[PATCH v2 41/69] target/arm: Handle FPCR.AH in negation step in FMLS (indexed)

[Peter Maydell]

Handle the FPCR.AH "don't negate the sign of a NaN" semantics in FMLS
(indexed). We do this by creating 6 new helpers, which allow us to
do the negation either by XOR (for AH=0) or by muladd flags
(for AH=1).

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
[PMM: Mostly from RTH's patch; error in index order into fns[][]
 fixed]
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/arm/helper.h            | 14 ++++++++++++++
 target/arm/tcg/translate-a64.c | 17 +++++++++++------
 target/arm/tcg/translate-sve.c | 31 +++++++++++++++++--------------
 target/arm/tcg/vec_helper.c    | 24 +++++++++++++++---------
 4 files changed, 57 insertions(+), 29 deletions(-)

diff --git a/target/arm/helper.h b/target/arm/helper.h
index 43505d5fedc..be47edff896 100644
--- a/target/arm/helper.h
+++ b/target/arm/helper.h
@@ -813,6 +813,20 @@ DEF_HELPER_FLAGS_6(gvec_fmla_idx_s, TCG_CALL_NO_RWG,
 DEF_HELPER_FLAGS_6(gvec_fmla_idx_d, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, fpst, i32)
 
+DEF_HELPER_FLAGS_6(gvec_fmls_idx_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_6(gvec_fmls_idx_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_6(gvec_fmls_idx_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, fpst, i32)
+
+DEF_HELPER_FLAGS_6(gvec_ah_fmls_idx_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_6(gvec_ah_fmls_idx_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_6(gvec_ah_fmls_idx_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, fpst, i32)
+
 DEF_HELPER_FLAGS_5(gvec_uqadd_b, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_5(gvec_uqadd_h, TCG_CALL_NO_RWG,
diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index 03b629e0ba0..2509a29528e 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -6737,10 +6737,16 @@ TRANS(FMULX_vi, do_fp3_vector_idx, a, 
f_vector_idx_fmulx)
 
 static bool do_fmla_vector_idx(DisasContext *s, arg_qrrx_e *a, bool neg)
 {
-    static gen_helper_gvec_4_ptr * const fns[3] = {
-        gen_helper_gvec_fmla_idx_h,
-        gen_helper_gvec_fmla_idx_s,
-        gen_helper_gvec_fmla_idx_d,
+    static gen_helper_gvec_4_ptr * const fns[3][3] = {
+        { gen_helper_gvec_fmla_idx_h,
+          gen_helper_gvec_fmla_idx_s,
+          gen_helper_gvec_fmla_idx_d },
+        { gen_helper_gvec_fmls_idx_h,
+          gen_helper_gvec_fmls_idx_s,
+          gen_helper_gvec_fmls_idx_d },
+        { gen_helper_gvec_ah_fmls_idx_h,
+          gen_helper_gvec_ah_fmls_idx_s,
+          gen_helper_gvec_ah_fmls_idx_d },
     };
     MemOp esz = a->esz;
     int check = fp_access_check_vector_hsd(s, a->q, esz);
@@ -6751,8 +6757,7 @@ static bool do_fmla_vector_idx(DisasContext *s, 
arg_qrrx_e *a, bool neg)
 
     gen_gvec_op4_fpst(s, a->q, a->rd, a->rn, a->rm, a->rd,
                       esz == MO_16 ? FPST_A64_F16 : FPST_A64,
-                      (a->idx << 1) | neg,
-                      fns[esz - 1]);
+                      a->idx, fns[neg ? 1 + s->fpcr_ah : 0][esz - 1]);
     return true;
 }
 
diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index 50f16d5affa..e81e996c56e 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -3524,21 +3524,24 @@ DO_SVE2_RRXR_ROT(CDOT_zzxw_d, 
gen_helper_sve2_cdot_idx_d)
  *** SVE Floating Point Multiply-Add Indexed Group
  */
 
-static bool do_FMLA_zzxz(DisasContext *s, arg_rrxr_esz *a, bool sub)
-{
-    static gen_helper_gvec_4_ptr * const fns[4] = {
-        NULL,
-        gen_helper_gvec_fmla_idx_h,
-        gen_helper_gvec_fmla_idx_s,
-        gen_helper_gvec_fmla_idx_d,
-    };
-    return gen_gvec_fpst_zzzz(s, fns[a->esz], a->rd, a->rn, a->rm, a->ra,
-                              (a->index << 1) | sub,
-                              a->esz == MO_16 ? FPST_A64_F16 : FPST_A64);
-}
+static gen_helper_gvec_4_ptr * const fmla_idx_fns[4] = {
+    NULL,                       gen_helper_gvec_fmla_idx_h,
+    gen_helper_gvec_fmla_idx_s, gen_helper_gvec_fmla_idx_d
+};
+TRANS_FEAT(FMLA_zzxz, aa64_sve, gen_gvec_fpst_zzzz,
+           fmla_idx_fns[a->esz], a->rd, a->rn, a->rm, a->ra, a->index,
+           a->esz == MO_16 ? FPST_A64_F16 : FPST_A64)
 
