[PATCH v5 24/60] target/riscv: vector single-width averaging add and subtract

[LIU Zhiwei]

Signed-off-by: LIU Zhiwei <address@hidden>
---
 target/riscv/helper.h                   |  17 ++++
 target/riscv/insn32.decode              |   5 +
 target/riscv/insn_trans/trans_rvv.inc.c |   7 ++
 target/riscv/vector_helper.c            | 129 ++++++++++++++++++++++++
 4 files changed, 158 insertions(+)

diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index 95da00d365..d3837d2ca4 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -707,3 +707,20 @@ DEF_HELPER_6(vssub_vx_b, void, ptr, ptr, tl, ptr, env, i32)
 DEF_HELPER_6(vssub_vx_h, void, ptr, ptr, tl, ptr, env, i32)
 DEF_HELPER_6(vssub_vx_w, void, ptr, ptr, tl, ptr, env, i32)
 DEF_HELPER_6(vssub_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+
+DEF_HELPER_6(vaadd_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vaadd_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vaadd_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vaadd_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vasub_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vasub_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vasub_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vasub_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vaadd_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vaadd_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vaadd_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vaadd_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vasub_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vasub_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vasub_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vasub_vx_d, void, ptr, ptr, tl, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 44baadf582..0227a16b16 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -412,6 +412,11 @@ vssubu_vv       100010 . ..... ..... 000 ..... 1010111 
@r_vm
 vssubu_vx       100010 . ..... ..... 100 ..... 1010111 @r_vm
 vssub_vv        100011 . ..... ..... 000 ..... 1010111 @r_vm
 vssub_vx        100011 . ..... ..... 100 ..... 1010111 @r_vm
+vaadd_vv        100100 . ..... ..... 000 ..... 1010111 @r_vm
+vaadd_vx        100100 . ..... ..... 100 ..... 1010111 @r_vm
+vaadd_vi        100100 . ..... ..... 011 ..... 1010111 @r_vm
+vasub_vv        100110 . ..... ..... 000 ..... 1010111 @r_vm
+vasub_vx        100110 . ..... ..... 100 ..... 1010111 @r_vm
 
