target/arm: Add BFADD, BFSUB, BFMUL, BFMAXNM, BFMINNM (predicated)

FEAT_SVE_B16B16 adds bfloat16 versions of the SVE floating point
(predicated) instructions, which are encoded via sz=0b00.
Add BFADD, BFSUB, BFMUL, BFMAXNM, BFMINNM; these are all the insns
in this group which do not change behaviour for AH=1.

We will deal with BFMAX/BFMIN (which do have different AH=1
behaviour) in a following commit.

Fixes: 7b1613a1020d2942 ("target/arm: Enable FEAT_SME2p1 on -cpu max")
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250718173032.2498900-3-peter.maydell@linaro.org

3 files changed, 32 insertions, 5 deletions

diff --git a/target/arm/tcg/helper-sve.h b/target/arm/tcg/helper-sve.h
index c36090d..d612bca 100644
--- a/target/arm/tcg/helper-sve.h
+++ b/target/arm/tcg/helper-sve.h
@@ -1196,6 +1196,8 @@ DEF_HELPER_FLAGS_5(sve_fcmne0_s, TCG_CALL_NO_RWG,
 DEF_HELPER_FLAGS_5(sve_fcmne0_d, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, fpst, i32)
 
+DEF_HELPER_FLAGS_6(sve_fadd_b16, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, fpst, i32)
 DEF_HELPER_FLAGS_6(sve_fadd_h, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, fpst, i32)
 DEF_HELPER_FLAGS_6(sve_fadd_s, TCG_CALL_NO_RWG,
@@ -1203,6 +1205,8 @@ DEF_HELPER_FLAGS_6(sve_fadd_s, TCG_CALL_NO_RWG,
 DEF_HELPER_FLAGS_6(sve_fadd_d, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, fpst, i32)
 
+DEF_HELPER_FLAGS_6(sve_fsub_b16, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, fpst, i32)
 DEF_HELPER_FLAGS_6(sve_fsub_h, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, fpst, i32)
 DEF_HELPER_FLAGS_6(sve_fsub_s, TCG_CALL_NO_RWG,
@@ -1210,6 +1214,8 @@ DEF_HELPER_FLAGS_6(sve_fsub_s, TCG_CALL_NO_RWG,
 DEF_HELPER_FLAGS_6(sve_fsub_d, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, fpst, i32)
 
+DEF_HELPER_FLAGS_6(sve_fmul_b16, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, fpst, i32)
 DEF_HELPER_FLAGS_6(sve_fmul_h, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, fpst, i32)
 DEF_HELPER_FLAGS_6(sve_fmul_s, TCG_CALL_NO_RWG,
@@ -1252,6 +1258,8 @@ DEF_HELPER_FLAGS_6(sve_ah_fmax_s, TCG_CALL_NO_RWG,
 DEF_HELPER_FLAGS_6(sve_ah_fmax_d, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, fpst, i32)
 
+DEF_HELPER_FLAGS_6(sve_fminnum_b16, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, fpst, i32)
 DEF_HELPER_FLAGS_6(sve_fminnum_h, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, fpst, i32)
 DEF_HELPER_FLAGS_6(sve_fminnum_s, TCG_CALL_NO_RWG,
@@ -1259,6 +1267,8 @@ DEF_HELPER_FLAGS_6(sve_fminnum_s, TCG_CALL_NO_RWG,
 DEF_HELPER_FLAGS_6(sve_fminnum_d, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, fpst, i32)
 
+DEF_HELPER_FLAGS_6(sve_fmaxnum_b16, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, fpst, i32)
 DEF_HELPER_FLAGS_6(sve_fmaxnum_h, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, fpst, i32)
 DEF_HELPER_FLAGS_6(sve_fmaxnum_s, TCG_CALL_NO_RWG,
diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c
index 43b872c..a229503 100644
--- a/target/arm/tcg/sve_helper.c
+++ b/target/arm/tcg/sve_helper.c
@@ -4629,14 +4629,17 @@ void HELPER(NAME)(void *vd, void *vn, void *vm, void *vg,       \
     } while (i != 0);                                           \
 }
 
+DO_ZPZZ_FP(sve_fadd_b16, uint16_t, H1_2, bfloat16_add)
 DO_ZPZZ_FP(sve_fadd_h, uint16_t, H1_2, float16_add)
 DO_ZPZZ_FP(sve_fadd_s, uint32_t, H1_4, float32_add)
 DO_ZPZZ_FP(sve_fadd_d, uint64_t, H1_8, float64_add)
 
