[PATCH v7 29/92] target/arm: Implement SVE2 SQSHRN, SQRSHRN

[Richard Henderson]

This completes the section "SVE2 bitwise shift right narrow".

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/arm/helper-sve.h    |  16 ++++++
 target/arm/sve.decode      |   4 ++
 target/arm/sve_helper.c    |  24 +++++++++
 target/arm/translate-sve.c | 105 +++++++++++++++++++++++++++++++++++++
 4 files changed, 149 insertions(+)

diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h
index ba6a24fc8b..1c7fe8e417 100644
--- a/target/arm/helper-sve.h
+++ b/target/arm/helper-sve.h
@@ -2476,6 +2476,22 @@ DEF_HELPER_FLAGS_3(sve2_sqrshrunt_h, TCG_CALL_NO_RWG, 
void, ptr, ptr, i32)
 DEF_HELPER_FLAGS_3(sve2_sqrshrunt_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
 DEF_HELPER_FLAGS_3(sve2_sqrshrunt_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
 
+DEF_HELPER_FLAGS_3(sve2_sqshrnb_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sve2_sqshrnb_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sve2_sqshrnb_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_3(sve2_sqshrnt_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sve2_sqshrnt_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sve2_sqshrnt_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_3(sve2_sqrshrnb_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sve2_sqrshrnb_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sve2_sqrshrnb_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_3(sve2_sqrshrnt_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sve2_sqrshrnt_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sve2_sqrshrnt_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+
 DEF_HELPER_FLAGS_3(sve2_uqshrnb_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
 DEF_HELPER_FLAGS_3(sve2_uqshrnb_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
 DEF_HELPER_FLAGS_3(sve2_uqshrnb_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index 13b5da0856..0674464695 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -1296,6 +1296,10 @@ SHRNB           01000101 .. 1 ..... 00 0100 ..... .....  
@rd_rn_tszimm_shr
 SHRNT           01000101 .. 1 ..... 00 0101 ..... .....  @rd_rn_tszimm_shr
 RSHRNB          01000101 .. 1 ..... 00 0110 ..... .....  @rd_rn_tszimm_shr
 RSHRNT          01000101 .. 1 ..... 00 0111 ..... .....  @rd_rn_tszimm_shr
+SQSHRNB         01000101 .. 1 ..... 00 1000 ..... .....  @rd_rn_tszimm_shr
+SQSHRNT         01000101 .. 1 ..... 00 1001 ..... .....  @rd_rn_tszimm_shr
+SQRSHRNB        01000101 .. 1 ..... 00 1010 ..... .....  @rd_rn_tszimm_shr
+SQRSHRNT        01000101 .. 1 ..... 00 1011 ..... .....  @rd_rn_tszimm_shr
 UQSHRNB         01000101 .. 1 ..... 00 1100 ..... .....  @rd_rn_tszimm_shr
 UQSHRNT         01000101 .. 1 ..... 00 1101 ..... .....  @rd_rn_tszimm_shr
 UQRSHRNB        01000101 .. 1 ..... 00 1110 ..... .....  @rd_rn_tszimm_shr
diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index 89262149f9..0ea4ae28db 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -1976,6 +1976,30 @@ DO_SHRNT(sve2_sqrshrunt_h, int16_t, uint8_t, H1_2, H1, 
DO_SQRSHRUN_H)
 DO_SHRNT(sve2_sqrshrunt_s, int32_t, uint16_t, H1_4, H1_2, DO_SQRSHRUN_S)
 DO_SHRNT(sve2_sqrshrunt_d, int64_t, uint32_t,     , H1_4, DO_SQRSHRUN_D)
 
