target/arm: Implement SME2 BFMOPA (non-widening)

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: 20250704142112.1018902-106-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

1 files changed, 51 insertions, 0 deletions

diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c
index d23d9f08d2..bb8ed1ed0e 100644
--- a/target/arm/tcg/sme_helper.c
+++ b/target/arm/tcg/sme_helper.c
@@ -1144,6 +1144,57 @@ void HELPER(sme_ah_fmops_d)(void *vza, void *vzn, void *vzm, void *vpn,
                float_muladd_negate_product);
 }
 
+static void do_bfmopa(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 = bfloat16_muladd(n, *m, *a, negf, fpst);
+                        }
+                        col += 2;
+                        pb >>= 2;
+                    } while (col & 15);
+                }
+            }
+            row += 2;
+            pa >>= 2;
+        } while (row & 15);
+    }
+}
+
+void HELPER(sme_bfmopa)(void *vza, void *vzn, void *vzm, void *vpn,
+                        void *vpm, float_status *fpst, uint32_t desc)
+{
+    do_bfmopa(vza, vzn, vzm, vpn, vpm, fpst, desc, 0, 0);
+}
+
+void HELPER(sme_bfmops)(void *vza, void *vzn, void *vzm, void *vpn,
+                        void *vpm, float_status *fpst, uint32_t desc)
+{
+    do_bfmopa(vza, vzn, vzm, vpn, vpm, fpst, desc, 1u << 15, 0);
+}
+
+void HELPER(sme_ah_bfmops)(void *vza, void *vzn, void *vzm, void *vpn,
+                           void *vpm, float_status *fpst, uint32_t desc)
+{
+    do_bfmopa(vza, vzn, vzm, vpn, vpm, fpst, desc, 0,
+              float_muladd_negate_product);
+}
+
 /*
  * Alter PAIR as needed for controlling predicates being false,
  * and for NEG on an enabled row element.