diff mbox series

[v6,12/14] tcg/riscv: Implement vector shi/s/v ops

Message ID 20241016193140.2206352-13-richard.henderson@linaro.org
State Superseded
Headers show
Series tcg/riscv: Add support for vector | expand

Commit Message

Richard Henderson Oct. 16, 2024, 7:31 p.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: <20241007025700.47259-11-zhiwei_liu@linux.alibaba.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 tcg/riscv/tcg-target-con-set.h |  1 +
 tcg/riscv/tcg-target.h         |  6 +--
 tcg/riscv/tcg-target.c.inc     | 76 ++++++++++++++++++++++++++++++++++
 3 files changed, 80 insertions(+), 3 deletions(-)
diff mbox series

Patch

diff --git a/tcg/riscv/tcg-target-con-set.h b/tcg/riscv/tcg-target-con-set.h
index d8ce5414f5..3c4ef44eb0 100644
--- a/tcg/riscv/tcg-target-con-set.h
+++ b/tcg/riscv/tcg-target-con-set.h
@@ -24,6 +24,7 @@  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, r)
 C_O1_I2(v, v, v)
 C_O1_I2(v, vK, v)
 C_O1_I2(v, v, vK)
diff --git a/tcg/riscv/tcg-target.h b/tcg/riscv/tcg-target.h
index 7005099810..76d30e789b 100644
--- a/tcg/riscv/tcg-target.h
+++ b/tcg/riscv/tcg-target.h
@@ -157,9 +157,9 @@  typedef enum {
 #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_shs_vec          0
-#define TCG_TARGET_HAS_shv_vec          0
+#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
 #define TCG_TARGET_HAS_sat_vec          1
 #define TCG_TARGET_HAS_minmax_vec       1
diff --git a/tcg/riscv/tcg-target.c.inc b/tcg/riscv/tcg-target.c.inc
index 35b244b7a2..2c78ea6507 100644
--- a/tcg/riscv/tcg-target.c.inc
+++ b/tcg/riscv/tcg-target.c.inc
@@ -326,6 +326,16 @@  typedef enum {
     OPC_VMSGT_VI = 0x7c000057 | V_OPIVI,
     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,
     OPC_VMV_V_I = 0x5e000057 | V_OPIVI,
     OPC_VMV_V_X = 0x5e000057 | V_OPIVX,
@@ -1551,6 +1561,17 @@  static void tcg_out_cmpsel(TCGContext *s, TCGType type, unsigned vece,
     }
 }
 
+static void tcg_out_vshifti(TCGContext *s, RISCVInsn opc_vi, RISCVInsn opc_vx,
+                             TCGReg dst, TCGReg src, unsigned imm)
+{
+    if (imm < 32) {
+        tcg_out_opc_vi(s, opc_vi, dst, src, imm);
+    } else {
+        tcg_out_movi(s, TCG_TYPE_I32, TCG_REG_TMP0, imm);
+        tcg_out_opc_vx(s, opc_vx, dst, src, TCG_REG_TMP0);
+    }
+}
+
 static void init_setting_vtype(TCGContext *s)
 {
     s->riscv_cur_type = TCG_TYPE_COUNT;
@@ -2431,6 +2452,42 @@  static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
         set_vtype_len_sew(s, type, vece);
         tcg_out_opc_vv_vi(s, OPC_VMINU_VV, OPC_VMINU_VI, a0, a1, a2, c2);
         break;
+    case INDEX_op_shls_vec:
+        set_vtype_len_sew(s, type, vece);
+        tcg_out_opc_vx(s, OPC_VSLL_VX, a0, a1, a2);
+        break;
+    case INDEX_op_shrs_vec:
+        set_vtype_len_sew(s, type, vece);
+        tcg_out_opc_vx(s, OPC_VSRL_VX, a0, a1, a2);
+        break;
+    case INDEX_op_sars_vec:
+        set_vtype_len_sew(s, type, vece);
+        tcg_out_opc_vx(s, OPC_VSRA_VX, a0, a1, a2);
+        break;
+    case INDEX_op_shlv_vec:
+        set_vtype_len_sew(s, type, vece);
+        tcg_out_opc_vv(s, OPC_VSLL_VV, a0, a1, a2);
+        break;
+    case INDEX_op_shrv_vec:
+        set_vtype_len_sew(s, type, vece);
+        tcg_out_opc_vv(s, OPC_VSRL_VV, a0, a1, a2);
+        break;
+    case INDEX_op_sarv_vec:
+        set_vtype_len_sew(s, type, vece);
+        tcg_out_opc_vv(s, OPC_VSRA_VV, a0, a1, a2);
+        break;
+    case INDEX_op_shli_vec:
+        set_vtype_len_sew(s, type, vece);
+        tcg_out_vshifti(s, OPC_VSLL_VI, OPC_VSLL_VX, a0, a1, a2);
+        break;
+    case INDEX_op_shri_vec:
+        set_vtype_len_sew(s, type, vece);
+        tcg_out_vshifti(s, OPC_VSRL_VI, OPC_VSRL_VX, a0, a1, a2);
+        break;
+    case INDEX_op_sari_vec:
+        set_vtype_len_sew(s, type, vece);
+        tcg_out_vshifti(s, OPC_VSRA_VI, OPC_VSRA_VX, a0, a1, a2);
+        break;
     case INDEX_op_cmp_vec:
         tcg_out_cmpsel(s, type, vece, args[3], a0, a1, a2, c2,
                        -1, true, 0, true);
@@ -2471,6 +2528,15 @@  int tcg_can_emit_vec_op(TCGOpcode opc, TCGType type, unsigned vece)
     case INDEX_op_smin_vec:
     case INDEX_op_umax_vec:
     case INDEX_op_umin_vec:
+    case INDEX_op_shls_vec:
+    case INDEX_op_shrs_vec:
+    case INDEX_op_sars_vec:
+    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_cmp_vec:
     case INDEX_op_cmpsel_vec:
         return 1;
@@ -2626,6 +2692,9 @@  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_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_and_vec:
@@ -2643,7 +2712,14 @@  static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode op)
     case INDEX_op_sub_vec:
         return C_O1_I2(v, vK, v);
     case INDEX_op_mul_vec:
+    case INDEX_op_shlv_vec:
+    case INDEX_op_shrv_vec:
+    case INDEX_op_sarv_vec:
         return C_O1_I2(v, v, v);
+    case INDEX_op_shls_vec:
+    case INDEX_op_shrs_vec:
+    case INDEX_op_sars_vec:
+        return C_O1_I2(v, v, r);
     case INDEX_op_cmp_vec:
         return C_O1_I2(v, v, vL);
     case INDEX_op_cmpsel_vec: