diff mbox series

[v7,06/14] tcg/riscv: Add support for basic vector opcodes

Message ID 20241022001134.828724-7-richard.henderson@linaro.org
State Superseded
Headers show
Series tcg/riscv: Add support for vector | expand

Commit Message

Richard Henderson Oct. 22, 2024, 12:11 a.m. UTC
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>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-ID: <20241007025700.47259-6-zhiwei_liu@linux.alibaba.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 tcg/riscv/tcg-target-con-set.h |  3 ++
 tcg/riscv/tcg-target-con-str.h |  1 +
 tcg/riscv/tcg-target.h         |  2 +-
 tcg/riscv/tcg-target.c.inc     | 80 ++++++++++++++++++++++++++++++++++
 4 files changed, 85 insertions(+), 1 deletion(-)
diff mbox series

Patch

diff --git a/tcg/riscv/tcg-target-con-set.h b/tcg/riscv/tcg-target-con-set.h
index d73a62b0f2..6513cebc4c 100644
--- a/tcg/riscv/tcg-target-con-set.h
+++ b/tcg/riscv/tcg-target-con-set.h
@@ -23,3 +23,6 @@  C_O1_I4(r, r, rI, rM, rM)
 C_O2_I4(r, r, rZ, rZ, rM, rM)
 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, vK)
diff --git a/tcg/riscv/tcg-target-con-str.h b/tcg/riscv/tcg-target-con-str.h
index b2b3211bcb..0aaad7b753 100644
--- a/tcg/riscv/tcg-target-con-str.h
+++ b/tcg/riscv/tcg-target-con-str.h
@@ -17,6 +17,7 @@  REGS('v', ALL_VECTOR_REGS)
  */
 CONST('I', TCG_CT_CONST_S12)
 CONST('J', TCG_CT_CONST_J12)
+CONST('K', TCG_CT_CONST_S5)
 CONST('N', TCG_CT_CONST_N12)
 CONST('M', TCG_CT_CONST_M12)
 CONST('Z', TCG_CT_CONST_ZERO)
diff --git a/tcg/riscv/tcg-target.h b/tcg/riscv/tcg-target.h
index 12a7a37aaa..acb8dfdf16 100644
--- a/tcg/riscv/tcg-target.h
+++ b/tcg/riscv/tcg-target.h
@@ -151,7 +151,7 @@  typedef enum {
 #define TCG_TARGET_HAS_nand_vec         0
 #define TCG_TARGET_HAS_nor_vec          0
 #define TCG_TARGET_HAS_eqv_vec          0
-#define TCG_TARGET_HAS_not_vec          0
+#define TCG_TARGET_HAS_not_vec          1
 #define TCG_TARGET_HAS_neg_vec          0
 #define TCG_TARGET_HAS_abs_vec          0
 #define TCG_TARGET_HAS_roti_vec         0
diff --git a/tcg/riscv/tcg-target.c.inc b/tcg/riscv/tcg-target.c.inc
index 17fcc21b0e..c8540f9a75 100644
--- a/tcg/riscv/tcg-target.c.inc
+++ b/tcg/riscv/tcg-target.c.inc
@@ -111,6 +111,7 @@  static TCGReg tcg_target_call_oarg_reg(TCGCallReturnKind kind, int slot)
 #define TCG_CT_CONST_N12   0x400
 #define TCG_CT_CONST_M12   0x800
 #define TCG_CT_CONST_J12  0x1000
+#define TCG_CT_CONST_S5   0x2000
 
 #define ALL_GENERAL_REGS   MAKE_64BIT_MASK(0, 32)
 #define ALL_VECTOR_REGS    MAKE_64BIT_MASK(32, 32)
@@ -129,6 +130,10 @@  static bool tcg_target_const_match(int64_t val, int ct,
     if ((ct & TCG_CT_CONST_ZERO) && val == 0) {
         return 1;
     }
+    if (type >= TCG_TYPE_V64) {
+        /* Val is replicated by VECE; extract the highest element. */
+        val >>= (-8 << vece) & 63;
+    }
     /*
      * Sign extended from 12 bits: [-0x800, 0x7ff].
      * Used for most arithmetic, as this is the isa field.
@@ -158,6 +163,13 @@  static bool tcg_target_const_match(int64_t val, int ct,
     if ((ct & TCG_CT_CONST_J12) && ~val >= -0x800 && ~val <= 0x7ff) {
         return 1;
     }
+    /*
+     * Sign extended from 5 bits: [-0x10, 0x0f].
+     * Used for vector-immediate.
+     */
+    if ((ct & TCG_CT_CONST_S5) && val >= -0x10 && val <= 0x0f) {
+        return 1;
+    }
     return 0;
 }
 
