On 11/4/2026 4:41 PM, Max Chou wrote:
Extend the vqwbdotau.vv and vqwbdotas.vv instructions to support
both 8-bit (Zvqwbdota8i) and 16-bit (Zvqwbdota16i) batched
dot-product operations.

Signed-off-by: Max Chou <[email protected]>
---

Reviewed-by: Daniel Henrique Barboza <[email protected]>

  target/riscv/helper.h                       | 4 +++-
  target/riscv/insn32.decode                  | 2 +-
  target/riscv/tcg/insn_trans/trans_rvv.c.inc | 5 +++--
  target/riscv/tcg/vector_helper.c            | 2 ++
  4 files changed, 9 insertions(+), 4 deletions(-)

diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index e48b9b4edec..84571a999f4 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -1400,9 +1400,11 @@ DEF_HELPER_6(vfwdota_vv, void, ptr, ptr, ptr, ptr, env, 
i32)
  DEF_HELPER_6(vfqwdota_vv, void, ptr, ptr, ptr, ptr, env, i32)
  DEF_HELPER_6(vfqwdota_alt_vv, void, ptr, ptr, ptr, ptr, env, i32)
-/* Zvqwbdota8i - 8-bit Integer Batched Dot Product */
+/* Zvqwbdota8i/Zvqwbdota16i - 8/16-bit Integer Batched Dot Product */
  DEF_HELPER_7(vqwbdotau_vv_b, void, ptr, ptr, ptr, ptr, i32, env, i32)
  DEF_HELPER_7(vqwbdotas_vv_b, void, ptr, ptr, ptr, ptr, i32, env, i32)
+DEF_HELPER_7(vqwbdotau_vv_h, void, ptr, ptr, ptr, ptr, i32, env, i32)
+DEF_HELPER_7(vqwbdotas_vv_h, void, ptr, ptr, ptr, ptr, i32, env, i32)
/* SiFive Custom int8 Matrix-Multiply */
  DEF_HELPER_5(sf_vqmaccu_4x8x4, void, ptr, ptr, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index bf325229100..8a06547a570 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -1109,6 +1109,6 @@ vfwdota_vv  100100 . ..... ..... 001 ..... 1110111 @r_vm
  vfqwdota_vv     100110 . ..... ..... 001 ..... 1110111 @r_vm
  vfqwdota_alt_vv 100111 . ..... ..... 001 ..... 1110111 @r_vm
-# *** Zvqwbdota8i 8-bit Integer Batched Dot-Product Extension ***
+# *** Zvqwbdota8i/Zvqwbdota16i Integer Batched Dot-Product Extension ***
  vqwbdotau_vv  101110 . ..... ..... 000 ..... 1110111 @r_vm
  vqwbdotas_vv  101111 . ..... ..... 000 ..... 1110111 @r_vm
diff --git a/target/riscv/tcg/insn_trans/trans_rvv.c.inc 
b/target/riscv/tcg/insn_trans/trans_rvv.c.inc
index bc12bcb9b72..650affc045b 100644
--- a/target/riscv/tcg/insn_trans/trans_rvv.c.inc
+++ b/target/riscv/tcg/insn_trans/trans_rvv.c.inc
@@ -4315,7 +4315,8 @@ static bool vext_vqwbdota_check(DisasContext *s, arg_rmrr 
*a)
      int32_t sew = s->sew;
      int32_t vd_eew = sew + 2;
      return vext_zvbdota_base_check(s, a, vd_eew) &&
-           (s->cfg_ptr->ext_zvqwbdota8i && sew == MO_8);
+           ((s->cfg_ptr->ext_zvqwbdota8i && sew == MO_8) ||
+            (s->cfg_ptr->ext_zvqwbdota16i && s->sew == MO_16));
  }
typedef void gen_helper_zvbdota_int(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_ptr,
@@ -4325,7 +4326,7 @@ typedef void gen_helper_zvbdota_int(TCGv_ptr, TCGv_ptr, 
TCGv_ptr, TCGv_ptr,
  static bool trans_##NAME(DisasContext *s, arg_rmrr *a)                   \
  {                                                                        \
      static gen_helper_zvbdota_int * const fns[2] = {                     \
-        gen_helper_##NAME##_b, NULL,                                     \
+        gen_helper_##NAME##_b, gen_helper_##NAME##_h,                    \
      };                                                                   \
      if (CHECK(s, a)) {                                                   \
          TCGv_ptr dest, src1, src2, mask;                                 \
diff --git a/target/riscv/tcg/vector_helper.c b/target/riscv/tcg/vector_helper.c
index 5ea073b6d76..683b14f28f3 100644
--- a/target/riscv/tcg/vector_helper.c
+++ b/target/riscv/tcg/vector_helper.c
@@ -6197,3 +6197,5 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void 
*vs2,                  \
GEN_VEXT_ZVBDOTA_INT(vqwbdotau_vv_b, 32, 8, uint8_t, H4, H1)
  GEN_VEXT_ZVBDOTA_INT(vqwbdotas_vv_b, 32, 8, int8_t, H4, H1)
+GEN_VEXT_ZVBDOTA_INT(vqwbdotau_vv_h, 64, 16, uint16_t, H8, H2)
+GEN_VEXT_ZVBDOTA_INT(vqwbdotas_vv_h, 64, 16, int16_t, H8, H2)


Reply via email to