target/arm: Convert VQSHL, VQSHLU to gvec

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20240912024114.1097832-26-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

6 files changed, 94 insertions, 110 deletions

diff --git a/target/arm/helper.h b/target/arm/helper.h
index b463be38c5..b40589d329 100644
--- a/target/arm/helper.h
+++ b/target/arm/helper.h
@@ -324,6 +324,18 @@ DEF_HELPER_FLAGS_5(neon_uqrshl_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32
 DEF_HELPER_FLAGS_5(neon_uqrshl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_5(neon_uqrshl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_5(neon_uqrshl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(neon_sqshli_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(neon_sqshli_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(neon_sqshli_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(neon_sqshli_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(neon_uqshli_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(neon_uqshli_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(neon_uqshli_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(neon_uqshli_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(neon_sqshlui_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(neon_sqshlui_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(neon_sqshlui_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(neon_sqshlui_d, TCG_CALL_NO_RWG, void, 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/gengvec.c b/target/arm/tcg/gengvec.c
index 3abdc57202..f652520b65 100644
--- a/target/arm/tcg/gengvec.c
+++ b/target/arm/tcg/gengvec.c
@@ -1313,6 +1313,42 @@ void gen_neon_uqrshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
                        opr_sz, max_sz, 0, fns[vece]);
 }
 
+void gen_neon_sqshli(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
+                     int64_t c, uint32_t opr_sz, uint32_t max_sz)
+{
+    static gen_helper_gvec_2_ptr * const fns[] = {
+        gen_helper_neon_sqshli_b, gen_helper_neon_sqshli_h,
+        gen_helper_neon_sqshli_s, gen_helper_neon_sqshli_d,
+    };
+    tcg_debug_assert(vece <= MO_64);
+    tcg_debug_assert(c >= 0 && c <= (8 << vece));
+    tcg_gen_gvec_2_ptr(rd_ofs, rn_ofs, tcg_env, opr_sz, max_sz, c, fns[vece]);
+}
+
+void gen_neon_uqshli(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
+                     int64_t c, uint32_t opr_sz, uint32_t max_sz)
+{
+    static gen_helper_gvec_2_ptr * const fns[] = {
+        gen_helper_neon_uqshli_b, gen_helper_neon_uqshli_h,
+        gen_helper_neon_uqshli_s, gen_helper_neon_uqshli_d,
+    };
+    tcg_debug_assert(vece <= MO_64);
+    tcg_debug_assert(c >= 0 && c <= (8 << vece));
+    tcg_gen_gvec_2_ptr(rd_ofs, rn_ofs, tcg_env, opr_sz, max_sz, c, fns[vece]);
+}
+
+void gen_neon_sqshlui(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
+                      int64_t c, uint32_t opr_sz, uint32_t max_sz)
+{
+    static gen_helper_gvec_2_ptr * const fns[] = {
+        gen_helper_neon_sqshlui_b, gen_helper_neon_sqshlui_h,
+        gen_helper_neon_sqshlui_s, gen_helper_neon_sqshlui_d,
+    };
+    tcg_debug_assert(vece <= MO_64);
+    tcg_debug_assert(c >= 0 && c <= (8 << vece));
+    tcg_gen_gvec_2_ptr(rd_ofs, rn_ofs, tcg_env, opr_sz, max_sz, c, 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-dp.decode b/target/arm/tcg/neon-dp.decode
index 788578c8fa..e883c6ab58 100644
--- a/target/arm/tcg/neon-dp.decode
+++ b/target/arm/tcg/neon-dp.decode
@@ -291,17 +291,17 @@ VSLI_2sh         1111 001 1 1 . ...... .... 0101 . . . 1 .... @2reg_shl_s
 VSLI_2sh         1111 001 1 1 . ...... .... 0101 . . . 1 .... @2reg_shl_h
 VSLI_2sh         1111 001 1 1 . ...... .... 0101 . . . 1 .... @2reg_shl_b
 
