[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[PATCH 11/31] target/arm: Implement SVE2 integer add/subtract long
From: |
Richard Henderson |
Subject: |
[PATCH 11/31] target/arm: Implement SVE2 integer add/subtract long |
Date: |
Thu, 26 Mar 2020 16:08:18 -0700 |
Signed-off-by: Richard Henderson <address@hidden>
---
target/arm/helper-sve.h | 24 ++++++++++++++++++++
target/arm/sve.decode | 19 ++++++++++++++++
target/arm/sve_helper.c | 43 +++++++++++++++++++++++++++++++++++
target/arm/translate-sve.c | 46 ++++++++++++++++++++++++++++++++++++++
4 files changed, 132 insertions(+)
diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h
index 368185944a..475fce7f3a 100644
--- a/target/arm/helper-sve.h
+++ b/target/arm/helper-sve.h
@@ -1372,6 +1372,30 @@ DEF_HELPER_FLAGS_5(sve_ftmad_h, TCG_CALL_NO_RWG, void,
ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(sve_ftmad_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(sve_ftmad_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_saddl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_saddl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_saddl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve2_ssubl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_ssubl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_ssubl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve2_sabdl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_sabdl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_sabdl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve2_uaddl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_uaddl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_uaddl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve2_usubl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_usubl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_usubl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve2_uabdl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_uabdl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_uabdl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
DEF_HELPER_FLAGS_4(sve_ldr, TCG_CALL_NO_WG, void, env, ptr, tl, int)
DEF_HELPER_FLAGS_4(sve_str, TCG_CALL_NO_WG, void, env, ptr, tl, int)
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index 86aee38668..a239fd3479 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -1161,3 +1161,22 @@ SUQADD 01000100 .. 011 100 100 ... ..... .....
@rdn_pg_rm
USQADD 01000100 .. 011 101 100 ... ..... ..... @rdn_pg_rm
SQSUB_zpzz 01000100 .. 011 110 100 ... ..... ..... @rdm_pg_rn # SQSUBR
UQSUB_zpzz 01000100 .. 011 111 100 ... ..... ..... @rdm_pg_rn # UQSUBR
+
+#### SVE2 Widening Integer Arithmetic
+
+## SVE2 integer add/subtract long
+
+SADDLB 01000101 .. 0 ..... 00 0000 ..... ..... @rd_rn_rm
+SADDLT 01000101 .. 0 ..... 00 0001 ..... ..... @rd_rn_rm
+UADDLB 01000101 .. 0 ..... 00 0010 ..... ..... @rd_rn_rm
+UADDLT 01000101 .. 0 ..... 00 0011 ..... ..... @rd_rn_rm
+
+SSUBLB 01000101 .. 0 ..... 00 0100 ..... ..... @rd_rn_rm
+SSUBLT 01000101 .. 0 ..... 00 0101 ..... ..... @rd_rn_rm
+USUBLB 01000101 .. 0 ..... 00 0110 ..... ..... @rd_rn_rm
+USUBLT 01000101 .. 0 ..... 00 0111 ..... ..... @rd_rn_rm
+
+SABDLB 01000101 .. 0 ..... 00 1100 ..... ..... @rd_rn_rm
+SABDLT 01000101 .. 0 ..... 00 1101 ..... ..... @rd_rn_rm
+UABDLB 01000101 .. 0 ..... 00 1110 ..... ..... @rd_rn_rm
+UABDLT 01000101 .. 0 ..... 00 1111 ..... ..... @rd_rn_rm
diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index bee00eaa44..7d7a59f620 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -1088,6 +1088,49 @@ DO_ZZW(sve_lsl_zzw_s, uint32_t, uint64_t, H1_4, DO_LSL)
#undef DO_ZPZ
#undef DO_ZPZ_D
+/*
+ * Three-operand expander, unpredicated, in which the two inputs are
+ * selected from the top or bottom half of the wide column.
