target/riscv: Refactor some of the generic vector functionality

Take some functions/macros out of `vector_helper` and put them in a new
module called `vector_internals`. This ensures they can be used by both
vector and vector-crypto helpers (latter implemented in proceeding
commits).

Signed-off-by: Kiran Ostrolenk <kiran.ostrolenk@codethink.co.uk>
Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
Signed-off-by: Max Chou <max.chou@sifive.com>
Acked-by: Alistair Francis <alistair.francis@wdc.com>
Message-ID: <20230711165917.2629866-2-max.chou@sifive.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>

1 files changed, 1 insertions, 200 deletions

diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 379f03df06..1f29236a63 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -27,6 +27,7 @@
 #include "fpu/softfloat.h"
 #include "tcg/tcg-gvec-desc.h"
 #include "internals.h"
+#include "vector_internals.h"
 #include <math.h>
 
 target_ulong HELPER(vsetvl)(CPURISCVState *env, target_ulong s1,
@@ -74,68 +75,6 @@ target_ulong HELPER(vsetvl)(CPURISCVState *env, target_ulong s1,
 }
 
 /*
- * 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
-
-static inline uint32_t vext_nf(uint32_t desc)
-{
-    return FIELD_EX32(simd_data(desc), VDATA, NF);
-}
-
-static inline uint32_t vext_vm(uint32_t desc)
-{
-    return FIELD_EX32(simd_data(desc), VDATA, VM);
-}
-
-/*
- * Encode LMUL to lmul as following:
- *     LMUL    vlmul    lmul
- *      1       000       0
- *      2       001       1
- *      4       010       2
- *      8       011       3
- *      -       100       -
- *     1/8      101      -3
- *     1/4      110      -2
- *     1/2      111      -1
- */
-static inline int32_t vext_lmul(uint32_t desc)
-{
-    return sextract32(FIELD_EX32(simd_data(desc), VDATA, LMUL), 0, 3);
-}
-
-static inline uint32_t vext_vta(uint32_t desc)
-{
-    return FIELD_EX32(simd_data(desc), VDATA, VTA);
-}
-
-static inline uint32_t vext_vma(uint32_t desc)
-{
-    return FIELD_EX32(simd_data(desc), VDATA, VMA);
-}
-
-static inline uint32_t vext_vta_all_1s(uint32_t desc)
-{
-    return FIELD_EX32(simd_data(desc), VDATA, VTA_ALL_1S);
-}
-
-/*
  * Get the maximum number of elements can be operated.
  *
  * log2_esz: log2 of element size in bytes.
@@ -153,21 +92,6 @@ static inline uint32_t vext_max_elems(uint32_t desc, uint32_t log2_esz)
     return scale < 0 ? vlenb >> -scale : vlenb << scale;
 }
 
-/*
- * Get number of total elements, including prestart, body and tail elements.
- * Note that when LMUL < 1, the tail includes the elements past VLMAX that
- * are held in the same vector register.
- */
-static inline uint32_t vext_get_total_elems(CPURISCVState *env, uint32_t desc,
-                                            uint32_t esz)
-{
-    uint32_t vlenb = simd_maxsz(desc);
-    uint32_t sew = 1 << FIELD_EX64(env->vtype, VTYPE, VSEW);
-    int8_t emul = ctzl(esz) - ctzl(sew) + vext_lmul(desc) < 0 ? 0 :
-                  ctzl(esz) - ctzl(sew) + vext_lmul(desc);
-    return (vlenb << emul) / esz;
-}
-
 static inline target_ulong adjust_addr(CPURISCVState *env, target_ulong addr)
 {
     return (addr & ~env->cur_pmmask) | env->cur_pmbase;
@@ -200,20 +124,6 @@ static void probe_pages(CPURISCVState *env, target_ulong addr,
     }
 }
 
-/* set agnostic elements to 1s */
-static void vext_set_elems_1s(void *base, uint32_t is_agnostic, uint32_t cnt,
-                              uint32_t tot)
-{
-    if (is_agnostic == 0) {
-        /* policy undisturbed */
-        return;
-    }
-    if (tot - cnt == 0) {
-        return;
-    }
-    memset(base + cnt, -1, tot - cnt);
-}
-
 static inline void vext_set_elem_mask(void *v0, int index,
                                       uint8_t value)
 {
@@ -223,18 +133,6 @@ static inline void vext_set_elem_mask(void *v0, int index,
     ((uint64_t *)v0)[idx] = deposit64(old, pos, 1, value);
 }
 
-/*
- * Earlier designs (pre-0.9) had a varying number of bits
- * per mask value (MLEN). In the 0.9 design, MLEN=1.
- * (Section 4.5)
- */
-static inline int vext_elem_mask(void *v0, int index)
-{
-    int idx = index / 64;
-    int pos = index  % 64;
-    return (((uint64_t *)v0)[idx] >> pos) & 1;
-}
-
 /* elements operations for load and store */
 typedef void vext_ldst_elem_fn(CPURISCVState *env, abi_ptr addr,
                                uint32_t idx, void *vd, uintptr_t retaddr);
@@ -729,18 +627,11 @@ 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
@@ -764,16 +655,6 @@ 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
 
