target/riscv: vector widening floating-point add/subtract instructions

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>
Message-Id: <20200701152549.1218-32-zhiwei_liu@c-sky.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>

4 files changed, 257 insertions, 0 deletions

diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index ba8a371..828b145 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -819,3 +819,20 @@ DEF_HELPER_6(vfsub_vf_d, void, ptr, ptr, i64, ptr, env, i32)
 DEF_HELPER_6(vfrsub_vf_h, void, ptr, ptr, i64, ptr, env, i32)
 DEF_HELPER_6(vfrsub_vf_w, void, ptr, ptr, i64, ptr, env, i32)
 DEF_HELPER_6(vfrsub_vf_d, void, ptr, ptr, i64, ptr, env, i32)
+
+DEF_HELPER_6(vfwadd_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwadd_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwsub_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwsub_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwadd_wv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwadd_wv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwsub_wv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwsub_wv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwadd_vf_h, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfwadd_vf_w, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfwsub_vf_h, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfwsub_vf_w, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfwadd_wf_h, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfwadd_wf_w, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfwsub_wf_h, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfwsub_wf_w, void, ptr, ptr, i64, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 9e26ed3..42d8a96 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -450,6 +450,14 @@ vfadd_vf        000000 . ..... ..... 101 ..... 1010111 @r_vm
 vfsub_vv        000010 . ..... ..... 001 ..... 1010111 @r_vm
 vfsub_vf        000010 . ..... ..... 101 ..... 1010111 @r_vm
 vfrsub_vf       100111 . ..... ..... 101 ..... 1010111 @r_vm
+vfwadd_vv       110000 . ..... ..... 001 ..... 1010111 @r_vm
+vfwadd_vf       110000 . ..... ..... 101 ..... 1010111 @r_vm
+vfwadd_wv       110100 . ..... ..... 001 ..... 1010111 @r_vm
+vfwadd_wf       110100 . ..... ..... 101 ..... 1010111 @r_vm
+vfwsub_vv       110010 . ..... ..... 001 ..... 1010111 @r_vm
+vfwsub_vf       110010 . ..... ..... 101 ..... 1010111 @r_vm
+vfwsub_wv       110110 . ..... ..... 001 ..... 1010111 @r_vm
+vfwsub_wf       110110 . ..... ..... 101 ..... 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 55a6e514..0224b66 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -1901,3 +1901,152 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a)            \
 GEN_OPFVF_TRANS(vfadd_vf,  opfvf_check)
 GEN_OPFVF_TRANS(vfsub_vf,  opfvf_check)
 GEN_OPFVF_TRANS(vfrsub_vf,  opfvf_check)
+
+/* Vector Widening Floating-Point Add/Subtract Instructions */
+static bool opfvv_widen_check(DisasContext *s, arg_rmrr *a)
+{
+    return (vext_check_isa_ill(s) &&
+            vext_check_overlap_mask(s, a->rd, a->vm, true) &&
+            vext_check_reg(s, a->rd, true) &&
+            vext_check_reg(s, a->rs2, false) &&
+            vext_check_reg(s, a->rs1, false) &&
+            vext_check_overlap_group(a->rd, 2 << s->lmul, a->rs2,
+                                     1 << s->lmul) &&
+            vext_check_overlap_group(a->rd, 2 << s->lmul, a->rs1,
+                                     1 << s->lmul) &&
