Implement the FPCR.AH semantics for the SVE FMAXV and FMINV
vector-reduction-to-scalar max/min operations.
Signed-off-by: Peter Maydell <peter.mayd...@linaro.org>
---
target/arm/tcg/helper-sve.h | 14 +++++++++++
target/arm/tcg/sve_helper.c | 43 +++++++++++++++++++++-------------
target/arm/tcg/translate-sve.c | 16 +++++++++++--
3 files changed, 55 insertions(+), 18 deletions(-)
diff --git a/target/arm/tcg/helper-sve.h b/target/arm/tcg/helper-sve.h
index 8349752e99b..7ca95b8fa94 100644
--- a/target/arm/tcg/helper-sve.h
+++ b/target/arm/tcg/helper-sve.h
@@ -1035,6 +1035,20 @@ DEF_HELPER_FLAGS_4(sve_fminv_s, TCG_CALL_NO_RWG,
DEF_HELPER_FLAGS_4(sve_fminv_d, TCG_CALL_NO_RWG,
i64, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_4(sve_ah_fmaxv_h, TCG_CALL_NO_RWG,
+ i64, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_4(sve_ah_fmaxv_s, TCG_CALL_NO_RWG,
+ i64, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_4(sve_ah_fmaxv_d, TCG_CALL_NO_RWG,
+ i64, ptr, ptr, fpst, i32)
+
+DEF_HELPER_FLAGS_4(sve_ah_fminv_h, TCG_CALL_NO_RWG,
+ i64, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_4(sve_ah_fminv_s, TCG_CALL_NO_RWG,
+ i64, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_4(sve_ah_fminv_d, TCG_CALL_NO_RWG,
+ i64, ptr, ptr, fpst, i32)
+
DEF_HELPER_FLAGS_5(sve_fadda_h, TCG_CALL_NO_RWG,
i64, i64, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_5(sve_fadda_s, TCG_CALL_NO_RWG,
diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c
index 9837c5bc7ac..3631d85f23a 100644
--- a/target/arm/tcg/sve_helper.c
+++ b/target/arm/tcg/sve_helper.c
@@ -4190,7 +4190,7 @@ static TYPE NAME##_reduce(TYPE *data, float_status
*status, uintptr_t n) \
uintptr_t half = n / 2; \
TYPE lo = NAME##_reduce(data, status, half); \
TYPE hi = NAME##_reduce(data + half, status, half); \
- return TYPE##_##FUNC(lo, hi, status); \
+ return FUNC(lo, hi, status); \
} \
} \
uint64_t HELPER(NAME)(void *vn, void *vg, float_status *s, uint32_t desc) \
@@ -4211,26 +4211,37 @@ uint64_t HELPER(NAME)(void *vn, void *vg, float_status
*s, uint32_t desc) \
return NAME##_reduce(data, s, maxsz / sizeof(TYPE)); \
}
-DO_REDUCE(sve_faddv_h, float16, H1_2, add, float16_zero)
-DO_REDUCE(sve_faddv_s, float32, H1_4, add, float32_zero)
-DO_REDUCE(sve_faddv_d, float64, H1_8, add, float64_zero)
+DO_REDUCE(sve_faddv_h, float16, H1_2, float16_add, float16_zero)
+DO_REDUCE(sve_faddv_s, float32, H1_4, float32_add, float32_zero)
+DO_REDUCE(sve_faddv_d, float64, H1_8, float64_add, float64_zero)
/* Identity is floatN_default_nan, without the function call. */
-DO_REDUCE(sve_fminnmv_h, float16, H1_2, minnum, 0x7E00)
-DO_REDUCE(sve_fminnmv_s, float32, H1_4, minnum, 0x7FC00000)
-DO_REDUCE(sve_fminnmv_d, float64, H1_8, minnum, 0x7FF8000000000000ULL)
+DO_REDUCE(sve_fminnmv_h, float16, H1_2, float16_minnum, 0x7E00)
+DO_REDUCE(sve_fminnmv_s, float32, H1_4, float32_minnum, 0x7FC00000)
