[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[PATCH v6 66/82] target/arm: Implement SVE2 FCVTLT
From: |
Richard Henderson |
Subject: |
[PATCH v6 66/82] target/arm: Implement SVE2 FCVTLT |
Date: |
Fri, 30 Apr 2021 13:25:54 -0700 |
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 d6b064bdc9..30b6dc49c8 100644
--- a/target/arm/helper-sve.h
+++ b/target/arm/helper-sve.h
@@ -2708,3 +2708,8 @@ 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 afc53639ac..fb998f5f34 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -1534,4 +1534,6 @@ 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 6164ae17cc..2684f40a62 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -7468,3 +7468,26 @@ 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 537449cbfa..f5bf122204 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -8186,3 +8186,19 @@ 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 v6 74/82] target/arm: Implement aarch64 SUDOT, USDOT, (continued)
- [PATCH v6 74/82] target/arm: Implement aarch64 SUDOT, USDOT, Richard Henderson, 2021/04/30
- [PATCH v6 65/82] target/arm: Implement SVE2 FCVTNT, Richard Henderson, 2021/04/30
- [PATCH v6 71/82] target/arm: Implement 128-bit ZIP, UZP, TRN, Richard Henderson, 2021/04/30
- [PATCH v6 49/82] target/arm: Pass separate addend to FCMLA helpers, Richard Henderson, 2021/04/30
- [PATCH v6 67/82] target/arm: Implement SVE2 FCVTXNT, FCVTX, Richard Henderson, 2021/04/30
- [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 <=
- [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, 2021/04/30
- [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