-/* 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);                           \
-}
 #define DO_SUB(N, M) (N - M)
 #define DO_RSUB(N, M) (M - N)
 
@@ -786,40 +667,6 @@ RVVCALL(OPIVV2, vsub_vv_h, OP_SSS_H, H2, H2, H2, DO_SUB)
 RVVCALL(OPIVV2, vsub_vv_w, OP_SSS_W, H4, H4, H4, DO_SUB)
 RVVCALL(OPIVV2, vsub_vv_d, OP_SSS_D, H8, H8, H8, DO_SUB)
 
-static void do_vext_vv(void *vd, void *v0, void *vs1, void *vs2,
-                       CPURISCVState *env, uint32_t desc,
-                       opivv2_fn *fn, uint32_t esz)
-{
-    uint32_t vm = vext_vm(desc);
-    uint32_t vl = env->vl;
-    uint32_t total_elems = vext_get_total_elems(env, desc, esz);
-    uint32_t vta = vext_vta(desc);
-    uint32_t vma = vext_vma(desc);
-    uint32_t i;
-
-    for (i = env->vstart; i < vl; i++) {
-        if (!vm && !vext_elem_mask(v0, i)) {
-            /* set masked-off elements to 1s */
-            vext_set_elems_1s(vd, vma, i * esz, (i + 1) * esz);
-            continue;
-        }
-        fn(vd, vs1, vs2, i);
-    }
-    env->vstart = 0;
-    /* set tail elements to 1s */
-    vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz);
-}
-
-/* generate the helpers for OPIVV */
-#define GEN_VEXT_VV(NAME, ESZ)                            \
-void HELPER(NAME)(void *vd, void *v0, void *vs1,          \
-                  void *vs2, CPURISCVState *env,          \
-                  uint32_t desc)                          \
-{                                                         \
-    do_vext_vv(vd, v0, vs1, vs2, env, desc,               \
-               do_##NAME, ESZ);                           \
-}
-
 GEN_VEXT_VV(vadd_vv_b, 1)
 GEN_VEXT_VV(vadd_vv_h, 2)
 GEN_VEXT_VV(vadd_vv_w, 4)
@@ -829,18 +676,6 @@ GEN_VEXT_VV(vsub_vv_h, 2)
 GEN_VEXT_VV(vsub_vv_w, 4)
 GEN_VEXT_VV(vsub_vv_d, 8)
 
-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);                      \
-}
 
 RVVCALL(OPIVX2, vadd_vx_b, OP_SSS_B, H1, H1, DO_ADD)
 RVVCALL(OPIVX2, vadd_vx_h, OP_SSS_H, H2, H2, DO_ADD)
@@ -855,40 +690,6 @@ RVVCALL(OPIVX2, vrsub_vx_h, OP_SSS_H, H2, H2, DO_RSUB)
 RVVCALL(OPIVX2, vrsub_vx_w, OP_SSS_W, H4, H4, DO_RSUB)
 RVVCALL(OPIVX2, vrsub_vx_d, OP_SSS_D, H8, H8, DO_RSUB)
 
-static void do_vext_vx(void *vd, void *v0, target_long s1, void *vs2,
-                       CPURISCVState *env, uint32_t desc,
-                       opivx2_fn fn, uint32_t esz)
-{
-    uint32_t vm = vext_vm(desc);
-    uint32_t vl = env->vl;
-    uint32_t total_elems = vext_get_total_elems(env, desc, esz);
-    uint32_t vta = vext_vta(desc);
-    uint32_t vma = vext_vma(desc);
-    uint32_t i;
-
-    for (i = env->vstart; i < vl; i++) {
-        if (!vm && !vext_elem_mask(v0, i)) {
-            /* set masked-off elements to 1s */
-            vext_set_elems_1s(vd, vma, i * esz, (i + 1) * esz);
-            continue;
-        }
-        fn(vd, s1, vs2, i);
-    }
-    env->vstart = 0;
-    /* set tail elements to 1s */
-    vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz);
-}
-
-/* generate the helpers for OPIVX */
-#define GEN_VEXT_VX(NAME, ESZ)                            \
-void HELPER(NAME)(void *vd, void *v0, target_ulong s1,    \
-                  void *vs2, CPURISCVState *env,          \
-                  uint32_t desc)                          \
-{                                                         \
-    do_vext_vx(vd, v0, s1, vs2, env, desc,                \
-               do_##NAME, ESZ);                           \
-}
-
 GEN_VEXT_VX(vadd_vx_b, 1)
 GEN_VEXT_VX(vadd_vx_h, 2)
 GEN_VEXT_VX(vadd_vx_w, 4)