Handle the FPCR.AH "don't negate the sign of a NaN" semantics
in FMLS (vector), by implementing a new set of helpers for
the AH=1 case.
The float_muladd_negate_product flag produces the same result
as negating either of the multiplication operands, assuming
neither of the operands are NaNs. But since FEAT_AFP does not
negate NaNs, this behaviour is exactly what we need.
Signed-off-by: Peter Maydell <peter.mayd...@linaro.org>
Reviewed-by: Richard Henderson <richard.hender...@linaro.org>
---
v2: squashed in RTH's patch to use the muladd flag
---
target/arm/helper.h | 4 ++++
target/arm/tcg/translate-a64.c | 7 ++++++-
target/arm/tcg/vec_helper.c | 22 ++++++++++++++++++++++
3 files changed, 32 insertions(+), 1 deletion(-)
diff --git a/target/arm/helper.h b/target/arm/helper.h
index be47edff896..f0a783b7088 100644
--- a/target/arm/helper.h
+++ b/target/arm/helper.h
@@ -782,6 +782,10 @@ DEF_HELPER_FLAGS_5(gvec_vfms_h, TCG_CALL_NO_RWG, void,
ptr, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_5(gvec_vfms_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst,
i32)
DEF_HELPER_FLAGS_5(gvec_vfms_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst,
i32)
+DEF_HELPER_FLAGS_5(gvec_ah_vfms_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst,
i32)
+DEF_HELPER_FLAGS_5(gvec_ah_vfms_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst,
i32)
+DEF_HELPER_FLAGS_5(gvec_ah_vfms_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst,
i32)
+
DEF_HELPER_FLAGS_5(gvec_ftsmul_h, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_5(gvec_ftsmul_s, TCG_CALL_NO_RWG,
diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index 2509a29528e..c209ac84228 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -5871,7 +5871,12 @@ static gen_helper_gvec_3_ptr * const f_vector_fmls[3] = {
gen_helper_gvec_vfms_s,
gen_helper_gvec_vfms_d,
};
-TRANS(FMLS_v, do_fp3_vector, a, 0, f_vector_fmls)
+static gen_helper_gvec_3_ptr * const f_vector_fmls_ah[3] = {
+ gen_helper_gvec_ah_vfms_h,
+ gen_helper_gvec_ah_vfms_s,
+ gen_helper_gvec_ah_vfms_d,
+};
+TRANS(FMLS_v, do_fp3_vector_2fn, a, 0, f_vector_fmls, f_vector_fmls_ah)
static gen_helper_gvec_3_ptr * const f_vector_fcmeq[3] = {
gen_helper_gvec_fceq_h,
diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c
index ae3cb50fa24..fc3e6587b81 100644
--- a/target/arm/tcg/vec_helper.c
+++ b/target/arm/tcg/vec_helper.c
@@ -1558,6 +1558,24 @@ static float64 float64_mulsub_f(float64 dest, float64
op1, float64 op2,
return float64_muladd(float64_chs(op1), op2, dest, 0, stat);
}
+static float16 float16_ah_mulsub_f(float16 dest, float16 op1, float16 op2,
+ float_status *stat)
+{
+ return float16_muladd(op1, op2, dest, float_muladd_negate_product, stat);
+}
+
+static float32 float32_ah_mulsub_f(float32 dest, float32 op1, float32 op2,
+ float_status *stat)
+{
+ return float32_muladd(op1, op2, dest, float_muladd_negate_product, stat);
+}
+
+static float64 float64_ah_mulsub_f(float64 dest, float64 op1, float64 op2,
+ float_status *stat)
+{
+ return float64_muladd(op1, op2, dest, float_muladd_negate_product, stat);
+}
+
#define DO_MULADD(NAME, FUNC, TYPE) \
void HELPER(NAME)(void *vd, void *vn, void *vm, \
float_status *stat, uint32_t desc) \
@@ -1584,6 +1602,10 @@ DO_MULADD(gvec_vfms_h, float16_mulsub_f, float16)
DO_MULADD(gvec_vfms_s, float32_mulsub_f, float32)
DO_MULADD(gvec_vfms_d, float64_mulsub_f, float64)
+DO_MULADD(gvec_ah_vfms_h, float16_ah_mulsub_f, float16)
+DO_MULADD(gvec_ah_vfms_s, float32_ah_mulsub_f, float32)
+DO_MULADD(gvec_ah_vfms_d, float64_ah_mulsub_f, float64)
+
/* For the indexed ops, SVE applies the index per 128-bit vector segment.
* For AdvSIMD, there is of course only one such vector segment.
*/
--
2.34.1