+            (s->lmul < 0x3) && (s->sew < 0x3) && (s->sew != 0));
+}
+
+/* OPFVV with WIDEN */
+#define GEN_OPFVV_WIDEN_TRANS(NAME, CHECK)                       \
+static bool trans_##NAME(DisasContext *s, arg_rmrr *a)           \
+{                                                                \
+    if (CHECK(s, a)) {                                           \
+        uint32_t data = 0;                                       \
+        static gen_helper_gvec_4_ptr * const fns[2] = {          \
+            gen_helper_##NAME##_h, gen_helper_##NAME##_w,        \
+        };                                                       \
+        TCGLabel *over = gen_new_label();                        \
+        gen_set_rm(s, 7);                                        \
+        tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);        \
+                                                                 \
+        data = FIELD_DP32(data, VDATA, MLEN, s->mlen);           \
+        data = FIELD_DP32(data, VDATA, VM, a->vm);               \
+        data = FIELD_DP32(data, VDATA, LMUL, s->lmul);           \
+        tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0),   \
+                           vreg_ofs(s, a->rs1),                  \
+                           vreg_ofs(s, a->rs2), cpu_env, 0,      \
+                           s->vlen / 8, data, fns[s->sew - 1]);  \
+        gen_set_label(over);                                     \
+        return true;                                             \
+    }                                                            \
+    return false;                                                \
+}
+
+GEN_OPFVV_WIDEN_TRANS(vfwadd_vv, opfvv_widen_check)
+GEN_OPFVV_WIDEN_TRANS(vfwsub_vv, opfvv_widen_check)
+
+static bool opfvf_widen_check(DisasContext *s, arg_rmrr *a)
+{
+    return (vext_check_isa_ill(s) &&
+            vext_check_overlap_mask(s, a->rd, a->vm, true) &&
+            vext_check_reg(s, a->rd, true) &&
+            vext_check_reg(s, a->rs2, false) &&
+            vext_check_overlap_group(a->rd, 2 << s->lmul, a->rs2,
+                                     1 << s->lmul) &&
+            (s->lmul < 0x3) && (s->sew < 0x3) && (s->sew != 0));
+}
+
+/* OPFVF with WIDEN */
+#define GEN_OPFVF_WIDEN_TRANS(NAME)                              \
+static bool trans_##NAME(DisasContext *s, arg_rmrr *a)           \
+{                                                                \
+    if (opfvf_widen_check(s, a)) {                               \
+        uint32_t data = 0;                                       \
+        static gen_helper_opfvf *const fns[2] = {                \
+            gen_helper_##NAME##_h, gen_helper_##NAME##_w,        \
+        };                                                       \
+        gen_set_rm(s, 7);                                        \
+        data = FIELD_DP32(data, VDATA, MLEN, s->mlen);           \
+        data = FIELD_DP32(data, VDATA, VM, a->vm);               \
+        data = FIELD_DP32(data, VDATA, LMUL, s->lmul);           \
+        return opfvf_trans(a->rd, a->rs1, a->rs2, data,          \
+                           fns[s->sew - 1], s);                  \
+    }                                                            \
+    return false;                                                \
+}
+
+GEN_OPFVF_WIDEN_TRANS(vfwadd_vf)
+GEN_OPFVF_WIDEN_TRANS(vfwsub_vf)
+
+static bool opfwv_widen_check(DisasContext *s, arg_rmrr *a)
+{
