diff mbox series

[v7,66/92] target/arm: Implement SVE mixed sign dot product (indexed)

Message ID 20210525010358.152808-67-richard.henderson@linaro.org (mailing list archive)
State New, archived
Headers show
Series target/arm: Implement SVE2 | expand

Commit Message

Richard Henderson May 25, 2021, 1:03 a.m. UTC
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
v7: Macroize the helpers.
---
 target/arm/cpu.h           |  5 +++++
 target/arm/helper.h        |  4 ++++
 target/arm/sve.decode      |  4 ++++
 target/arm/translate-sve.c | 16 ++++++++++++++++
 target/arm/vec_helper.c    |  2 ++
 5 files changed, 31 insertions(+)
diff mbox series

Patch

diff --git a/target/arm/cpu.h b/target/arm/cpu.h
index 595bc6349d..0a41142d35 100644
--- a/target/arm/cpu.h
+++ b/target/arm/cpu.h
@@ -4246,6 +4246,11 @@  static inline bool isar_feature_aa64_sve2_bitperm(const ARMISARegisters *id)
     return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, BITPERM) != 0;
 }
 
+static inline bool isar_feature_aa64_sve_i8mm(const ARMISARegisters *id)
+{
+    return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, I8MM) != 0;
+}
+
 static inline bool isar_feature_aa64_sve_f32mm(const ARMISARegisters *id)
 {
     return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, F32MM) != 0;
diff --git a/target/arm/helper.h b/target/arm/helper.h
index e7c463fff5..e4c6458f98 100644
--- a/target/arm/helper.h
+++ b/target/arm/helper.h
@@ -621,6 +621,10 @@  DEF_HELPER_FLAGS_5(gvec_sdot_idx_h, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_5(gvec_udot_idx_h, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_sudot_idx_b, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_usdot_idx_b, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
 
 DEF_HELPER_FLAGS_5(gvec_fcaddh, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index 0339410cf7..c6b32a3f69 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -816,6 +816,10 @@  SQRDMLSH_zzxz_h 01000100 0. 1 ..... 000101 ..... .....   @rrxr_3 esz=1
 SQRDMLSH_zzxz_s 01000100 10 1 ..... 000101 ..... .....   @rrxr_2 esz=2
 SQRDMLSH_zzxz_d 01000100 11 1 ..... 000101 ..... .....   @rrxr_1 esz=3
 
+# SVE mixed sign dot product (indexed)
+USDOT_zzxw_s    01000100 10 1 ..... 000110 ..... .....   @rrxr_2 esz=2
+SUDOT_zzxw_s    01000100 10 1 ..... 000111 ..... .....   @rrxr_2 esz=2
+
 # SVE2 saturating multiply-add (indexed)
 SQDMLALB_zzxw_s 01000100 10 1 ..... 0010.0 ..... .....   @rrxr_3a esz=2
 SQDMLALB_zzxw_d 01000100 11 1 ..... 0010.0 ..... .....   @rrxr_2a esz=3
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index b454f50a6b..30894a4143 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -3838,6 +3838,22 @@  DO_RRXR(trans_SDOT_zzxw_d, gen_helper_gvec_sdot_idx_h)
 DO_RRXR(trans_UDOT_zzxw_s, gen_helper_gvec_udot_idx_b)
 DO_RRXR(trans_UDOT_zzxw_d, gen_helper_gvec_udot_idx_h)
 
+static bool trans_SUDOT_zzxw_s(DisasContext *s, arg_rrxr_esz *a)
+{
+    if (!dc_isar_feature(aa64_sve_i8mm, s)) {
+        return false;
+    }
+    return do_zzxz_ool(s, a, gen_helper_gvec_sudot_idx_b);
+}
+
+static bool trans_USDOT_zzxw_s(DisasContext *s, arg_rrxr_esz *a)
+{
+    if (!dc_isar_feature(aa64_sve_i8mm, s)) {
+        return false;
+    }
+    return do_zzxz_ool(s, a, gen_helper_gvec_usdot_idx_b);
+}
+
 #undef DO_RRXR
 
 static bool do_sve2_zzz_data(DisasContext *s, int rd, int rn, int rm, int data,
diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c
index 1c4266a9c0..f128b41eac 100644
--- a/target/arm/vec_helper.c
+++ b/target/arm/vec_helper.c
@@ -598,6 +598,8 @@  void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc)  \
 
 DO_DOT_IDX(gvec_sdot_idx_b, int32_t, int8_t, int8_t, H4)
 DO_DOT_IDX(gvec_udot_idx_b, uint32_t, uint8_t, uint8_t, H4)
+DO_DOT_IDX(gvec_sudot_idx_b, int32_t, int8_t, uint8_t, H4)
+DO_DOT_IDX(gvec_usdot_idx_b, int32_t, uint8_t, int8_t, H4)
 DO_DOT_IDX(gvec_sdot_idx_h, int64_t, int16_t, int16_t, )
 DO_DOT_IDX(gvec_udot_idx_h, uint64_t, uint16_t, uint16_t, )