/tcg/riscv/tcg-target.c.inc
+++ b/tcg/riscv/tcg-target.c.inc
@@ -303,6 +303,12 @@  typedef enum {
     OPC_VS2R_V = 0x2000027 | V_UNIT_STRIDE_WHOLE_REG | V_NF(1),
     OPC_VS4R_V = 0x2000027 | V_UNIT_STRIDE_WHOLE_REG | V_NF(3),
     OPC_VS8R_V = 0x2000027 | V_UNIT_STRIDE_WHOLE_REG | V_NF(7),
+
+    OPC_VMV_V_V = 0x5e000057 | V_OPIVV,
+    OPC_VMV_V_I = 0x5e000057 | V_OPIVI,
+    OPC_VMV_V_X = 0x5e000057 | V_OPIVX,
+
+    OPC_VMVNR_V = 0x9e000057 | V_OPIVI,
 } RISCVInsn;
 
 /*
@@ -544,6 +550,7 @@  static bool patch_reloc(tcg_insn_unit *code_ptr, int type,
 static void tcg_out_opc_reg_vec(TCGContext *s, RISCVInsn opc,
                                 TCGReg d, TCGReg s1, TCGReg s2, bool vm)
 {
+    tcg_debug_assert(d >= TCG_REG_V0 && d >= TCG_REG_V0);
     tcg_out32(s, encode_r(opc, d, s1, s2) | (vm << 25));
 }
 
@@ -656,6 +663,21 @@  static bool tcg_out_mov(TCGContext *s, TCGType type, TCGReg ret, TCGReg arg)
     case TCG_TYPE_I64:
         tcg_out_opc_imm(s, OPC_ADDI, ret, arg, 0);
         break;
+    case TCG_TYPE_V64:
+    case TCG_TYPE_V128:
+    case TCG_TYPE_V256:
+        {
+            int nf = get_vec_type_bytes(type) / riscv_vlenb;
+
+            if (nf != 0) {
+                tcg_debug_assert(is_power_of_2(nf) && nf <= 8);
+                tcg_out_opc_vi(s, OPC_VMVNR_V, ret, arg, nf - 1, true);
+            } else {
+                riscv_set_vec_config_vl(s, type);
+                tcg_out_opc_vv(s, OPC_VMV_V_V, ret, TCG_REG_V0, arg, true);
+            }
+        }
+        break;
     default:
         g_assert_not_reached();
     }
@@ -1042,6 +1064,33 @@  static void tcg_out_addsub2(TCGContext *s,
     }
 }
 
+static bool tcg_out_dup_vec(TCGContext *s, TCGType type, unsigned vece,
+                                   TCGReg dst, TCGReg src)
+{
+    riscv_set_vec_config_vl_vece(s, type, vece);
+    tcg_out_opc_vx(s, OPC_VMV_V_X, dst, TCG_REG_V0, src, true);
+    return true;
+}
+
+static bool tcg_out_dupm_vec(TCGContext *s, TCGType type, unsigned vece,
+                                    TCGReg dst, TCGReg base, intptr_t offset)
+{
+    tcg_out_ld(s, TCG_TYPE_REG, TCG_REG_TMP0, base, offset);
+    return tcg_out_dup_vec(s, type, vece, dst, TCG_REG_TMP0);
+}
+
+static void tcg_out_dupi_vec(TCGContext *s, TCGType type, unsigned vece,
+                                    TCGReg dst, int64_t arg)
+{
+    if (arg < 16 && arg >= -16) {
+        riscv_set_vec_config_vl_vece(s, type, vece);
+        tcg_out_opc_vi(s, OPC_VMV_V_I, dst, TCG_REG_V0, arg, true);
+        return;
+    }
+    tcg_out_movi(s, TCG_TYPE_I64, TCG_REG_TMP0, arg);
+    tcg_out_dup_vec(s, type, vece, dst, TCG_REG_TMP0);
+}
+
 static const struct {
     RISCVInsn op;
     bool swap;
@@ -2170,6 +2219,9 @@  static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
     a2 = args[2];
 
     switch (opc) {
+    case INDEX_op_dupm_vec:
+        tcg_out_dupm_vec(s, type, vece, a0, a1, a2);
+        break;
     case INDEX_op_ld_vec:
         tcg_out_ld(s, type, a0, a1, a2);
         break;
@@ -2341,6 +2393,8 @@  static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode op)
 
     case INDEX_op_st_vec:
         return C_O0_I2(v, r);
+    case INDEX_op_dup_vec:
+    case INDEX_op_dupm_vec:
     case INDEX_op_ld_vec:
         return C_O1_I1(v, r);
     default: