[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[PATCH v4 69/78] target/arm: Implement SVE2 FCVTLT
From: |
Richard Henderson |
Subject: |
[PATCH v4 69/78] target/arm: Implement SVE2 FCVTLT |
Date: |
Tue, 9 Mar 2021 08:20:32 -0800 |
From: Stephen Long <steplong@quicinc.com>
Signed-off-by: Stephen Long <steplong@quicinc.com>
Message-Id: <20200428174332.17162-3-steplong@quicinc.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/helper-sve.h | 5 +++++
target/arm/sve.decode | 2 ++
target/arm/sve_helper.c | 23 +++++++++++++++++++++++
target/arm/translate-sve.c | 16 ++++++++++++++++
4 files changed, 46 insertions(+)
diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h
index eedb70eb50..8569d384b9 100644
--- a/target/arm/helper-sve.h
+++ b/target/arm/helper-sve.h
@@ -2739,3 +2739,8 @@ 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)
+
+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)
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index 2c38fe4691..d152193e89 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -1576,4 +1576,6 @@ 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
+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
diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index b719a3aacf..3b3f1eca5d 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -7620,3 +7620,26 @@ void HELPER(NAME)(void *vd, void *vn, void *vg, void
*status, uint32_t desc) \
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)
+
+#define DO_FCVTLT(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)) { \
+ TYPEN nn = *(TYPEN *)(vn + HN(i + sizeof(TYPEN))); \
+ *(TYPEW *)(vd + HW(i)) = OP(nn, status); \
+ } \
+ } while (i & 63); \
+ } while (i != 0); \
+}
+
+DO_FCVTLT(sve2_fcvtlt_hs, uint32_t, uint16_t, H1_4, H1_2, sve_f16_to_f32)
+DO_FCVTLT(sve2_fcvtlt_sd, uint64_t, uint32_t, H1_4, H1_2, float32_to_float64)
+
+#undef DO_FCVTLT
+#undef DO_FCVTNT
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index 83fab9a6fc..c29984d244 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -8237,3 +8237,19 @@ static bool trans_FCVTNT_ds(DisasContext *s, arg_rpr_esz
*a)
}
return do_zpz_ptr(s, a->rd, a->rn, a->pg, false,
gen_helper_sve2_fcvtnt_ds);
}
+
+static bool trans_FCVTLT_hs(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_fcvtlt_hs);
+}
+
+static bool trans_FCVTLT_sd(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_fcvtlt_sd);
+}
--
2.25.1
- [PATCH v4 68/78] target/arm: Implement SVE2 FCVTNT, (continued)
- [PATCH v4 68/78] target/arm: Implement SVE2 FCVTNT, Richard Henderson, 2021/03/09
- [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 <=
- [PATCH v4 71/78] target/arm: Implement SVE2 FLOGB, Richard Henderson, 2021/03/09
- [PATCH v4 76/78] target/arm: Implement SVE2 fp multiply-add long, Richard Henderson, 2021/03/09
- [PATCH v4 73/78] target/arm: Implement SVE2 LD1RO, Richard Henderson, 2021/03/09
- Re: [PATCH v4 00/78] target/arm: Implement SVE2, no-reply, 2021/03/09
- Re: [PATCH v4 00/78] target/arm: Implement SVE2, Peter Maydell, 2021/03/10