[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[PATCH v6 64/82] target/arm: Implement SVE2 TBL, TBX
|
From: |
Richard Henderson |
|
Subject: |
[PATCH v6 64/82] target/arm: Implement SVE2 TBL, TBX |
|
Date: |
Fri, 30 Apr 2021 13:25:52 -0700 |
From: Stephen Long <steplong@quicinc.com>
Signed-off-by: Stephen Long <steplong@quicinc.com>
Message-Id: <20200428144352.9275-1-steplong@quicinc.com>
[rth: rearrange the macros a little and rebase]
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/helper-sve.h | 10 +++++
target/arm/sve.decode | 5 +++
target/arm/sve_helper.c | 90 ++++++++++++++++++++++++++++++--------
target/arm/translate-sve.c | 33 ++++++++++++++
4 files changed, 119 insertions(+), 19 deletions(-)
diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h
index 0be0d90bee..41c08a963b 100644
--- a/target/arm/helper-sve.h
+++ b/target/arm/helper-sve.h
@@ -661,6 +661,16 @@ DEF_HELPER_FLAGS_4(sve_tbl_h, TCG_CALL_NO_RWG, void, ptr,
ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve_tbl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve_tbl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_tbl_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_tbl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_tbl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_tbl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve2_tbx_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_tbx_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_tbx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_tbx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
DEF_HELPER_FLAGS_3(sve_sunpk_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
DEF_HELPER_FLAGS_3(sve_sunpk_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
DEF_HELPER_FLAGS_3(sve_sunpk_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index 7a2770cb0c..38aaf1b37e 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -558,6 +558,11 @@ TBL 00000101 .. 1 ..... 001100 ..... .....
@rd_rn_rm
# SVE unpack vector elements
UNPK 00000101 esz:2 1100 u:1 h:1 001110 rn:5 rd:5
+# SVE2 Table Lookup (three sources)
+
+TBL_sve2 00000101 .. 1 ..... 001010 ..... ..... @rd_rn_rm
+TBX 00000101 .. 1 ..... 001011 ..... ..... @rd_rn_rm
+
### SVE Permute - Predicates Group
# SVE permute predicate elements
diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index e8a8425522..8dc04441aa 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -2915,28 +2915,80 @@ void HELPER(sve_rev_d)(void *vd, void *vn, uint32_t
desc)
}
}
-#define DO_TBL(NAME, TYPE, H) \
-void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \
-{ \
- intptr_t i, opr_sz = simd_oprsz(desc); \
- uintptr_t elem = opr_sz / sizeof(TYPE); \
- TYPE *d = vd, *n = vn, *m = vm; \
- ARMVectorReg tmp; \
- if (unlikely(vd == vn)) { \
- n = memcpy(&tmp, vn, opr_sz); \
- } \
- for (i = 0; i < elem; i++) { \
- TYPE j = m[H(i)]; \
- d[H(i)] = j < elem ? n[H(j)] : 0; \
- } \
+typedef void tb_impl_fn(void *, void *, void *, void *, uintptr_t, bool);
+
+static inline void do_tbl1(void *vd, void *vn, void *vm, uint32_t desc,
+ bool is_tbx, tb_impl_fn *fn)
+{
+ ARMVectorReg scratch;
+ uintptr_t oprsz = simd_oprsz(desc);
+
+ if (unlikely(vd == vn)) {
+ vn = memcpy(&scratch, vn, oprsz);
+ }
+
+ fn(vd, vn, NULL, vm, oprsz, is_tbx);
}
-DO_TBL(sve_tbl_b, uint8_t, H1)
-DO_TBL(sve_tbl_h, uint16_t, H2)
-DO_TBL(sve_tbl_s, uint32_t, H4)
-DO_TBL(sve_tbl_d, uint64_t, )
+static inline void do_tbl2(void *vd, void *vn0, void *vn1, void *vm,
+ uint32_t desc, bool is_tbx, tb_impl_fn *fn)
+{
+ ARMVectorReg scratch;
+ uintptr_t oprsz = simd_oprsz(desc);
-#undef TBL
+ if (unlikely(vd == vn0)) {
+ vn0 = memcpy(&scratch, vn0, oprsz);
+ if (vd == vn1) {
+ vn1 = vn0;
+ }
+ } else if (unlikely(vd == vn1)) {
+ vn1 = memcpy(&scratch, vn1, oprsz);
