[PATCH 24/61] target/arm: Implement SME2 SMOPS, UMOPS (2-way)

[Richard Henderson]

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/arm/tcg/helper-sme.h    |  4 ++++
 target/arm/tcg/sme_helper.c    | 37 +++++++++++++++++++++++++---------
 target/arm/tcg/translate-sme.c |  2 ++
 target/arm/tcg/sme.decode      |  2 ++
 4 files changed, 35 insertions(+), 10 deletions(-)

diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h
index 17d1a7c102..ecd06f2cd1 100644
--- a/target/arm/tcg/helper-sme.h
+++ b/target/arm/tcg/helper-sme.h
@@ -156,3 +156,7 @@ DEF_HELPER_FLAGS_6(sme_usmopa_d, TCG_CALL_NO_RWG,
 
 DEF_HELPER_FLAGS_6(sme2_bmopa_s, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sme2_smopa2_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sme2_umopa2_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c
index 6d8e2cedc9..d973d83957 100644
--- a/target/arm/tcg/sme_helper.c
+++ b/target/arm/tcg/sme_helper.c
@@ -1231,7 +1231,7 @@ static inline void do_imopa_d(uint64_t *za, uint64_t *zn, 
uint64_t *zm,
     }
 }
 
-#define DEF_IMOP_32(NAME, NTYPE, MTYPE) \
+#define DEF_IMOP_8x4_32(NAME, NTYPE, MTYPE) \
 static uint32_t NAME(uint32_t n, uint32_t m, uint32_t a, uint8_t p, bool neg) \
 {                                                                           \
     uint32_t sum = 0;                                                       \
@@ -1244,7 +1244,7 @@ static uint32_t NAME(uint32_t n, uint32_t m, uint32_t a, 
uint8_t p, bool neg) \
     return neg ? a - sum : a + sum;                                         \
 }
 
-#define DEF_IMOP_64(NAME, NTYPE, MTYPE) \
+#define DEF_IMOP_16x4_64(NAME, NTYPE, MTYPE) \
 static uint64_t NAME(uint64_t n, uint64_t m, uint64_t a, uint8_t p, bool neg) \
 {                                                                           \
     uint64_t sum = 0;                                                       \
@@ -1257,15 +1257,15 @@ static uint64_t NAME(uint64_t n, uint64_t m, uint64_t 
a, uint8_t p, bool neg) \
     return neg ? a - sum : a + sum;                                         \
 }
 
-DEF_IMOP_32(smopa_s, int8_t, int8_t)
-DEF_IMOP_32(umopa_s, uint8_t, uint8_t)
-DEF_IMOP_32(sumopa_s, int8_t, uint8_t)
-DEF_IMOP_32(usmopa_s, uint8_t, int8_t)
+DEF_IMOP_8x4_32(smopa_s, int8_t, int8_t)
+DEF_IMOP_8x4_32(umopa_s, uint8_t, uint8_t)
+DEF_IMOP_8x4_32(sumopa_s, int8_t, uint8_t)
+DEF_IMOP_8x4_32(usmopa_s, uint8_t, int8_t)
 
-DEF_IMOP_64(smopa_d, int16_t, int16_t)
-DEF_IMOP_64(umopa_d, uint16_t, uint16_t)
-DEF_IMOP_64(sumopa_d, int16_t, uint16_t)
-DEF_IMOP_64(usmopa_d, uint16_t, int16_t)
+DEF_IMOP_16x4_64(smopa_d, int16_t, int16_t)
+DEF_IMOP_16x4_64(umopa_d, uint16_t, uint16_t)
+DEF_IMOP_16x4_64(sumopa_d, int16_t, uint16_t)
+DEF_IMOP_16x4_64(usmopa_d, uint16_t, int16_t)
 
 #define DEF_IMOPH(P, NAME, S) \
     void HELPER(P##_##NAME##_##S)(void *vza, void *vzn, void *vzm,          \
@@ -1295,3 +1295,20 @@ static uint32_t bmopa_s(uint32_t n, uint32_t m, uint32_t 
a, uint8_t p, bool neg)
 }
 
 DEF_IMOPH(sme2, bmopa, s)
+
+#define DEF_IMOP_16x2_32(NAME, NTYPE, MTYPE) \
+static uint32_t NAME(uint32_t n, uint32_t m, uint32_t a, uint8_t p, bool neg) \
+{                                                                           \
+    uint32_t sum = 0;                                                       \
+    /* Apply P to N as a mask, making the inactive elements 0. */           \
+    n &= expand_pred_h(p);                                                  \
+    sum += (NTYPE)(n >> 0) * (MTYPE)(m >> 0);                               \
+    sum += (NTYPE)(n >> 16) * (MTYPE)(m >> 16);                             \
+    return neg ? a - sum : a + sum;                                         \
+}
+
+DEF_IMOP_16x2_32(smopa2_s, int16_t, int16_t)
+DEF_IMOP_16x2_32(umopa2_s, uint16_t, uint16_t)
+
+DEF_IMOPH(sme2, smopa2, s)
+DEF_IMOPH(sme2, umopa2, s)
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index 25139cb7aa..57c7aacb6d 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -509,3 +509,5 @@ TRANS_FEAT(SUMOPA_d, aa64_sme_i16i64, do_outprod, a, MO_64, 
gen_helper_sme_sumop
 TRANS_FEAT(USMOPA_d, aa64_sme_i16i64, do_outprod, a, MO_64, 
gen_helper_sme_usmopa_d)
 
 TRANS_FEAT(BMOPA, aa64_sme2, do_outprod, a, MO_32, gen_helper_sme2_bmopa_s)
+TRANS_FEAT(SMOPA2_s, aa64_sme2, do_outprod, a, MO_32, gen_helper_sme2_smopa2_s)
+TRANS_FEAT(UMOPA2_s, aa64_sme2, do_outprod, a, MO_32, gen_helper_sme2_umopa2_s)
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index de8d04cb87..36f369d02a 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -167,3 +167,5 @@ USMOPA_d        1010000 1 11 0 ..... ... ... ..... . 0 ...  
    @op_64
 UMOPA_d         1010000 1 11 1 ..... ... ... ..... . 0 ...      @op_64
 
 BMOPA           1000000 0 10 0 ..... ... ... ..... . 10 ..      @op_32
+SMOPA2_s        1010000 0 10 0 ..... ... ... ..... . 10 ..      @op_32
+UMOPA2_s        1010000 1 10 0 ..... ... ... ..... . 10 ..      @op_32
-- 
2.43.0