[PATCH v10 28/61] target/riscv: vector single-width scaling shift instructions

[LIU Zhiwei]

Signed-off-by: LIU Zhiwei <zhiwei_liu@c-sky.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
---
 target/riscv/helper.h                   |  17 ++++
 target/riscv/insn32.decode              |   6 ++
 target/riscv/insn_trans/trans_rvv.inc.c |   8 ++
 target/riscv/vector_helper.c            | 117 ++++++++++++++++++++++++
 4 files changed, 148 insertions(+)

diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index f123302b82..78438f1ad6 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -773,3 +773,20 @@ DEF_HELPER_6(vwsmaccsu_vx_w, void, ptr, ptr, tl, ptr, env, 
i32)
 DEF_HELPER_6(vwsmaccus_vx_b, void, ptr, ptr, tl, ptr, env, i32)
 DEF_HELPER_6(vwsmaccus_vx_h, void, ptr, ptr, tl, ptr, env, i32)
 DEF_HELPER_6(vwsmaccus_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+
+DEF_HELPER_6(vssrl_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vssrl_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vssrl_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vssrl_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vssra_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vssra_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vssra_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vssra_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vssrl_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vssrl_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vssrl_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vssrl_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vssra_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vssra_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vssra_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vssra_vx_d, void, ptr, ptr, tl, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 8cc2bf4864..7d5dfeb5c7 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -433,6 +433,12 @@ vwsmacc_vx      111101 . ..... ..... 100 ..... 1010111 
@r_vm
 vwsmaccsu_vv    111110 . ..... ..... 000 ..... 1010111 @r_vm
 vwsmaccsu_vx    111110 . ..... ..... 100 ..... 1010111 @r_vm
 vwsmaccus_vx    111111 . ..... ..... 100 ..... 1010111 @r_vm
+vssrl_vv        101010 . ..... ..... 000 ..... 1010111 @r_vm
+vssrl_vx        101010 . ..... ..... 100 ..... 1010111 @r_vm
+vssrl_vi        101010 . ..... ..... 011 ..... 1010111 @r_vm
+vssra_vv        101011 . ..... ..... 000 ..... 1010111 @r_vm
+vssra_vx        101011 . ..... ..... 100 ..... 1010111 @r_vm
+vssra_vi        101011 . ..... ..... 011 ..... 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 3886b2f45a..0d9e65a194 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -1767,3 +1767,11 @@ GEN_OPIVX_WIDEN_TRANS(vwsmaccu_vx)
 GEN_OPIVX_WIDEN_TRANS(vwsmacc_vx)
 GEN_OPIVX_WIDEN_TRANS(vwsmaccsu_vx)
 GEN_OPIVX_WIDEN_TRANS(vwsmaccus_vx)
+
+/* Vector Single-Width Scaling Shift Instructions */
+GEN_OPIVV_TRANS(vssrl_vv, opivv_check)
+GEN_OPIVV_TRANS(vssra_vv, opivv_check)
+GEN_OPIVX_TRANS(vssrl_vx,  opivx_check)
+GEN_OPIVX_TRANS(vssra_vx,  opivx_check)
+GEN_OPIVI_TRANS(vssrl_vi, 1, vssrl_vx, opivx_check)
+GEN_OPIVI_TRANS(vssra_vi, 0, vssra_vx, opivx_check)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index d653ec5e2b..c33e845a90 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -2909,3 +2909,120 @@ RVVCALL(OPIVX3_RM, vwsmaccus_vx_w, WOP_SUS_W, H8, H4, 
vwsmaccus32)
 GEN_VEXT_VX_RM(vwsmaccus_vx_b, 1, 2, clearh)
 GEN_VEXT_VX_RM(vwsmaccus_vx_h, 2, 4, clearl)
 GEN_VEXT_VX_RM(vwsmaccus_vx_w, 4, 8, clearq)
+
+/* Vector Single-Width Scaling Shift Instructions */
