[PATCH v4 34/78] target/arm: Implement SVE2 saturating multiply-add long

[Richard Henderson]

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/arm/helper-sve.h    | 14 ++++++++++
 target/arm/sve.decode      | 14 ++++++++++
 target/arm/sve_helper.c    | 30 +++++++++++++++++++++
 target/arm/translate-sve.c | 54 ++++++++++++++++++++++++++++++++++++++
 4 files changed, 112 insertions(+)

diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h
index 11dc6870de..d8f390617c 100644
--- a/target/arm/helper-sve.h
+++ b/target/arm/helper-sve.h
@@ -2559,3 +2559,17 @@ DEF_HELPER_FLAGS_5(sve2_bcax, TCG_CALL_NO_RWG, void, 
ptr, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_5(sve2_bsl1n, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_5(sve2_bsl2n, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_5(sve2_nbsl, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(sve2_sqdmlal_zzzw_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_sqdmlal_zzzw_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_sqdmlal_zzzw_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(sve2_sqdmlsl_zzzw_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_sqdmlsl_zzzw_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_sqdmlsl_zzzw_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index 47fca5e12d..52f615b39e 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -1332,3 +1332,17 @@ FMAXNMP         01100100 .. 010 10 0 100 ... ..... ..... 
@rdn_pg_rm
 FMINNMP         01100100 .. 010 10 1 100 ... ..... ..... @rdn_pg_rm
 FMAXP           01100100 .. 010 11 0 100 ... ..... ..... @rdn_pg_rm
 FMINP           01100100 .. 010 11 1 100 ... ..... ..... @rdn_pg_rm
+
+#### SVE Integer Multiply-Add (unpredicated)
+
+## SVE2 saturating multiply-add long
+
+SQDMLALB_zzzw   01000100 .. 0 ..... 0110 00 ..... .....  @rda_rn_rm
+SQDMLALT_zzzw   01000100 .. 0 ..... 0110 01 ..... .....  @rda_rn_rm
+SQDMLSLB_zzzw   01000100 .. 0 ..... 0110 10 ..... .....  @rda_rn_rm
+SQDMLSLT_zzzw   01000100 .. 0 ..... 0110 11 ..... .....  @rda_rn_rm
+
+## SVE2 saturating multiply-add interleaved long
+
+SQDMLALBT       01000100 .. 0 ..... 00001 0 ..... .....  @rda_rn_rm
+SQDMLSLBT       01000100 .. 0 ..... 00001 1 ..... .....  @rda_rn_rm
diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index 7a2af036c1..bd7332be43 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -1400,6 +1400,36 @@ void HELPER(sve2_adcl_d)(void *vd, void *vn, void *vm, 
void *va, uint32_t desc)
     }
 }
 
