[PATCH v2 021/100] target/arm: Implement SVE2 integer halving add/subtract (predicated)

[Richard Henderson]

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/arm/helper-sve.h    | 54 ++++++++++++++++++++++++++++++++++++++
 target/arm/sve.decode      | 11 ++++++++
 target/arm/sve_helper.c    | 39 +++++++++++++++++++++++++++
 target/arm/translate-sve.c |  8 ++++++
 4 files changed, 112 insertions(+)

diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h
index 53c5c1d3f9..e02c3661c3 100644
--- a/target/arm/helper-sve.h
+++ b/target/arm/helper-sve.h
@@ -226,6 +226,60 @@ DEF_HELPER_FLAGS_5(sve2_uqrshl_zpzz_s, TCG_CALL_NO_RWG,
 DEF_HELPER_FLAGS_5(sve2_uqrshl_zpzz_d, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
 
+DEF_HELPER_FLAGS_5(sve2_shadd_zpzz_b, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_shadd_zpzz_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_shadd_zpzz_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_shadd_zpzz_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(sve2_uhadd_zpzz_b, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_uhadd_zpzz_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_uhadd_zpzz_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_uhadd_zpzz_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(sve2_srhadd_zpzz_b, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_srhadd_zpzz_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_srhadd_zpzz_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_srhadd_zpzz_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(sve2_urhadd_zpzz_b, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_urhadd_zpzz_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_urhadd_zpzz_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_urhadd_zpzz_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(sve2_shsub_zpzz_b, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_shsub_zpzz_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_shsub_zpzz_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_shsub_zpzz_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(sve2_uhsub_zpzz_b, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_uhsub_zpzz_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_uhsub_zpzz_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_uhsub_zpzz_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+
 DEF_HELPER_FLAGS_5(sve_sdiv_zpzz_s, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_5(sve_sdiv_zpzz_d, TCG_CALL_NO_RWG,
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index 2bf3eff1cf..2d5104b84f 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -1132,3 +1132,14 @@ SQRSHL          01000100 .. 001 010 100 ... ..... .....  
@rdn_pg_rm
 UQRSHL          01000100 .. 001 011 100 ... ..... .....  @rdn_pg_rm
 SQRSHL          01000100 .. 001 110 100 ... ..... .....  @rdm_pg_rn # SQRSHLR
 UQRSHL          01000100 .. 001 111 100 ... ..... .....  @rdm_pg_rn # UQRSHLR
+
+### SVE2 integer halving add/subtract (predicated)
+
+SHADD           01000100 .. 010 000 100 ... ..... .....  @rdn_pg_rm
+UHADD           01000100 .. 010 001 100 ... ..... .....  @rdn_pg_rm
+SHSUB           01000100 .. 010 010 100 ... ..... .....  @rdn_pg_rm
+UHSUB           01000100 .. 010 011 100 ... ..... .....  @rdn_pg_rm
+SRHADD          01000100 .. 010 100 100 ... ..... .....  @rdn_pg_rm
+URHADD          01000100 .. 010 101 100 ... ..... .....  @rdn_pg_rm
+SHSUB           01000100 .. 010 110 100 ... ..... .....  @rdm_pg_rn # SHSUBR
+UHSUB           01000100 .. 010 111 100 ... ..... .....  @rdm_pg_rn # UHSUBR
diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index 341ec23491..b578556a22 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -639,6 +639,45 @@ DO_ZPZZ(sve2_uqrshl_zpzz_h, uint16_t, H1_2, do_uqrshl_h)
 DO_ZPZZ(sve2_uqrshl_zpzz_s, uint32_t, H1_4, do_uqrshl_s)
 DO_ZPZZ_D(sve2_uqrshl_zpzz_d, uint64_t, do_uqrshl_d)
 
