target/arm: Add BFMIN, BFMAX (predicated)

FEAT_SVE_B16B16 adds bfloat16 versions of the SVE floating point
(predicated) instructions, which are encoded via sz=0b00.  Add the
BFMAX and BFMIN insns.  These have separate behaviour for AH=1 and
AH=0; we have already implemented the AH=1 helper for the SME2
versions of these insns.

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: 20250718173032.2498900-4-peter.maydell@linaro.org

3 files changed, 27 insertions, 2 deletions

diff --git a/target/arm/tcg/helper-sve.h b/target/arm/tcg/helper-sve.h
index d612bca..cb6c235 100644
--- a/target/arm/tcg/helper-sve.h
+++ b/target/arm/tcg/helper-sve.h
@@ -1230,6 +1230,8 @@ DEF_HELPER_FLAGS_6(sve_fdiv_s, TCG_CALL_NO_RWG,
 DEF_HELPER_FLAGS_6(sve_fdiv_d, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, fpst, i32)
 
+DEF_HELPER_FLAGS_6(sve_fmin_b16, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, fpst, i32)
 DEF_HELPER_FLAGS_6(sve_fmin_h, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, fpst, i32)
 DEF_HELPER_FLAGS_6(sve_fmin_s, TCG_CALL_NO_RWG,
@@ -1237,6 +1239,8 @@ DEF_HELPER_FLAGS_6(sve_fmin_s, TCG_CALL_NO_RWG,
 DEF_HELPER_FLAGS_6(sve_fmin_d, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, fpst, i32)
 
+DEF_HELPER_FLAGS_6(sve_fmax_b16, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, fpst, i32)
 DEF_HELPER_FLAGS_6(sve_fmax_h, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, fpst, i32)
 DEF_HELPER_FLAGS_6(sve_fmax_s, TCG_CALL_NO_RWG,
@@ -1244,6 +1248,8 @@ DEF_HELPER_FLAGS_6(sve_fmax_s, TCG_CALL_NO_RWG,
 DEF_HELPER_FLAGS_6(sve_fmax_d, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, fpst, i32)
 
+DEF_HELPER_FLAGS_6(sve_ah_fmin_b16, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, fpst, i32)
 DEF_HELPER_FLAGS_6(sve_ah_fmin_h, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, fpst, i32)
 DEF_HELPER_FLAGS_6(sve_ah_fmin_s, TCG_CALL_NO_RWG,
@@ -1251,6 +1257,8 @@ DEF_HELPER_FLAGS_6(sve_ah_fmin_s, TCG_CALL_NO_RWG,
 DEF_HELPER_FLAGS_6(sve_ah_fmin_d, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, fpst, i32)
 
+DEF_HELPER_FLAGS_6(sve_ah_fmax_b16, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, fpst, i32)
 DEF_HELPER_FLAGS_6(sve_ah_fmax_h, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, fpst, i32)
 DEF_HELPER_FLAGS_6(sve_ah_fmax_s, TCG_CALL_NO_RWG,
diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c
index a229503..1a56fa8 100644
--- a/target/arm/tcg/sve_helper.c
+++ b/target/arm/tcg/sve_helper.c
@@ -4648,18 +4648,22 @@ DO_ZPZZ_FP(sve_fdiv_h, uint16_t, H1_2, float16_div)
 DO_ZPZZ_FP(sve_fdiv_s, uint32_t, H1_4, float32_div)
 DO_ZPZZ_FP(sve_fdiv_d, uint64_t, H1_8, float64_div)
 
+DO_ZPZZ_FP(sve_fmin_b16, uint16_t, H1_2, bfloat16_min)
 DO_ZPZZ_FP(sve_fmin_h, uint16_t, H1_2, float16_min)
 DO_ZPZZ_FP(sve_fmin_s, uint32_t, H1_4, float32_min)
 DO_ZPZZ_FP(sve_fmin_d, uint64_t, H1_8, float64_min)
 
+DO_ZPZZ_FP(sve_fmax_b16, uint16_t, H1_2, bfloat16_max)
 DO_ZPZZ_FP(sve_fmax_h, uint16_t, H1_2, float16_max)
 DO_ZPZZ_FP(sve_fmax_s, uint32_t, H1_4, float32_max)
 DO_ZPZZ_FP(sve_fmax_d, uint64_t, H1_8, float64_max)
 
+DO_ZPZZ_FP(sve_ah_fmin_b16, uint16_t, H1_2, helper_sme2_ah_fmin_b16)
 DO_ZPZZ_FP(sve_ah_fmin_h, uint16_t, H1_2, helper_vfp_ah_minh)
 DO_ZPZZ_FP(sve_ah_fmin_s, uint32_t, H1_4, helper_vfp_ah_mins)
 DO_ZPZZ_FP(sve_ah_fmin_d, uint64_t, H1_8, helper_vfp_ah_mind)
 
+DO_ZPZZ_FP(sve_ah_fmax_b16, uint16_t, H1_2, helper_sme2_ah_fmax_b16)
 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)
diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index 2739c22..27af3df 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -4218,11 +4218,24 @@ TRANS_FEAT_NONSTREAMING(FTSMUL, aa64_sve, gen_gvec_fpst_arg_zzz,
     };                                                          \
     TRANS_FEAT(NAME, FEAT, gen_gvec_fpst_arg_zpzz, name##_zpzz_fns[a->esz], a)
 
+#define DO_ZPZZ_AH_FP_B16(NAME, FEAT, name, ah_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                    \
+    };                                                                  \
+    static gen_helper_gvec_4_ptr * const name##_ah_zpzz_fns[4] = {      \
+        gen_helper_##ah_name##_b16, gen_helper_##ah_name##_h,           \
+        gen_helper_##ah_name##_s, gen_helper_##ah_name##_d              \
+    };                                                                  \
+    TRANS_FEAT(NAME, FEAT, gen_gvec_fpst_arg_zpzz,                      \
+               s->fpcr_ah ? name##_ah_zpzz_fns[a->esz] :                \
+               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_AH_FP_B16(FMIN_zpzz, aa64_sve, sve_fmin, sve_ah_fmin)
+DO_ZPZZ_AH_FP_B16(FMAX_zpzz, aa64_sve, sve_fmax, sve_ah_fmax)
 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)