+ }
+
+ fn(vd, vn0, vn1, vm, oprsz, is_tbx);
+}
+
+#define DO_TB(SUFF, TYPE, H) \
+static inline void do_tb_##SUFF(void *vd, void *vt0, void *vt1, \
+ void *vm, uintptr_t oprsz, bool is_tbx) \
+{ \
+ TYPE *d = vd, *tbl0 = vt0, *tbl1 = vt1, *indexes = vm; \
+ uintptr_t i, nelem = oprsz / sizeof(TYPE); \
+ for (i = 0; i < nelem; ++i) { \
+ TYPE index = indexes[H1(i)], val = 0; \
+ if (index < nelem) { \
+ val = tbl0[H(index)]; \
+ } else { \
+ index -= nelem; \
+ if (tbl1 && index < nelem) { \
+ val = tbl1[H(index)]; \
+ } else if (is_tbx) { \
+ continue; \
+ } \
+ } \
+ d[H(i)] = val; \
+ } \
+} \
+void HELPER(sve_tbl_##SUFF)(void *vd, void *vn, void *vm, uint32_t desc) \
+{ \
+ do_tbl1(vd, vn, vm, desc, false, do_tb_##SUFF); \
+} \
+void HELPER(sve2_tbl_##SUFF)(void *vd, void *vn0, void *vn1, \
+ void *vm, uint32_t desc) \
+{ \
+ do_tbl2(vd, vn0, vn1, vm, desc, false, do_tb_##SUFF); \
+} \
+void HELPER(sve2_tbx_##SUFF)(void *vd, void *vn, void *vm, uint32_t desc) \
+{ \
+ do_tbl1(vd, vn, vm, desc, true, do_tb_##SUFF); \
+}
+
+DO_TB(b, uint8_t, H1)
+DO_TB(h, uint16_t, H2)
+DO_TB(s, uint32_t, H4)
+DO_TB(d, uint64_t, )
+
+#undef DO_TB
#define DO_UNPK(NAME, TYPED, TYPES, HD, HS) \
void HELPER(NAME)(void *vd, void *vn, uint32_t desc) \
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index 5f2a2b1eb2..7bf8326fab 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -2417,6 +2417,39 @@ static bool trans_TBL(DisasContext *s, arg_rrr_esz *a)
return true;
}
+static bool trans_TBL_sve2(DisasContext *s, arg_rrr_esz *a)
+{
+ static gen_helper_gvec_4 * const fns[4] = {
+ gen_helper_sve2_tbl_b, gen_helper_sve2_tbl_h,
+ gen_helper_sve2_tbl_s, gen_helper_sve2_tbl_d
+ };
+
+ if (!dc_isar_feature(aa64_sve2, s)) {
+ return false;
+ }
+ if (sve_access_check(s)) {
+ gen_gvec_ool_zzzz(s, fns[a->esz], a->rd, a->rn,
+ (a->rn + 1) % 32, a->rm, 0);
+ }
+ return true;
+}
+
+static bool trans_TBX(DisasContext *s, arg_rrr_esz *a)
+{
+ static gen_helper_gvec_3 * const fns[4] = {
+ gen_helper_sve2_tbx_b, gen_helper_sve2_tbx_h,
+ gen_helper_sve2_tbx_s, gen_helper_sve2_tbx_d
+ };
+
+ if (!dc_isar_feature(aa64_sve2, s)) {
+ return false;
+ }
+ if (sve_access_check(s)) {
+ gen_gvec_ool_zzz(s, fns[a->esz], a->rd, a->rn, a->rm, 0);
+ }
+ return true;
+}
+
static bool trans_UNPK(DisasContext *s, arg_UNPK *a)
{
static gen_helper_gvec_2 * const fns[4][2] = {
--
2.25.1
- [PATCH v6 54/82] target/arm: Implement SVE2 saturating multiply-add high (indexed), (continued)
- [PATCH v6 54/82] target/arm: Implement SVE2 saturating multiply-add high (indexed), Richard Henderson, 2021/04/30
- [PATCH v6 45/82] target/arm: Implement SVE2 gather load insns, Richard Henderson, 2021/04/30
- [PATCH v6 51/82] target/arm: Split out formats for 3 vectors + 1 index, Richard Henderson, 2021/04/30
- [PATCH v6 53/82] target/arm: Implement SVE2 integer multiply-add (indexed), Richard Henderson, 2021/04/30
- [PATCH v6 52/82] target/arm: Implement SVE2 integer multiply (indexed), Richard Henderson, 2021/04/30
- [PATCH v6 58/82] target/arm: Implement SVE2 saturating multiply high (indexed), Richard Henderson, 2021/04/30
- [PATCH v6 72/82] target/arm: Implement SVE2 bitwise shift immediate, Richard Henderson, 2021/04/30
- [PATCH v6 44/82] target/arm: Implement SVE2 scatter store insns, Richard Henderson, 2021/04/30
- [PATCH v6 61/82] target/arm: Implement SVE2 crypto unary operations, Richard Henderson, 2021/04/30
- [PATCH v6 76/82] target/arm: Remove unused fpst from VDOT_scalar, Richard Henderson, 2021/04/30
- [PATCH v6 64/82] target/arm: Implement SVE2 TBL, TBX,
Richard Henderson <=
- [PATCH v6 63/82] target/arm: Implement SVE2 crypto constructive binary operations, Richard Henderson, 2021/04/30
- [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