+DO_REDUCE(sve_fminnmv_d, float64, H1_8, float64_minnum, 0x7FF8000000000000ULL)
-DO_REDUCE(sve_fmaxnmv_h, float16, H1_2, maxnum, 0x7E00)
-DO_REDUCE(sve_fmaxnmv_s, float32, H1_4, maxnum, 0x7FC00000)
-DO_REDUCE(sve_fmaxnmv_d, float64, H1_8, maxnum, 0x7FF8000000000000ULL)
+DO_REDUCE(sve_fmaxnmv_h, float16, H1_2, float16_maxnum, 0x7E00)
+DO_REDUCE(sve_fmaxnmv_s, float32, H1_4, float32_maxnum, 0x7FC00000)
+DO_REDUCE(sve_fmaxnmv_d, float64, H1_8, float64_maxnum, 0x7FF8000000000000ULL)
-DO_REDUCE(sve_fminv_h, float16, H1_2, min, float16_infinity)
-DO_REDUCE(sve_fminv_s, float32, H1_4, min, float32_infinity)
-DO_REDUCE(sve_fminv_d, float64, H1_8, min, float64_infinity)
+DO_REDUCE(sve_fminv_h, float16, H1_2, float16_min, float16_infinity)
+DO_REDUCE(sve_fminv_s, float32, H1_4, float32_min, float32_infinity)
+DO_REDUCE(sve_fminv_d, float64, H1_8, float64_min, float64_infinity)
-DO_REDUCE(sve_fmaxv_h, float16, H1_2, max, float16_chs(float16_infinity))
-DO_REDUCE(sve_fmaxv_s, float32, H1_4, max, float32_chs(float32_infinity))
-DO_REDUCE(sve_fmaxv_d, float64, H1_8, max, float64_chs(float64_infinity))
+DO_REDUCE(sve_fmaxv_h, float16, H1_2, float16_max,
float16_chs(float16_infinity))
+DO_REDUCE(sve_fmaxv_s, float32, H1_4, float32_max,
float32_chs(float32_infinity))
+DO_REDUCE(sve_fmaxv_d, float64, H1_8, float64_max,
float64_chs(float64_infinity))
+
+DO_REDUCE(sve_ah_fminv_h, float16, H1_2, helper_vfp_ah_minh, float16_infinity)
+DO_REDUCE(sve_ah_fminv_s, float32, H1_4, helper_vfp_ah_mins, float32_infinity)
+DO_REDUCE(sve_ah_fminv_d, float64, H1_8, helper_vfp_ah_mind, float64_infinity)
+
+DO_REDUCE(sve_ah_fmaxv_h, float16, H1_2, helper_vfp_ah_maxh,
+ float16_chs(float16_infinity))
+DO_REDUCE(sve_ah_fmaxv_s, float32, H1_4, helper_vfp_ah_maxs,
+ float32_chs(float32_infinity))
+DO_REDUCE(sve_ah_fmaxv_d, float64, H1_8, helper_vfp_ah_maxd,
+ float64_chs(float64_infinity))
#undef DO_REDUCE
diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index ad415c43565..effa23cefd7 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -3588,11 +3588,23 @@ static bool do_reduce(DisasContext *s, arg_rpr_esz *a,
}; \
TRANS_FEAT(NAME, aa64_sve, do_reduce, a, name##_fns[a->esz])
+#define DO_VPZ_AH(NAME, name) \
+ static gen_helper_fp_reduce * const name##_fns[4] = { \
+ NULL, gen_helper_sve_##name##_h, \
+ gen_helper_sve_##name##_s, gen_helper_sve_##name##_d, \
+ }; \
+ static gen_helper_fp_reduce * const name##_ah_fns[4] = { \
+ NULL, gen_helper_sve_ah_##name##_h, \
+ gen_helper_sve_ah_##name##_s, gen_helper_sve_ah_##name##_d, \
+ }; \
+ TRANS_FEAT(NAME, aa64_sve, do_reduce, a, \
+ s->fpcr_ah ? name##_ah_fns[a->esz] : name##_fns[a->esz])
+
DO_VPZ(FADDV, faddv)
DO_VPZ(FMINNMV, fminnmv)
DO_VPZ(FMAXNMV, fmaxnmv)
-DO_VPZ(FMINV, fminv)
-DO_VPZ(FMAXV, fmaxv)
+DO_VPZ_AH(FMINV, fminv)
+DO_VPZ_AH(FMAXV, fmaxv)
#undef DO_VPZ
--
2.34.1
