From: Kiran Ostrolenk <kiran.ostrolenk@xxxxxxxxxxxxxxx>
This refactoring ensures these functions/macros can be used by both
vector and vector-crypto helpers (latter implemented in proceeding
commit).
Also moves the checks out of `do_opiv{v,x,i}_gvec{,_shift}` functions
and into the corresponding macros. This enables the functions to be
reused in proceeding commit without check duplication.
Co-authored-by: Nazar Kazakov <nazar.kazakov@xxxxxxxxxxxxxxx>
Signed-off-by: Nazar Kazakov <nazar.kazakov@xxxxxxxxxxxxxxx>
Signed-off-by: Kiran Ostrolenk <kiran.ostrolenk@xxxxxxxxxxxxxxx>
---
target/riscv/insn_trans/trans_rvv.c.inc | 28 +++++++--------
target/riscv/vector_helper.c | 45 -----------------------
target/riscv/vector_internals.h | 48 +++++++++++++++++++++++++
3 files changed, 60 insertions(+), 61 deletions(-)
diff --git a/target/riscv/insn_trans/trans_rvv.c.inc b/target/riscv/insn_trans/trans_rvv.c.inc
index 4106bd6994..bb5e2c5407 100644
--- a/target/riscv/insn_trans/trans_rvv.c.inc
+++ b/target/riscv/insn_trans/trans_rvv.c.inc
@@ -1187,9 +1187,6 @@ do_opivv_gvec(DisasContext *s, arg_rmrr *a, GVecGen3Fn *gvec_fn,
gen_helper_gvec_4_ptr *fn)
{
TCGLabel *over = gen_new_label();
- if (!opivv_check(s, a)) {
- return false;
- }
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
@@ -1223,6 +1220,9 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \
gen_helper_##NAME##_b, gen_helper_##NAME##_h, \
gen_helper_##NAME##_w, gen_helper_##NAME##_d, \
}; \
+ if (!opivv_check(s, a)) { \
+ return false; \
+ } \
return do_opivv_gvec(s, a, tcg_gen_gvec_##SUF, fns[s->sew]); \
}
@@ -1282,10 +1282,6 @@ static inline bool
do_opivx_gvec(DisasContext *s, arg_rmrr *a, GVecGen2sFn *gvec_fn,
gen_helper_opivx *fn)
{
- if (!opivx_check(s, a)) {
- return false;
- }
-
if (a->vm && s->vl_eq_vlmax && !(s->vta && s->lmul < 0)) {
TCGv_i64 src1 = tcg_temp_new_i64();
@@ -1307,6 +1303,9 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \
gen_helper_##NAME##_b, gen_helper_##NAME##_h, \
gen_helper_##NAME##_w, gen_helper_##NAME##_d, \
}; \
+ if (!opivx_check(s, a)) { \
+ return false; \
+ } \
return do_opivx_gvec(s, a, tcg_gen_gvec_##SUF, fns[s->sew]); \
}
@@ -1439,10 +1438,6 @@ static inline bool
do_opivi_gvec(DisasContext *s, arg_rmrr *a, GVecGen2iFn *gvec_fn,
gen_helper_opivx *fn, imm_mode_t imm_mode)
{
- if (!opivx_check(s, a)) {
- return false;
- }
-
if (a->vm && s->vl_eq_vlmax && !(s->vta && s->lmul < 0)) {
gvec_fn(s->sew, vreg_ofs(s, a->rd), vreg_ofs(s, a->rs2),
extract_imm(s, a->rs1, imm_mode), MAXSZ(s), MAXSZ(s));
@@ -1460,6 +1455,9 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \
gen_helper_##OPIVX##_b, gen_helper_##OPIVX##_h, \
gen_helper_##OPIVX##_w, gen_helper_##OPIVX##_d, \
}; \
+ if (!opivx_check(s, a)) { \
+ return false; \
+ } \
return do_opivi_gvec(s, a, tcg_gen_gvec_##SUF, \
fns[s->sew], IMM_MODE); \
}
@@ -1785,10 +1783,6 @@ static inline bool
do_opivx_gvec_shift(DisasContext *s, arg_rmrr *a, GVecGen2sFn32 *gvec_fn,
gen_helper_opivx *fn)
{
- if (!opivx_check(s, a)) {
- return false;
- }
-
if (a->vm && s->vl_eq_vlmax && !(s->vta && s->lmul < 0)) {
TCGv_i32 src1 = tcg_temp_new_i32();
@@ -1810,7 +1804,9 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \
gen_helper_##NAME##_b, gen_helper_##NAME##_h, \
gen_helper_##NAME##_w, gen_helper_##NAME##_d, \
}; \
- \
+ if (!opivx_check(s, a)) { \
+ return false; \
+ } \
return do_opivx_gvec_shift(s, a, tcg_gen_gvec_##SUF, fns[s->sew]); \
}
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 09b790653e..27fefef10e 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -76,26 +76,6 @@ target_ulong HELPER(vsetvl)(CPURISCVState *env, target_ulong s1,
return vl;
}
-/*
- * Note that vector data is stored in host-endian 64-bit chunks,
- * so addressing units smaller than that needs a host-endian fixup.
- */
-#if HOST_BIG_ENDIAN
-#define H1(x) ((x) ^ 7)
-#define H1_2(x) ((x) ^ 6)
-#define H1_4(x) ((x) ^ 4)
-#define H2(x) ((x) ^ 3)
-#define H4(x) ((x) ^ 1)
-#define H8(x) ((x))
-#else
-#define H1(x) (x)
-#define H1_2(x) (x)
-#define H1_4(x) (x)
-#define H2(x) (x)
-#define H4(x) (x)
-#define H8(x) (x)
-#endif
-
/*
* Get the maximum number of elements can be operated.
*
@@ -657,18 +637,11 @@ GEN_VEXT_ST_WHOLE(vs8r_v, int8_t, ste_b)
*** Vector Integer Arithmetic Instructions
*/
-/* expand macro args before macro */
-#define RVVCALL(macro, ...) macro(__VA_ARGS__)
-
/* (TD, T1, T2, TX1, TX2) */
#define OP_SSS_B int8_t, int8_t, int8_t, int8_t, int8_t
#define OP_SSS_H int16_t, int16_t, int16_t, int16_t, int16_t
#define OP_SSS_W int32_t, int32_t, int32_t, int32_t, int32_t
#define OP_SSS_D int64_t, int64_t, int64_t, int64_t, int64_t
-#define OP_UUU_B uint8_t, uint8_t, uint8_t, uint8_t, uint8_t
-#define OP_UUU_H uint16_t, uint16_t, uint16_t, uint16_t, uint16_t
-#define OP_UUU_W uint32_t, uint32_t, uint32_t, uint32_t, uint32_t
-#define OP_UUU_D uint64_t, uint64_t, uint64_t, uint64_t, uint64_t
#define OP_SUS_B int8_t, uint8_t, int8_t, uint8_t, int8_t
#define OP_SUS_H int16_t, uint16_t, int16_t, uint16_t, int16_t
#define OP_SUS_W int32_t, uint32_t, int32_t, uint32_t, int32_t
@@ -692,14 +665,6 @@ GEN_VEXT_ST_WHOLE(vs8r_v, int8_t, ste_b)
#define NOP_UUU_H uint16_t, uint16_t, uint32_t, uint16_t, uint32_t
#define NOP_UUU_W uint32_t, uint32_t, uint64_t, uint32_t, uint64_t
-
-#define OPIVV2(NAME, TD, T1, T2, TX1, TX2, HD, HS1, HS2, OP) \
-static void do_##NAME(void *vd, void *vs1, void *vs2, int i) \
-{ \
- TX1 s1 = *((T1 *)vs1 + HS1(i)); \
- TX2 s2 = *((T2 *)vs2 + HS2(i)); \
- *((TD *)vd + HD(i)) = OP(s2, s1); \
-}
#define DO_SUB(N, M) (N - M)
#define DO_RSUB(N, M) (M - N)
@@ -721,16 +686,6 @@ GEN_VEXT_VV(vsub_vv_h, 2)
GEN_VEXT_VV(vsub_vv_w, 4)
GEN_VEXT_VV(vsub_vv_d, 8)
-/*
- * (T1)s1 gives the real operator type.
- * (TX1)(T1)s1 expands the operator type of widen or narrow operations.
- */
-#define OPIVX2(NAME, TD, T1, T2, TX1, TX2, HD, HS2, OP) \
-static void do_##NAME(void *vd, target_long s1, void *vs2, int i) \
-{ \
- TX2 s2 = *((T2 *)vs2 + HS2(i)); \
- *((TD *)vd + HD(i)) = OP(s2, (TX1)(T1)s1); \
-}
RVVCALL(OPIVX2, vadd_vx_b, OP_SSS_B, H1, H1, DO_ADD)
RVVCALL(OPIVX2, vadd_vx_h, OP_SSS_H, H2, H2, DO_ADD)
diff --git a/target/riscv/vector_internals.h b/target/riscv/vector_internals.h
index 90500e5df6..749d138beb 100644
--- a/target/riscv/vector_internals.h
+++ b/target/riscv/vector_internals.h
@@ -30,6 +30,26 @@ static inline uint32_t vext_nf(uint32_t desc)
return FIELD_EX32(simd_data(desc), VDATA, NF);
}
+/*
+ * Note that vector data is stored in host-endian 64-bit chunks,
+ * so addressing units smaller than that needs a host-endian fixup.
+ */
+#if HOST_BIG_ENDIAN
+#define H1(x) ((x) ^ 7)
+#define H1_2(x) ((x) ^ 6)
+#define H1_4(x) ((x) ^ 4)
+#define H2(x) ((x) ^ 3)
+#define H4(x) ((x) ^ 1)
+#define H8(x) ((x))
+#else
+#define H1(x) (x)
+#define H1_2(x) (x)
+#define H1_4(x) (x)
+#define H2(x) (x)
+#define H4(x) (x)
+#define H8(x) (x)
+#endif
+
/*
* Encode LMUL to lmul as following:
* LMUL vlmul lmul
@@ -98,9 +118,26 @@ static inline uint32_t vext_get_total_elems(CPURISCVState *env, uint32_t desc,
void vext_set_elems_1s(void *base, uint32_t is_agnostic, uint32_t cnt,
uint32_t tot);
+/* expand macro args before macro */
+#define RVVCALL(macro, ...) macro(__VA_ARGS__)
+
+/* (TD, T1, T2, TX1, TX2) */
+#define OP_UUU_B uint8_t, uint8_t, uint8_t, uint8_t, uint8_t
+#define OP_UUU_H uint16_t, uint16_t, uint16_t, uint16_t, uint16_t
+#define OP_UUU_W uint32_t, uint32_t, uint32_t, uint32_t, uint32_t
+#define OP_UUU_D uint64_t, uint64_t, uint64_t, uint64_t, uint64_t
+
/* operation of two vector elements */
typedef void opivv2_fn(void *vd, void *vs1, void *vs2, int i);
+#define OPIVV2(NAME, TD, T1, T2, TX1, TX2, HD, HS1, HS2, OP) \
+static void do_##NAME(void *vd, void *vs1, void *vs2, int i) \
+{ \
+ TX1 s1 = *((T1 *)vs1 + HS1(i)); \
+ TX2 s2 = *((T2 *)vs2 + HS2(i)); \
+ *((TD *)vd + HD(i)) = OP(s2, s1); \
+}
+
void do_vext_vv(void *vd, void *v0, void *vs1, void *vs2,
CPURISCVState *env, uint32_t desc,
opivv2_fn *fn, uint32_t esz);
@@ -117,6 +154,17 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \
typedef void opivx2_fn(void *vd, target_long s1, void *vs2, int i);
+/*
+ * (T1)s1 gives the real operator type.
+ * (TX1)(T1)s1 expands the operator type of widen or narrow operations.
+ */
+#define OPIVX2(NAME, TD, T1, T2, TX1, TX2, HD, HS2, OP) \
+static void do_##NAME(void *vd, target_long s1, void *vs2, int i) \
+{ \
+ TX2 s2 = *((T2 *)vs2 + HS2(i)); \
+ *((TD *)vd + HD(i)) = OP(s2, (TX1)(T1)s1); \
+}
+
void do_vext_vx(void *vd, void *v0, target_long s1, void *vs2,
CPURISCVState *env, uint32_t desc,
opivx2_fn fn, uint32_t esz);
--
2.39.2
