target/arm: Introduce gen_gvec_urecpe, gen_gvec_ursqrte

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20241211163036.2297116-68-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

5 files changed, 48 insertions, 2 deletions

diff --git a/target/arm/helper.h b/target/arm/helper.h
index 1132a5c..9919b13 100644
--- a/target/arm/helper.h
+++ b/target/arm/helper.h
@@ -1121,6 +1121,9 @@ DEF_HELPER_FLAGS_4(gvec_uminp_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(gvec_uminp_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(gvec_uminp_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 
+DEF_HELPER_FLAGS_3(gvec_urecpe_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(gvec_ursqrte_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+
 #ifdef TARGET_AARCH64
 #include "tcg/helper-a64.h"
 #include "tcg/helper-sve.h"
diff --git a/target/arm/tcg/gengvec.c b/target/arm/tcg/gengvec.c
index 01c9d54..01867f8 100644
--- a/target/arm/tcg/gengvec.c
+++ b/target/arm/tcg/gengvec.c
@@ -2711,3 +2711,19 @@ void gen_gvec_fneg(unsigned vece, uint32_t dofs, uint32_t aofs,
     uint64_t s_bit = 1ull << ((8 << vece) - 1);
     tcg_gen_gvec_xori(vece, dofs, aofs, s_bit, oprsz, maxsz);
 }
+
+void gen_gvec_urecpe(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
+                     uint32_t opr_sz, uint32_t max_sz)
+{
+    assert(vece == MO_32);
+    tcg_gen_gvec_2_ool(rd_ofs, rn_ofs, opr_sz, max_sz, 0,
+                       gen_helper_gvec_urecpe_s);
+}
+
+void gen_gvec_ursqrte(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
+                      uint32_t opr_sz, uint32_t max_sz)
+{
+    assert(vece == MO_32);
+    tcg_gen_gvec_2_ool(rd_ofs, rn_ofs, opr_sz, max_sz, 0,
+                       gen_helper_gvec_ursqrte_s);
+}
diff --git a/target/arm/tcg/translate-neon.c b/target/arm/tcg/translate-neon.c
index f9ca889..c4fecb8 100644
--- a/target/arm/tcg/translate-neon.c
+++ b/target/arm/tcg/translate-neon.c
@@ -3070,7 +3070,7 @@ static bool trans_VRECPE(DisasContext *s, arg_2misc *a)
     if (a->size != 2) {
         return false;
     }
-    return do_2misc(s, a, gen_helper_recpe_u32);
+    return do_2misc_vec(s, a, gen_gvec_urecpe);
 }
 
 static bool trans_VRSQRTE(DisasContext *s, arg_2misc *a)
@@ -3078,7 +3078,7 @@ static bool trans_VRSQRTE(DisasContext *s, arg_2misc *a)
     if (a->size != 2) {
         return false;
     }
-    return do_2misc(s, a, gen_helper_rsqrte_u32);
+    return do_2misc_vec(s, a, gen_gvec_ursqrte);
 }
 
 #define WRAP_1OP_ENV_FN(WRAPNAME, FUNC) \
diff --git a/target/arm/tcg/translate.h b/target/arm/tcg/translate.h
index b996de2..9b9abf1 100644
--- a/target/arm/tcg/translate.h
+++ b/target/arm/tcg/translate.h
@@ -608,6 +608,11 @@ void gen_gvec_fabs(unsigned vece, uint32_t dofs, uint32_t aofs,
 void gen_gvec_fneg(unsigned vece, uint32_t dofs, uint32_t aofs,
                    uint32_t oprsz, uint32_t maxsz);
 
+void gen_gvec_urecpe(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
+                     uint32_t opr_sz, uint32_t max_sz);
+void gen_gvec_ursqrte(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
+                      uint32_t opr_sz, uint32_t max_sz);
+
 /*
  * Forward to the isar_feature_* tests given a DisasContext pointer.
  */
diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c
index ee84774..768f745 100644
--- a/target/arm/tcg/vec_helper.c
+++ b/target/arm/tcg/vec_helper.c
@@ -3099,3 +3099,25 @@ void HELPER(gvec_rbit_b)(void *vd, void *vn, uint32_t desc)
     }
     clear_tail(d, opr_sz, simd_maxsz(desc));
 }
+
+void HELPER(gvec_urecpe_s)(void *vd, void *vn, uint32_t desc)
+{
+    intptr_t i, opr_sz = simd_oprsz(desc);
+    uint32_t *d = vd, *n = vn;
+
+    for (i = 0; i < opr_sz / 4; ++i) {
+        d[i] = helper_recpe_u32(n[i]);
+    }
+    clear_tail(d, opr_sz, simd_maxsz(desc));
+}
+
+void HELPER(gvec_ursqrte_s)(void *vd, void *vn, uint32_t desc)
+{
+    intptr_t i, opr_sz = simd_oprsz(desc);
+    uint32_t *d = vd, *n = vn;
+
+    for (i = 0; i < opr_sz / 4; ++i) {
+        d[i] = helper_rsqrte_u32(n[i]);
+    }
+    clear_tail(d, opr_sz, simd_maxsz(desc));
+}