+DO_ZPZZ_FP(sve_fsub_b16, uint16_t, H1_2, bfloat16_sub)
 DO_ZPZZ_FP(sve_fsub_h, uint16_t, H1_2, float16_sub)
 DO_ZPZZ_FP(sve_fsub_s, uint32_t, H1_4, float32_sub)
 DO_ZPZZ_FP(sve_fsub_d, uint64_t, H1_8, float64_sub)
 
+DO_ZPZZ_FP(sve_fmul_b16, uint16_t, H1_2, bfloat16_mul)
 DO_ZPZZ_FP(sve_fmul_h, uint16_t, H1_2, float16_mul)
 DO_ZPZZ_FP(sve_fmul_s, uint32_t, H1_4, float32_mul)
 DO_ZPZZ_FP(sve_fmul_d, uint64_t, H1_8, float64_mul)
@@ -4661,10 +4664,12 @@ DO_ZPZZ_FP(sve_ah_fmax_h, uint16_t, H1_2, helper_vfp_ah_maxh)
 DO_ZPZZ_FP(sve_ah_fmax_s, uint32_t, H1_4, helper_vfp_ah_maxs)
 DO_ZPZZ_FP(sve_ah_fmax_d, uint64_t, H1_8, helper_vfp_ah_maxd)
 
+DO_ZPZZ_FP(sve_fminnum_b16, uint16_t, H1_2, bfloat16_minnum)
 DO_ZPZZ_FP(sve_fminnum_h, uint16_t, H1_2, float16_minnum)
 DO_ZPZZ_FP(sve_fminnum_s, uint32_t, H1_4, float32_minnum)
 DO_ZPZZ_FP(sve_fminnum_d, uint64_t, H1_8, float64_minnum)
 
+DO_ZPZZ_FP(sve_fmaxnum_b16, uint16_t, H1_2, bfloat16_maxnum)
 DO_ZPZZ_FP(sve_fmaxnum_h, uint16_t, H1_2, float16_maxnum)
 DO_ZPZZ_FP(sve_fmaxnum_s, uint32_t, H1_4, float32_maxnum)
 DO_ZPZZ_FP(sve_fmaxnum_d, uint64_t, H1_8, float64_maxnum)
diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index f00cccf..2739c22 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -407,6 +407,10 @@ static bool gen_gvec_fpst_zzzp(DisasContext *s, gen_helper_gvec_4_ptr *fn,
 static bool gen_gvec_fpst_arg_zpzz(DisasContext *s, gen_helper_gvec_4_ptr *fn,
                                    arg_rprr_esz *a)
 {
+    /* These insns use MO_8 to encode BFloat16. */
+    if (a->esz == MO_8 && !dc_isar_feature(aa64_sve_b16b16, s)) {
+        return false;
+    }
     return gen_gvec_fpst_zzzp(s, fn, a->rd, a->rn, a->rm, a->pg, 0,
                               a->esz == MO_16 ? FPST_A64_F16 : FPST_A64);
 }
@@ -4206,13 +4210,21 @@ TRANS_FEAT_NONSTREAMING(FTSMUL, aa64_sve, gen_gvec_fpst_arg_zzz,
                s->fpcr_ah ? name##_ah_zpzz_fns[a->esz] :                \
                name##_zpzz_fns[a->esz], a)
 
-DO_ZPZZ_FP(FADD_zpzz, aa64_sve, sve_fadd)
-DO_ZPZZ_FP(FSUB_zpzz, aa64_sve, sve_fsub)
-DO_ZPZZ_FP(FMUL_zpzz, aa64_sve, sve_fmul)
+/* Similar, but for insns where sz == 0 encodes bfloat16 */
+#define DO_ZPZZ_FP_B16(NAME, FEAT, name) \
+    static gen_helper_gvec_4_ptr * const name##_zpzz_fns[4] = { \
+        gen_helper_##name##_b16, gen_helper_##name##_h,         \
+        gen_helper_##name##_s, gen_helper_##name##_d            \
+    };                                                          \
+    TRANS_FEAT(NAME, FEAT, gen_gvec_fpst_arg_zpzz, name##_zpzz_fns[a->esz], a)
+
+DO_ZPZZ_FP_B16(FADD_zpzz, aa64_sve, sve_fadd)
+DO_ZPZZ_FP_B16(FSUB_zpzz, aa64_sve, sve_fsub)
+DO_ZPZZ_FP_B16(FMUL_zpzz, aa64_sve, sve_fmul)
 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_B16(FMINNM_zpzz, aa64_sve, sve_fminnum)
+DO_ZPZZ_FP_B16(FMAXNM_zpzz, aa64_sve, sve_fmaxnum)
 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)