+#define DO_SQSHRN_H(x, sh) do_sat_bhs(x >> sh, INT8_MIN, INT8_MAX)
+#define DO_SQSHRN_S(x, sh) do_sat_bhs(x >> sh, INT16_MIN, INT16_MAX)
+#define DO_SQSHRN_D(x, sh) do_sat_bhs(x >> sh, INT32_MIN, INT32_MAX)
+
+DO_SHRNB(sve2_sqshrnb_h, int16_t, uint8_t, DO_SQSHRN_H)
+DO_SHRNB(sve2_sqshrnb_s, int32_t, uint16_t, DO_SQSHRN_S)
+DO_SHRNB(sve2_sqshrnb_d, int64_t, uint32_t, DO_SQSHRN_D)
+
+DO_SHRNT(sve2_sqshrnt_h, int16_t, uint8_t, H1_2, H1, DO_SQSHRN_H)
+DO_SHRNT(sve2_sqshrnt_s, int32_t, uint16_t, H1_4, H1_2, DO_SQSHRN_S)
+DO_SHRNT(sve2_sqshrnt_d, int64_t, uint32_t,     , H1_4, DO_SQSHRN_D)
+
+#define DO_SQRSHRN_H(x, sh) do_sat_bhs(do_srshr(x, sh), INT8_MIN, INT8_MAX)
+#define DO_SQRSHRN_S(x, sh) do_sat_bhs(do_srshr(x, sh), INT16_MIN, INT16_MAX)
+#define DO_SQRSHRN_D(x, sh) do_sat_bhs(do_srshr(x, sh), INT32_MIN, INT32_MAX)
+
+DO_SHRNB(sve2_sqrshrnb_h, int16_t, uint8_t, DO_SQRSHRN_H)
+DO_SHRNB(sve2_sqrshrnb_s, int32_t, uint16_t, DO_SQRSHRN_S)
+DO_SHRNB(sve2_sqrshrnb_d, int64_t, uint32_t, DO_SQRSHRN_D)
+
+DO_SHRNT(sve2_sqrshrnt_h, int16_t, uint8_t, H1_2, H1, DO_SQRSHRN_H)
+DO_SHRNT(sve2_sqrshrnt_s, int32_t, uint16_t, H1_4, H1_2, DO_SQRSHRN_S)
+DO_SHRNT(sve2_sqrshrnt_d, int64_t, uint32_t,     , H1_4, DO_SQRSHRN_D)
+
 #define DO_UQSHRN_H(x, sh) MIN(x >> sh, UINT8_MAX)
 #define DO_UQSHRN_S(x, sh) MIN(x >> sh, UINT16_MAX)
 #define DO_UQSHRN_D(x, sh) MIN(x >> sh, UINT32_MAX)
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index e5c71005c8..4141d76311 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -6956,6 +6956,111 @@ static bool trans_SQRSHRUNT(DisasContext *s, 
arg_rri_esz *a)
     return do_sve2_shr_narrow(s, a, ops);
 }
 
