[RFC v5 40/68] target/riscv: rvv-1.0: single-width averaging add and subtract instructions

[frank . chang]

From: Frank Chang <frank.chang@sifive.com>

Add the following instructions:

* vaaddu.vv
* vaaddu.vx
* vasubu.vv
* vasubu.vx

Remove the following instructions:

* vadd.vi

Signed-off-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/riscv/helper.h                   | 16 ++++++
 target/riscv/insn32.decode              | 13 +++--
 target/riscv/insn_trans/trans_rvv.c.inc |  5 +-
 target/riscv/vector_helper.c            | 74 +++++++++++++++++++++++++
 4 files changed, 102 insertions(+), 6 deletions(-)

diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index fd59b07af3..290d32078e 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -698,18 +698,34 @@ 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(vaaddu_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vaaddu_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vaaddu_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vaaddu_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(vasubu_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vasubu_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vasubu_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vasubu_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(vaaddu_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vaaddu_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vaaddu_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vaaddu_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)
+DEF_HELPER_6(vasubu_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vasubu_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vasubu_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vasubu_vx_d, void, ptr, ptr, tl, ptr, env, i32)
 
 DEF_HELPER_6(vsmul_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
 DEF_HELPER_6(vsmul_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 158ef6e49f..9fcb985e9f 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -468,11 +468,14 @@ 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
+vaadd_vv        001001 . ..... ..... 010 ..... 1010111 @r_vm
+vaadd_vx        001001 . ..... ..... 110 ..... 1010111 @r_vm
+vaaddu_vv       001000 . ..... ..... 010 ..... 1010111 @r_vm
+vaaddu_vx       001000 . ..... ..... 110 ..... 1010111 @r_vm
+vasub_vv        001011 . ..... ..... 010 ..... 1010111 @r_vm
+vasub_vx        001011 . ..... ..... 110 ..... 1010111 @r_vm
+vasubu_vv       001010 . ..... ..... 010 ..... 1010111 @r_vm
+vasubu_vx       001010 . ..... ..... 110 ..... 1010111 @r_vm
 vsmul_vv        100111 . ..... ..... 000 ..... 1010111 @r_vm
 vsmul_vx        100111 . ..... ..... 100 ..... 1010111 @r_vm
 vwsmaccu_vv     111100 . ..... ..... 000 ..... 1010111 @r_vm
diff --git a/target/riscv/insn_trans/trans_rvv.c.inc 
b/target/riscv/insn_trans/trans_rvv.c.inc
index 12250c776d..cce1712af0 100644
--- a/target/riscv/insn_trans/trans_rvv.c.inc
+++ b/target/riscv/insn_trans/trans_rvv.c.inc
@@ -2254,10 +2254,13 @@ GEN_OPIVI_TRANS(vsadd_vi, IMM_SX, vsadd_vx, opivx_check)
 
 /* Vector Single-Width Averaging Add and Subtract */
 GEN_OPIVV_TRANS(vaadd_vv, opivv_check)
+GEN_OPIVV_TRANS(vaaddu_vv, opivv_check)
 GEN_OPIVV_TRANS(vasub_vv, opivv_check)
+GEN_OPIVV_TRANS(vasubu_vv, opivv_check)
 GEN_OPIVX_TRANS(vaadd_vx,  opivx_check)
+GEN_OPIVX_TRANS(vaaddu_vx,  opivx_check)
 GEN_OPIVX_TRANS(vasub_vx,  opivx_check)
-GEN_OPIVI_TRANS(vaadd_vi, 0, vaadd_vx, opivx_check)
+GEN_OPIVX_TRANS(vasubu_vx,  opivx_check)
 
 /* Vector Single-Width Fractional Multiply with Rounding and Saturation */
 GEN_OPIVV_TRANS(vsmul_vv, opivv_check)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 40ef5ab53a..c37d040411 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -2502,6 +2502,43 @@ GEN_VEXT_VX_RM(vaadd_vx_h, 2, 2)
 GEN_VEXT_VX_RM(vaadd_vx_w, 4, 4)
 GEN_VEXT_VX_RM(vaadd_vx_d, 8, 8)
 