+    return (vext_check_isa_ill(s) &&
+            vext_check_overlap_mask(s, a->rd, a->vm, true) &&
+            vext_check_reg(s, a->rd, true) &&
+            vext_check_reg(s, a->rs2, true) &&
+            vext_check_reg(s, a->rs1, false) &&
+            vext_check_overlap_group(a->rd, 2 << s->lmul, a->rs1,
+                                     1 << s->lmul) &&
+            (s->lmul < 0x3) && (s->sew < 0x3) && (s->sew != 0));
+}
+
+/* WIDEN OPFVV with WIDEN */
+#define GEN_OPFWV_WIDEN_TRANS(NAME)                                \
+static bool trans_##NAME(DisasContext *s, arg_rmrr *a)             \
+{                                                                  \
+    if (opfwv_widen_check(s, a)) {                                 \
+        uint32_t data = 0;                                         \
+        static gen_helper_gvec_4_ptr * const fns[2] = {            \
+            gen_helper_##NAME##_h, gen_helper_##NAME##_w,          \
+        };                                                         \
+        TCGLabel *over = gen_new_label();                          \
+        gen_set_rm(s, 7);                                          \
+        tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);          \
+                                                                   \
+        data = FIELD_DP32(data, VDATA, MLEN, s->mlen);             \
+        data = FIELD_DP32(data, VDATA, VM, a->vm);                 \
+        data = FIELD_DP32(data, VDATA, LMUL, s->lmul);             \
+        tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0),     \
+                           vreg_ofs(s, a->rs1),                    \
+                           vreg_ofs(s, a->rs2), cpu_env, 0,        \
+                           s->vlen / 8, data, fns[s->sew - 1]);    \
+        gen_set_label(over);                                       \
+        return true;                                               \
+    }                                                              \
+    return false;                                                  \
+}
+
+GEN_OPFWV_WIDEN_TRANS(vfwadd_wv)
+GEN_OPFWV_WIDEN_TRANS(vfwsub_wv)
+
+static bool opfwf_widen_check(DisasContext *s, arg_rmrr *a)
+{
+    return (vext_check_isa_ill(s) &&
+            vext_check_overlap_mask(s, a->rd, a->vm, true) &&
+            vext_check_reg(s, a->rd, true) &&
+            vext_check_reg(s, a->rs2, true) &&
+            (s->lmul < 0x3) && (s->sew < 0x3) && (s->sew != 0));
+}
+
+/* WIDEN OPFVF with WIDEN */
+#define GEN_OPFWF_WIDEN_TRANS(NAME)                              \
+static bool trans_##NAME(DisasContext *s, arg_rmrr *a)           \
+{                                                                \
+    if (opfwf_widen_check(s, a)) {                               \
+        uint32_t data = 0;                                       \
+        static gen_helper_opfvf *const fns[2] = {                \
+            gen_helper_##NAME##_h, gen_helper_##NAME##_w,        \
+        };                                                       \
+        gen_set_rm(s, 7);                                        \
+        data = FIELD_DP32(data, VDATA, MLEN, s->mlen);           \
+        data = FIELD_DP32(data, VDATA, VM, a->vm);               \
+        data = FIELD_DP32(data, VDATA, LMUL, s->lmul);           \
+        return opfvf_trans(a->rd, a->rs1, a->rs2, data,          \
+                           fns[s->sew - 1], s);                  \
