[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[PATCH v6 68/82] target/arm: Implement SVE2 FLOGB
From: |
Richard Henderson |
Subject: |
[PATCH v6 68/82] target/arm: Implement SVE2 FLOGB |
Date: |
Fri, 30 Apr 2021 13:25:56 -0700 |
From: Stephen Long <steplong@quicinc.com>
Signed-off-by: Stephen Long <steplong@quicinc.com>
Message-Id: <20200430191405.21641-1-steplong@quicinc.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
v2: Fixed esz index and c++ comments
v3: Fixed denormal arithmetic and raise invalid.
---
target/arm/helper-sve.h | 4 +++
target/arm/sve.decode | 3 +++
target/arm/sve_helper.c | 52 ++++++++++++++++++++++++++++++++++++++
target/arm/translate-sve.c | 24 ++++++++++++++++++
4 files changed, 83 insertions(+)
diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h
index 30b6dc49c8..96bd200e73 100644
--- a/target/arm/helper-sve.h
+++ b/target/arm/helper-sve.h
@@ -2713,3 +2713,7 @@ DEF_HELPER_FLAGS_5(sve2_fcvtlt_hs, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(sve2_fcvtlt_sd, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(flogb_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(flogb_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(flogb_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index 46153d6a84..17adb393ff 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -1539,3 +1539,6 @@ FCVTNT_sh 01100100 10 0010 00 101 ... ..... .....
@rd_pg_rn_e0
FCVTLT_hs 01100100 10 0010 01 101 ... ..... ..... @rd_pg_rn_e0
FCVTNT_ds 01100100 11 0010 10 101 ... ..... ..... @rd_pg_rn_e0
FCVTLT_sd 01100100 11 0010 11 101 ... ..... ..... @rd_pg_rn_e0
+
+### SVE2 floating-point convert to integer
+FLOGB 01100101 00 011 esz:2 0101 pg:3 rn:5 rd:5 &rpr_esz
diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index 2684f40a62..754301a3a6 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -4575,6 +4575,58 @@ DO_ZPZ_FP(sve_ucvt_dh, uint64_t, , uint64_to_float16)
DO_ZPZ_FP(sve_ucvt_ds, uint64_t, , uint64_to_float32)
DO_ZPZ_FP(sve_ucvt_dd, uint64_t, , uint64_to_float64)
+static int16_t do_float16_logb_as_int(float16 a, float_status *s)
+{
+ if (float16_is_normal(a)) {
+ return extract16(a, 10, 5) - 15;
+ } else if (float16_is_infinity(a)) {
+ return INT16_MAX;
+ } else if (float16_is_any_nan(a) || float16_is_zero(a)) {
+ float_raise(float_flag_invalid, s);
+ return INT16_MIN;
+ } else {
+ /*
+ * denormal: bias - fractional_zeros
+ * = bias + masked_zeros - uint32_zeros
+ */
+ return -15 + 22 - clz32(extract16(a, 0, 10));
+ }
+}
+
+static int32_t do_float32_logb_as_int(float32 a, float_status *s)
+{
+ if (float32_is_normal(a)) {
+ return extract32(a, 23, 8) - 127;
+ } else if (float32_is_infinity(a)) {
+ return INT32_MAX;
+ } else if (float32_is_any_nan(a) || float32_is_zero(a)) {
+ float_raise(float_flag_invalid, s);
+ return INT32_MIN;
+ } else {
+ /* denormal (see above) */
+ return -127 + 9 - clz32(extract32(a, 0, 23));
+ }
+}
+
+static int64_t do_float64_logb_as_int(float64 a, float_status *s)
+{
+ if (float64_is_normal(a)) {
+ return extract64(a, 52, 11) - 1023;
+ } else if (float64_is_infinity(a)) {
+ return INT64_MAX;
+ } else if (float64_is_any_nan(a) || float64_is_zero(a)) {
+ float_raise(float_flag_invalid, s);
+ return INT64_MIN;
+ } else {
+ /* denormal (see above) */
+ return -1023 + 12 - clz64(extract64(a, 0, 52));
+ }
+}
+
+DO_ZPZ_FP(flogb_h, float16, H1_2, do_float16_logb_as_int)
+DO_ZPZ_FP(flogb_s, float32, H1_4, do_float32_logb_as_int)
+DO_ZPZ_FP(flogb_d, float64, , do_float64_logb_as_int)
+
#undef DO_ZPZ_FP
static void do_fmla_zpzzz_h(void *vd, void *vn, void *vm, void *va, void *vg,
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index 87e5c8ac63..a949f53f4a 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -8231,3 +8231,27 @@ static bool trans_FCVTXNT_ds(DisasContext *s,
arg_rpr_esz *a)
}
return do_frint_mode(s, a, float_round_to_odd, gen_helper_sve2_fcvtnt_ds);
}
+
+static bool trans_FLOGB(DisasContext *s, arg_rpr_esz *a)
+{
+ static gen_helper_gvec_3_ptr * const fns[] = {
+ NULL, gen_helper_flogb_h,
+ gen_helper_flogb_s, gen_helper_flogb_d
+ };
+
+ if (!dc_isar_feature(aa64_sve2, s) || fns[a->esz] == NULL) {
+ return false;
+ }
+ if (sve_access_check(s)) {
+ TCGv_ptr status =
+ fpstatus_ptr(a->esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR);
+ unsigned vsz = vec_full_reg_size(s);
+
+ tcg_gen_gvec_3_ptr(vec_full_reg_offset(s, a->rd),
+ vec_full_reg_offset(s, a->rn),
+ pred_full_reg_offset(s, a->pg),
+ status, vsz, vsz, 0, fns[a->esz]);
+ tcg_temp_free_ptr(status);
+ }
+ return true;
+}
--
2.25.1
- [PATCH v6 73/82] target/arm: Implement SVE2 fp multiply-add long, (continued)
- [PATCH v6 73/82] target/arm: Implement SVE2 fp multiply-add long, Richard Henderson, 2021/04/30
- [PATCH v6 56/82] target/arm: Implement SVE2 saturating multiply (indexed), Richard Henderson, 2021/04/30
- [PATCH v6 62/82] target/arm: Implement SVE2 crypto destructive binary operations, Richard Henderson, 2021/04/30
- [PATCH v6 69/82] target/arm: Share table of sve load functions, Richard Henderson, 2021/04/30
- [PATCH v6 78/82] target/arm: Split decode of VSDOT and VUDOT, Richard Henderson, 2021/04/30
- [PATCH v6 66/82] target/arm: Implement SVE2 FCVTLT, Richard Henderson, 2021/04/30
- [PATCH v6 70/82] target/arm: Implement SVE2 LD1RO, Richard Henderson, 2021/04/30
- [PATCH v6 79/82] target/arm: Implement aarch32 VSUDOT, VUSDOT, Richard Henderson, 2021/04/30
- [PATCH v6 75/82] target/arm: Split out do_neon_ddda_fpst, Richard Henderson, 2021/04/30
- [PATCH v6 77/82] target/arm: Fix decode for VDOT (indexed), Richard Henderson, 2021/04/30
- [PATCH v6 68/82] target/arm: Implement SVE2 FLOGB,
Richard Henderson <=
- [PATCH v6 80/82] target/arm: Implement integer matrix multiply accumulate, Richard Henderson, 2021/04/30
- [PATCH v6 82/82] target/arm: Enable SVE2 and related extensions, Richard Henderson, 2021/04/30
- [PATCH v6 81/82] linux-user/aarch64: Enable hwcap bits for sve2 and related extensions, Richard Henderson, 2021/04/30