diff mbox series

[45/76] target/arm: Implement FPCR.AH semantics for scalar FMIN/FMAX

Message ID 20250124162836.2332150-46-peter.maydell@linaro.org
State New
Headers show
Series target/arm: Implement FEAT_AFP and FEAT_RPRES | expand

Commit Message

Peter Maydell Jan. 24, 2025, 4:28 p.m. UTC
When FPCR.AH == 1, floating point FMIN and FMAX have some odd special
cases:

 * comparing two zeroes (even of different sign) or comparing a NaN
   with anything always returns the second argument (possibly
   squashed to zero)
 * denormal outputs are not squashed to zero regardless of FZ or FZ16

Implement these semantics in new helper functions and select them at
translate time if FPCR.AH is 1 for the scalar FMAX and FMIN insns.
(We will convert the other FMAX and FMIN insns in subsequent
commits.)

Note that FMINNM and FMAXNM are not affected.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-a64.h    |  7 +++++++
 target/arm/tcg/helper-a64.c    | 36 ++++++++++++++++++++++++++++++++++
 target/arm/tcg/translate-a64.c | 23 ++++++++++++++++++++--
 3 files changed, 64 insertions(+), 2 deletions(-)
diff mbox series

Patch

diff --git a/target/arm/tcg/helper-a64.h b/target/arm/tcg/helper-a64.h
index bac12fbe55b..ae0424f6de9 100644
--- a/target/arm/tcg/helper-a64.h
+++ b/target/arm/tcg/helper-a64.h
@@ -67,6 +67,13 @@  DEF_HELPER_4(advsimd_muladd2h, i32, i32, i32, i32, fpst)
 DEF_HELPER_2(advsimd_rinth_exact, f16, f16, fpst)
 DEF_HELPER_2(advsimd_rinth, f16, f16, fpst)
 
+DEF_HELPER_3(vfp_ah_minh, f16, f16, f16, fpst)
+DEF_HELPER_3(vfp_ah_mins, f32, f32, f32, fpst)
+DEF_HELPER_3(vfp_ah_mind, f64, f64, f64, fpst)
+DEF_HELPER_3(vfp_ah_maxh, f16, f16, f16, fpst)
+DEF_HELPER_3(vfp_ah_maxs, f32, f32, f32, fpst)
+DEF_HELPER_3(vfp_ah_maxd, f64, f64, f64, fpst)
+
 DEF_HELPER_2(exception_return, void, env, i64)
 DEF_HELPER_FLAGS_2(dc_zva, TCG_CALL_NO_WG, void, env, i64)
 
diff --git a/target/arm/tcg/helper-a64.c b/target/arm/tcg/helper-a64.c
index 05036089dd7..406d76e1129 100644
--- a/target/arm/tcg/helper-a64.c
+++ b/target/arm/tcg/helper-a64.c
@@ -399,6 +399,42 @@  float32 HELPER(fcvtx_f64_to_f32)(float64 a, float_status *fpst)
     return r;
 }
 
+/*
+ * AH=1 min/max have some odd special cases:
+ * comparing two zeroes (even of different sign), (NaN, anything),
+ * or (anything, NaN) should return the second argument (possibly
+ * squashed to zero).
+ * Also, denormal outputs are not squashed to zero regardless of FZ or FZ16.
+ */
+#define AH_MINMAX_HELPER(NAME, CTYPE, FLOATTYPE, MINMAX)                \
+    CTYPE HELPER(NAME)(CTYPE a, CTYPE b, float_status *fpst)            \
+    {                                                                   \
+        bool save;                                                      \
+        CTYPE r;                                                        \
+        a = FLOATTYPE ## _squash_input_denormal(a, fpst);               \
+        b = FLOATTYPE ## _squash_input_denormal(b, fpst);               \
+        if (FLOATTYPE ## _is_zero(a) && FLOATTYPE ## _is_zero(b)) {     \
+            return b;                                                   \
+        }                                                               \
+        if (FLOATTYPE ## _is_any_nan(a) ||                              \
+            FLOATTYPE ## _is_any_nan(b)) {                              \
+            float_raise(float_flag_invalid, fpst);                      \
+            return b;                                                   \
+        }                                                               \
+        save = get_flush_to_zero(fpst);                                 \
+        set_flush_to_zero(false, fpst);                                 \
+        r = FLOATTYPE ## _ ## MINMAX(a, b, fpst);                       \
+        set_flush_to_zero(save, fpst);                                  \
+        return r;                                                       \
+    }
+
+AH_MINMAX_HELPER(vfp_ah_minh, dh_ctype_f16, float16, min)
+AH_MINMAX_HELPER(vfp_ah_mins, float32, float32, min)
+AH_MINMAX_HELPER(vfp_ah_mind, float64, float64, min)
+AH_MINMAX_HELPER(vfp_ah_maxh, dh_ctype_f16, float16, max)
+AH_MINMAX_HELPER(vfp_ah_maxs, float32, float32, max)
+AH_MINMAX_HELPER(vfp_ah_maxd, float64, float64, max)
+
 /* 64-bit versions of the CRC helpers. Note that although the operation
  * (and the prototypes of crc32c() and crc32() mean that only the bottom
  * 32 bits of the accumulator and result are used, we pass and return
diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index d3575ac1154..a6f24ad9746 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -5152,6 +5152,15 @@  static bool do_fp3_scalar_ah(DisasContext *s, arg_rrr_e *a, const FPScalar *f,
                                        select_fpst(s, a->esz));
 }
 
+/* Some insns need to call different helpers when FPCR.AH == 1 */
+static bool do_fp3_scalar_2fn(DisasContext *s, arg_rrr_e *a,
+                              const FPScalar *fnormal,
+                              const FPScalar *fah,
+                              int mergereg)
+{
+    return do_fp3_scalar(s, a, s->fpcr_ah ? fah : fnormal, mergereg);
+}
+
 static const FPScalar f_scalar_fadd = {
     gen_helper_vfp_addh,
     gen_helper_vfp_adds,
@@ -5185,14 +5194,24 @@  static const FPScalar f_scalar_fmax = {
     gen_helper_vfp_maxs,
     gen_helper_vfp_maxd,
 };
-TRANS(FMAX_s, do_fp3_scalar, a, &f_scalar_fmax, a->rn)
+static const FPScalar f_scalar_fmax_ah = {
+    gen_helper_vfp_ah_maxh,
+    gen_helper_vfp_ah_maxs,
+    gen_helper_vfp_ah_maxd,
+};
+TRANS(FMAX_s, do_fp3_scalar_2fn, a, &f_scalar_fmax, &f_scalar_fmax_ah, a->rn)
 
 static const FPScalar f_scalar_fmin = {
     gen_helper_vfp_minh,
     gen_helper_vfp_mins,
     gen_helper_vfp_mind,
 };
-TRANS(FMIN_s, do_fp3_scalar, a, &f_scalar_fmin, a->rn)
+static const FPScalar f_scalar_fmin_ah = {
+    gen_helper_vfp_ah_minh,
+    gen_helper_vfp_ah_mins,
+    gen_helper_vfp_ah_mind,
+};
+TRANS(FMIN_s, do_fp3_scalar_2fn, a, &f_scalar_fmin, &f_scalar_fmin_ah, a->rn)
 
 static const FPScalar f_scalar_fmaxnm = {
     gen_helper_vfp_maxnumh,