diff mbox series

[v2,42/69] target/arm: Handle FPCR.AH in negation in FMLS (vector)

Message ID 20250201164012.1660228-43-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 
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.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@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 mbox series

Patch

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.
  */