[PATCH v7 67/92] target/arm: Implement SVE mixed sign dot product

[Richard Henderson]

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/arm/helper.h        |  1 +
 target/arm/sve.decode      |  4 ++++
 target/arm/translate-sve.c | 16 ++++++++++++++++
 target/arm/vec_helper.c    |  1 +
 4 files changed, 22 insertions(+)

diff --git a/target/arm/helper.h b/target/arm/helper.h
index e4c6458f98..2e212ae96b 100644
--- a/target/arm/helper.h
+++ b/target/arm/helper.h
@@ -612,6 +612,7 @@ DEF_HELPER_FLAGS_5(gvec_sdot_b, TCG_CALL_NO_RWG, void, ptr, 
ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_5(gvec_udot_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_5(gvec_sdot_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_5(gvec_udot_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_usdot_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, 
i32)
 
 DEF_HELPER_FLAGS_5(gvec_sdot_idx_b, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index c6b32a3f69..9f037fe5a7 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -1530,6 +1530,10 @@ UMLSLT_zzzw     01000100 .. 0 ..... 010 111 ..... .....  
@rda_rn_rm
 CMLA_zzzz       01000100 esz:2 0 rm:5 0010 rot:2 rn:5 rd:5  ra=%reg_movprfx
 SQRDCMLAH_zzzz  01000100 esz:2 0 rm:5 0011 rot:2 rn:5 rd:5  ra=%reg_movprfx
 
+## SVE mixed sign dot product
+
+USDOT_zzzz      01000100 .. 0 ..... 011 110 ..... .....  @rda_rn_rm
+
 ### SVE2 floating point matrix multiply accumulate
 
 FMMLA           01100100 .. 1 ..... 111001 ..... .....  @rda_rn_rm
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index 30894a4143..ae078b095a 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -8132,3 +8132,19 @@ static bool trans_SQRDCMLAH_zzzz(DisasContext *s, 
arg_SQRDCMLAH_zzzz *a)
     }
     return true;
 }
+
+static bool trans_USDOT_zzzz(DisasContext *s, arg_USDOT_zzzz *a)
+{
+    if (a->esz != 2 || !dc_isar_feature(aa64_sve_i8mm, s)) {
+        return false;
+    }
+    if (sve_access_check(s)) {
+        unsigned vsz = vec_full_reg_size(s);
+        tcg_gen_gvec_4_ool(vec_full_reg_offset(s, a->rd),
+                           vec_full_reg_offset(s, a->rn),
+                           vec_full_reg_offset(s, a->rm),
+                           vec_full_reg_offset(s, a->ra),
+                           vsz, vsz, 0, gen_helper_gvec_usdot_b);
+    }
+    return true;
+}
diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c
index f128b41eac..21ae1258f2 100644
--- a/target/arm/vec_helper.c
+++ b/target/arm/vec_helper.c
@@ -566,6 +566,7 @@ void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, 
uint32_t desc)  \
 
 DO_DOT(gvec_sdot_b, int32_t, int8_t, int8_t)
 DO_DOT(gvec_udot_b, uint32_t, uint8_t, uint8_t)
+DO_DOT(gvec_usdot_b, uint32_t, uint8_t, int8_t)
 DO_DOT(gvec_sdot_h, int64_t, int16_t, int16_t)
 DO_DOT(gvec_udot_h, uint64_t, uint16_t, uint16_t)
 
-- 
2.25.1