[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[PATCH v4 68/78] target/arm: Implement SVE2 FCVTNT
From: |
Richard Henderson |
Subject: |
[PATCH v4 68/78] target/arm: Implement SVE2 FCVTNT |
Date: |
Tue, 9 Mar 2021 08:20:31 -0800 |
From: Stephen Long <steplong@quicinc.com>
Signed-off-by: Stephen Long <steplong@quicinc.com>
Message-Id: <20200428174332.17162-2-steplong@quicinc.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/helper-sve.h | 5 +++++
target/arm/sve.decode | 4 ++++
target/arm/sve_helper.c | 20 ++++++++++++++++++++
target/arm/translate-sve.c | 16 ++++++++++++++++
4 files changed, 45 insertions(+)
diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h
index c85cd85a0b..eedb70eb50 100644
--- a/target/arm/helper-sve.h
+++ b/target/arm/helper-sve.h
@@ -2734,3 +2734,8 @@ DEF_HELPER_FLAGS_5(sve2_sqrdcmlah_idx_h, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(sve2_sqrdcmlah_idx_s, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(sve2_fcvtnt_sh, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_fcvtnt_ds, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index 9bf37e322f..2c38fe4691 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -1573,3 +1573,7 @@ SM4E 01000101 00 10001 1 11100 0 ..... .....
@rdn_rm_e0
# SVE2 crypto constructive binary operations
SM4EKEY 01000101 00 1 ..... 11110 0 ..... ..... @rd_rn_rm_e0
RAX1 01000101 00 1 ..... 11110 1 ..... ..... @rd_rn_rm_e0
+
+### SVE2 floating-point convert precision odd elements
+FCVTNT_sh 01100100 10 0010 00 101 ... ..... ..... @rd_pg_rn_e0
+FCVTNT_ds 01100100 11 0010 10 101 ... ..... ..... @rd_pg_rn_e0
diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index c406ae289c..b719a3aacf 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -7600,3 +7600,23 @@ void HELPER(fmmla_d)(void *vd, void *vn, void *vm, void
*va,
d[3] = float64_add(a[3], float64_add(p0, p1, status), status);
}
}
+
+#define DO_FCVTNT(NAME, TYPEW, TYPEN, HW, HN, OP) \
+void HELPER(NAME)(void *vd, void *vn, void *vg, void *status, uint32_t desc) \
+{ \
+ intptr_t i = simd_oprsz(desc); \
+ uint64_t *g = vg; \
+ do { \
+ uint64_t pg = g[(i - 1) >> 6]; \
+ do { \
+ i -= sizeof(TYPEW); \
+ if (likely((pg >> (i & 63)) & 1)) { \
+ TYPEW nn = *(TYPEW *)(vn + HW(i)); \
+ *(TYPEN *)(vd + HN(i + sizeof(TYPEN))) = OP(nn, status); \
+ } \
+ } while (i & 63); \
+ } while (i != 0); \
+}
+
+DO_FCVTNT(sve2_fcvtnt_sh, uint32_t, uint16_t, H1_4, H1_2, sve_f32_to_f16)
+DO_FCVTNT(sve2_fcvtnt_ds, uint64_t, uint32_t, H1_4, H1_2, float64_to_float32)
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index 6959cc9d9c..83fab9a6fc 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -8221,3 +8221,19 @@ static bool trans_RAX1(DisasContext *s, arg_rrr_esz *a)
}
return true;
}
+
+static bool trans_FCVTNT_sh(DisasContext *s, arg_rpr_esz *a)
+{
+ if (!dc_isar_feature(aa64_sve2, s)) {
+ return false;
+ }
+ return do_zpz_ptr(s, a->rd, a->rn, a->pg, false,
gen_helper_sve2_fcvtnt_sh);
+}
+
+static bool trans_FCVTNT_ds(DisasContext *s, arg_rpr_esz *a)
+{
+ if (!dc_isar_feature(aa64_sve2, s)) {
+ return false;
+ }
+ return do_zpz_ptr(s, a->rd, a->rn, a->pg, false,
gen_helper_sve2_fcvtnt_ds);
+}
--
2.25.1
- [PATCH v4 52/78] target/arm: Implement SVE2 integer multiply (indexed), (continued)
- [PATCH v4 52/78] target/arm: Implement SVE2 integer multiply (indexed), Richard Henderson, 2021/03/09
- [PATCH v4 56/78] target/arm: Implement SVE2 integer multiply long (indexed), Richard Henderson, 2021/03/09
- [PATCH v4 53/78] target/arm: Implement SVE2 integer multiply-add (indexed), Richard Henderson, 2021/03/09
- [PATCH v4 59/78] target/arm: Implement SVE2 saturating multiply high (indexed), Richard Henderson, 2021/03/09
- [PATCH v4 63/78] target/arm: Implement SVE mixed sign dot product, Richard Henderson, 2021/03/09
- [PATCH v4 57/78] target/arm: Implement SVE2 saturating multiply (indexed), Richard Henderson, 2021/03/09
- [PATCH v4 58/78] target/arm: Implement SVE2 signed saturating doubling multiply high, Richard Henderson, 2021/03/09
- [PATCH v4 65/78] target/arm: Implement SVE2 crypto destructive binary operations, Richard Henderson, 2021/03/09
- [PATCH v4 66/78] target/arm: Implement SVE2 crypto constructive binary operations, Richard Henderson, 2021/03/09
- [PATCH v4 67/78] target/arm: Implement SVE2 TBL, TBX, Richard Henderson, 2021/03/09
- [PATCH v4 68/78] target/arm: Implement SVE2 FCVTNT,
Richard Henderson <=
- [PATCH v4 64/78] target/arm: Implement SVE2 crypto unary operations, Richard Henderson, 2021/03/09
- [PATCH v4 61/78] target/arm: Implement SVE2 complex integer multiply-add (indexed), Richard Henderson, 2021/03/09
- [PATCH v4 60/78] target/arm: Implement SVE2 multiply-add long (indexed), Richard Henderson, 2021/03/09
- [PATCH v4 74/78] target/arm: Implement 128-bit ZIP, UZP, TRN, Richard Henderson, 2021/03/09
- [PATCH v4 70/78] target/arm: Implement SVE2 FCVTXNT, FCVTX, Richard Henderson, 2021/03/09
- [PATCH v4 78/78] target/arm: Enable SVE2 and some extensions, Richard Henderson, 2021/03/09
- [PATCH v4 77/78] target/arm: Implement SVE2 complex integer dot product, Richard Henderson, 2021/03/09
- [PATCH v4 72/78] target/arm: Share table of sve load functions, Richard Henderson, 2021/03/09
- [PATCH v4 75/78] target/arm: Implement SVE2 bitwise shift immediate, Richard Henderson, 2021/03/09
- [PATCH v4 69/78] target/arm: Implement SVE2 FCVTLT, Richard Henderson, 2021/03/09