target/arm: Implement FMOPA (non-widening) for fp16

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-105-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

4 files changed, 63 insertions, 0 deletions

diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h
index 2b22c6a..fac70a8 100644
--- a/target/arm/tcg/helper-sme.h
+++ b/target/arm/tcg/helper-sme.h
@@ -137,6 +137,8 @@ DEF_HELPER_FLAGS_5(sme_addva_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
 
 DEF_HELPER_FLAGS_7(sme_fmopa_w_h, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_7(sme_fmopa_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, fpst, i32)
 DEF_HELPER_FLAGS_7(sme_fmopa_s, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, ptr, fpst, i32)
 DEF_HELPER_FLAGS_7(sme_fmopa_d, TCG_CALL_NO_RWG,
@@ -146,6 +148,8 @@ DEF_HELPER_FLAGS_7(sme_bfmopa_w, TCG_CALL_NO_RWG,
 
 DEF_HELPER_FLAGS_7(sme_fmops_w_h, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_7(sme_fmops_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, fpst, i32)
 DEF_HELPER_FLAGS_7(sme_fmops_s, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, ptr, fpst, i32)
 DEF_HELPER_FLAGS_7(sme_fmops_d, TCG_CALL_NO_RWG,
@@ -155,6 +159,8 @@ DEF_HELPER_FLAGS_7(sme_bfmops_w, TCG_CALL_NO_RWG,
 
 DEF_HELPER_FLAGS_7(sme_ah_fmops_w_h, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_7(sme_ah_fmops_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, fpst, i32)
 DEF_HELPER_FLAGS_7(sme_ah_fmops_s, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, ptr, fpst, i32)
 DEF_HELPER_FLAGS_7(sme_ah_fmops_d, TCG_CALL_NO_RWG,
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index 8ad86f7..3c58fdd 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -183,9 +183,11 @@ ADDVA_d         11000000 11 01000 1 ... ... ..... 00 ...        @adda_64
 ### SME Outer Product
 
 &op             zad zn zm pm pn sub:bool
+@op_16          ........ ... zm:5 pm:3 pn:3 zn:5 sub:1 ... zad:1 &op
 @op_32          ........ ... zm:5 pm:3 pn:3 zn:5 sub:1 .. zad:2 &op
 @op_64          ........ ... zm:5 pm:3 pn:3 zn:5 sub:1 .  zad:3 &op
 
+FMOPA_h         10000001 100 ..... ... ... ..... . 100 .        @op_16
 FMOPA_s         10000000 100 ..... ... ... ..... . 00 ..        @op_32
 FMOPA_d         10000000 110 ..... ... ... ..... . 0 ...        @op_64
 
diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c
index eff0ce7..d23d9f0 100644
--- a/target/arm/tcg/sme_helper.c
+++ b/target/arm/tcg/sme_helper.c
@@ -1002,6 +1002,57 @@ void HELPER(sme_addva_d)(void *vzda, void *vzn, void *vpn,
     }
 }
 
+static void do_fmopa_h(void *vza, void *vzn, void *vzm, uint16_t *pn,
+                       uint16_t *pm, float_status *fpst, uint32_t desc,
+                       uint16_t negx, int negf)
+{
+    intptr_t row, col, oprsz = simd_maxsz(desc);
+
+    for (row = 0; row < oprsz; ) {
+        uint16_t pa = pn[H2(row >> 4)];
+        do {
+            if (pa & 1) {
+                void *vza_row = vza + tile_vslice_offset(row);
+                uint16_t n = *(uint32_t *)(vzn + H1_2(row)) ^ negx;
+
+                for (col = 0; col < oprsz; ) {
+                    uint16_t pb = pm[H2(col >> 4)];
+                    do {
+                        if (pb & 1) {
+                            uint16_t *a = vza_row + H1_2(col);
+                            uint16_t *m = vzm + H1_2(col);
+                            *a = float16_muladd(n, *m, *a, negf, fpst);
+                        }
+                        col += 2;
+                        pb >>= 2;
+                    } while (col & 15);
+                }
+            }
+            row += 2;
+            pa >>= 2;
+        } while (row & 15);
+    }
+}
+
+void HELPER(sme_fmopa_h)(void *vza, void *vzn, void *vzm, void *vpn,
+                         void *vpm, float_status *fpst, uint32_t desc)
+{
+    do_fmopa_h(vza, vzn, vzm, vpn, vpm, fpst, desc, 0, 0);
+}
+
+void HELPER(sme_fmops_h)(void *vza, void *vzn, void *vzm, void *vpn,
+                         void *vpm, float_status *fpst, uint32_t desc)
+{
+    do_fmopa_h(vza, vzn, vzm, vpn, vpm, fpst, desc, 1u << 15, 0);
+}
+
+void HELPER(sme_ah_fmops_h)(void *vza, void *vzn, void *vzm, void *vpn,
+                            void *vpm, float_status *fpst, uint32_t desc)
+{
+    do_fmopa_h(vza, vzn, vzm, vpn, vpm, fpst, desc, 0,
+               float_muladd_negate_product);
+}
+
 static void do_fmopa_s(void *vza, void *vzn, void *vzm, uint16_t *pn,
                        uint16_t *pm, float_status *fpst, uint32_t desc,
                        uint32_t negx, int negf)
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index 782f408..119a566 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -569,6 +569,10 @@ TRANS_FEAT(FMOPA_w_h, aa64_sme, do_outprod_env, a, MO_32,
            !a->sub ? gen_helper_sme_fmopa_w_h
            : !s->fpcr_ah ? gen_helper_sme_fmops_w_h
            : gen_helper_sme_ah_fmops_w_h)
+TRANS_FEAT(FMOPA_h, aa64_sme_f16f16, do_outprod_fpst, a, MO_16, FPST_ZA_F16,
+           !a->sub ? gen_helper_sme_fmopa_h
+           : !s->fpcr_ah ? gen_helper_sme_fmops_h
+           : gen_helper_sme_ah_fmops_h)
 TRANS_FEAT(FMOPA_s, aa64_sme, do_outprod_fpst, a, MO_32, FPST_ZA,
            !a->sub ? gen_helper_sme_fmopa_s
            : !s->fpcr_ah ? gen_helper_sme_fmops_s