-VQSHLU_64_2sh    1111 001 1 1 . ...... .... 0110 . . . 1 .... @2reg_shl_d
+VQSHLU_2sh       1111 001 1 1 . ...... .... 0110 . . . 1 .... @2reg_shl_d
 VQSHLU_2sh       1111 001 1 1 . ...... .... 0110 . . . 1 .... @2reg_shl_s
 VQSHLU_2sh       1111 001 1 1 . ...... .... 0110 . . . 1 .... @2reg_shl_h
 VQSHLU_2sh       1111 001 1 1 . ...... .... 0110 . . . 1 .... @2reg_shl_b
 
-VQSHL_S_64_2sh   1111 001 0 1 . ...... .... 0111 . . . 1 .... @2reg_shl_d
+VQSHL_S_2sh      1111 001 0 1 . ...... .... 0111 . . . 1 .... @2reg_shl_d
 VQSHL_S_2sh      1111 001 0 1 . ...... .... 0111 . . . 1 .... @2reg_shl_s
 VQSHL_S_2sh      1111 001 0 1 . ...... .... 0111 . . . 1 .... @2reg_shl_h
 VQSHL_S_2sh      1111 001 0 1 . ...... .... 0111 . . . 1 .... @2reg_shl_b
 
-VQSHL_U_64_2sh   1111 001 1 1 . ...... .... 0111 . . . 1 .... @2reg_shl_d
+VQSHL_U_2sh      1111 001 1 1 . ...... .... 0111 . . . 1 .... @2reg_shl_d
 VQSHL_U_2sh      1111 001 1 1 . ...... .... 0111 . . . 1 .... @2reg_shl_s
 VQSHL_U_2sh      1111 001 1 1 . ...... .... 0111 . . . 1 .... @2reg_shl_h
 VQSHL_U_2sh      1111 001 1 1 . ...... .... 0111 . . . 1 .... @2reg_shl_b
diff --git a/target/arm/tcg/neon_helper.c b/target/arm/tcg/neon_helper.c
index 082bfd88ad..739e16e441 100644
--- a/target/arm/tcg/neon_helper.c
+++ b/target/arm/tcg/neon_helper.c
@@ -141,6 +141,19 @@ void HELPER(name)(void *vd, void *vn, void *vm, void *venv, uint32_t desc) \
     clear_tail(d, opr_sz, simd_maxsz(desc));                    \
 }
 
+#define NEON_GVEC_VOP2i_ENV(name, vtype) \
+void HELPER(name)(void *vd, void *vn, void *venv, uint32_t desc) \
+{                                                               \
+    intptr_t i, opr_sz = simd_oprsz(desc);                      \
+    int imm = simd_data(desc);                                  \
+    vtype *d = vd, *n = vn;                                     \
+    CPUARMState *env = venv;                                    \
+    for (i = 0; i < opr_sz / sizeof(vtype); i++) {              \
+        NEON_FN(d[i], n[i], imm);                               \
+    }                                                           \
+    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.  */
@@ -271,22 +284,26 @@ uint64_t HELPER(neon_rshl_u64)(uint64_t val, uint64_t shift)
     (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)
+NEON_GVEC_VOP2i_ENV(neon_uqshli_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)
+NEON_GVEC_VOP2i_ENV(neon_uqshli_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)
+NEON_GVEC_VOP2i_ENV(neon_uqshli_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)
+NEON_GVEC_VOP2i_ENV(neon_uqshli_d, uint64_t)
 #undef NEON_FN
 
 uint32_t HELPER(neon_qshl_u32)(CPUARMState *env, uint32_t val, uint32_t shift)
@@ -303,22 +320,26 @@ uint64_t HELPER(neon_qshl_u64)(CPUARMState *env, uint64_t val, uint64_t shift)
     (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)
+NEON_GVEC_VOP2i_ENV(neon_sqshli_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)
+NEON_GVEC_VOP2i_ENV(neon_sqshli_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)
+NEON_GVEC_VOP2i_ENV(neon_sqshli_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)
+NEON_GVEC_VOP2i_ENV(neon_sqshli_d, int64_t)
 #undef NEON_FN
 