 vsetvli         0 ........... ..... 111 ..... 1010111  @r2_zimm
 vsetvl          1000000 ..... ..... 111 ..... 1010111  @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c 
b/target/riscv/insn_trans/trans_rvv.inc.c
index ad55766b98..9988fad2fe 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -1521,3 +1521,10 @@ GEN_OPIVX_TRANS(vssubu_vx,  opivx_check)
 GEN_OPIVX_TRANS(vssub_vx,  opivx_check)
 GEN_OPIVI_TRANS(vsaddu_vi, 1, vsaddu_vx, opivx_check)
 GEN_OPIVI_TRANS(vsadd_vi, 0, vsadd_vx, opivx_check)
+
+/* Vector Single-Width Averaging Add and Subtract */
+GEN_OPIVV_TRANS(vaadd_vv, opivv_check)
+GEN_OPIVV_TRANS(vasub_vv, opivv_check)
+GEN_OPIVX_TRANS(vaadd_vx,  opivx_check)
+GEN_OPIVX_TRANS(vasub_vx,  opivx_check)
+GEN_OPIVI_TRANS(vaadd_vi, 0, vaadd_vx, opivx_check)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index c7b8c1bff4..b0a7a3b6e4 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -2291,3 +2291,132 @@ GEN_VEXT_VX_ENV(vssub_vx_b, 1, 1, clearb)
 GEN_VEXT_VX_ENV(vssub_vx_h, 2, 2, clearh)
 GEN_VEXT_VX_ENV(vssub_vx_w, 4, 4, clearl)
 GEN_VEXT_VX_ENV(vssub_vx_d, 8, 8, clearq)
+
+/* Vector Single-Width Averaging Add and Subtract */
+static inline uint8_t get_round(CPURISCVState *env, uint64_t v, uint8_t shift)
+{
+    uint8_t d = extract64(v, shift, 1);
+    uint8_t d1;
+    uint64_t D1, D2;
+    int mod = env->vxrm;
+
+    if (shift == 0 || shift > 64) {
+        return 0;
+    }
+
+    d1 = extract64(v, shift - 1, 1);
+    D1 = extract64(v, 0, shift);
+    if (mod == 0) { /* round-to-nearest-up (add +0.5 LSB) */
+        return d1;
+    } else if (mod == 1) { /* round-to-nearest-even */
+        if (shift > 1) {
+            D2 = extract64(v, 0, shift - 1);
+            return d1 & ((D2 != 0) | d);
+        } else {
+            return d1 & d;
+        }
+    } else if (mod == 3) { /* round-to-odd (OR bits into LSB, aka "jam") */
+        return !d & (D1 != 0);
+    }
+    return 0; /* round-down (truncate) */
+}
+
+static inline int8_t aadd8(CPURISCVState *env, int8_t a, int8_t b)
+{
+    int16_t res = (int16_t)a + (int16_t)b;
+    uint8_t round = get_round(env, res, 1);
+    res   = (res >> 1) + round;
+    return res;
+}
+static inline int16_t aadd16(CPURISCVState *env, int16_t a, int16_t b)
+{
+    int32_t res = (int32_t)a + (int32_t)b;
+    uint8_t round = get_round(env, res, 1);
+    res   = (res >> 1) + round;
+    return res;
+}
+static inline int32_t aadd32(CPURISCVState *env, int32_t a, int32_t b)
+{
+    int64_t res = (int64_t)a + (int64_t)b;
+    uint8_t round = get_round(env, res, 1);
+    res   = (res >> 1) + round;
+    return res;
+}
+static inline int64_t aadd64(CPURISCVState *env, int64_t a, int64_t b)
+{
+    int64_t res = (int64_t)a + (int64_t)b;
+    uint8_t round = get_round(env, res, 1); /* get_round only need v[d : 0] */
+    if (((res ^ a) & (res ^ b)) >> 63 == -1LL) { /* overflow */
+        res = ((res >> 1) ^ INT64_MIN) + round;
+    } else {
+        res   = (res >> 1) + round;
+    }
+    return res;
+}
+RVVCALL(OPIVV2_ENV, vaadd_vv_b, OP_SSS_B, H1, H1, H1, aadd8)
+RVVCALL(OPIVV2_ENV, vaadd_vv_h, OP_SSS_H, H2, H2, H2, aadd16)
+RVVCALL(OPIVV2_ENV, vaadd_vv_w, OP_SSS_W, H4, H4, H4, aadd32)
+RVVCALL(OPIVV2_ENV, vaadd_vv_d, OP_SSS_D, H8, H8, H8, aadd64)
+GEN_VEXT_VV_ENV(vaadd_vv_b, 1, 1, clearb)
+GEN_VEXT_VV_ENV(vaadd_vv_h, 2, 2, clearh)
+GEN_VEXT_VV_ENV(vaadd_vv_w, 4, 4, clearl)
+GEN_VEXT_VV_ENV(vaadd_vv_d, 8, 8, clearq)
+
+RVVCALL(OPIVX2_ENV, vaadd_vx_b, OP_SSS_B, H1, H1, aadd8)
+RVVCALL(OPIVX2_ENV, vaadd_vx_h, OP_SSS_H, H2, H2, aadd16)
+RVVCALL(OPIVX2_ENV, vaadd_vx_w, OP_SSS_W, H4, H4, aadd32)
+RVVCALL(OPIVX2_ENV, vaadd_vx_d, OP_SSS_D, H8, H8, aadd64)
+GEN_VEXT_VX_ENV(vaadd_vx_b, 1, 1, clearb)
+GEN_VEXT_VX_ENV(vaadd_vx_h, 2, 2, clearh)
+GEN_VEXT_VX_ENV(vaadd_vx_w, 4, 4, clearl)
+GEN_VEXT_VX_ENV(vaadd_vx_d, 8, 8, clearq)
+
+static inline int8_t asub8(CPURISCVState *env, int8_t a, int8_t b)
+{
+    int16_t res = (int16_t)a - (int16_t)b;
+    uint8_t round = get_round(env, res, 1);
+    res   = (res >> 1) + round;
+    return res;
+}
+static inline int16_t asub16(CPURISCVState *env, int16_t a, int16_t b)
+{
+    int32_t res = (int32_t)a - (int32_t)b;
+    uint8_t round = get_round(env, res, 1);
+    res   = (res >> 1) + round;
+    return res;
+}
+static inline int32_t asub32(CPURISCVState *env, int32_t a, int32_t b)
+{
+    int64_t res = (int64_t)a - (int64_t)b;
+    uint8_t round = get_round(env, res, 1);
+    res   = (res >> 1) + round;
+    return res;
+}
+static inline int64_t asub64(CPURISCVState *env, int64_t a, int64_t b)
+{
+    int64_t res = (int64_t)a - (int64_t)b;
+    uint8_t round = get_round(env, res, 1); /* get_round only need v[d : 0] */
+    if (((res ^ a) & (a ^ b)) >> 63 == -1LL) { /* overflow */
+        res = ((res >> 1) ^ INT64_MIN) + round;
+    } else {
+        res   = (res >> 1) + round;
+    }
+    return res;
+}
+RVVCALL(OPIVV2_ENV, vasub_vv_b, OP_SSS_B, H1, H1, H1, asub8)
+RVVCALL(OPIVV2_ENV, vasub_vv_h, OP_SSS_H, H2, H2, H2, asub16)
+RVVCALL(OPIVV2_ENV, vasub_vv_w, OP_SSS_W, H4, H4, H4, asub32)
+RVVCALL(OPIVV2_ENV, vasub_vv_d, OP_SSS_D, H8, H8, H8, asub64)
+GEN_VEXT_VV_ENV(vasub_vv_b, 1, 1, clearb)
+GEN_VEXT_VV_ENV(vasub_vv_h, 2, 2, clearh)
+GEN_VEXT_VV_ENV(vasub_vv_w, 4, 4, clearl)
+GEN_VEXT_VV_ENV(vasub_vv_d, 8, 8, clearq)
+
+RVVCALL(OPIVX2_ENV, vasub_vx_b, OP_SSS_B, H1, H1, asub8)
+RVVCALL(OPIVX2_ENV, vasub_vx_h, OP_SSS_H, H2, H2, asub16)
+RVVCALL(OPIVX2_ENV, vasub_vx_w, OP_SSS_W, H4, H4, asub32)
+RVVCALL(OPIVX2_ENV, vasub_vx_d, OP_SSS_D, H8, H8, asub64)
+GEN_VEXT_VX_ENV(vasub_vx_b, 1, 1, clearb)
+GEN_VEXT_VX_ENV(vasub_vx_h, 2, 2, clearh)
+GEN_VEXT_VX_ENV(vasub_vx_w, 4, 4, clearl)
+GEN_VEXT_VX_ENV(vasub_vx_d, 8, 8, clearq)
-- 
2.23.0