target/arm: Handle FPCR.AH in negation steps in SVE FCADD

The negation steps in FCADD must honour FPCR.AH's "don't change the
sign of a NaN" semantics.  Implement this in the same way we did for
the base ASIMD FCADD, by encoding FPCR.AH into the SIMD data field
passed to the helper and using that to decide whether to negate the
values.

The construction of neg_imag and neg_real were done to make it easy
to apply both in parallel with two simple logical operations.  This
changed with FPCR.AH, which is more complex than that. Switch to
an approach that follows the pseudocode more closely, by extracting
the 'rot=1' parameter from the SIMD data field and changing the
sign of the appropriate input value.

Note that there was a naming issue with neg_imag and neg_real.
They were named backward, with neg_imag being non-zero for rot=1,
and vice versa.  This was combined with reversed usage within the
loop, so that the negation in the end turned out correct.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>

target/arm/tcg/sve_helper.c

@@ -5131,8 +5131,8 @@ void HELPER(sve_fcadd_h)(void *vd, void *vn, void *vm, void *vg,
 {
     intptr_t j, i = simd_oprsz(desc);
     uint64_t *g = vg;
-    float16 neg_imag = float16_set_sign(0, simd_data(desc));
+    bool rot = extract32(desc, SIMD_DATA_SHIFT, 1);
-    float16 neg_real = float16_chs(neg_imag);
+    bool fpcr_ah = extract32(desc, SIMD_DATA_SHIFT + 1, 1);
 
     do {
         uint64_t pg = g[(i - 1) >> 6];
@@ -5144,9 +5144,15 @@ void HELPER(sve_fcadd_h)(void *vd, void *vn, void *vm, void *vg,
             i -= 2 * sizeof(float16);
 
             e0 = *(float16 *)(vn + H1_2(i));
-            e1 = *(float16 *)(vm + H1_2(j)) ^ neg_real;
+            e1 = *(float16 *)(vm + H1_2(j));
             e2 = *(float16 *)(vn + H1_2(j));
-            e3 = *(float16 *)(vm + H1_2(i)) ^ neg_imag;
+            e3 = *(float16 *)(vm + H1_2(i));
+
+            if (rot) {
+                e3 = float16_maybe_ah_chs(e3, fpcr_ah);
+            } else {
+                e1 = float16_maybe_ah_chs(e1, fpcr_ah);
+            }
 
             if (likely((pg >> (i & 63)) & 1)) {
                 *(float16 *)(vd + H1_2(i)) = float16_add(e0, e1, s);
@@ -5163,8 +5169,8 @@ void HELPER(sve_fcadd_s)(void *vd, void *vn, void *vm, void *vg,
 {
     intptr_t j, i = simd_oprsz(desc);
     uint64_t *g = vg;
-    float32 neg_imag = float32_set_sign(0, simd_data(desc));
+    bool rot = extract32(desc, SIMD_DATA_SHIFT, 1);
-    float32 neg_real = float32_chs(neg_imag);
+    bool fpcr_ah = extract32(desc, SIMD_DATA_SHIFT + 1, 1);
 
     do {
         uint64_t pg = g[(i - 1) >> 6];
@@ -5176,9 +5182,15 @@ void HELPER(sve_fcadd_s)(void *vd, void *vn, void *vm, void *vg,
             i -= 2 * sizeof(float32);
 
             e0 = *(float32 *)(vn + H1_2(i));
-            e1 = *(float32 *)(vm + H1_2(j)) ^ neg_real;
+            e1 = *(float32 *)(vm + H1_2(j));
             e2 = *(float32 *)(vn + H1_2(j));
-            e3 = *(float32 *)(vm + H1_2(i)) ^ neg_imag;
+            e3 = *(float32 *)(vm + H1_2(i));
+
+            if (rot) {
+                e3 = float32_maybe_ah_chs(e3, fpcr_ah);
+            } else {
+                e1 = float32_maybe_ah_chs(e1, fpcr_ah);
+            }
 