 uint32_t HELPER(neon_qshl_s32)(CPUARMState *env, uint32_t val, uint32_t shift)
@@ -334,11 +355,13 @@ uint64_t HELPER(neon_qshl_s64)(CPUARMState *env, uint64_t val, uint64_t shift)
 #define NEON_FN(dest, src1, src2) \
     (dest = do_suqrshl_bhs(src1, (int8_t)src2, 8, false, env->vfp.qc))
 NEON_VOP_ENV(qshlu_s8, neon_s8, 4)
+NEON_GVEC_VOP2i_ENV(neon_sqshlui_b, int8_t)
 #undef NEON_FN
 
 #define NEON_FN(dest, src1, src2) \
     (dest = do_suqrshl_bhs(src1, (int8_t)src2, 16, false, env->vfp.qc))
 NEON_VOP_ENV(qshlu_s16, neon_s16, 2)
+NEON_GVEC_VOP2i_ENV(neon_sqshlui_h, int16_t)
 #undef NEON_FN
 
 uint32_t HELPER(neon_qshlu_s32)(CPUARMState *env, uint32_t val, uint32_t shift)
@@ -352,6 +375,16 @@ uint64_t HELPER(neon_qshlu_s64)(CPUARMState *env, uint64_t val, uint64_t shift)
 }
 
