diff mbox series

[v2,46/67] target/arm: Convert SQSHL and UQSHL (register) to gvec

Message ID 20240524232121.284515-47-richard.henderson@linaro.org
State Superseded
Headers show
Series target/arm: Convert a64 advsimd to decodetree (part 1) | expand

Commit Message

Richard Henderson May 24, 2024, 11:21 p.m. UTC
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/arm/helper.h             |  8 ++++++++
 target/arm/tcg/translate.h      |  4 ++++
 target/arm/tcg/neon-dp.decode   | 10 ++-------
 target/arm/tcg/gengvec.c        | 24 ++++++++++++++++++++++
 target/arm/tcg/neon_helper.c    | 36 +++++++++++++++++++++++++++++++++
 target/arm/tcg/translate-a64.c  | 17 +++++++---------
 target/arm/tcg/translate-neon.c |  6 ++----
 7 files changed, 83 insertions(+), 22 deletions(-)

Comments

Peter Maydell May 28, 2024, 3:53 p.m. UTC | #1
On Sat, 25 May 2024 at 00:28, Richard Henderson
<richard.henderson@linaro.org> wrote:
>
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
> ---
>  target/arm/helper.h             |  8 ++++++++
>  target/arm/tcg/translate.h      |  4 ++++
>  target/arm/tcg/neon-dp.decode   | 10 ++-------
>  target/arm/tcg/gengvec.c        | 24 ++++++++++++++++++++++
>  target/arm/tcg/neon_helper.c    | 36 +++++++++++++++++++++++++++++++++
>  target/arm/tcg/translate-a64.c  | 17 +++++++---------
>  target/arm/tcg/translate-neon.c |  6 ++----
>  7 files changed, 83 insertions(+), 22 deletions(-)


> +#define NEON_GVEC_VOP2_ENV(name, vtype) \
> +void HELPER(name)(void *vd, void *vn, void *vm, void *venv, uint32_t desc) \
> +{                                                               \
> +    intptr_t i, opr_sz = simd_oprsz(desc);                      \
> +    vtype *d = vd, *n = vn, *m = vm;                            \
> +    CPUARMState *env = venv;                                    \
> +    for (i = 0; i < opr_sz / sizeof(vtype); i++) {              \
> +        NEON_FN(d[i], n[i], m[i]);                              \
> +    }                                                           \
> +    clear_tail(d, opr_sz, simd_maxsz(desc));                    \
> +}
> +

Same question about H macros as for patch 44.

-- PMM
Richard Henderson May 28, 2024, 5:31 p.m. UTC | #2
On 5/28/24 08:53, Peter Maydell wrote:
> On Sat, 25 May 2024 at 00:28, Richard Henderson
> <richard.henderson@linaro.org> wrote:
>>
>> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
>> ---
>>   target/arm/helper.h             |  8 ++++++++
>>   target/arm/tcg/translate.h      |  4 ++++
>>   target/arm/tcg/neon-dp.decode   | 10 ++-------
>>   target/arm/tcg/gengvec.c        | 24 ++++++++++++++++++++++
>>   target/arm/tcg/neon_helper.c    | 36 +++++++++++++++++++++++++++++++++
>>   target/arm/tcg/translate-a64.c  | 17 +++++++---------
>>   target/arm/tcg/translate-neon.c |  6 ++----
>>   7 files changed, 83 insertions(+), 22 deletions(-)
> 
> 
>> +#define NEON_GVEC_VOP2_ENV(name, vtype) \
>> +void HELPER(name)(void *vd, void *vn, void *vm, void *venv, uint32_t desc) \
>> +{                                                               \
>> +    intptr_t i, opr_sz = simd_oprsz(desc);                      \
>> +    vtype *d = vd, *n = vn, *m = vm;                            \
>> +    CPUARMState *env = venv;                                    \
>> +    for (i = 0; i < opr_sz / sizeof(vtype); i++) {              \
>> +        NEON_FN(d[i], n[i], m[i]);                              \
>> +    }                                                           \
>> +    clear_tail(d, opr_sz, simd_maxsz(desc));                    \
>> +}
>> +
> 
> Same question about H macros as for patch 44.

No H macros needed.


r~
diff mbox series

Patch

diff --git a/target/arm/helper.h b/target/arm/helper.h
index 25eb7bf5df..f345087ddb 100644
--- a/target/arm/helper.h
+++ b/target/arm/helper.h
@@ -326,6 +326,14 @@  DEF_HELPER_3(neon_qrshl_u32, i32, env, i32, i32)
 DEF_HELPER_3(neon_qrshl_s32, i32, env, i32, i32)
 DEF_HELPER_3(neon_qrshl_u64, i64, env, i64, i64)
 DEF_HELPER_3(neon_qrshl_s64, i64, env, i64, i64)
+DEF_HELPER_FLAGS_5(neon_sqshl_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(neon_sqshl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(neon_sqshl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(neon_sqshl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(neon_uqshl_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(neon_uqshl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(neon_uqshl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(neon_uqshl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
 
 DEF_HELPER_FLAGS_4(gvec_srshl_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(gvec_srshl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
diff --git a/target/arm/tcg/translate.h b/target/arm/tcg/translate.h
index ea63ffc47b..6c6d4d49e7 100644
--- a/target/arm/tcg/translate.h
+++ b/target/arm/tcg/translate.h
@@ -463,6 +463,10 @@  void gen_gvec_srshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
                     uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz);
 void gen_gvec_urshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
                     uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz);
+void gen_neon_sqshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
+                    uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz);
+void gen_neon_uqshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
+                    uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz);
 
 void gen_cmtst_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b);
 void gen_ushl_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b);
diff --git a/target/arm/tcg/neon-dp.decode b/target/arm/tcg/neon-dp.decode
index 8525c65c0d..6d4996b8d8 100644
--- a/target/arm/tcg/neon-dp.decode
+++ b/target/arm/tcg/neon-dp.decode
@@ -109,14 +109,8 @@  VSHL_U_3s        1111 001 1 0 . .. .... .... 0100 . . . 0 .... @3same_rev
 @3same_64_rev    .... ... . . . 11 .... .... .... . q:1 . . .... \
                  &3same vm=%vn_dp vn=%vm_dp vd=%vd_dp size=3
 
-{
-  VQSHL_S64_3s   1111 001 0 0 . .. .... .... 0100 . . . 1 .... @3same_64_rev
-  VQSHL_S_3s     1111 001 0 0 . .. .... .... 0100 . . . 1 .... @3same_rev
-}
-{
-  VQSHL_U64_3s   1111 001 1 0 . .. .... .... 0100 . . . 1 .... @3same_64_rev
-  VQSHL_U_3s     1111 001 1 0 . .. .... .... 0100 . . . 1 .... @3same_rev
-}
+VQSHL_S_3s       1111 001 0 0 . .. .... .... 0100 . . . 1 .... @3same_rev
+VQSHL_U_3s       1111 001 1 0 . .. .... .... 0100 . . . 1 .... @3same_rev
 VRSHL_S_3s       1111 001 0 0 . .. .... .... 0101 . . . 0 .... @3same_rev
 VRSHL_U_3s       1111 001 1 0 . .. .... .... 0101 . . . 0 .... @3same_rev
 {
diff --git a/target/arm/tcg/gengvec.c b/target/arm/tcg/gengvec.c
index d9a9132722..773dbf41d3 100644
--- a/target/arm/tcg/gengvec.c
+++ b/target/arm/tcg/gengvec.c
@@ -1239,6 +1239,30 @@  void gen_gvec_urshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
     tcg_gen_gvec_3_ool(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, 0, fns[vece]);
 }
 
+void gen_neon_sqshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
+                    uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz)
+{
+    static gen_helper_gvec_3_ptr * const fns[] = {
+        gen_helper_neon_sqshl_b, gen_helper_neon_sqshl_h,
+        gen_helper_neon_sqshl_s, gen_helper_neon_sqshl_d,
+    };
+    tcg_debug_assert(vece <= MO_64);
+    tcg_gen_gvec_3_ptr(rd_ofs, rn_ofs, rm_ofs, tcg_env,
+                       opr_sz, max_sz, 0, fns[vece]);
+}
+
+void gen_neon_uqshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
+                    uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz)
+{
+    static gen_helper_gvec_3_ptr * const fns[] = {
+        gen_helper_neon_uqshl_b, gen_helper_neon_uqshl_h,
+        gen_helper_neon_uqshl_s, gen_helper_neon_uqshl_d,
+    };
+    tcg_debug_assert(vece <= MO_64);
+    tcg_gen_gvec_3_ptr(rd_ofs, rn_ofs, rm_ofs, tcg_env,
+                       opr_sz, max_sz, 0, fns[vece]);
+}
+
 void gen_uqadd_bhs(TCGv_i64 res, TCGv_i64 qc, TCGv_i64 a, TCGv_i64 b, MemOp esz)
 {
     uint64_t max = MAKE_64BIT_MASK(0, 8 << esz);
diff --git a/target/arm/tcg/neon_helper.c b/target/arm/tcg/neon_helper.c
index 516ecc1dcb..88301f0dcb 100644
--- a/target/arm/tcg/neon_helper.c
+++ b/target/arm/tcg/neon_helper.c
@@ -129,6 +129,18 @@  void HELPER(name)(void *vd, void *vn, void *vm, uint32_t desc) \
     clear_tail(d, opr_sz, simd_maxsz(desc));                    \
 }
 
+#define NEON_GVEC_VOP2_ENV(name, vtype) \
+void HELPER(name)(void *vd, void *vn, void *vm, void *venv, uint32_t desc) \
+{                                                               \
+    intptr_t i, opr_sz = simd_oprsz(desc);                      \
+    vtype *d = vd, *n = vn, *m = vm;                            \
+    CPUARMState *env = venv;                                    \
+    for (i = 0; i < opr_sz / sizeof(vtype); i++) {              \
+        NEON_FN(d[i], n[i], m[i]);                              \
+    }                                                           \
+    clear_tail(d, opr_sz, simd_maxsz(desc));                    \
+}
+
 /* Pairwise operations.  */
 /* For 32-bit elements each segment only contains a single element, so
    the elementwise and pairwise operations are the same.  */
@@ -339,11 +351,23 @@  uint64_t HELPER(neon_rshl_u64)(uint64_t val, uint64_t shift)
 #define NEON_FN(dest, src1, src2) \
     (dest = do_uqrshl_bhs(src1, (int8_t)src2, 8, false, env->vfp.qc))
 NEON_VOP_ENV(qshl_u8, neon_u8, 4)
+NEON_GVEC_VOP2_ENV(neon_uqshl_b, uint8_t)
 #undef NEON_FN
 
 #define NEON_FN(dest, src1, src2) \
     (dest = do_uqrshl_bhs(src1, (int8_t)src2, 16, false, env->vfp.qc))
 NEON_VOP_ENV(qshl_u16, neon_u16, 2)
+NEON_GVEC_VOP2_ENV(neon_uqshl_h, uint16_t)
+#undef NEON_FN
+
+#define NEON_FN(dest, src1, src2) \
+    (dest = do_uqrshl_bhs(src1, (int8_t)src2, 32, false, env->vfp.qc))
+NEON_GVEC_VOP2_ENV(neon_uqshl_s, uint32_t)
+#undef NEON_FN
+
+#define NEON_FN(dest, src1, src2) \
+    (dest = do_uqrshl_d(src1, (int8_t)src2, false, env->vfp.qc))
+NEON_GVEC_VOP2_ENV(neon_uqshl_d, uint64_t)
 #undef NEON_FN
 
 uint32_t HELPER(neon_qshl_u32)(CPUARMState *env, uint32_t val, uint32_t shift)
@@ -359,11 +383,23 @@  uint64_t HELPER(neon_qshl_u64)(CPUARMState *env, uint64_t val, uint64_t shift)
 #define NEON_FN(dest, src1, src2) \
     (dest = do_sqrshl_bhs(src1, (int8_t)src2, 8, false, env->vfp.qc))
 NEON_VOP_ENV(qshl_s8, neon_s8, 4)
+NEON_GVEC_VOP2_ENV(neon_sqshl_b, int8_t)
 #undef NEON_FN
 
