diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index 76c41b9bdb..e8db9f39b1 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -6106,8 +6106,14 @@ static gen_helper_gvec_3_ptr * const f_vector_fcadd[3] = {
     gen_helper_gvec_fcadds,
     gen_helper_gvec_fcaddd,
 };
-TRANS_FEAT(FCADD_90, aa64_fcma, do_fp3_vector, a, 0, f_vector_fcadd)
-TRANS_FEAT(FCADD_270, aa64_fcma, do_fp3_vector, a, 1, f_vector_fcadd)
+/*
+ * Encode FPCR.AH into the data so the helper knows whether the
+ * negations it does should avoid flipping the sign bit on a NaN
+ */
+TRANS_FEAT(FCADD_90, aa64_fcma, do_fp3_vector, a, 0 | (s->fpcr_ah << 1),
+           f_vector_fcadd)
+TRANS_FEAT(FCADD_270, aa64_fcma, do_fp3_vector, a, 1 | (s->fpcr_ah << 1),
+           f_vector_fcadd)
 
 static bool trans_FCMLA_v(DisasContext *s, arg_FCMLA_v *a)
 {
diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c
index 0b84a562c0..b181b9734d 100644
--- a/target/arm/tcg/vec_helper.c
+++ b/target/arm/tcg/vec_helper.c
@@ -879,19 +879,21 @@ void HELPER(gvec_fcaddh)(void *vd, void *vn, void *vm,
     float16 *d = vd;
     float16 *n = vn;
     float16 *m = vm;
-    uint32_t neg_real = extract32(desc, SIMD_DATA_SHIFT, 1);
-    uint32_t neg_imag = neg_real ^ 1;
+    bool rot = extract32(desc, SIMD_DATA_SHIFT, 1);
+    bool fpcr_ah = extract64(desc, SIMD_DATA_SHIFT + 1, 1);
     uintptr_t i;
 
-    /* Shift boolean to the sign bit so we can xor to negate.  */
-    neg_real <<= 15;
-    neg_imag <<= 15;
-
     for (i = 0; i < opr_sz / 2; i += 2) {
         float16 e0 = n[H2(i)];
-        float16 e1 = m[H2(i + 1)] ^ neg_imag;
+        float16 e1 = m[H2(i + 1)];
         float16 e2 = n[H2(i + 1)];
-        float16 e3 = m[H2(i)] ^ neg_real;
+        float16 e3 = m[H2(i)];
+
+        if (rot) {
+            e3 = float16_maybe_ah_chs(e3, fpcr_ah);
+        } else {
+            e1 = float16_maybe_ah_chs(e1, fpcr_ah);
+        }
 
         d[H2(i)] = float16_add(e0, e1, fpst);
         d[H2(i + 1)] = float16_add(e2, e3, fpst);
@@ -906,19 +908,21 @@ void HELPER(gvec_fcadds)(void *vd, void *vn, void *vm,
     float32 *d = vd;
     float32 *n = vn;
     float32 *m = vm;
-    uint32_t neg_real = extract32(desc, SIMD_DATA_SHIFT, 1);
-    uint32_t neg_imag = neg_real ^ 1;
+    bool rot = extract32(desc, SIMD_DATA_SHIFT, 1);
+    bool fpcr_ah = extract64(desc, SIMD_DATA_SHIFT + 1, 1);
     uintptr_t i;
 
-    /* Shift boolean to the sign bit so we can xor to negate.  */
-    neg_real <<= 31;
-    neg_imag <<= 31;
-
     for (i = 0; i < opr_sz / 4; i += 2) {
         float32 e0 = n[H4(i)];
-        float32 e1 = m[H4(i + 1)] ^ neg_imag;
+        float32 e1 = m[H4(i + 1)];
         float32 e2 = n[H4(i + 1)];
-        float32 e3 = m[H4(i)] ^ neg_real;
+        float32 e3 = m[H4(i)];
+
+        if (rot) {
+            e3 = float32_maybe_ah_chs(e3, fpcr_ah);
+        } else {
+            e1 = float32_maybe_ah_chs(e1, fpcr_ah);
+        }
 
         d[H4(i)] = float32_add(e0, e1, fpst);
         d[H4(i + 1)] = float32_add(e2, e3, fpst);
@@ -933,19 +937,21 @@ void HELPER(gvec_fcaddd)(void *vd, void *vn, void *vm,
     float64 *d = vd;
     float64 *n = vn;
     float64 *m = vm;
-    uint64_t neg_real = extract64(desc, SIMD_DATA_SHIFT, 1);
-    uint64_t neg_imag = neg_real ^ 1;
+    bool rot = extract32(desc, SIMD_DATA_SHIFT, 1);
+    bool fpcr_ah = extract64(desc, SIMD_DATA_SHIFT + 1, 1);
     uintptr_t i;
 
-    /* Shift boolean to the sign bit so we can xor to negate.  */
-    neg_real <<= 63;
-    neg_imag <<= 63;
-
     for (i = 0; i < opr_sz / 8; i += 2) {
         float64 e0 = n[i];
-        float64 e1 = m[i + 1] ^ neg_imag;
+        float64 e1 = m[i + 1];
         float64 e2 = n[i + 1];
-        float64 e3 = m[i] ^ neg_real;
+        float64 e3 = m[i];
+
+        if (rot) {
+            e3 = float64_maybe_ah_chs(e3, fpcr_ah);
+        } else {
+            e1 = float64_maybe_ah_chs(e1, fpcr_ah);
+        }
 
         d[i] = float64_add(e0, e1, fpst);
         d[i + 1] = float64_add(e2, e3, fpst);