target/riscv: vector integer add-with-carry / subtract-with-borrow instructions

Signed-off-by: LIU Zhiwei <zhiwei_liu@c-sky.com>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20200701152549.1218-13-zhiwei_liu@c-sky.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>

1 files changed, 137 insertions, 0 deletions

diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 06435ed82a..e152641b4f 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -187,6 +187,14 @@ static void clearq(void *vd, uint32_t idx, uint32_t cnt, uint32_t tot)
     vext_clear(cur, cnt, tot);
 }
 
+static inline void vext_set_elem_mask(void *v0, int mlen, int index,
+        uint8_t value)
+{
+    int idx = (index * mlen) / 64;
+    int pos = (index * mlen) % 64;
+    uint64_t old = ((uint64_t *)v0)[idx];
+    ((uint64_t *)v0)[idx] = deposit64(old, pos, mlen, value);
+}
 
 static inline int vext_elem_mask(void *v0, int mlen, int index)
 {
@@ -1128,3 +1136,132 @@ GEN_VEXT_VX(vwadd_wx_w, 4, 8, clearq)
 GEN_VEXT_VX(vwsub_wx_b, 1, 2, clearh)
 GEN_VEXT_VX(vwsub_wx_h, 2, 4, clearl)
 GEN_VEXT_VX(vwsub_wx_w, 4, 8, clearq)
+
+/* Vector Integer Add-with-Carry / Subtract-with-Borrow Instructions */
+#define DO_VADC(N, M, C) (N + M + C)
+#define DO_VSBC(N, M, C) (N - M - C)
+
+#define GEN_VEXT_VADC_VVM(NAME, ETYPE, H, DO_OP, CLEAR_FN)    \
+void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2,   \
+                  CPURISCVState *env, uint32_t desc)          \
+{                                                             \
+    uint32_t mlen = vext_mlen(desc);                          \
+    uint32_t vl = env->vl;                                    \
+    uint32_t esz = sizeof(ETYPE);                             \
+    uint32_t vlmax = vext_maxsz(desc) / esz;                  \
+    uint32_t i;                                               \
+                                                              \
+    for (i = 0; i < vl; i++) {                                \
+        ETYPE s1 = *((ETYPE *)vs1 + H(i));                    \
+        ETYPE s2 = *((ETYPE *)vs2 + H(i));                    \
+        uint8_t carry = vext_elem_mask(v0, mlen, i);          \
+                                                              \
+        *((ETYPE *)vd + H(i)) = DO_OP(s2, s1, carry);         \
+    }                                                         \
+    CLEAR_FN(vd, vl, vl * esz, vlmax * esz);                  \
+}
+
+GEN_VEXT_VADC_VVM(vadc_vvm_b, uint8_t,  H1, DO_VADC, clearb)
+GEN_VEXT_VADC_VVM(vadc_vvm_h, uint16_t, H2, DO_VADC, clearh)
+GEN_VEXT_VADC_VVM(vadc_vvm_w, uint32_t, H4, DO_VADC, clearl)
+GEN_VEXT_VADC_VVM(vadc_vvm_d, uint64_t, H8, DO_VADC, clearq)
+
+GEN_VEXT_VADC_VVM(vsbc_vvm_b, uint8_t,  H1, DO_VSBC, clearb)
+GEN_VEXT_VADC_VVM(vsbc_vvm_h, uint16_t, H2, DO_VSBC, clearh)
+GEN_VEXT_VADC_VVM(vsbc_vvm_w, uint32_t, H4, DO_VSBC, clearl)
+GEN_VEXT_VADC_VVM(vsbc_vvm_d, uint64_t, H8, DO_VSBC, clearq)
+
+#define GEN_VEXT_VADC_VXM(NAME, ETYPE, H, DO_OP, CLEAR_FN)               \
+void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2,        \
+                  CPURISCVState *env, uint32_t desc)                     \
+{                                                                        \
+    uint32_t mlen = vext_mlen(desc);                                     \
+    uint32_t vl = env->vl;                                               \
+    uint32_t esz = sizeof(ETYPE);                                        \
+    uint32_t vlmax = vext_maxsz(desc) / esz;                             \
+    uint32_t i;                                                          \
+                                                                         \
+    for (i = 0; i < vl; i++) {                                           \
+        ETYPE s2 = *((ETYPE *)vs2 + H(i));                               \
+        uint8_t carry = vext_elem_mask(v0, mlen, i);                     \
+                                                                         \
+        *((ETYPE *)vd + H(i)) = DO_OP(s2, (ETYPE)(target_long)s1, carry);\
+    }                                                                    \