+static void gen_sqshrnb_vec(unsigned vece, TCGv_vec d,
+                            TCGv_vec n, int64_t shr)
+{
+    TCGv_vec t = tcg_temp_new_vec_matching(d);
+    int halfbits = 4 << vece;
+    int64_t max = MAKE_64BIT_MASK(0, halfbits - 1);
+    int64_t min = -max - 1;
+
+    tcg_gen_sari_vec(vece, n, n, shr);
+    tcg_gen_dupi_vec(vece, t, min);
+    tcg_gen_smax_vec(vece, n, n, t);
+    tcg_gen_dupi_vec(vece, t, max);
+    tcg_gen_smin_vec(vece, n, n, t);
+    tcg_gen_dupi_vec(vece, t, MAKE_64BIT_MASK(0, halfbits));
+    tcg_gen_and_vec(vece, d, n, t);
+    tcg_temp_free_vec(t);
+}
+
+static bool trans_SQSHRNB(DisasContext *s, arg_rri_esz *a)
+{
+    static const TCGOpcode vec_list[] = {
+        INDEX_op_sari_vec, INDEX_op_smax_vec, INDEX_op_smin_vec, 0
+    };
+    static const GVecGen2i ops[3] = {
+        { .fniv = gen_sqshrnb_vec,
+          .opt_opc = vec_list,
+          .fno = gen_helper_sve2_sqshrnb_h,
+          .vece = MO_16 },
+        { .fniv = gen_sqshrnb_vec,
+          .opt_opc = vec_list,
+          .fno = gen_helper_sve2_sqshrnb_s,
+          .vece = MO_32 },
+        { .fniv = gen_sqshrnb_vec,
+          .opt_opc = vec_list,
+          .fno = gen_helper_sve2_sqshrnb_d,
+          .vece = MO_64 },
+    };
+    return do_sve2_shr_narrow(s, a, ops);
+}
+
+static void gen_sqshrnt_vec(unsigned vece, TCGv_vec d,
+                             TCGv_vec n, int64_t shr)
+{
+    TCGv_vec t = tcg_temp_new_vec_matching(d);
+    int halfbits = 4 << vece;
+    int64_t max = MAKE_64BIT_MASK(0, halfbits - 1);
+    int64_t min = -max - 1;
+
+    tcg_gen_sari_vec(vece, n, n, shr);
+    tcg_gen_dupi_vec(vece, t, min);
+    tcg_gen_smax_vec(vece, n, n, t);
+    tcg_gen_dupi_vec(vece, t, max);
+    tcg_gen_smin_vec(vece, n, n, t);
+    tcg_gen_shli_vec(vece, n, n, halfbits);
+    tcg_gen_dupi_vec(vece, t, MAKE_64BIT_MASK(0, halfbits));
+    tcg_gen_bitsel_vec(vece, d, t, d, n);
+    tcg_temp_free_vec(t);
+}
+
+static bool trans_SQSHRNT(DisasContext *s, arg_rri_esz *a)
+{
+    static const TCGOpcode vec_list[] = {
+        INDEX_op_shli_vec, INDEX_op_sari_vec,
+        INDEX_op_smax_vec, INDEX_op_smin_vec, 0
+    };
+    static const GVecGen2i ops[3] = {
+        { .fniv = gen_sqshrnt_vec,
+          .opt_opc = vec_list,
+          .load_dest = true,
+          .fno = gen_helper_sve2_sqshrnt_h,
+          .vece = MO_16 },
+        { .fniv = gen_sqshrnt_vec,
+          .opt_opc = vec_list,
+          .load_dest = true,
+          .fno = gen_helper_sve2_sqshrnt_s,
+          .vece = MO_32 },
+        { .fniv = gen_sqshrnt_vec,
+          .opt_opc = vec_list,
+          .load_dest = true,
+          .fno = gen_helper_sve2_sqshrnt_d,
+          .vece = MO_64 },
+    };
+    return do_sve2_shr_narrow(s, a, ops);
+}
+
+static bool trans_SQRSHRNB(DisasContext *s, arg_rri_esz *a)
+{
+    static const GVecGen2i ops[3] = {
+        { .fno = gen_helper_sve2_sqrshrnb_h },
+        { .fno = gen_helper_sve2_sqrshrnb_s },
+        { .fno = gen_helper_sve2_sqrshrnb_d },
+    };
+    return do_sve2_shr_narrow(s, a, ops);
+}
+
+static bool trans_SQRSHRNT(DisasContext *s, arg_rri_esz *a)
+{
+    static const GVecGen2i ops[3] = {
+        { .fno = gen_helper_sve2_sqrshrnt_h },
+        { .fno = gen_helper_sve2_sqrshrnt_s },
+        { .fno = gen_helper_sve2_sqrshrnt_d },
+    };
+    return do_sve2_shr_narrow(s, a, ops);
+}
+
 static void gen_uqshrnb_vec(unsigned vece, TCGv_vec d,
                             TCGv_vec n, int64_t shr)
 {
-- 
2.25.1