target/arm: Handle FPCR.NEP for NEP for FMUL, FMULX scalar by element

do_fp3_scalar_idx() is used only for the FMUL and FMULX scalar by
element instructions; these both need to merge the result with the Rn
register when FPCR.NEP is set.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>

diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index ac8196136c402f4a444717ba14098636c060de6b..f31acee30aa0704026f332c80c5a1155bff30344 100644 (file)
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -6296,7 +6296,7 @@ static bool do_fp3_scalar_idx(DisasContext *s, arg_rrx_e *a, const FPScalar *f)
 
             read_vec_element(s, t1, a->rm, a->idx, MO_64);
             f->gen_d(t0, t0, t1, fpstatus_ptr(FPST_A64));
-            write_fp_dreg(s, a->rd, t0);
+            write_fp_dreg_merging(s, a->rd, a->rn, t0);
         }
         break;
     case MO_32:
@@ -6306,7 +6306,7 @@ static bool do_fp3_scalar_idx(DisasContext *s, arg_rrx_e *a, const FPScalar *f)
 
             read_vec_element_i32(s, t1, a->rm, a->idx, MO_32);
             f->gen_s(t0, t0, t1, fpstatus_ptr(FPST_A64));
-            write_fp_sreg(s, a->rd, t0);
+            write_fp_sreg_merging(s, a->rd, a->rn, t0);
         }
         break;
     case MO_16:
@@ -6319,7 +6319,7 @@ static bool do_fp3_scalar_idx(DisasContext *s, arg_rrx_e *a, const FPScalar *f)
 
             read_vec_element_i32(s, t1, a->rm, a->idx, MO_16);
             f->gen_h(t0, t0, t1, fpstatus_ptr(FPST_A64_F16));
-            write_fp_sreg(s, a->rd, t0);
+            write_fp_hreg_merging(s, a->rd, a->rn, t0);
         }
         break;
     default: