1 files changed, 69 insertions, 0 deletions
diff --git a/target/arm/sme_helper.c b/target/arm/sme_helper.c
index f1e924d..7dc76b6 100644
--- a/target/arm/sme_helper.c
+++ b/target/arm/sme_helper.c
@@ -25,6 +25,7 @@
 #include "exec/cpu_ldst.h"
 #include "exec/exec-all.h"
 #include "qemu/int128.h"
+#include "fpu/softfloat.h"
 #include "vec_internal.h"
 #include "sve_ldst_internal.h"
 
@@ -918,3 +919,71 @@ void HELPER(sme_addva_d)(void *vzda, void *vzn, void *vpn,
         }
     }
 }
+
+void HELPER(sme_fmopa_s)(void *vza, void *vzn, void *vzm, void *vpn,
+                         void *vpm, void *vst, uint32_t desc)
+{
+    intptr_t row, col, oprsz = simd_maxsz(desc);
+    uint32_t neg = simd_data(desc) << 31;
+    uint16_t *pn = vpn, *pm = vpm;
+    float_status fpst;
+
+    /*
+     * Make a copy of float_status because this operation does not
+     * update the cumulative fp exception status.  It also produces
+     * default nans.
+     */
+    fpst = *(float_status *)vst;
+    set_default_nan_mode(true, &fpst);
+
+    for (row = 0; row < oprsz; ) {
+        uint16_t pa = pn[H2(row >> 4)];
+        do {
+            if (pa & 1) {
+                void *vza_row = vza + tile_vslice_offset(row);
+                uint32_t n = *(uint32_t *)(vzn + H1_4(row)) ^ neg;
+
+                for (col = 0; col < oprsz; ) {
+                    uint16_t pb = pm[H2(col >> 4)];
+                    do {
+                        if (pb & 1) {
+                            uint32_t *a = vza_row + H1_4(col);
+                            uint32_t *m = vzm + H1_4(col);
+                            *a = float32_muladd(n, *m, *a, 0, vst);
+                        }
+                        col += 4;
+                        pb >>= 4;
+                    } while (col & 15);
+                }
+            }
+            row += 4;
+            pa >>= 4;
+        } while (row & 15);
+    }
+}
+
+void HELPER(sme_fmopa_d)(void *vza, void *vzn, void *vzm, void *vpn,
+                         void *vpm, void *vst, uint32_t desc)
+{
+    intptr_t row, col, oprsz = simd_oprsz(desc) / 8;
+    uint64_t neg = (uint64_t)simd_data(desc) << 63;
+    uint64_t *za = vza, *zn = vzn, *zm = vzm;
+    uint8_t *pn = vpn, *pm = vpm;
+    float_status fpst = *(float_status *)vst;
+
+    set_default_nan_mode(true, &fpst);
+
+    for (row = 0; row < oprsz; ++row) {
+        if (pn[H1(row)] & 1) {
+            uint64_t *za_row = &za[tile_vslice_index(row)];
+            uint64_t n = zn[row] ^ neg;
+
+            for (col = 0; col < oprsz; ++col) {
+                if (pm[H1(col)] & 1) {
+                    uint64_t *a = &za_row[col];
+                    *a = float64_muladd(n, zm[col], *a, 0, &fpst);
+                }
+            }
+        }
+    }
+}