+#define DO_HADD_BHS(n, m)  (((int64_t)n + m) >> 1)
+#define DO_HADD_D(n, m)    ((n >> 1) + (m >> 1) + (n & m & 1))
+
+DO_ZPZZ(sve2_shadd_zpzz_b, int8_t, H1_2, DO_HADD_BHS)
+DO_ZPZZ(sve2_shadd_zpzz_h, int16_t, H1_2, DO_HADD_BHS)
+DO_ZPZZ(sve2_shadd_zpzz_s, int32_t, H1_4, DO_HADD_BHS)
+DO_ZPZZ_D(sve2_shadd_zpzz_d, int64_t, DO_HADD_D)
+
+DO_ZPZZ(sve2_uhadd_zpzz_b, uint8_t, H1_2, DO_HADD_BHS)
+DO_ZPZZ(sve2_uhadd_zpzz_h, uint16_t, H1_2, DO_HADD_BHS)
+DO_ZPZZ(sve2_uhadd_zpzz_s, uint32_t, H1_4, DO_HADD_BHS)
+DO_ZPZZ_D(sve2_uhadd_zpzz_d, uint64_t, DO_HADD_D)
+
+#define DO_RHADD_BHS(n, m)  (((int64_t)n + m + 1) >> 1)
+#define DO_RHADD_D(n, m)    ((n >> 1) + (m >> 1) + ((n | m) & 1))
+
+DO_ZPZZ(sve2_srhadd_zpzz_b, int8_t, H1_2, DO_RHADD_BHS)
+DO_ZPZZ(sve2_srhadd_zpzz_h, int16_t, H1_2, DO_RHADD_BHS)
+DO_ZPZZ(sve2_srhadd_zpzz_s, int32_t, H1_4, DO_RHADD_BHS)
+DO_ZPZZ_D(sve2_srhadd_zpzz_d, int64_t, DO_RHADD_D)
+
+DO_ZPZZ(sve2_urhadd_zpzz_b, uint8_t, H1_2, DO_RHADD_BHS)
+DO_ZPZZ(sve2_urhadd_zpzz_h, uint16_t, H1_2, DO_RHADD_BHS)
+DO_ZPZZ(sve2_urhadd_zpzz_s, uint32_t, H1_4, DO_RHADD_BHS)
+DO_ZPZZ_D(sve2_urhadd_zpzz_d, uint64_t, DO_RHADD_D)
+
+#define DO_HSUB_BHS(n, m)  (((int64_t)n - m) >> 1)
+#define DO_HSUB_D(n, m)    ((n >> 1) - (m >> 1) - (~n & m & 1))
+
+DO_ZPZZ(sve2_shsub_zpzz_b, int8_t, H1_2, DO_HSUB_BHS)
+DO_ZPZZ(sve2_shsub_zpzz_h, int16_t, H1_2, DO_HSUB_BHS)
+DO_ZPZZ(sve2_shsub_zpzz_s, int32_t, H1_4, DO_HSUB_BHS)
+DO_ZPZZ_D(sve2_shsub_zpzz_d, int64_t, DO_HSUB_D)
+
+DO_ZPZZ(sve2_uhsub_zpzz_b, uint8_t, H1_2, DO_HSUB_BHS)
+DO_ZPZZ(sve2_uhsub_zpzz_h, uint16_t, H1_2, DO_HSUB_BHS)
+DO_ZPZZ(sve2_uhsub_zpzz_s, uint32_t, H1_4, DO_HSUB_BHS)
+DO_ZPZZ_D(sve2_uhsub_zpzz_d, uint64_t, DO_HSUB_D)
+
 #undef DO_ZPZZ
 #undef DO_ZPZZ_D
 
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index 77c4ba95b0..dac662a586 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -5515,3 +5515,11 @@ DO_SVE2_ZPZZ(SRSHL, srshl)
 DO_SVE2_ZPZZ(UQSHL, uqshl)
 DO_SVE2_ZPZZ(UQRSHL, uqrshl)
 DO_SVE2_ZPZZ(URSHL, urshl)
+
+DO_SVE2_ZPZZ(SHADD, shadd)
+DO_SVE2_ZPZZ(SRHADD, srhadd)
+DO_SVE2_ZPZZ(SHSUB, shsub)
+
+DO_SVE2_ZPZZ(UHADD, uhadd)
+DO_SVE2_ZPZZ(URHADD, urhadd)
+DO_SVE2_ZPZZ(UHSUB, uhsub)
-- 
2.25.1