[PATCH v4 04/78] target/arm: Implement SVE2 integer unary operations (predicated)

[Richard Henderson]

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
v2: Fix sqabs, sqneg (laurent desnogues)
---
 target/arm/helper-sve.h    | 13 +++++++++++
 target/arm/sve.decode      |  7 ++++++
 target/arm/sve_helper.c    | 29 +++++++++++++++++++----
 target/arm/translate-sve.c | 47 ++++++++++++++++++++++++++++++++++++++
 4 files changed, 92 insertions(+), 4 deletions(-)

diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h
index b2a274b40b..9992e93e2b 100644
--- a/target/arm/helper-sve.h
+++ b/target/arm/helper-sve.h
@@ -502,6 +502,19 @@ DEF_HELPER_FLAGS_4(sve_rbit_h, TCG_CALL_NO_RWG, void, ptr, 
ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(sve_rbit_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(sve_rbit_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 
+DEF_HELPER_FLAGS_4(sve2_sqabs_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_sqabs_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_sqabs_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_sqabs_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve2_sqneg_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_sqneg_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_sqneg_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_sqneg_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve2_urecpe_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_ursqrte_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
 DEF_HELPER_FLAGS_5(sve_splice, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
 
 DEF_HELPER_FLAGS_5(sve_cmpeq_ppzz_b, TCG_CALL_NO_RWG,
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index 0524c01fcf..5ba542969b 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -1105,3 +1105,10 @@ PMUL_zzz        00000100 00 1 ..... 0110 01 ..... .....  
@rd_rn_rm_e0
 
 SADALP_zpzz     01000100 .. 000 100 101 ... ..... .....  @rdm_pg_rn
 UADALP_zpzz     01000100 .. 000 101 101 ... ..... .....  @rdm_pg_rn
+
+### SVE2 integer unary operations (predicated)
+
+URECPE          01000100 .. 000 000 101 ... ..... .....  @rd_pg_rn
+URSQRTE         01000100 .. 000 001 101 ... ..... .....  @rd_pg_rn
+SQABS           01000100 .. 001 000 101 ... ..... .....  @rd_pg_rn
+SQNEG           01000100 .. 001 001 101 ... ..... .....  @rd_pg_rn
diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index 00bb82da91..5dcdd26db0 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -535,8 +535,8 @@ static inline uint64_t do_sadalp_d(uint64_t n, uint64_t m)
     return m + n1 + n2;
 }
 
-DO_ZPZZ(sve2_sadalp_zpzz_h, int16_t, H1_2, do_sadalp_h)
-DO_ZPZZ(sve2_sadalp_zpzz_s, int32_t, H1_4, do_sadalp_s)
+DO_ZPZZ(sve2_sadalp_zpzz_h, uint16_t, H1_2, do_sadalp_h)
+DO_ZPZZ(sve2_sadalp_zpzz_s, uint32_t, H1_4, do_sadalp_s)
 DO_ZPZZ_D(sve2_sadalp_zpzz_d, uint64_t, do_sadalp_d)
 
 static inline uint16_t do_uadalp_h(uint16_t n, uint16_t m)
@@ -557,8 +557,8 @@ static inline uint64_t do_uadalp_d(uint64_t n, uint64_t m)
     return m + n1 + n2;
 }
 
-DO_ZPZZ(sve2_uadalp_zpzz_h, int16_t, H1_2, do_uadalp_h)
-DO_ZPZZ(sve2_uadalp_zpzz_s, int32_t, H1_4, do_uadalp_s)
+DO_ZPZZ(sve2_uadalp_zpzz_h, uint16_t, H1_2, do_uadalp_h)
+DO_ZPZZ(sve2_uadalp_zpzz_s, uint32_t, H1_4, do_uadalp_s)
 DO_ZPZZ_D(sve2_uadalp_zpzz_d, uint64_t, do_uadalp_d)
 
