target/arm: Implement SVE2 integer multiply long

Exclude PMULL from this category for the moment.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-14-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h
index 3286a9c2054af3f9e230947227d4d945951e485e..ad8121eec6a1aadd2ad144150fbb68b5f12441bd 100644 (file)
--- a/target/arm/helper-sve.h
+++ b/target/arm/helper-sve.h
@@ -2347,4 +2347,19 @@ DEF_HELPER_FLAGS_6(sve_stdd_le_zd_mte, TCG_CALL_NO_WG,
 DEF_HELPER_FLAGS_6(sve_stdd_be_zd_mte, TCG_CALL_NO_WG,
                    void, env, ptr, ptr, ptr, tl, i32)
 
+DEF_HELPER_FLAGS_4(sve2_sqdmull_zzz_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_sqdmull_zzz_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_sqdmull_zzz_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve2_smull_zzz_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_smull_zzz_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_smull_zzz_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve2_umull_zzz_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_umull_zzz_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_umull_zzz_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
 DEF_HELPER_FLAGS_4(sve2_pmull_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)

diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index f6f21426ef2fbbb28f6f7727aa604c327b2195a8..d9a72b7661c4641eb6d8cd55b85cd80ab9d2b57b 100644 (file)
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -1196,3 +1196,12 @@ SSUBWB          01000101 .. 0 ..... 010 100 ..... .....  @rd_rn_rm
 SSUBWT          01000101 .. 0 ..... 010 101 ..... .....  @rd_rn_rm
 USUBWB          01000101 .. 0 ..... 010 110 ..... .....  @rd_rn_rm
 USUBWT          01000101 .. 0 ..... 010 111 ..... .....  @rd_rn_rm
+
+## SVE2 integer multiply long
+
+SQDMULLB_zzz    01000101 .. 0 ..... 011 000 ..... .....  @rd_rn_rm
+SQDMULLT_zzz    01000101 .. 0 ..... 011 001 ..... .....  @rd_rn_rm
+SMULLB_zzz      01000101 .. 0 ..... 011 100 ..... .....  @rd_rn_rm
+SMULLT_zzz      01000101 .. 0 ..... 011 101 ..... .....  @rd_rn_rm
+UMULLB_zzz      01000101 .. 0 ..... 011 110 ..... .....  @rd_rn_rm
+UMULLT_zzz      01000101 .. 0 ..... 011 111 ..... .....  @rd_rn_rm

diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index 374e02dbf8515a149380075564cafae4820596de..cfd1a7cb4974cfd5f740f37817c05a91bea18b57 100644 (file)
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -1163,6 +1163,37 @@ DO_ZZZ_TB(sve2_uabdl_h, uint16_t, uint8_t, H1_2, H1, DO_ABD)
 DO_ZZZ_TB(sve2_uabdl_s, uint32_t, uint16_t, H1_4, H1_2, DO_ABD)
 DO_ZZZ_TB(sve2_uabdl_d, uint64_t, uint32_t,     , H1_4, DO_ABD)
 
+DO_ZZZ_TB(sve2_smull_zzz_h, int16_t, int8_t, H1_2, H1, DO_MUL)
+DO_ZZZ_TB(sve2_smull_zzz_s, int32_t, int16_t, H1_4, H1_2, DO_MUL)
+DO_ZZZ_TB(sve2_smull_zzz_d, int64_t, int32_t,     , H1_4, DO_MUL)
+
+DO_ZZZ_TB(sve2_umull_zzz_h, uint16_t, uint8_t, H1_2, H1, DO_MUL)
+DO_ZZZ_TB(sve2_umull_zzz_s, uint32_t, uint16_t, H1_4, H1_2, DO_MUL)
+DO_ZZZ_TB(sve2_umull_zzz_d, uint64_t, uint32_t,     , H1_4, DO_MUL)
+
+/* Note that the multiply cannot overflow, but the doubling can. */
+static inline int16_t do_sqdmull_h(int16_t n, int16_t m)
+{
+    int16_t val = n * m;
+    return DO_SQADD_H(val, val);
+}
+
+static inline int32_t do_sqdmull_s(int32_t n, int32_t m)
+{
+    int32_t val = n * m;
+    return DO_SQADD_S(val, val);
+}
+
+static inline int64_t do_sqdmull_d(int64_t n, int64_t m)
+{
+    int64_t val = n * m;
+    return do_sqadd_d(val, val);
+}
+
+DO_ZZZ_TB(sve2_sqdmull_zzz_h, int16_t, int8_t, H1_2, H1, do_sqdmull_h)
+DO_ZZZ_TB(sve2_sqdmull_zzz_s, int32_t, int16_t, H1_4, H1_2, do_sqdmull_s)
+DO_ZZZ_TB(sve2_sqdmull_zzz_d, int64_t, int32_t,     , H1_4, do_sqdmull_d)
+
 #undef DO_ZZZ_TB
 
 #define DO_ZZZ_WTB(NAME, TYPEW, TYPEN, HW, HN, OP) \

diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index 70900c122f022c8b564d0a673e251e55d0fddaec..19a1f289d8abf7836dc878ed8c2f7f46965845b6 100644 (file)
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -6021,6 +6021,15 @@ DO_SVE2_ZZZ_TB(SADDLBT, saddl, false, true)
 DO_SVE2_ZZZ_TB(SSUBLBT, ssubl, false, true)
 DO_SVE2_ZZZ_TB(SSUBLTB, ssubl, true, false)
 
+DO_SVE2_ZZZ_TB(SQDMULLB_zzz, sqdmull_zzz, false, false)
+DO_SVE2_ZZZ_TB(SQDMULLT_zzz, sqdmull_zzz, true, true)
+
+DO_SVE2_ZZZ_TB(SMULLB_zzz, smull_zzz, false, false)
+DO_SVE2_ZZZ_TB(SMULLT_zzz, smull_zzz, true, true)
+
+DO_SVE2_ZZZ_TB(UMULLB_zzz, umull_zzz, false, false)
+DO_SVE2_ZZZ_TB(UMULLT_zzz, umull_zzz, true, true)
+
 #define DO_SVE2_ZZZ_WTB(NAME, name, SEL2) \
 static bool trans_##NAME(DisasContext *s, arg_rrr_esz *a)       \
 {                                                               \