+ */
+#define DO_ZZZ_TB(NAME, TYPE, TYPEN, OP) \
+void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \
+{ \
+ intptr_t i, opr_sz = simd_oprsz(desc); \
+ int sel1 = (simd_data(desc) & 1) * sizeof(TYPE); \
+ int sel2 = (simd_data(desc) & 2) * (sizeof(TYPE) / 2); \
+ for (i = 0; i < opr_sz; i += sizeof(TYPE)) { \
+ TYPE nn = (TYPEN)(*(TYPE *)(vn + i) >> sel1); \
+ TYPE mm = (TYPEN)(*(TYPE *)(vm + i) >> sel2); \
+ *(TYPE *)(vd + i) = OP(nn, mm); \
+ } \
+}
+
+DO_ZZZ_TB(sve2_saddl_h, int16_t, int8_t, DO_ADD)
+DO_ZZZ_TB(sve2_saddl_s, int32_t, int16_t, DO_ADD)
+DO_ZZZ_TB(sve2_saddl_d, int64_t, int32_t, DO_ADD)
+
+DO_ZZZ_TB(sve2_ssubl_h, int16_t, int8_t, DO_SUB)
+DO_ZZZ_TB(sve2_ssubl_s, int32_t, int16_t, DO_SUB)
+DO_ZZZ_TB(sve2_ssubl_d, int64_t, int32_t, DO_SUB)
+
+DO_ZZZ_TB(sve2_sabdl_h, int16_t, int8_t, DO_ABD)
+DO_ZZZ_TB(sve2_sabdl_s, int32_t, int16_t, DO_ABD)
+DO_ZZZ_TB(sve2_sabdl_d, int64_t, int32_t, DO_ABD)
+
+DO_ZZZ_TB(sve2_uaddl_h, uint16_t, uint8_t, DO_ADD)
+DO_ZZZ_TB(sve2_uaddl_s, uint32_t, uint16_t, DO_ADD)
+DO_ZZZ_TB(sve2_uaddl_d, uint64_t, uint32_t, DO_ADD)
+
+DO_ZZZ_TB(sve2_usubl_h, uint16_t, uint8_t, DO_SUB)
+DO_ZZZ_TB(sve2_usubl_s, uint32_t, uint16_t, DO_SUB)
+DO_ZZZ_TB(sve2_usubl_d, uint64_t, uint32_t, DO_SUB)
+
+DO_ZZZ_TB(sve2_uabdl_h, uint16_t, uint8_t, DO_ABD)
+DO_ZZZ_TB(sve2_uabdl_s, uint32_t, uint16_t, DO_ABD)
+DO_ZZZ_TB(sve2_uabdl_d, uint64_t, uint32_t, DO_ABD)
+
+#undef DO_ZZZ_TB
+
/* Two-operand reduction expander, controlled by a predicate.
* The difference between TYPERED and TYPERET has to do with
* sign-extension. E.g. for SMAX, TYPERED must be signed,
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index 21dfb2455a..ee8a6fd912 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -6005,3 +6005,49 @@ DO_SVE2_ZPZZ(SQSUB_zpzz, sqsub)
DO_SVE2_ZPZZ(UQSUB_zpzz, uqsub)
DO_SVE2_ZPZZ(SUQADD, suqadd)
DO_SVE2_ZPZZ(USQADD, usqadd)
+
+/*
+ * SVE2 Widening Integer Arithmetic
+ */
+
+static bool do_sve2_zzw_ool(DisasContext *s, arg_rrr_esz *a,
+ gen_helper_gvec_3 *fn, int data)
+{
+ if (fn == NULL || !dc_isar_feature(aa64_sve2, s)) {
+ return false;
+ }
+ if (sve_access_check(s)) {
+ unsigned vsz = vec_full_reg_size(s);
+ tcg_gen_gvec_3_ool(vec_full_reg_offset(s, a->rd),
+ vec_full_reg_offset(s, a->rn),
+ vec_full_reg_offset(s, a->rm),
+ vsz, vsz, data, fn);
+ }
+ return true;
+}
+
+#define DO_SVE2_ZZZ_TB(NAME, name, SEL1, SEL2) \
+static bool trans_##NAME(DisasContext *s, arg_rrr_esz *a) \
+{ \
+ static gen_helper_gvec_3 * const fns[4] = { \
+ NULL, gen_helper_sve2_##name##_h, \
+ gen_helper_sve2_##name##_s, gen_helper_sve2_##name##_d, \
+ }; \
+ return do_sve2_zzw_ool(s, a, fns[a->esz], (SEL2 << 1) | SEL1); \
+}
+