 #define NEON_FN(dest, src1, src2) \
+    (dest = do_suqrshl_bhs(src1, (int8_t)src2, 32, false, env->vfp.qc))
+NEON_GVEC_VOP2i_ENV(neon_sqshlui_s, int32_t)
+#undef NEON_FN
+
+#define NEON_FN(dest, src1, src2) \
+    (dest = do_suqrshl_d(src1, (int8_t)src2, false, env->vfp.qc))
+NEON_GVEC_VOP2i_ENV(neon_sqshlui_d, int64_t)
+#undef NEON_FN
+
+#define NEON_FN(dest, src1, src2) \
     (dest = do_uqrshl_bhs(src1, (int8_t)src2, 8, true, env->vfp.qc))
 NEON_VOP_ENV(qrshl_u8, neon_u8, 4)
 NEON_GVEC_VOP2_ENV(neon_uqrshl_b, uint8_t)
diff --git a/target/arm/tcg/translate-neon.c b/target/arm/tcg/translate-neon.c
index a31a78c347..6dd70d1c53 100644
--- a/target/arm/tcg/translate-neon.c
+++ b/target/arm/tcg/translate-neon.c
@@ -1101,113 +1101,9 @@ DO_2SH(VRSRA_S, gen_gvec_srsra)
 DO_2SH(VRSRA_U, gen_gvec_ursra)
 DO_2SH(VSHR_S, gen_gvec_sshr)
 DO_2SH(VSHR_U, gen_gvec_ushr)
-
-static bool do_2shift_env_64(DisasContext *s, arg_2reg_shift *a,
-                             NeonGenTwo64OpEnvFn *fn)
-{
-    /*
-     * 2-reg-and-shift operations, size == 3 case, where the
-     * function needs to be passed tcg_env.
-     */
-    TCGv_i64 constimm;
-    int pass;
-
-    if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
-        return false;
-    }
-
-    /* UNDEF accesses to D16-D31 if they don't exist. */
-    if (!dc_isar_feature(aa32_simd_r32, s) &&
-        ((a->vd | a->vm) & 0x10)) {
-        return false;
-    }
-
-    if ((a->vm | a->vd) & a->q) {
-        return false;
-    }
-
-    if (!vfp_access_check(s)) {
-        return true;
-    }
-
-    /*
-     * To avoid excessive duplication of ops we implement shift
-     * by immediate using the variable shift operations.
-     */
-    constimm = tcg_constant_i64(dup_const(a->size, a->shift));
-
-    for (pass = 0; pass < a->q + 1; pass++) {
-        TCGv_i64 tmp = tcg_temp_new_i64();
-
-        read_neon_element64(tmp, a->vm, pass, MO_64);
-        fn(tmp, tcg_env, tmp, constimm);
-        write_neon_element64(tmp, a->vd, pass, MO_64);
-    }
-    return true;
-}
-
-static bool do_2shift_env_32(DisasContext *s, arg_2reg_shift *a,
-                             NeonGenTwoOpEnvFn *fn)
-{
-    /*
-     * 2-reg-and-shift operations, size < 3 case, where the
-     * helper needs to be passed tcg_env.
-     */
-    TCGv_i32 constimm, tmp;
-    int pass;
-
-    if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
-        return false;
-    }
-
-    /* UNDEF accesses to D16-D31 if they don't exist. */
-    if (!dc_isar_feature(aa32_simd_r32, s) &&
-        ((a->vd | a->vm) & 0x10)) {
-        return false;
-    }
-
-    if ((a->vm | a->vd) & a->q) {
-        return false;
-    }
-
-    if (!vfp_access_check(s)) {
-        return true;
-    }
-
-    /*
-     * To avoid excessive duplication of ops we implement shift
-     * by immediate using the variable shift operations.
-     */
-    constimm = tcg_constant_i32(dup_const(a->size, a->shift));
-    tmp = tcg_temp_new_i32();
-
-    for (pass = 0; pass < (a->q ? 4 : 2); pass++) {
-        read_neon_element32(tmp, a->vm, pass, MO_32);
-        fn(tmp, tcg_env, tmp, constimm);
-        write_neon_element32(tmp, a->vd, pass, MO_32);
-    }
-    return true;
-}
-
-#define DO_2SHIFT_ENV(INSN, FUNC)                                       \
-    static bool trans_##INSN##_64_2sh(DisasContext *s, arg_2reg_shift *a) \
-    {                                                                   \
-        return do_2shift_env_64(s, a, gen_helper_neon_##FUNC##64);      \
-    }                                                                   \
-    static bool trans_##INSN##_2sh(DisasContext *s, arg_2reg_shift *a)  \
-    {                                                                   \
-        static NeonGenTwoOpEnvFn * const fns[] = {                      \
-            gen_helper_neon_##FUNC##8,                                  \
-            gen_helper_neon_##FUNC##16,                                 \
-            gen_helper_neon_##FUNC##32,                                 \
-        };                                                              \
-        assert(a->size < ARRAY_SIZE(fns));                              \
-        return do_2shift_env_32(s, a, fns[a->size]);                    \
-    }
-
-DO_2SHIFT_ENV(VQSHLU, qshlu_s)
-DO_2SHIFT_ENV(VQSHL_U, qshl_u)
-DO_2SHIFT_ENV(VQSHL_S, qshl_s)
+DO_2SH(VQSHLU, gen_neon_sqshlui)
+DO_2SH(VQSHL_U, gen_neon_uqshli)
+DO_2SH(VQSHL_S, gen_neon_sqshli)
 
 static bool do_2shift_narrow_64(DisasContext *s, arg_2reg_shift *a,
                                 NeonGenTwo64OpFn *shiftfn,
diff --git a/target/arm/tcg/translate.h b/target/arm/tcg/translate.h
index 45990ae292..7721c627e9 100644
--- a/target/arm/tcg/translate.h
+++ b/target/arm/tcg/translate.h
@@ -471,6 +471,13 @@ void gen_neon_sqrshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
 void gen_neon_uqrshl(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_sqshli(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
+                     int64_t c, uint32_t opr_sz, uint32_t max_sz);
+void gen_neon_uqshli(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
+                     int64_t c, uint32_t opr_sz, uint32_t max_sz);
+void gen_neon_sqshlui(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
+                      int64_t c, uint32_t opr_sz, uint32_t max_sz);
+
 void gen_gvec_shadd(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_uhadd(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,