+#define DO_SQDMLAL(NAME, TYPEW, TYPEN, HW, HN, DMUL_OP, SUM_OP) \
+void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \
+{                                                                       \
+    intptr_t i, opr_sz = simd_oprsz(desc);                              \
+    int sel1 = extract32(desc, SIMD_DATA_SHIFT, 1) * sizeof(TYPEN);     \
+    int sel2 = extract32(desc, SIMD_DATA_SHIFT + 1, 1) * sizeof(TYPEN); \
+    for (i = 0; i < opr_sz; i += sizeof(TYPEW)) {                       \
+        TYPEW nn = *(TYPEN *)(vn + HN(i + sel1));                       \
+        TYPEW mm = *(TYPEN *)(vm + HN(i + sel2));                       \
+        TYPEW aa = *(TYPEW *)(va + HW(i));                              \
+        *(TYPEW *)(vd + HW(i)) = SUM_OP(aa, DMUL_OP(nn, mm));           \
+    }                                                                   \
+}
+
+DO_SQDMLAL(sve2_sqdmlal_zzzw_h, int16_t, int8_t, H1_2, H1,
+           do_sqdmull_h, DO_SQADD_H)
+DO_SQDMLAL(sve2_sqdmlal_zzzw_s, int32_t, int16_t, H1_4, H1_2,
+           do_sqdmull_s, DO_SQADD_S)
+DO_SQDMLAL(sve2_sqdmlal_zzzw_d, int64_t, int32_t,     , H1_4,
+           do_sqdmull_d, do_sqadd_d)
+
+DO_SQDMLAL(sve2_sqdmlsl_zzzw_h, int16_t, int8_t, H1_2, H1,
+           do_sqdmull_h, DO_SQSUB_H)
+DO_SQDMLAL(sve2_sqdmlsl_zzzw_s, int32_t, int16_t, H1_4, H1_2,
+           do_sqdmull_s, DO_SQSUB_S)
+DO_SQDMLAL(sve2_sqdmlsl_zzzw_d, int64_t, int32_t,     , H1_4,
+           do_sqdmull_d, do_sqsub_d)
+
+#undef DO_SQDMLAL
+
 #define DO_BITPERM(NAME, TYPE, OP) \
 void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \
 {                                                              \
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index c339702cd3..15cbca0674 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -7509,3 +7509,57 @@ DO_SVE2_ZPZZ_FP(FMAXNMP, fmaxnmp)
 DO_SVE2_ZPZZ_FP(FMINNMP, fminnmp)
 DO_SVE2_ZPZZ_FP(FMAXP, fmaxp)
 DO_SVE2_ZPZZ_FP(FMINP, fminp)
+
+/*
+ * SVE Integer Multiply-Add (unpredicated)
+ */
+
+static bool do_sqdmlal_zzzw(DisasContext *s, arg_rrrr_esz *a,
+                            bool sel1, bool sel2)
+{
+    static gen_helper_gvec_4 * const fns[] = {
+        NULL,                           gen_helper_sve2_sqdmlal_zzzw_h,
+        gen_helper_sve2_sqdmlal_zzzw_s, gen_helper_sve2_sqdmlal_zzzw_d,
+    };
+    return do_sve2_zzzz_ool(s, a, fns[a->esz], (sel2 << 1) | sel1);
+}
+
+static bool do_sqdmlsl_zzzw(DisasContext *s, arg_rrrr_esz *a,
+                            bool sel1, bool sel2)
+{
+    static gen_helper_gvec_4 * const fns[] = {
+        NULL,                           gen_helper_sve2_sqdmlsl_zzzw_h,
+        gen_helper_sve2_sqdmlsl_zzzw_s, gen_helper_sve2_sqdmlsl_zzzw_d,
+    };
+    return do_sve2_zzzz_ool(s, a, fns[a->esz], (sel2 << 1) | sel1);
+}
+
+static bool trans_SQDMLALB_zzzw(DisasContext *s, arg_rrrr_esz *a)
+{
+    return do_sqdmlal_zzzw(s, a, false, false);
+}
+
+static bool trans_SQDMLALT_zzzw(DisasContext *s, arg_rrrr_esz *a)
+{
+    return do_sqdmlal_zzzw(s, a, true, true);
+}
+
+static bool trans_SQDMLALBT(DisasContext *s, arg_rrrr_esz *a)
+{
+    return do_sqdmlal_zzzw(s, a, false, true);
+}
+
+static bool trans_SQDMLSLB_zzzw(DisasContext *s, arg_rrrr_esz *a)
+{
+    return do_sqdmlsl_zzzw(s, a, false, false);
+}
+
+static bool trans_SQDMLSLT_zzzw(DisasContext *s, arg_rrrr_esz *a)
+{
+    return do_sqdmlsl_zzzw(s, a, true, true);
+}
+
+static bool trans_SQDMLSLBT(DisasContext *s, arg_rrrr_esz *a)
+{
+    return do_sqdmlsl_zzzw(s, a, false, true);
+}
-- 
2.25.1