+    CLEAR_FN(vd, vl, vl * esz, vlmax * esz);                             \
+}
+
+GEN_VEXT_VADC_VXM(vadc_vxm_b, uint8_t,  H1, DO_VADC, clearb)
+GEN_VEXT_VADC_VXM(vadc_vxm_h, uint16_t, H2, DO_VADC, clearh)
+GEN_VEXT_VADC_VXM(vadc_vxm_w, uint32_t, H4, DO_VADC, clearl)
+GEN_VEXT_VADC_VXM(vadc_vxm_d, uint64_t, H8, DO_VADC, clearq)
+
+GEN_VEXT_VADC_VXM(vsbc_vxm_b, uint8_t,  H1, DO_VSBC, clearb)
+GEN_VEXT_VADC_VXM(vsbc_vxm_h, uint16_t, H2, DO_VSBC, clearh)
+GEN_VEXT_VADC_VXM(vsbc_vxm_w, uint32_t, H4, DO_VSBC, clearl)
+GEN_VEXT_VADC_VXM(vsbc_vxm_d, uint64_t, H8, DO_VSBC, clearq)
+
+#define DO_MADC(N, M, C) (C ? (__typeof(N))(N + M + 1) <= N :           \
+                          (__typeof(N))(N + M) < N)
+#define DO_MSBC(N, M, C) (C ? N <= M : N < M)
+
+#define GEN_VEXT_VMADC_VVM(NAME, ETYPE, H, DO_OP)             \
+void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2,   \
+                  CPURISCVState *env, uint32_t desc)          \
+{                                                             \
+    uint32_t mlen = vext_mlen(desc);                          \
+    uint32_t vl = env->vl;                                    \
+    uint32_t vlmax = vext_maxsz(desc) / sizeof(ETYPE);        \
+    uint32_t i;                                               \
+                                                              \
+    for (i = 0; i < vl; i++) {                                \
+        ETYPE s1 = *((ETYPE *)vs1 + H(i));                    \
+        ETYPE s2 = *((ETYPE *)vs2 + H(i));                    \
+        uint8_t carry = vext_elem_mask(v0, mlen, i);          \
+                                                              \
+        vext_set_elem_mask(vd, mlen, i, DO_OP(s2, s1, carry));\
+    }                                                         \
+    for (; i < vlmax; i++) {                                  \
+        vext_set_elem_mask(vd, mlen, i, 0);                   \
+    }                                                         \
+}
+
+GEN_VEXT_VMADC_VVM(vmadc_vvm_b, uint8_t,  H1, DO_MADC)
+GEN_VEXT_VMADC_VVM(vmadc_vvm_h, uint16_t, H2, DO_MADC)
+GEN_VEXT_VMADC_VVM(vmadc_vvm_w, uint32_t, H4, DO_MADC)
+GEN_VEXT_VMADC_VVM(vmadc_vvm_d, uint64_t, H8, DO_MADC)
+
+GEN_VEXT_VMADC_VVM(vmsbc_vvm_b, uint8_t,  H1, DO_MSBC)
+GEN_VEXT_VMADC_VVM(vmsbc_vvm_h, uint16_t, H2, DO_MSBC)
+GEN_VEXT_VMADC_VVM(vmsbc_vvm_w, uint32_t, H4, DO_MSBC)
+GEN_VEXT_VMADC_VVM(vmsbc_vvm_d, uint64_t, H8, DO_MSBC)
+
+#define GEN_VEXT_VMADC_VXM(NAME, ETYPE, H, DO_OP)               \
+void HELPER(NAME)(void *vd, void *v0, target_ulong s1,          \
+                  void *vs2, CPURISCVState *env, uint32_t desc) \
+{                                                               \
+    uint32_t mlen = vext_mlen(desc);                            \
+    uint32_t vl = env->vl;                                      \
+    uint32_t vlmax = vext_maxsz(desc) / sizeof(ETYPE);          \
+    uint32_t i;                                                 \
+                                                                \
+    for (i = 0; i < vl; i++) {                                  \
+        ETYPE s2 = *((ETYPE *)vs2 + H(i));                      \
+        uint8_t carry = vext_elem_mask(v0, mlen, i);            \
+                                                                \
+        vext_set_elem_mask(vd, mlen, i,                         \
+                DO_OP(s2, (ETYPE)(target_long)s1, carry));      \
+    }                                                           \
+    for (; i < vlmax; i++) {                                    \
+        vext_set_elem_mask(vd, mlen, i, 0);                     \
+    }                                                           \
+}
+
+GEN_VEXT_VMADC_VXM(vmadc_vxm_b, uint8_t,  H1, DO_MADC)
+GEN_VEXT_VMADC_VXM(vmadc_vxm_h, uint16_t, H2, DO_MADC)
+GEN_VEXT_VMADC_VXM(vmadc_vxm_w, uint32_t, H4, DO_MADC)
+GEN_VEXT_VMADC_VXM(vmadc_vxm_d, uint64_t, H8, DO_MADC)
+
+GEN_VEXT_VMADC_VXM(vmsbc_vxm_b, uint8_t,  H1, DO_MSBC)
+GEN_VEXT_VMADC_VXM(vmsbc_vxm_h, uint16_t, H2, DO_MSBC)
+GEN_VEXT_VMADC_VXM(vmsbc_vxm_w, uint32_t, H4, DO_MSBC)
+GEN_VEXT_VMADC_VXM(vmsbc_vxm_d, uint64_t, H8, DO_MSBC)