+static inline uint8_t
+vssrl8(CPURISCVState *env, int vxrm, uint8_t a, uint8_t b)
+{
+    uint8_t round, shift = b & 0x7;
+    uint8_t res;
+
+    round = get_round(vxrm, a, shift);
+    res   = (a >> shift)  + round;
+    return res;
+}
+static inline uint16_t
+vssrl16(CPURISCVState *env, int vxrm, uint16_t a, uint16_t b)
+{
+    uint8_t round, shift = b & 0xf;
+    uint16_t res;
+
+    round = get_round(vxrm, a, shift);
+    res   = (a >> shift)  + round;
+    return res;
+}
+static inline uint32_t
+vssrl32(CPURISCVState *env, int vxrm, uint32_t a, uint32_t b)
+{
+    uint8_t round, shift = b & 0x1f;
+    uint32_t res;
+
+    round = get_round(vxrm, a, shift);
+    res   = (a >> shift)  + round;
+    return res;
+}
+static inline uint64_t
+vssrl64(CPURISCVState *env, int vxrm, uint64_t a, uint64_t b)
+{
+    uint8_t round, shift = b & 0x3f;
+    uint64_t res;
+
+    round = get_round(vxrm, a, shift);
+    res   = (a >> shift)  + round;
+    return res;
+}
+RVVCALL(OPIVV2_RM, vssrl_vv_b, OP_UUU_B, H1, H1, H1, vssrl8)
+RVVCALL(OPIVV2_RM, vssrl_vv_h, OP_UUU_H, H2, H2, H2, vssrl16)
+RVVCALL(OPIVV2_RM, vssrl_vv_w, OP_UUU_W, H4, H4, H4, vssrl32)
+RVVCALL(OPIVV2_RM, vssrl_vv_d, OP_UUU_D, H8, H8, H8, vssrl64)
+GEN_VEXT_VV_RM(vssrl_vv_b, 1, 1, clearb)
+GEN_VEXT_VV_RM(vssrl_vv_h, 2, 2, clearh)
+GEN_VEXT_VV_RM(vssrl_vv_w, 4, 4, clearl)
+GEN_VEXT_VV_RM(vssrl_vv_d, 8, 8, clearq)
+
+RVVCALL(OPIVX2_RM, vssrl_vx_b, OP_UUU_B, H1, H1, vssrl8)
+RVVCALL(OPIVX2_RM, vssrl_vx_h, OP_UUU_H, H2, H2, vssrl16)
+RVVCALL(OPIVX2_RM, vssrl_vx_w, OP_UUU_W, H4, H4, vssrl32)
+RVVCALL(OPIVX2_RM, vssrl_vx_d, OP_UUU_D, H8, H8, vssrl64)
+GEN_VEXT_VX_RM(vssrl_vx_b, 1, 1, clearb)
+GEN_VEXT_VX_RM(vssrl_vx_h, 2, 2, clearh)
+GEN_VEXT_VX_RM(vssrl_vx_w, 4, 4, clearl)
+GEN_VEXT_VX_RM(vssrl_vx_d, 8, 8, clearq)
+
+static inline int8_t
+vssra8(CPURISCVState *env, int vxrm, int8_t a, int8_t b)
+{
+    uint8_t round, shift = b & 0x7;
+    int8_t res;
+
+    round = get_round(vxrm, a, shift);
+    res   = (a >> shift)  + round;
+    return res;
+}
+static inline int16_t
+vssra16(CPURISCVState *env, int vxrm, int16_t a, int16_t b)
+{
+    uint8_t round, shift = b & 0xf;
+    int16_t res;
+
+    round = get_round(vxrm, a, shift);
+    res   = (a >> shift)  + round;
+    return res;
+}
+static inline int32_t
+vssra32(CPURISCVState *env, int vxrm, int32_t a, int32_t b)
+{
+    uint8_t round, shift = b & 0x1f;
+    int32_t res;
+
+    round = get_round(vxrm, a, shift);
+    res   = (a >> shift)  + round;
+    return res;
+}
+static inline int64_t
+vssra64(CPURISCVState *env, int vxrm, int64_t a, int64_t b)
+{
+    uint8_t round, shift = b & 0x3f;
+    int64_t res;
+
+    round = get_round(vxrm, a, shift);
+    res   = (a >> shift)  + round;
+    return res;
+}
+RVVCALL(OPIVV2_RM, vssra_vv_b, OP_SSS_B, H1, H1, H1, vssra8)
+RVVCALL(OPIVV2_RM, vssra_vv_h, OP_SSS_H, H2, H2, H2, vssra16)
+RVVCALL(OPIVV2_RM, vssra_vv_w, OP_SSS_W, H4, H4, H4, vssra32)
+RVVCALL(OPIVV2_RM, vssra_vv_d, OP_SSS_D, H8, H8, H8, vssra64)
+GEN_VEXT_VV_RM(vssra_vv_b, 1, 1, clearb)
+GEN_VEXT_VV_RM(vssra_vv_h, 2, 2, clearh)
+GEN_VEXT_VV_RM(vssra_vv_w, 4, 4, clearl)
+GEN_VEXT_VV_RM(vssra_vv_d, 8, 8, clearq)
+
+RVVCALL(OPIVX2_RM, vssra_vx_b, OP_SSS_B, H1, H1, vssra8)
+RVVCALL(OPIVX2_RM, vssra_vx_h, OP_SSS_H, H2, H2, vssra16)
+RVVCALL(OPIVX2_RM, vssra_vx_w, OP_SSS_W, H4, H4, vssra32)
+RVVCALL(OPIVX2_RM, vssra_vx_d, OP_SSS_D, H8, H8, vssra64)
+GEN_VEXT_VX_RM(vssra_vx_b, 1, 1, clearb)
+GEN_VEXT_VX_RM(vssra_vx_h, 2, 2, clearh)
+GEN_VEXT_VX_RM(vssra_vx_w, 4, 4, clearl)
+GEN_VEXT_VX_RM(vssra_vx_d, 8, 8, clearq)
-- 
2.23.0