+    }                                                            \
+    return false;                                                \
+}
+
+GEN_OPFWF_WIDEN_TRANS(vfwadd_wf)
+GEN_OPFWF_WIDEN_TRANS(vfwsub_wf)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index a2bbe84..b31f52b 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -3278,3 +3278,86 @@ RVVCALL(OPFVF2, vfrsub_vf_d, OP_UUU_D, H8, H8, float64_rsub)
 GEN_VEXT_VF(vfrsub_vf_h, 2, 2, clearh)
 GEN_VEXT_VF(vfrsub_vf_w, 4, 4, clearl)
 GEN_VEXT_VF(vfrsub_vf_d, 8, 8, clearq)
+
+/* Vector Widening Floating-Point Add/Subtract Instructions */
+static uint32_t vfwadd16(uint16_t a, uint16_t b, float_status *s)
+{
+    return float32_add(float16_to_float32(a, true, s),
+            float16_to_float32(b, true, s), s);
+}
+
+static uint64_t vfwadd32(uint32_t a, uint32_t b, float_status *s)
+{
+    return float64_add(float32_to_float64(a, s),
+            float32_to_float64(b, s), s);
+
+}
+
+RVVCALL(OPFVV2, vfwadd_vv_h, WOP_UUU_H, H4, H2, H2, vfwadd16)
+RVVCALL(OPFVV2, vfwadd_vv_w, WOP_UUU_W, H8, H4, H4, vfwadd32)
+GEN_VEXT_VV_ENV(vfwadd_vv_h, 2, 4, clearl)
+GEN_VEXT_VV_ENV(vfwadd_vv_w, 4, 8, clearq)
+RVVCALL(OPFVF2, vfwadd_vf_h, WOP_UUU_H, H4, H2, vfwadd16)
+RVVCALL(OPFVF2, vfwadd_vf_w, WOP_UUU_W, H8, H4, vfwadd32)
+GEN_VEXT_VF(vfwadd_vf_h, 2, 4, clearl)
+GEN_VEXT_VF(vfwadd_vf_w, 4, 8, clearq)
+
+static uint32_t vfwsub16(uint16_t a, uint16_t b, float_status *s)
+{
+    return float32_sub(float16_to_float32(a, true, s),
+            float16_to_float32(b, true, s), s);
+}
+
+static uint64_t vfwsub32(uint32_t a, uint32_t b, float_status *s)
+{
+    return float64_sub(float32_to_float64(a, s),
+            float32_to_float64(b, s), s);
+
+}
+
+RVVCALL(OPFVV2, vfwsub_vv_h, WOP_UUU_H, H4, H2, H2, vfwsub16)
+RVVCALL(OPFVV2, vfwsub_vv_w, WOP_UUU_W, H8, H4, H4, vfwsub32)
+GEN_VEXT_VV_ENV(vfwsub_vv_h, 2, 4, clearl)
+GEN_VEXT_VV_ENV(vfwsub_vv_w, 4, 8, clearq)
+RVVCALL(OPFVF2, vfwsub_vf_h, WOP_UUU_H, H4, H2, vfwsub16)
+RVVCALL(OPFVF2, vfwsub_vf_w, WOP_UUU_W, H8, H4, vfwsub32)
+GEN_VEXT_VF(vfwsub_vf_h, 2, 4, clearl)
+GEN_VEXT_VF(vfwsub_vf_w, 4, 8, clearq)
+
+static uint32_t vfwaddw16(uint32_t a, uint16_t b, float_status *s)
+{
+    return float32_add(a, float16_to_float32(b, true, s), s);
+}
+
+static uint64_t vfwaddw32(uint64_t a, uint32_t b, float_status *s)
+{
+    return float64_add(a, float32_to_float64(b, s), s);
+}
+
+RVVCALL(OPFVV2, vfwadd_wv_h, WOP_WUUU_H, H4, H2, H2, vfwaddw16)
+RVVCALL(OPFVV2, vfwadd_wv_w, WOP_WUUU_W, H8, H4, H4, vfwaddw32)
+GEN_VEXT_VV_ENV(vfwadd_wv_h, 2, 4, clearl)
+GEN_VEXT_VV_ENV(vfwadd_wv_w, 4, 8, clearq)
+RVVCALL(OPFVF2, vfwadd_wf_h, WOP_WUUU_H, H4, H2, vfwaddw16)
+RVVCALL(OPFVF2, vfwadd_wf_w, WOP_WUUU_W, H8, H4, vfwaddw32)
+GEN_VEXT_VF(vfwadd_wf_h, 2, 4, clearl)
+GEN_VEXT_VF(vfwadd_wf_w, 4, 8, clearq)
+
+static uint32_t vfwsubw16(uint32_t a, uint16_t b, float_status *s)
+{
+    return float32_sub(a, float16_to_float32(b, true, s), s);
+}
+
+static uint64_t vfwsubw32(uint64_t a, uint32_t b, float_status *s)
+{
+    return float64_sub(a, float32_to_float64(b, s), s);
+}
+
+RVVCALL(OPFVV2, vfwsub_wv_h, WOP_WUUU_H, H4, H2, H2, vfwsubw16)
+RVVCALL(OPFVV2, vfwsub_wv_w, WOP_WUUU_W, H8, H4, H4, vfwsubw32)
+GEN_VEXT_VV_ENV(vfwsub_wv_h, 2, 4, clearl)
+GEN_VEXT_VV_ENV(vfwsub_wv_w, 4, 8, clearq)
+RVVCALL(OPFVF2, vfwsub_wf_h, WOP_WUUU_H, H4, H2, vfwsubw16)
+RVVCALL(OPFVF2, vfwsub_wf_w, WOP_WUUU_W, H8, H4, vfwsubw32)
+GEN_VEXT_VF(vfwsub_wf_h, 2, 4, clearl)
+GEN_VEXT_VF(vfwsub_wf_w, 4, 8, clearq)