+static inline uint32_t aaddu32(CPURISCVState *env, int vxrm,
+                               uint32_t a, uint32_t b)
+{
+    uint64_t res = (uint64_t)a + b;
+    uint8_t round = get_round(vxrm, res, 1);
+
+    return (res >> 1) + round;
+}
+
+static inline uint64_t aaddu64(CPURISCVState *env, int vxrm,
+                               uint64_t a, uint64_t b)
+{
+    uint64_t res = a + b;
+    uint8_t round = get_round(vxrm, res, 1);
+    uint64_t over = (uint64_t)(res < a) << 63;
+
+    return ((res >> 1) | over) + round;
+}
+
+RVVCALL(OPIVV2_RM, vaaddu_vv_b, OP_UUU_B, H1, H1, H1, aaddu32)
+RVVCALL(OPIVV2_RM, vaaddu_vv_h, OP_UUU_H, H2, H2, H2, aaddu32)
+RVVCALL(OPIVV2_RM, vaaddu_vv_w, OP_UUU_W, H4, H4, H4, aaddu32)
+RVVCALL(OPIVV2_RM, vaaddu_vv_d, OP_UUU_D, H8, H8, H8, aaddu64)
+GEN_VEXT_VV_RM(vaaddu_vv_b, 1, 1)
+GEN_VEXT_VV_RM(vaaddu_vv_h, 2, 2)
+GEN_VEXT_VV_RM(vaaddu_vv_w, 4, 4)
+GEN_VEXT_VV_RM(vaaddu_vv_d, 8, 8)
+
+RVVCALL(OPIVX2_RM, vaaddu_vx_b, OP_UUU_B, H1, H1, aaddu32)
+RVVCALL(OPIVX2_RM, vaaddu_vx_h, OP_UUU_H, H2, H2, aaddu32)
+RVVCALL(OPIVX2_RM, vaaddu_vx_w, OP_UUU_W, H4, H4, aaddu32)
+RVVCALL(OPIVX2_RM, vaaddu_vx_d, OP_UUU_D, H8, H8, aaddu64)
+GEN_VEXT_VX_RM(vaaddu_vx_b, 1, 1)
+GEN_VEXT_VX_RM(vaaddu_vx_h, 2, 2)
+GEN_VEXT_VX_RM(vaaddu_vx_w, 4, 4)
+GEN_VEXT_VX_RM(vaaddu_vx_d, 8, 8)
+
 static inline int32_t asub32(CPURISCVState *env, int vxrm, int32_t a, int32_t 
b)
 {
     int64_t res = (int64_t)a - b;
@@ -2538,6 +2575,43 @@ GEN_VEXT_VX_RM(vasub_vx_h, 2, 2)
 GEN_VEXT_VX_RM(vasub_vx_w, 4, 4)
 GEN_VEXT_VX_RM(vasub_vx_d, 8, 8)
 
+static inline uint32_t asubu32(CPURISCVState *env, int vxrm,
+                               uint32_t a, uint32_t b)
+{
+    int64_t res = (int64_t)a - b;
+    uint8_t round = get_round(vxrm, res, 1);
+
+    return (res >> 1) + round;
+}
+
+static inline uint64_t asubu64(CPURISCVState *env, int vxrm,
+                               uint64_t a, uint64_t b)
+{
+    uint64_t res = (uint64_t)a - b;
+    uint8_t round = get_round(vxrm, res, 1);
+    uint64_t over = (uint64_t)(res > a) << 63;
+
+    return ((res >> 1) | over) + round;
+}
+
+RVVCALL(OPIVV2_RM, vasubu_vv_b, OP_UUU_B, H1, H1, H1, asubu32)
+RVVCALL(OPIVV2_RM, vasubu_vv_h, OP_UUU_H, H2, H2, H2, asubu32)
+RVVCALL(OPIVV2_RM, vasubu_vv_w, OP_UUU_W, H4, H4, H4, asubu32)
+RVVCALL(OPIVV2_RM, vasubu_vv_d, OP_UUU_D, H8, H8, H8, asubu64)
+GEN_VEXT_VV_RM(vasubu_vv_b, 1, 1)
+GEN_VEXT_VV_RM(vasubu_vv_h, 2, 2)
+GEN_VEXT_VV_RM(vasubu_vv_w, 4, 4)
+GEN_VEXT_VV_RM(vasubu_vv_d, 8, 8)
+
+RVVCALL(OPIVX2_RM, vasubu_vx_b, OP_UUU_B, H1, H1, asubu32)
+RVVCALL(OPIVX2_RM, vasubu_vx_h, OP_UUU_H, H2, H2, asubu32)
+RVVCALL(OPIVX2_RM, vasubu_vx_w, OP_UUU_W, H4, H4, asubu32)
+RVVCALL(OPIVX2_RM, vasubu_vx_d, OP_UUU_D, H8, H8, asubu64)
+GEN_VEXT_VX_RM(vasubu_vx_b, 1, 1)
+GEN_VEXT_VX_RM(vasubu_vx_h, 2, 2)
+GEN_VEXT_VX_RM(vasubu_vx_w, 4, 4)
+GEN_VEXT_VX_RM(vasubu_vx_d, 8, 8)
+
 /* Vector Single-Width Fractional Multiply with Rounding and Saturation */
 static inline int8_t vsmul8(CPURISCVState *env, int vxrm, int8_t a, int8_t b)
 {
-- 
2.17.1