             if (likely((pg >> (i & 63)) & 1)) {
                 *(float32 *)(vd + H1_2(i)) = float32_add(e0, e1, s);
@@ -5195,8 +5207,8 @@ void HELPER(sve_fcadd_d)(void *vd, void *vn, void *vm, void *vg,
 {
     intptr_t j, i = simd_oprsz(desc);
     uint64_t *g = vg;
-    float64 neg_imag = float64_set_sign(0, simd_data(desc));
+    bool rot = extract32(desc, SIMD_DATA_SHIFT, 1);
-    float64 neg_real = float64_chs(neg_imag);
+    bool fpcr_ah = extract32(desc, SIMD_DATA_SHIFT + 1, 1);
 
     do {
         uint64_t pg = g[(i - 1) >> 6];
@@ -5208,9 +5220,15 @@ void HELPER(sve_fcadd_d)(void *vd, void *vn, void *vm, void *vg,
             i -= 2 * sizeof(float64);
 
             e0 = *(float64 *)(vn + H1_2(i));
-            e1 = *(float64 *)(vm + H1_2(j)) ^ neg_real;
+            e1 = *(float64 *)(vm + H1_2(j));
             e2 = *(float64 *)(vn + H1_2(j));
-            e3 = *(float64 *)(vm + H1_2(i)) ^ neg_imag;
+            e3 = *(float64 *)(vm + H1_2(i));
+
+            if (rot) {
+                e3 = float64_maybe_ah_chs(e3, fpcr_ah);
+            } else {
+                e1 = float64_maybe_ah_chs(e1, fpcr_ah);
+            }
 
             if (likely((pg >> (i & 63)) & 1)) {
                 *(float64 *)(vd + H1_2(i)) = float64_add(e0, e1, s);

target/arm/tcg/translate-sve.c

@@ -3916,7 +3916,7 @@ static gen_helper_gvec_4_ptr * const fcadd_fns[] = {
     gen_helper_sve_fcadd_s, gen_helper_sve_fcadd_d,
 };
 TRANS_FEAT(FCADD, aa64_sve, gen_gvec_fpst_zzzp, fcadd_fns[a->esz],
-           a->rd, a->rn, a->rm, a->pg, a->rot,
+           a->rd, a->rn, a->rm, a->pg, a->rot | (s->fpcr_ah << 1),
            a->esz == MO_16 ? FPST_A64_F16 : FPST_A64)
 
 #define DO_FMLA(NAME, name) \

target/arm/tcg/vec_internal.h

@@ -20,6 +20,8 @@
 #ifndef TARGET_ARM_VEC_INTERNAL_H
 #define TARGET_ARM_VEC_INTERNAL_H
 
+#include "fpu/softfloat.h"
+
 /*
  * Note that vector data is stored in host-endian 64-bit chunks,
  * so addressing units smaller than that needs a host-endian fixup.
@@ -265,4 +267,19 @@ float32 bfdotadd_ebf(float32 sum, uint32_t e1, uint32_t e2,
  */
 bool is_ebf(CPUARMState *env, float_status *statusp, float_status *oddstatusp);
 
+static inline float16 float16_maybe_ah_chs(float16 a, bool fpcr_ah)
+{
+    return fpcr_ah && float16_is_any_nan(a) ? a : float16_chs(a);
+}
+
+static inline float32 float32_maybe_ah_chs(float32 a, bool fpcr_ah)
+{
+    return fpcr_ah && float32_is_any_nan(a) ? a : float32_chs(a);
+}
+
+static inline float64 float64_maybe_ah_chs(float64 a, bool fpcr_ah)
+{
+    return fpcr_ah && float64_is_any_nan(a) ? a : float64_chs(a);
+}
+
 #endif /* TARGET_ARM_VEC_INTERNAL_H */