[PATCH v2 085/100] target/arm: Implement SVE mixed sign dot product

[Richard Henderson]

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/arm/helper.h        |  2 ++
 target/arm/sve.decode      |  4 ++++
 target/arm/translate-sve.c | 16 ++++++++++++++++
 target/arm/vec_helper.c    | 18 ++++++++++++++++++
 4 files changed, 40 insertions(+)

diff --git a/target/arm/helper.h b/target/arm/helper.h
index 6fac613dfc..bfeb327272 100644
--- a/target/arm/helper.h
+++ b/target/arm/helper.h
@@ -578,6 +578,8 @@ 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 51acbfa797..0be8a020f6 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -1523,6 +1523,10 @@ 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 fe4b4b7387..152b0b605d 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -7666,3 +7666,19 @@ 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_sve2_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 e1689d730f..a51cbf2c7e 100644
--- a/target/arm/vec_helper.c
+++ b/target/arm/vec_helper.c
@@ -580,6 +580,24 @@ void HELPER(gvec_udot_b)(void *vd, void *vn, void *vm, 
void *va, uint32_t desc)
     clear_tail(d, opr_sz, simd_maxsz(desc));
 }
 
+void HELPER(gvec_usdot_b)(void *vd, void *vn, void *vm,
+                          void *va, uint32_t desc)
+{
+    intptr_t i, opr_sz = simd_oprsz(desc);
+    int32_t *d = vd, *a = va;
+    uint8_t *n = vn;
+    int8_t *m = vm;
+
+    for (i = 0; i < opr_sz / 4; ++i) {
+        d[i] = (a[i] +
+                n[i * 4 + 0] * m[i * 4 + 0] +
+                n[i * 4 + 1] * m[i * 4 + 1] +
+                n[i * 4 + 2] * m[i * 4 + 2] +
+                n[i * 4 + 3] * m[i * 4 + 3]);
+    }
+    clear_tail(d, opr_sz, simd_maxsz(desc));
+}
+
 void HELPER(gvec_sdot_h)(void *vd, void *vn, void *vm, void *va, uint32_t desc)
 {
     intptr_t i, opr_sz = simd_oprsz(desc);
-- 
2.25.1