@@ -310,6 +322,16 @@  typedef enum {
     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_VADD_VV = 0x57 | V_OPIVV,
+    OPC_VADD_VI = 0x57 | V_OPIVI,
+    OPC_VSUB_VV = 0x8000057 | V_OPIVV,
+    OPC_VAND_VV = 0x24000057 | V_OPIVV,
+    OPC_VAND_VI = 0x24000057 | V_OPIVI,
+    OPC_VOR_VV = 0x28000057 | V_OPIVV,
+    OPC_VOR_VI = 0x28000057 | V_OPIVI,
+    OPC_VXOR_VV = 0x2c000057 | V_OPIVV,
+    OPC_VXOR_VI = 0x2c000057 | V_OPIVI,
+
     OPC_VMV_V_V = 0x5e000057 | V_OPIVV,
     OPC_VMV_V_I = 0x5e000057 | V_OPIVI,
     OPC_VMV_V_X = 0x5e000057 | V_OPIVX,
@@ -568,6 +590,12 @@  static bool patch_reloc(tcg_insn_unit *code_ptr, int type,
  * With RVV 1.0, vs2 is the first operand, while rs1/imm is the
  * second operand.
  */
+static void tcg_out_opc_vv(TCGContext *s, RISCVInsn opc,
+                           TCGReg vd, TCGReg vs2, TCGReg vs1)
+{
+    tcg_out32(s, encode_v(opc, vd, vs1, vs2, true));
+}
+
 static void tcg_out_opc_vx(TCGContext *s, RISCVInsn opc,
                            TCGReg vd, TCGReg vs2, TCGReg rs1)
 {
@@ -580,6 +608,16 @@  static void tcg_out_opc_vi(TCGContext *s, RISCVInsn opc,
     tcg_out32(s, encode_vi(opc, vd, imm, vs2, true));
 }
 
+static void tcg_out_opc_vv_vi(TCGContext *s, RISCVInsn o_vv, RISCVInsn o_vi,
+                              TCGReg vd, TCGReg vs2, TCGArg vi1, int c_vi1)
+{
+    if (c_vi1) {
+        tcg_out_opc_vi(s, o_vi, vd, vs2, vi1);
+    } else {
+        tcg_out_opc_vv(s, o_vv, vd, vs2, vi1);
+    }
+}
+
 typedef struct VsetCache {
     uint32_t movi_insn;
     uint32_t vset_insn;
@@ -2165,10 +2203,12 @@  static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
 {
     TCGType type = vecl + TCG_TYPE_V64;
     TCGArg a0, a1, a2;
+    int c2;
 
     a0 = args[0];
     a1 = args[1];
     a2 = args[2];
+    c2 = const_args[2];
 
     switch (opc) {
     case INDEX_op_dupm_vec:
@@ -2180,6 +2220,30 @@  static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
     case INDEX_op_st_vec:
         tcg_out_st(s, type, a0, a1, a2);
         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);
+        break;
+    case INDEX_op_sub_vec:
+        set_vtype_len_sew(s, type, vece);
+        tcg_out_opc_vv(s, OPC_VSUB_VV, a0, a1, a2);
+        break;
+    case INDEX_op_and_vec:
+        set_vtype_len(s, type);
+        tcg_out_opc_vv_vi(s, OPC_VAND_VV, OPC_VAND_VI, a0, a1, a2, c2);
+        break;
+    case INDEX_op_or_vec:
+        set_vtype_len(s, type);
+        tcg_out_opc_vv_vi(s, OPC_VOR_VV, OPC_VOR_VI, a0, a1, a2, c2);
+        break;
+    case INDEX_op_xor_vec:
+        set_vtype_len(s, type);
+        tcg_out_opc_vv_vi(s, OPC_VXOR_VV, OPC_VXOR_VI, a0, a1, a2, c2);
+        break;
+    case INDEX_op_not_vec:
+        set_vtype_len(s, type);
+        tcg_out_opc_vi(s, OPC_VXOR_VI, a0, a1, -1);
+        break;
     case INDEX_op_mov_vec: /* Always emitted via tcg_out_mov.  */
     case INDEX_op_dup_vec: /* Always emitted via tcg_out_dup_vec.  */
     default:
@@ -2196,6 +2260,13 @@  void tcg_expand_vec_op(TCGOpcode opc, TCGType type, unsigned vece,
 int tcg_can_emit_vec_op(TCGOpcode opc, TCGType type, unsigned vece)
 {
     switch (opc) {
+    case INDEX_op_add_vec:
+    case INDEX_op_sub_vec:
+    case INDEX_op_and_vec:
+    case INDEX_op_or_vec:
+    case INDEX_op_xor_vec:
+    case INDEX_op_not_vec:
+        return 1;
     default:
         return 0;
     }
@@ -2346,6 +2417,15 @@  static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode op)
     case INDEX_op_dupm_vec:
     case INDEX_op_ld_vec:
         return C_O1_I1(v, r);
+    case INDEX_op_not_vec:
+        return C_O1_I1(v, v);
+    case INDEX_op_add_vec:
+    case INDEX_op_and_vec:
+    case INDEX_op_or_vec:
+    case INDEX_op_xor_vec:
+        return C_O1_I2(v, v, vK);
+    case INDEX_op_sub_vec:
+        return C_O1_I2(v, v, v);
     default:
         g_assert_not_reached();
     }