[PULL 10/24] tcg/riscv: Implement vector sat/mul ops

Richard Henderson posted 24 patches 1 month ago
There is a newer version of this series
[PULL 10/24] tcg/riscv: Implement vector sat/mul ops
Posted by Richard Henderson 1 month ago
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: <20241007025700.47259-9-zhiwei_liu@linux.alibaba.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 tcg/riscv/tcg-target.h     |  4 ++--
 tcg/riscv/tcg-target.c.inc | 41 ++++++++++++++++++++++++++++++++++++++
 2 files changed, 43 insertions(+), 2 deletions(-)

diff --git a/tcg/riscv/tcg-target.h b/tcg/riscv/tcg-target.h
index ae10381e02..1d4d8878ce 100644
--- a/tcg/riscv/tcg-target.h
+++ b/tcg/riscv/tcg-target.h
@@ -160,8 +160,8 @@ typedef enum {
 #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_mul_vec          0
-#define TCG_TARGET_HAS_sat_vec          0
+#define TCG_TARGET_HAS_mul_vec          1
+#define TCG_TARGET_HAS_sat_vec          1
 #define TCG_TARGET_HAS_minmax_vec       0
 #define TCG_TARGET_HAS_bitsel_vec       0
 #define TCG_TARGET_HAS_cmpsel_vec       1
diff --git a/tcg/riscv/tcg-target.c.inc b/tcg/riscv/tcg-target.c.inc
index 1ce2f291d3..4758555565 100644
--- a/tcg/riscv/tcg-target.c.inc
+++ b/tcg/riscv/tcg-target.c.inc
@@ -284,6 +284,16 @@ typedef enum {
     OPC_VXOR_VV = 0x2c000057 | V_OPIVV,
     OPC_VXOR_VI = 0x2c000057 | V_OPIVI,
 
+    OPC_VMUL_VV = 0x94000057 | V_OPMVV,
+    OPC_VSADD_VV = 0x84000057 | V_OPIVV,
+    OPC_VSADD_VI = 0x84000057 | V_OPIVI,
+    OPC_VSSUB_VV = 0x8c000057 | V_OPIVV,
+    OPC_VSSUB_VI = 0x8c000057 | V_OPIVI,
+    OPC_VSADDU_VV = 0x80000057 | V_OPIVV,
+    OPC_VSADDU_VI = 0x80000057 | V_OPIVI,
+    OPC_VSSUBU_VV = 0x88000057 | V_OPIVV,
+    OPC_VSSUBU_VI = 0x88000057 | V_OPIVI,
+
     OPC_VMSEQ_VV = 0x60000057 | V_OPIVV,
     OPC_VMSEQ_VI = 0x60000057 | V_OPIVI,
     OPC_VMSEQ_VX = 0x60000057 | V_OPIVX,
@@ -2376,6 +2386,26 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
         set_vtype_len_sew(s, type, vece);
         tcg_out_opc_vi(s, OPC_VRSUB_VI, a0, a1, 0);
         break;
+    case INDEX_op_mul_vec:
+        set_vtype_len_sew(s, type, vece);
+        tcg_out_opc_vv(s, OPC_VMUL_VV, a0, a1, a2);
+        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);
+        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);
+        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);
+        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);
+        break;
     case INDEX_op_cmp_vec:
         tcg_out_cmpsel(s, type, vece, args[3], a0, a1, a2, c2,
                        -1, true, 0, true);
@@ -2407,6 +2437,11 @@ int tcg_can_emit_vec_op(TCGOpcode opc, TCGType type, unsigned vece)
     case INDEX_op_xor_vec:
     case INDEX_op_not_vec:
     case INDEX_op_neg_vec:
+    case INDEX_op_mul_vec:
+    case INDEX_op_ssadd_vec:
+    case INDEX_op_sssub_vec:
+    case INDEX_op_usadd_vec:
+    case INDEX_op_ussub_vec:
     case INDEX_op_cmp_vec:
     case INDEX_op_cmpsel_vec:
         return 1;
@@ -2567,9 +2602,15 @@ static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode op)
     case INDEX_op_and_vec:
     case INDEX_op_or_vec:
     case INDEX_op_xor_vec:
+    case INDEX_op_ssadd_vec:
+    case INDEX_op_sssub_vec:
+    case INDEX_op_usadd_vec:
+    case INDEX_op_ussub_vec:
         return C_O1_I2(v, v, vK);
     case INDEX_op_sub_vec:
         return C_O1_I2(v, vK, v);
+    case INDEX_op_mul_vec:
+        return C_O1_I2(v, v, v);
     case INDEX_op_cmp_vec:
         return C_O1_I2(v, v, vL);
     case INDEX_op_cmpsel_vec:
-- 
2.43.0