 #undef DO_ZPZZ
@@ -728,6 +728,27 @@ DO_ZPZ(sve_rbit_h, uint16_t, H1_2, revbit16)
 DO_ZPZ(sve_rbit_s, uint32_t, H1_4, revbit32)
 DO_ZPZ_D(sve_rbit_d, uint64_t, revbit64)
 
+#define DO_SQABS(X) \
+    ({ __typeof(X) x_ = (X), min_ = 1ull << (sizeof(X) * 8 - 1); \
+       x_ >= 0 ? x_ : x_ == min_ ? -min_ - 1 : -x_; })
+
+DO_ZPZ(sve2_sqabs_b, int8_t, H1, DO_SQABS)
+DO_ZPZ(sve2_sqabs_h, int16_t, H1_2, DO_SQABS)
+DO_ZPZ(sve2_sqabs_s, int32_t, H1_4, DO_SQABS)
+DO_ZPZ_D(sve2_sqabs_d, int64_t, DO_SQABS)
+
+#define DO_SQNEG(X) \
+    ({ __typeof(X) x_ = (X), min_ = 1ull << (sizeof(X) * 8 - 1); \
+       x_ == min_ ? -min_ - 1 : -x_; })
+
+DO_ZPZ(sve2_sqneg_b, uint8_t, H1, DO_SQNEG)
+DO_ZPZ(sve2_sqneg_h, uint16_t, H1_2, DO_SQNEG)
+DO_ZPZ(sve2_sqneg_s, uint32_t, H1_4, DO_SQNEG)
+DO_ZPZ_D(sve2_sqneg_d, uint64_t, DO_SQNEG)
+
+DO_ZPZ(sve2_urecpe_s, uint32_t, H1_4, helper_recpe_u32)
+DO_ZPZ(sve2_ursqrte_s, uint32_t, H1_4, helper_rsqrte_u32)
+
 /* Three-operand expander, unpredicated, in which the third operand is "wide".
  */
 #define DO_ZZW(NAME, TYPE, TYPEW, H, OP)                       \
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index 603e673696..2d8b9d2e70 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -5885,3 +5885,50 @@ static bool trans_UADALP_zpzz(DisasContext *s, 
arg_rprr_esz *a)
     }
     return do_sve2_zpzz_ool(s, a, fns[a->esz - 1]);
 }
+
+/*
+ * SVE2 integer unary operations (predicated)
+ */
+
+static bool do_sve2_zpz_ool(DisasContext *s, arg_rpr_esz *a,
+                            gen_helper_gvec_3 *fn)
+{
+    if (!dc_isar_feature(aa64_sve2, s)) {
+        return false;
+    }
+    return do_zpz_ool(s, a, fn);
+}
+
+static bool trans_URECPE(DisasContext *s, arg_rpr_esz *a)
+{
+    if (a->esz != 2) {
+        return false;
+    }
+    return do_sve2_zpz_ool(s, a, gen_helper_sve2_urecpe_s);
+}
+
+static bool trans_URSQRTE(DisasContext *s, arg_rpr_esz *a)
+{
+    if (a->esz != 2) {
+        return false;
+    }
+    return do_sve2_zpz_ool(s, a, gen_helper_sve2_ursqrte_s);
+}
+
+static bool trans_SQABS(DisasContext *s, arg_rpr_esz *a)
+{
+    static gen_helper_gvec_3 * const fns[4] = {
+        gen_helper_sve2_sqabs_b, gen_helper_sve2_sqabs_h,
+        gen_helper_sve2_sqabs_s, gen_helper_sve2_sqabs_d,
+    };
+    return do_sve2_zpz_ool(s, a, fns[a->esz]);
+}
+
+static bool trans_SQNEG(DisasContext *s, arg_rpr_esz *a)
+{
+    static gen_helper_gvec_3 * const fns[4] = {
+        gen_helper_sve2_sqneg_b, gen_helper_sve2_sqneg_h,
+        gen_helper_sve2_sqneg_s, gen_helper_sve2_sqneg_d,
+    };
+    return do_sve2_zpz_ool(s, a, fns[a->esz]);
+}
-- 
2.25.1