 #define NEON_FN(dest, src1, src2) \
     (dest = do_sqrshl_bhs(src1, (int8_t)src2, 16, false, env->vfp.qc))
 NEON_VOP_ENV(qshl_s16, neon_s16, 2)
+NEON_GVEC_VOP2_ENV(neon_sqshl_h, int16_t)
+#undef NEON_FN
+
+#define NEON_FN(dest, src1, src2) \
+    (dest = do_sqrshl_bhs(src1, (int8_t)src2, 32, false, env->vfp.qc))
+NEON_GVEC_VOP2_ENV(neon_sqshl_s, int32_t)
+#undef NEON_FN
+
+#define NEON_FN(dest, src1, src2) \
+    (dest = do_sqrshl_d(src1, (int8_t)src2, false, env->vfp.qc))
+NEON_GVEC_VOP2_ENV(neon_sqshl_d, int64_t)
 #undef NEON_FN
 
 uint32_t HELPER(neon_qshl_s32)(CPUARMState *env, uint32_t val, uint32_t shift)
diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index 24f2025997..50b653bb4d 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -10935,6 +10935,13 @@  static void disas_simd_3same_int(DisasContext *s, uint32_t insn)
     }
 
     switch (opcode) {
+    case 0x09: /* SQSHL, UQSHL */
+        if (u) {
+            gen_gvec_fn3(s, is_q, rd, rn, rm, gen_neon_uqshl, size);
+        } else {
+            gen_gvec_fn3(s, is_q, rd, rn, rm, gen_neon_sqshl, size);
+        }
+        return;
     case 0x0c: /* SMAX, UMAX */
         if (u) {
             gen_gvec_fn3(s, is_q, rd, rn, rm, tcg_gen_gvec_umax, size);
@@ -11076,16 +11083,6 @@  static void disas_simd_3same_int(DisasContext *s, uint32_t insn)
                 genfn = fns[size][u];
                 break;
             }
-            case 0x9: /* SQSHL, UQSHL */
-            {
-                static NeonGenTwoOpEnvFn * const fns[3][2] = {
-                    { gen_helper_neon_qshl_s8, gen_helper_neon_qshl_u8 },
-                    { gen_helper_neon_qshl_s16, gen_helper_neon_qshl_u16 },
-                    { gen_helper_neon_qshl_s32, gen_helper_neon_qshl_u32 },
-                };
-                genenvfn = fns[size][u];
-                break;
-            }
             case 0xb: /* SQRSHL, UQRSHL */
             {
                 static NeonGenTwoOpEnvFn * const fns[3][2] = {
diff --git a/target/arm/tcg/translate-neon.c b/target/arm/tcg/translate-neon.c
index 337488bbf1..a3eec47092 100644
--- a/target/arm/tcg/translate-neon.c
+++ b/target/arm/tcg/translate-neon.c
@@ -796,6 +796,8 @@  DO_3SAME(VQSUB_S, gen_gvec_sqsub_qc)
 DO_3SAME(VQSUB_U, gen_gvec_uqsub_qc)
 DO_3SAME(VRSHL_S, gen_gvec_srshl)
 DO_3SAME(VRSHL_U, gen_gvec_urshl)
+DO_3SAME(VQSHL_S, gen_neon_sqshl)
+DO_3SAME(VQSHL_U, gen_neon_uqshl)
 
 /* These insns are all gvec_bitsel but with the inputs in various orders. */
 #define DO_3SAME_BITSEL(INSN, O1, O2, O3)                               \
@@ -931,8 +933,6 @@  DO_SHA2(SHA256SU1, gen_helper_crypto_sha256su1)
     }                                                                   \
     DO_3SAME_64(INSN, gen_##INSN##_elt)
 
-DO_3SAME_64_ENV(VQSHL_S64, gen_helper_neon_qshl_s64)
-DO_3SAME_64_ENV(VQSHL_U64, gen_helper_neon_qshl_u64)
 DO_3SAME_64_ENV(VQRSHL_S64, gen_helper_neon_qrshl_s64)
 DO_3SAME_64_ENV(VQRSHL_U64, gen_helper_neon_qrshl_u64)
 
@@ -1000,8 +1000,6 @@  DO_3SAME_32(VHSUB_U, hsub_u)
 DO_3SAME_32(VRHADD_S, rhadd_s)
 DO_3SAME_32(VRHADD_U, rhadd_u)
 
-DO_3SAME_32_ENV(VQSHL_S, qshl_s)
-DO_3SAME_32_ENV(VQSHL_U, qshl_u)
 DO_3SAME_32_ENV(VQRSHL_S, qrshl_s)
 DO_3SAME_32_ENV(VQRSHL_U, qrshl_u)