diff mbox series

[v2,38/69] target/arm: Handle FPCR.AH in negation steps in FCADD

Message ID 20250201164012.1660228-39-peter.maydell@linaro.org
State New
Headers show
Series target/arm: FEAT_AFP and FEAT_RPRES | expand

Commit Message

Peter Maydell Feb. 1, 2025, 4:39 p.m. UTC 
The negation steps in FCADD must honour FPCR.AH's "don't change the
sign of a NaN" semantics.  Implement this 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 closer to the pseudocode, where we extract the rot
parameter from the SIMD data word and negate the appropriate
input value.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/arm/tcg/translate-a64.c | 10 +++++--
 target/arm/tcg/vec_helper.c    | 54 +++++++++++++++++++---------------
 2 files changed, 38 insertions(+), 26 deletions(-)
diff mbox series

Patch

diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index 0c1e97e6c40..52f93cb905b 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -6117,8 +6117,14 @@  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 0b84a562c03..b181b9734d4 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);