+DO_SVE2_ZZZ_TB(SADDLB, saddl, false, false)
+DO_SVE2_ZZZ_TB(SSUBLB, ssubl, false, false)
+DO_SVE2_ZZZ_TB(SABDLB, sabdl, false, false)
+
+DO_SVE2_ZZZ_TB(UADDLB, uaddl, false, false)
+DO_SVE2_ZZZ_TB(USUBLB, usubl, false, false)
+DO_SVE2_ZZZ_TB(UABDLB, uabdl, false, false)
+
+DO_SVE2_ZZZ_TB(SADDLT, saddl, true, true)
+DO_SVE2_ZZZ_TB(SSUBLT, ssubl, true, true)
+DO_SVE2_ZZZ_TB(SABDLT, sabdl, true, true)
+
+DO_SVE2_ZZZ_TB(UADDLT, uaddl, true, true)
+DO_SVE2_ZZZ_TB(USUBLT, usubl, true, true)
+DO_SVE2_ZZZ_TB(UABDLT, uabdl, true, true)
--
2.20.1
- [PATCH for-5.1 00/31] target/arm: SVE2, part 1, Richard Henderson, 2020/03/26
- [PATCH 01/31] target/arm: Add ID_AA64ZFR0 fields and isar_feature_aa64_sve2, Richard Henderson, 2020/03/26
- [PATCH 02/31] target/arm: Implement SVE2 Integer Multiply - Unpredicated, Richard Henderson, 2020/03/26
- [PATCH 03/31] target/arm: Implement SVE2 integer pairwise add and accumulate long, Richard Henderson, 2020/03/26
- [PATCH 04/31] target/arm: Remove fp_status from helper_{recpe, rsqrte}_u32, Richard Henderson, 2020/03/26
- [PATCH 05/31] target/arm: Implement SVE2 integer unary operations (predicated), Richard Henderson, 2020/03/26
- [PATCH 08/31] target/arm: Implement SVE2 integer halving add/subtract (predicated), Richard Henderson, 2020/03/26
- [PATCH 07/31] target/arm: Implement SVE2 saturating/rounding bitwise shift left (predicated), Richard Henderson, 2020/03/26
- [PATCH 06/31] target/arm: Split out saturating/rounding shifts from neon, Richard Henderson, 2020/03/26
- [PATCH 09/31] target/arm: Implement SVE2 integer pairwise arithmetic, Richard Henderson, 2020/03/26
- [PATCH 11/31] target/arm: Implement SVE2 integer add/subtract long,
Richard Henderson <=
- [PATCH 12/31] target/arm: Implement SVE2 integer add/subtract interleaved long, Richard Henderson, 2020/03/26
- [PATCH 10/31] target/arm: Implement SVE2 saturating add/subtract (predicated), Richard Henderson, 2020/03/26
- [PATCH 13/31] target/arm: Implement SVE2 integer add/subtract wide, Richard Henderson, 2020/03/26
- [PATCH 14/31] target/arm: Implement SVE2 integer multiply long, Richard Henderson, 2020/03/26
- [PATCH 15/31] target/arm: Implement PMULLB and PMULLT, Richard Henderson, 2020/03/26
- [PATCH 16/31] target/arm: Tidy SVE tszimm shift formats, Richard Henderson, 2020/03/26
- [PATCH 17/31] target/arm: Implement SVE2 bitwise shift left long, Richard Henderson, 2020/03/26
- [PATCH 18/31] target/arm: Implement SVE2 bitwise exclusive-or interleaved, Richard Henderson, 2020/03/26
- [PATCH 19/31] target/arm: Implement SVE2 bitwise permute, Richard Henderson, 2020/03/26
- [PATCH 20/31] target/arm: Implement SVE2 complex integer add, Richard Henderson, 2020/03/26