-TRANS_FEAT(FMLA_zzxz, aa64_sve, do_FMLA_zzxz, a, false)
-TRANS_FEAT(FMLS_zzxz, aa64_sve, do_FMLA_zzxz, a, true)
+static gen_helper_gvec_4_ptr * const fmls_idx_fns[4][2] = {
+    { NULL, NULL },
+    { gen_helper_gvec_fmls_idx_h, gen_helper_gvec_ah_fmls_idx_h },
+    { gen_helper_gvec_fmls_idx_s, gen_helper_gvec_ah_fmls_idx_s },
+    { gen_helper_gvec_fmls_idx_d, gen_helper_gvec_ah_fmls_idx_d },
+};
+TRANS_FEAT(FMLS_zzxz, aa64_sve, gen_gvec_fpst_zzzz,
+           fmls_idx_fns[a->esz][s->fpcr_ah],
+           a->rd, a->rn, a->rm, a->ra, a->index,
+           a->esz == MO_16 ? FPST_A64_F16 : FPST_A64)
 
 /*
  *** SVE Floating Point Multiply Indexed Group
diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c
index e4c519f9e33..ae3cb50fa24 100644
--- a/target/arm/tcg/vec_helper.c
+++ b/target/arm/tcg/vec_helper.c
@@ -1680,29 +1680,35 @@ DO_FMUL_IDX(gvec_fmls_nf_idx_s, float32_sub, 
float32_mul, float32, H4)
 
 #undef DO_FMUL_IDX
 
-#define DO_FMLA_IDX(NAME, TYPE, H)                                         \
+#define DO_FMLA_IDX(NAME, TYPE, H, NEGX, NEGF)                             \
 void HELPER(NAME)(void *vd, void *vn, void *vm, void *va,                  \
                   float_status *stat, uint32_t desc)                       \
 {                                                                          \
     intptr_t i, j, oprsz = simd_oprsz(desc);                               \
     intptr_t segment = MIN(16, oprsz) / sizeof(TYPE);                      \
-    TYPE op1_neg = extract32(desc, SIMD_DATA_SHIFT, 1);                    \
-    intptr_t idx = desc >> (SIMD_DATA_SHIFT + 1);                          \
+    intptr_t idx = simd_data(desc);                                        \
     TYPE *d = vd, *n = vn, *m = vm, *a = va;                               \
-    op1_neg <<= (8 * sizeof(TYPE) - 1);                                    \
     for (i = 0; i < oprsz / sizeof(TYPE); i += segment) {                  \
         TYPE mm = m[H(i + idx)];                                           \
         for (j = 0; j < segment; j++) {                                    \
-            d[i + j] = TYPE##_muladd(n[i + j] ^ op1_neg,                   \
-                                     mm, a[i + j], 0, stat);               \
+            d[i + j] = TYPE##_muladd(n[i + j] ^ NEGX, mm,                  \
+                                     a[i + j], NEGF, stat);                \
         }                                                                  \
     }                                                                      \
     clear_tail(d, oprsz, simd_maxsz(desc));                                \
 }
 
-DO_FMLA_IDX(gvec_fmla_idx_h, float16, H2)
-DO_FMLA_IDX(gvec_fmla_idx_s, float32, H4)
-DO_FMLA_IDX(gvec_fmla_idx_d, float64, H8)
+DO_FMLA_IDX(gvec_fmla_idx_h, float16, H2, 0, 0)
+DO_FMLA_IDX(gvec_fmla_idx_s, float32, H4, 0, 0)
+DO_FMLA_IDX(gvec_fmla_idx_d, float64, H8, 0, 0)
+
+DO_FMLA_IDX(gvec_fmls_idx_h, float16, H2, INT16_MIN, 0)
+DO_FMLA_IDX(gvec_fmls_idx_s, float32, H4, INT32_MIN, 0)
+DO_FMLA_IDX(gvec_fmls_idx_d, float64, H8, INT64_MIN, 0)
+
+DO_FMLA_IDX(gvec_ah_fmls_idx_h, float16, H2, 0, float_muladd_negate_product)
+DO_FMLA_IDX(gvec_ah_fmls_idx_s, float32, H4, 0, float_muladd_negate_product)
+DO_FMLA_IDX(gvec_ah_fmls_idx_d, float64, H8, 0, float_muladd_negate_product)
 
 #undef DO_FMLA_IDX
 
-- 
2.34.1