Make the SVE FABD insn honour the FPCR.AH "don't negate the sign
of a NaN" semantics.
Signed-off-by: Peter Maydell <peter.mayd...@linaro.org>
Reviewed-by: Richard Henderson <richard.hender...@linaro.org>
---
target/arm/tcg/helper-sve.h | 7 +++++++
target/arm/tcg/sve_helper.c | 22 ++++++++++++++++++++++
target/arm/tcg/translate-sve.c | 2 +-
3 files changed, 30 insertions(+), 1 deletion(-)
diff --git a/target/arm/tcg/helper-sve.h b/target/arm/tcg/helper-sve.h
index ff12f650c87..29c70f054af 100644
--- a/target/arm/tcg/helper-sve.h
+++ b/target/arm/tcg/helper-sve.h
@@ -1183,6 +1183,13 @@ DEF_HELPER_FLAGS_6(sve_fabd_s, TCG_CALL_NO_RWG,
DEF_HELPER_FLAGS_6(sve_fabd_d, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_6(sve_ah_fabd_h, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_6(sve_ah_fabd_s, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_6(sve_ah_fabd_d, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, fpst, i32)
+
DEF_HELPER_FLAGS_6(sve_fscalbn_h, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_6(sve_fscalbn_s, TCG_CALL_NO_RWG,
diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c
index 5ce7d736475..8527a7495a6 100644
--- a/target/arm/tcg/sve_helper.c
+++ b/target/arm/tcg/sve_helper.c
@@ -4394,9 +4394,31 @@ static inline float64 abd_d(float64 a, float64 b,
float_status *s)
return float64_abs(float64_sub(a, b, s));
}
+/* ABD when FPCR.AH = 1: avoid flipping sign bit of a NaN result */
+static float16 ah_abd_h(float16 op1, float16 op2, float_status *stat)
+{
+ float16 r = float16_sub(op1, op2, stat);
+ return float16_is_any_nan(r) ? r : float16_abs(r);
+}
+
+static float32 ah_abd_s(float32 op1, float32 op2, float_status *stat)
+{
+ float32 r = float32_sub(op1, op2, stat);
+ return float32_is_any_nan(r) ? r : float32_abs(r);
+}
+
+static float64 ah_abd_d(float64 op1, float64 op2, float_status *stat)
+{
+ float64 r = float64_sub(op1, op2, stat);
+ return float64_is_any_nan(r) ? r : float64_abs(r);
+}
+
DO_ZPZZ_FP(sve_fabd_h, uint16_t, H1_2, abd_h)
DO_ZPZZ_FP(sve_fabd_s, uint32_t, H1_4, abd_s)
DO_ZPZZ_FP(sve_fabd_d, uint64_t, H1_8, abd_d)
+DO_ZPZZ_FP(sve_ah_fabd_h, uint16_t, H1_2, ah_abd_h)
+DO_ZPZZ_FP(sve_ah_fabd_s, uint32_t, H1_4, ah_abd_s)
+DO_ZPZZ_FP(sve_ah_fabd_d, uint64_t, H1_8, ah_abd_d)
static inline float64 scalbn_d(float64 a, int64_t b, float_status *s)
{
diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index 646d0171d99..0d8bd1a49c4 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -3789,7 +3789,7 @@ DO_ZPZZ_AH_FP(FMIN_zpzz, aa64_sve, sve_fmin, sve_ah_fmin)
DO_ZPZZ_AH_FP(FMAX_zpzz, aa64_sve, sve_fmax, sve_ah_fmax)
DO_ZPZZ_FP(FMINNM_zpzz, aa64_sve, sve_fminnum)
DO_ZPZZ_FP(FMAXNM_zpzz, aa64_sve, sve_fmaxnum)
-DO_ZPZZ_FP(FABD, aa64_sve, sve_fabd)
+DO_ZPZZ_AH_FP(FABD, aa64_sve, sve_fabd, sve_ah_fabd)
DO_ZPZZ_FP(FSCALE, aa64_sve, sve_fscalbn)
DO_ZPZZ_FP(FDIV, aa64_sve, sve_fdiv)
DO_ZPZZ_FP(FMULX, aa64_sve, sve_fmulx)
--
2.34.1
